From 5d80e3b30aa31e597dd6ee81cb0ad4d4aa237994 Mon Sep 17 00:00:00 2001 From: a-slide Date: Thu, 2 May 2019 10:57:23 +0100 Subject: [PATCH 1/4] Add Log file output --- NanopolishComp/Eventalign_collapse.py | 33 +- NanopolishComp/Freq_meth_calculate.py | 31 +- NanopolishComp/common.py | 12 +- docs/demo/Eventalign_collapse_usage.ipynb | 813 ++++++++++---------- docs/demo/Freq_meth_calculate_usage.ipynb | 889 +++++++++++----------- 5 files changed, 938 insertions(+), 840 deletions(-) diff --git a/NanopolishComp/Eventalign_collapse.py b/NanopolishComp/Eventalign_collapse.py index f026fbe..6b1bf56 100755 --- a/NanopolishComp/Eventalign_collapse.py +++ b/NanopolishComp/Eventalign_collapse.py @@ -13,15 +13,18 @@ # Standard library imports import multiprocessing as mp from time import time -from collections import OrderedDict +from collections import * import traceback +import datetime # Third party imports import numpy as np from tqdm import tqdm # Local imports -from NanopolishComp.common import file_readable, dir_writable, NanopolishCompError +from NanopolishComp.common import * +from NanopolishComp import __version__ as package_version +from NanopolishComp import __name__ as package_name #~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~LOGGING INFO~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~# import logging @@ -65,12 +68,28 @@ def __init__ (self, Reduce verbosity """ + # Save init options in dict for later + kwargs = locals() + # Define overall verbose level self.log = logging.getLogger() if verbose: self.log.setLevel (logging.DEBUG) elif quiet: self.log.setLevel (logging.WARNING) + else: + self.log.setLevel (logging.INFO) + + # Collect args in dict for log report + self.option_d = OrderedDict() + self.option_d["package_name"] = package_name + self.option_d["package_version"] = package_version + self.option_d["timestamp"] = str(datetime.datetime.now()) + for i, j in kwargs.items(): + if i != "self": + self.option_d[i]=j + self.log.debug ("Options summary") + self.log.debug (dict_to_str(self.option_d)) # Verify parameters validity self.log.info ("Checking arguments") @@ -128,6 +147,11 @@ def __init__ (self, self.log.warning ("\nAn error occured. All processes were killed\n") raise E + def __repr__ (self): + m = "General options:\n" + m+=dict_to_str(self.option_d) + return m + #~~~~~~~~~~~~~~~~~~~~~~~~~~~~~PRIVATE METHODS~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~# def _split_reads (self, in_q, error_q): """ @@ -307,6 +331,11 @@ def _write_output (self, out_q, error_q): # Flag last line data_fp.write ("#\n") + # Open log file + log_fn = os.path.join(self.outdir, self.outprefix+"_eventalign_collapse.log") + with open (log_fn, "w") as log_fp: + log_fp.write (str(self)) + # Manage exceptions and deal poison pills except Exception: error_q.put (NanopolishCompError(traceback.format_exc())) diff --git a/NanopolishComp/Freq_meth_calculate.py b/NanopolishComp/Freq_meth_calculate.py index 302b5d2..accd91e 100755 --- a/NanopolishComp/Freq_meth_calculate.py +++ b/NanopolishComp/Freq_meth_calculate.py @@ -6,12 +6,15 @@ # Standard library imports from collections import * import csv +import datetime # Third party imports from tqdm import tqdm # Local imports from NanopolishComp.common import * +from NanopolishComp import __version__ as package_version +from NanopolishComp import __name__ as package_name #~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~LOGGING INFO~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~# import logging @@ -56,12 +59,28 @@ def __init__ (self, Reduce verbosity """ + # Save init options in dict for later + kwargs = locals() + # Define overall verbose level self.log = logging.getLogger() if verbose: self.log.setLevel (logging.DEBUG) elif quiet: self.log.setLevel (logging.WARNING) + else: + self.log.setLevel (logging.INFO) + + # Collect args in dict for log report + self.option_d = OrderedDict() + self.option_d["package_name"] = package_name + self.option_d["package_version"] = package_version + self.option_d["timestamp"] = str(datetime.datetime.now()) + for i, j in kwargs.items(): + if i != "self": + self.option_d[i]=j + self.log.debug ("Options summary") + self.log.debug (dict_to_str(self.option_d)) # Verify parameters validity self.log.warning ("## Checking arguments ##") @@ -144,7 +163,7 @@ def _parse_methylation_calls(self, fn, min_llr=2.5, min_depth=10, min_meth_freq= # Print read level counter summary self.log.debug ("Read sites summary") - self.log.debug (counter_to_str(self.site_c)) + self.log.debug (dict_to_str(self.site_c)) self.log.info ("Filtering out positions with low coverage or methylation frequency") filtered_sites_d = OrderedDict() @@ -164,16 +183,17 @@ def _parse_methylation_calls(self, fn, min_llr=2.5, min_depth=10, min_meth_freq= # Print genomic positions level counter summary self.log.debug ("Genomic positions summary") - self.log.debug (counter_to_str(self.pos_c)) + self.log.debug (dict_to_str(self.pos_c)) return filtered_sites_d def __repr__ (self): - m = "" + m = "General options:\n" + m+=dict_to_str(self.option_d) m+="Read sites summary:\n" - m+=counter_to_str(self.site_c) + m+=dict_to_str(self.site_c) m+="Genomic positions summary:\n" - m+=counter_to_str(self.pos_c) + m+=dict_to_str(self.pos_c) return m def _write_output (self, sites_d, outdir, outprefix): @@ -202,7 +222,6 @@ def _write_output (self, sites_d, outdir, outprefix): self.log.info("Writing log file") fn = os.path.join(outdir, outprefix+"_freq_meth_calculate.log") with open (fn, "w") as fp: - # Write header fp.write (str(self)) #~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~HELPER CLASS~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~# diff --git a/NanopolishComp/common.py b/NanopolishComp/common.py index dcbc3ba..5fb9a32 100644 --- a/NanopolishComp/common.py +++ b/NanopolishComp/common.py @@ -48,11 +48,15 @@ def find_subseq_index (seq, subseq): yield i i = seq.find(subseq, i+1) -def counter_to_str (c): - """ Transform a counter dict to a tabulated str """ +def dict_to_str (c): + """ Transform a dict to a tabulated str """ m = "" - for i, j in c.most_common(): - m += "\t{}: {:,}\n".format(i, j) + if type(c) == Counter: + for i, j in c.most_common(): + m += "\t{}: {:,}\n".format(i, j) + else: + for i, j in c.items(): + m += "\t{}: {}\n".format(i, j) return m def jhelp (f:"python function or method"): diff --git a/docs/demo/Eventalign_collapse_usage.ipynb b/docs/demo/Eventalign_collapse_usage.ipynb index 6f2db13..926a373 100644 --- a/docs/demo/Eventalign_collapse_usage.ipynb +++ b/docs/demo/Eventalign_collapse_usage.ipynb @@ -132,8 +132,8 @@ "execution_count": 1, "metadata": { "ExecuteTime": { - "end_time": "2019-05-01T09:26:14.620270Z", - "start_time": "2019-05-01T09:26:13.548810Z" + "end_time": "2019-05-02T09:32:44.181603Z", + "start_time": "2019-05-02T09:32:43.073764Z" } }, "outputs": [ @@ -218,8 +218,8 @@ "execution_count": 2, "metadata": { "ExecuteTime": { - "end_time": "2019-05-01T09:26:15.786260Z", - "start_time": "2019-05-01T09:26:14.624302Z" + "end_time": "2019-05-02T09:32:45.417414Z", + "start_time": "2019-05-02T09:32:44.184921Z" }, "scrolled": false }, @@ -259,9 +259,9 @@ "Starting to process files\n", "\r", "0 reads [00:00, ? reads/s]\r", - "13 reads [00:00, 106.55 reads/s]\r", - "21 reads [00:00, 129.30 reads/s]\n", - "[Eventalign_collapse] total reads: 21 [127.11 reads/s]\n", + "11 reads [00:00, 96.75 reads/s]\r", + "21 reads [00:00, 118.91 reads/s]\n", + "[Eventalign_collapse] total reads: 21 [116.81 reads/s]\n", "\n" ] } @@ -290,8 +290,8 @@ "execution_count": 3, "metadata": { "ExecuteTime": { - "end_time": "2019-05-01T09:26:16.975890Z", - "start_time": "2019-05-01T09:26:15.790652Z" + "end_time": "2019-05-02T09:32:46.592916Z", + "start_time": "2019-05-02T09:32:45.421223Z" } }, "outputs": [ @@ -325,6 +325,20 @@ "name": "stderr", "output_type": "stream", "text": [ + "Options summary\n", + "\tpackage_name: NanopolishComp\n", + "\tpackage_version: 0.6.1\n", + "\ttimestamp: 2019-05-02 10:32:46.350455\n", + "\tquiet: False\n", + "\tverbose: True\n", + "\tthreads: 4\n", + "\tstat_fields: ['mean', 'median', 'num_signals']\n", + "\twrite_samples: False\n", + "\tmax_reads: None\n", + "\toutprefix: out\n", + "\toutdir: ./output\n", + "\tinput_fn: 0\n", + "\n", "Checking arguments\n", "\tTesting input file readability\n", "Testing output dir writability\n", @@ -337,14 +351,13 @@ "\t[write_output] Start rwriting output\n", "\r", "0 reads [00:00, ? reads/s]\r", - "8 reads [00:00, 78.08 reads/s]\r", - "19 reads [00:00, 80.03 reads/s]\t[split_reads] Done\n", + "12 reads [00:00, 119.55 reads/s]\t[split_reads] Done\n", "\t[process_read 1] Done\n", "\t[process_read 2] Done\n", "\r", - "21 reads [00:00, 96.20 reads/s]\n", + "21 reads [00:00, 116.86 reads/s]\n", "\t[write_output] Done\n", - "[Eventalign_collapse] total reads: 21 [95.11 reads/s]\n", + "[Eventalign_collapse] total reads: 21 [115.22 reads/s]\n", "\n" ] } @@ -373,8 +386,8 @@ "execution_count": 4, "metadata": { "ExecuteTime": { - "end_time": "2019-05-01T09:26:17.994606Z", - "start_time": "2019-05-01T09:26:16.979903Z" + "end_time": "2019-05-02T09:32:47.658878Z", + "start_time": "2019-05-02T09:32:46.598203Z" }, "scrolled": true }, @@ -409,240 +422,240 @@ "name": "stderr", "output_type": "stream", "text": [ - "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_243_strand.fast5\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014833698560:\n", + "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_319_strand.fast5\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205845075712:\n", " #000: H5F.c line 509 in H5Fopen(): unable to open file\n", " major: File accessibilty\n", " minor: Unable to open file\n", " #001: H5Fint.c line 1400 in H5F__open(): unable to open file\n", " major: File accessibilty\n", " minor: Unable to open file\n", - " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Wed May 1 10:26:17 2019\n", - ", name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_348_strand.fast5', tent_flags = 0\n", + " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Thu May 2 10:32:47 2019\n", + ", name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_243_strand.fast5', tent_flags = 0\n", " major: File accessibilty\n", " minor: Unable to open file\n", " #003: H5FD.c line 734 in H5FD_open(): open failed\n", " major: Virtual File Layer\n", " minor: Unable to initialize object\n", - " #004: H5FDsec2.c line 346 in H5FD_sec2_open(): unable to open file: name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_348_strand.fast5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0\n", + " #004: H5FDsec2.c line 346 in H5FD_sec2_open(): unable to open file: name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_243_strand.fast5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0\n", " major: File accessibilty\n", " minor: Unable to open file\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014833698560:\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205845075712:\n", " #000: H5L.c line 805 in H5Lexists(): not a location\n", " major: Invalid arguments to routine\n", " minor: Inappropriate type\n", " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", " major: Invalid arguments to routine\n", " minor: Bad value\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014833698560:\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205845075712:\n", " #000: H5L.c line 805 in H5Lexists(): not a location\n", " major: Invalid arguments to routine\n", " minor: Inappropriate type\n", " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", " major: Invalid arguments to routine\n", " minor: Bad value\n", - "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_348_strand.fast5\n", - "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_108_strand.fast5\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014825305856:\n", + "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_243_strand.fast5\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205845075712:\n", " #000: H5F.c line 509 in H5Fopen(): unable to open file\n", " major: File accessibilty\n", " minor: Unable to open file\n", " #001: H5Fint.c line 1400 in H5F__open(): unable to open file\n", " major: File accessibilty\n", " minor: Unable to open file\n", - " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Wed May 1 10:26:17 2019\n", - ", name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_319_strand.fast5', tent_flags = 0\n", + " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Thu May 2 10:32:47 2019\n", + ", name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_36_strand.fast5', tent_flags = 0\n", " major: File accessibilty\n", " minor: Unable to open file\n", " #003: H5FD.c line 734 in H5FD_open(): open failed\n", " major: Virtual File Layer\n", " minor: Unable to initialize object\n", - " #004: H5FDsec2.c line 346 in H5FD_sec2_open(): unable to open file: name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_319_strand.fast5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0\n", + " #004: H5FDsec2.c line 346 in H5FD_sec2_open(): unable to open file: name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_36_strand.fast5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0\n", " major: File accessibilty\n", " minor: Unable to open file\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014825305856:\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205845075712:\n", " #000: H5L.c line 805 in H5Lexists(): not a location\n", " major: Invalid arguments to routine\n", " minor: Inappropriate type\n", " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", " major: Invalid arguments to routine\n", " minor: Bad value\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014825305856:\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205845075712:\n", " #000: H5L.c line 805 in H5Lexists(): not a location\n", " major: Invalid arguments to routine\n", " minor: Inappropriate type\n", " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", " major: Invalid arguments to routine\n", " minor: Bad value\n", - "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_319_strand.fast5\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014825305856:\n", + "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_36_strand.fast5\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", " #000: H5F.c line 509 in H5Fopen(): unable to open file\n", " major: File accessibilty\n", " minor: Unable to open file\n", " #001: H5Fint.c line 1400 in H5F__open(): unable to open file\n", " major: File accessibilty\n", " minor: Unable to open file\n", - " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Wed May 1 10:26:17 2019\n", - ", name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_237_strand.fast5', tent_flags = 0\n", + " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Thu May 2 10:32:47 2019\n", + ", name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_343_strand.fast5', tent_flags = 0\n", " major: File accessibilty\n", " minor: Unable to open file\n", " #003: H5FD.c line 734 in H5FD_open(): open failed\n", " major: Virtual File Layer\n", " minor: Unable to initialize object\n", - " #004: H5FDsec2.c line 346 in H5FD_sec2_open(): unable to open file: name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_237_strand.fast5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0\n", + " #004: H5FDsec2.c line 346 in H5FD_sec2_open(): unable to open file: name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_343_strand.fast5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0\n", " major: File accessibilty\n", " minor: Unable to open file\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014825305856:\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", " #000: H5L.c line 805 in H5Lexists(): not a location\n", " major: Invalid arguments to routine\n", " minor: Inappropriate type\n", " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", " major: Invalid arguments to routine\n", " minor: Bad value\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014825305856:\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", " #000: H5L.c line 805 in H5Lexists(): not a location\n", " major: Invalid arguments to routine\n", " minor: Inappropriate type\n", " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", " major: Invalid arguments to routine\n", " minor: Bad value\n", - "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_237_strand.fast5\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014825305856:\n", + "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_343_strand.fast5\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", " #000: H5F.c line 509 in H5Fopen(): unable to open file\n", " major: File accessibilty\n", " minor: Unable to open file\n", " #001: H5Fint.c line 1400 in H5F__open(): unable to open file\n", " major: File accessibilty\n", " minor: Unable to open file\n", - " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Wed May 1 10:26:17 2019\n", - ", name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_318_strand.fast5', tent_flags = 0\n", + " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Thu May 2 10:32:47 2019\n", + ", name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_237_strand.fast5', tent_flags = 0\n", " major: File accessibilty\n", " minor: Unable to open file\n", " #003: H5FD.c line 734 in H5FD_open(): open failed\n", " major: Virtual File Layer\n", " minor: Unable to initialize object\n", - " #004: H5FDsec2.c line 346 in H5FD_sec2_open(): unable to open file: name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_318_strand.fast5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0\n", + " #004: H5FDsec2.c line 346 in H5FD_sec2_open(): unable to open file: name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_237_strand.fast5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0\n", " major: File accessibilty\n", " minor: Unable to open file\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014825305856:\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", " #000: H5L.c line 805 in H5Lexists(): not a location\n", " major: Invalid arguments to routine\n", " minor: Inappropriate type\n", " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", " major: Invalid arguments to routine\n", " minor: Bad value\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014825305856:\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", " #000: H5L.c line 805 in H5Lexists(): not a location\n", " major: Invalid arguments to routine\n", " minor: Inappropriate type\n", " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", " major: Invalid arguments to routine\n", " minor: Bad value\n", - "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_318_strand.fast5\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014833698560:\n", + "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_237_strand.fast5\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205861861120:\n", " #000: H5F.c line 509 in H5Fopen(): unable to open file\n", " major: File accessibilty\n", " minor: Unable to open file\n", " #001: H5Fint.c line 1400 in H5F__open(): unable to open file\n", " major: File accessibilty\n", " minor: Unable to open file\n", - " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Wed May 1 10:26:17 2019\n", - ", name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_36_strand.fast5', tent_flags = 0\n", + " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Thu May 2 10:32:47 2019\n", + ", name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_348_strand.fast5', tent_flags = 0\n", " major: File accessibilty\n", " minor: Unable to open file\n", " #003: H5FD.c line 734 in H5FD_open(): open failed\n", " major: Virtual File Layer\n", " minor: Unable to initialize object\n", - " #004: H5FDsec2.c line 346 in H5FD_sec2_open(): unable to open file: name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_36_strand.fast5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0\n", + " #004: H5FDsec2.c line 346 in H5FD_sec2_open(): unable to open file: name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_348_strand.fast5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0\n", " major: File accessibilty\n", " minor: Unable to open file\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014833698560:\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205861861120:\n", " #000: H5L.c line 805 in H5Lexists(): not a location\n", " major: Invalid arguments to routine\n", " minor: Inappropriate type\n", " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", " major: Invalid arguments to routine\n", " minor: Bad value\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014833698560:\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205861861120:\n", " #000: H5L.c line 805 in H5Lexists(): not a location\n", " major: Invalid arguments to routine\n", " minor: Inappropriate type\n", " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", " major: Invalid arguments to routine\n", " minor: Bad value\n", - "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_36_strand.fast5\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014816913152:\n", + "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_348_strand.fast5\n", + "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_108_strand.fast5\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", " #000: H5F.c line 509 in H5Fopen(): unable to open file\n", " major: File accessibilty\n", " minor: Unable to open file\n", " #001: H5Fint.c line 1400 in H5F__open(): unable to open file\n", " major: File accessibilty\n", " minor: Unable to open file\n", - " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Wed May 1 10:26:17 2019\n", - ", name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_343_strand.fast5', tent_flags = 0\n", + " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Thu May 2 10:32:47 2019\n", + ", name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_318_strand.fast5', tent_flags = 0\n", " major: File accessibilty\n", " minor: Unable to open file\n", " #003: H5FD.c line 734 in H5FD_open(): open failed\n", " major: Virtual File Layer\n", " minor: Unable to initialize object\n", - " #004: H5FDsec2.c line 346 in H5FD_sec2_open(): unable to open file: name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_343_strand.fast5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0\n", + " #004: H5FDsec2.c line 346 in H5FD_sec2_open(): unable to open file: name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_318_strand.fast5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0\n", " major: File accessibilty\n", " minor: Unable to open file\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014816913152:\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", " #000: H5L.c line 805 in H5Lexists(): not a location\n", " major: Invalid arguments to routine\n", " minor: Inappropriate type\n", " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", " major: Invalid arguments to routine\n", " minor: Bad value\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014816913152:\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", " #000: H5L.c line 805 in H5Lexists(): not a location\n", " major: Invalid arguments to routine\n", " minor: Inappropriate type\n", " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", " major: Invalid arguments to routine\n", " minor: Bad value\n", - "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_343_strand.fast5\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014825305856:\n", + "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_318_strand.fast5\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205845075712:\n", " #000: H5F.c line 509 in H5Fopen(): unable to open file\n", " major: File accessibilty\n", " minor: Unable to open file\n", " #001: H5Fint.c line 1400 in H5F__open(): unable to open file\n", " major: File accessibilty\n", " minor: Unable to open file\n", - " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Wed May 1 10:26:17 2019\n", - ", name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_354_strand.fast5', tent_flags = 0\n", + " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Thu May 2 10:32:47 2019\n", + ", name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_290_strand.fast5', tent_flags = 0\n", " major: File accessibilty\n", " minor: Unable to open file\n", " #003: H5FD.c line 734 in H5FD_open(): open failed\n", " major: Virtual File Layer\n", " minor: Unable to initialize object\n", - " #004: H5FDsec2.c line 346 in H5FD_sec2_open(): unable to open file: name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_354_strand.fast5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0\n", + " #004: H5FDsec2.c line 346 in H5FD_sec2_open(): unable to open file: name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_290_strand.fast5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0\n", " major: File accessibilty\n", " minor: Unable to open file\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014825305856:\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205845075712:\n", " #000: H5L.c line 805 in H5Lexists(): not a location\n", " major: Invalid arguments to routine\n", " minor: Inappropriate type\n", " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", " major: Invalid arguments to routine\n", " minor: Bad value\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014825305856:\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205845075712:\n", " #000: H5L.c line 805 in H5Lexists(): not a location\n", " major: Invalid arguments to routine\n", " minor: Inappropriate type\n", " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", " major: Invalid arguments to routine\n", " minor: Bad value\n", - "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_354_strand.fast5\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014825305856:\n", + "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_290_strand.fast5\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205845075712:\n", " #000: H5F.c line 509 in H5Fopen(): unable to open file\n", " major: File accessibilty\n", " minor: Unable to open file\n", " #001: H5Fint.c line 1400 in H5F__open(): unable to open file\n", " major: File accessibilty\n", " minor: Unable to open file\n", - " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Wed May 1 10:26:17 2019\n", + " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Thu May 2 10:32:47 2019\n", ", name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_103_strand.fast5', tent_flags = 0\n", " major: File accessibilty\n", " minor: Unable to open file\n", @@ -652,14 +665,14 @@ " #004: H5FDsec2.c line 346 in H5FD_sec2_open(): unable to open file: name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_103_strand.fast5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0\n", " major: File accessibilty\n", " minor: Unable to open file\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014825305856:\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205845075712:\n", " #000: H5L.c line 805 in H5Lexists(): not a location\n", " major: Invalid arguments to routine\n", " minor: Inappropriate type\n", " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", " major: Invalid arguments to routine\n", " minor: Bad value\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014825305856:\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205845075712:\n", " #000: H5L.c line 805 in H5Lexists(): not a location\n", " major: Invalid arguments to routine\n", " minor: Inappropriate type\n", @@ -667,14 +680,14 @@ " major: Invalid arguments to routine\n", " minor: Bad value\n", "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_103_strand.fast5\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014816913152:\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", " #000: H5F.c line 509 in H5Fopen(): unable to open file\n", " major: File accessibilty\n", " minor: Unable to open file\n", " #001: H5Fint.c line 1400 in H5F__open(): unable to open file\n", " major: File accessibilty\n", " minor: Unable to open file\n", - " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Wed May 1 10:26:17 2019\n", + " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Thu May 2 10:32:47 2019\n", ", name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_418_strand.fast5', tent_flags = 0\n", " major: File accessibilty\n", " minor: Unable to open file\n", @@ -684,14 +697,14 @@ " #004: H5FDsec2.c line 346 in H5FD_sec2_open(): unable to open file: name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_418_strand.fast5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0\n", " major: File accessibilty\n", " minor: Unable to open file\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014816913152:\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", " #000: H5L.c line 805 in H5Lexists(): not a location\n", " major: Invalid arguments to routine\n", " minor: Inappropriate type\n", " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", " major: Invalid arguments to routine\n", " minor: Bad value\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014816913152:\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", " #000: H5L.c line 805 in H5Lexists(): not a location\n", " major: Invalid arguments to routine\n", " minor: Inappropriate type\n", @@ -699,15 +712,14 @@ " major: Invalid arguments to routine\n", " minor: Bad value\n", "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_418_strand.fast5\n", - "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_290_strand.fast5\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014816913152:\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", " #000: H5F.c line 509 in H5Fopen(): unable to open file\n", " major: File accessibilty\n", " minor: Unable to open file\n", " #001: H5Fint.c line 1400 in H5F__open(): unable to open file\n", " major: File accessibilty\n", " minor: Unable to open file\n", - " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Wed May 1 10:26:17 2019\n", + " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Thu May 2 10:32:47 2019\n", ", name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_191_strand.fast5', tent_flags = 0\n", " major: File accessibilty\n", " minor: Unable to open file\n", @@ -717,14 +729,14 @@ " #004: H5FDsec2.c line 346 in H5FD_sec2_open(): unable to open file: name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_191_strand.fast5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0\n", " major: File accessibilty\n", " minor: Unable to open file\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014816913152:\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", " #000: H5L.c line 805 in H5Lexists(): not a location\n", " major: Invalid arguments to routine\n", " minor: Inappropriate type\n", " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", " major: Invalid arguments to routine\n", " minor: Bad value\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014816913152:\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", " #000: H5L.c line 805 in H5Lexists(): not a location\n", " major: Invalid arguments to routine\n", " minor: Inappropriate type\n", @@ -732,46 +744,46 @@ " major: Invalid arguments to routine\n", " minor: Bad value\n", "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_191_strand.fast5\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014825305856:\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", " #000: H5F.c line 509 in H5Fopen(): unable to open file\n", " major: File accessibilty\n", " minor: Unable to open file\n", " #001: H5Fint.c line 1400 in H5F__open(): unable to open file\n", " major: File accessibilty\n", " minor: Unable to open file\n", - " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Wed May 1 10:26:17 2019\n", - ", name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_382_strand.fast5', tent_flags = 0\n", + " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Thu May 2 10:32:47 2019\n", + ", name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_301_strand.fast5', tent_flags = 0\n", " major: File accessibilty\n", " minor: Unable to open file\n", " #003: H5FD.c line 734 in H5FD_open(): open failed\n", " major: Virtual File Layer\n", " minor: Unable to initialize object\n", - " #004: H5FDsec2.c line 346 in H5FD_sec2_open(): unable to open file: name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_382_strand.fast5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0\n", + " #004: H5FDsec2.c line 346 in H5FD_sec2_open(): unable to open file: name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_301_strand.fast5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0\n", " major: File accessibilty\n", " minor: Unable to open file\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014825305856:\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", " #000: H5L.c line 805 in H5Lexists(): not a location\n", " major: Invalid arguments to routine\n", " minor: Inappropriate type\n", " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", " major: Invalid arguments to routine\n", " minor: Bad value\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014825305856:\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", " #000: H5L.c line 805 in H5Lexists(): not a location\n", " major: Invalid arguments to routine\n", " minor: Inappropriate type\n", " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", " major: Invalid arguments to routine\n", " minor: Bad value\n", - "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_382_strand.fast5\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014816913152:\n", + "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_301_strand.fast5\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", " #000: H5F.c line 509 in H5Fopen(): unable to open file\n", " major: File accessibilty\n", " minor: Unable to open file\n", " #001: H5Fint.c line 1400 in H5F__open(): unable to open file\n", " major: File accessibilty\n", " minor: Unable to open file\n", - " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Wed May 1 10:26:17 2019\n", + " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Thu May 2 10:32:47 2019\n", ", name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_224_strand.fast5', tent_flags = 0\n", " major: File accessibilty\n", " minor: Unable to open file\n", @@ -781,14 +793,14 @@ " #004: H5FDsec2.c line 346 in H5FD_sec2_open(): unable to open file: name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_224_strand.fast5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0\n", " major: File accessibilty\n", " minor: Unable to open file\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014816913152:\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", " #000: H5L.c line 805 in H5Lexists(): not a location\n", " major: Invalid arguments to routine\n", " minor: Inappropriate type\n", " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", " major: Invalid arguments to routine\n", " minor: Bad value\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014816913152:\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", " #000: H5L.c line 805 in H5Lexists(): not a location\n", " major: Invalid arguments to routine\n", " minor: Inappropriate type\n", @@ -796,15 +808,14 @@ " major: Invalid arguments to routine\n", " minor: Bad value\n", "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_224_strand.fast5\n", - "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_301_strand.fast5\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014825305856:\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", " #000: H5F.c line 509 in H5Fopen(): unable to open file\n", " major: File accessibilty\n", " minor: Unable to open file\n", " #001: H5Fint.c line 1400 in H5F__open(): unable to open file\n", " major: File accessibilty\n", " minor: Unable to open file\n", - " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Wed May 1 10:26:17 2019\n", + " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Thu May 2 10:32:47 2019\n", ", name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_410_strand.fast5', tent_flags = 0\n", " major: File accessibilty\n", " minor: Unable to open file\n", @@ -814,14 +825,14 @@ " #004: H5FDsec2.c line 346 in H5FD_sec2_open(): unable to open file: name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_410_strand.fast5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0\n", " major: File accessibilty\n", " minor: Unable to open file\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014825305856:\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", " #000: H5L.c line 805 in H5Lexists(): not a location\n", " major: Invalid arguments to routine\n", " minor: Inappropriate type\n", " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", " major: Invalid arguments to routine\n", " minor: Bad value\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014825305856:\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", " #000: H5L.c line 805 in H5Lexists(): not a location\n", " major: Invalid arguments to routine\n", " minor: Inappropriate type\n", @@ -829,14 +840,78 @@ " major: Invalid arguments to routine\n", " minor: Bad value\n", "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_410_strand.fast5\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014825305856:\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", " #000: H5F.c line 509 in H5Fopen(): unable to open file\n", " major: File accessibilty\n", " minor: Unable to open file\n", " #001: H5Fint.c line 1400 in H5F__open(): unable to open file\n", " major: File accessibilty\n", " minor: Unable to open file\n", - " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Wed May 1 10:26:17 2019\n", + " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Thu May 2 10:32:47 2019\n", + ", name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_382_strand.fast5', tent_flags = 0\n", + " major: File accessibilty\n", + " minor: Unable to open file\n", + " #003: H5FD.c line 734 in H5FD_open(): open failed\n", + " major: Virtual File Layer\n", + " minor: Unable to initialize object\n", + " #004: H5FDsec2.c line 346 in H5FD_sec2_open(): unable to open file: name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_382_strand.fast5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0\n", + " major: File accessibilty\n", + " minor: Unable to open file\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", + " #000: H5L.c line 805 in H5Lexists(): not a location\n", + " major: Invalid arguments to routine\n", + " minor: Inappropriate type\n", + " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", + " major: Invalid arguments to routine\n", + " minor: Bad value\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", + " #000: H5L.c line 805 in H5Lexists(): not a location\n", + " major: Invalid arguments to routine\n", + " minor: Inappropriate type\n", + " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", + " major: Invalid arguments to routine\n", + " minor: Bad value\n", + "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_382_strand.fast5\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", + " #000: H5F.c line 509 in H5Fopen(): unable to open file\n", + " major: File accessibilty\n", + " minor: Unable to open file\n", + " #001: H5Fint.c line 1400 in H5F__open(): unable to open file\n", + " major: File accessibilty\n", + " minor: Unable to open file\n", + " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Thu May 2 10:32:47 2019\n", + ", name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_192_strand.fast5', tent_flags = 0\n", + " major: File accessibilty\n", + " minor: Unable to open file\n", + " #003: H5FD.c line 734 in H5FD_open(): open failed\n", + " major: Virtual File Layer\n", + " minor: Unable to initialize object\n", + " #004: H5FDsec2.c line 346 in H5FD_sec2_open(): unable to open file: name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_192_strand.fast5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0\n", + " major: File accessibilty\n", + " minor: Unable to open file\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", + " #000: H5L.c line 805 in H5Lexists(): not a location\n", + " major: Invalid arguments to routine\n", + " minor: Inappropriate type\n", + " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", + " major: Invalid arguments to routine\n", + " minor: Bad value\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", + " #000: H5L.c line 805 in H5Lexists(): not a location\n", + " major: Invalid arguments to routine\n", + " minor: Inappropriate type\n", + " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", + " major: Invalid arguments to routine\n", + " minor: Bad value\n", + "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_192_strand.fast5\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", + " #000: H5F.c line 509 in H5Fopen(): unable to open file\n", + " major: File accessibilty\n", + " minor: Unable to open file\n", + " #001: H5Fint.c line 1400 in H5F__open(): unable to open file\n", + " major: File accessibilty\n", + " minor: Unable to open file\n", + " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Thu May 2 10:32:47 2019\n", ", name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_113_strand.fast5', tent_flags = 0\n", " major: File accessibilty\n", " minor: Unable to open file\n", @@ -846,14 +921,14 @@ " #004: H5FDsec2.c line 346 in H5FD_sec2_open(): unable to open file: name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_113_strand.fast5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0\n", " major: File accessibilty\n", " minor: Unable to open file\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014825305856:\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", " #000: H5L.c line 805 in H5Lexists(): not a location\n", " major: Invalid arguments to routine\n", " minor: Inappropriate type\n", " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", " major: Invalid arguments to routine\n", " minor: Bad value\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014825305856:\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", " #000: H5L.c line 805 in H5Lexists(): not a location\n", " major: Invalid arguments to routine\n", " minor: Inappropriate type\n", @@ -861,14 +936,14 @@ " major: Invalid arguments to routine\n", " minor: Bad value\n", "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_113_strand.fast5\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014816913152:\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205845075712:\n", " #000: H5F.c line 509 in H5Fopen(): unable to open file\n", " major: File accessibilty\n", " minor: Unable to open file\n", " #001: H5Fint.c line 1400 in H5F__open(): unable to open file\n", " major: File accessibilty\n", " minor: Unable to open file\n", - " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Wed May 1 10:26:17 2019\n", + " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Thu May 2 10:32:47 2019\n", ", name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_382_strand.fast5', tent_flags = 0\n", " major: File accessibilty\n", " minor: Unable to open file\n", @@ -878,14 +953,14 @@ " #004: H5FDsec2.c line 346 in H5FD_sec2_open(): unable to open file: name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_382_strand.fast5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0\n", " major: File accessibilty\n", " minor: Unable to open file\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014816913152:\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205845075712:\n", " #000: H5L.c line 805 in H5Lexists(): not a location\n", " major: Invalid arguments to routine\n", " minor: Inappropriate type\n", " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", " major: Invalid arguments to routine\n", " minor: Bad value\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014816913152:\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205845075712:\n", " #000: H5L.c line 805 in H5Lexists(): not a location\n", " major: Invalid arguments to routine\n", " minor: Inappropriate type\n", @@ -893,39 +968,39 @@ " major: Invalid arguments to routine\n", " minor: Bad value\n", "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_382_strand.fast5\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014833698560:\n", + "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_38_strand.fast5\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205861861120:\n", " #000: H5F.c line 509 in H5Fopen(): unable to open file\n", " major: File accessibilty\n", " minor: Unable to open file\n", " #001: H5Fint.c line 1400 in H5F__open(): unable to open file\n", " major: File accessibilty\n", " minor: Unable to open file\n", - " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Wed May 1 10:26:17 2019\n", - ", name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_38_strand.fast5', tent_flags = 0\n", + " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Thu May 2 10:32:47 2019\n", + ", name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_354_strand.fast5', tent_flags = 0\n", " major: File accessibilty\n", " minor: Unable to open file\n", " #003: H5FD.c line 734 in H5FD_open(): open failed\n", " major: Virtual File Layer\n", " minor: Unable to initialize object\n", - " #004: H5FDsec2.c line 346 in H5FD_sec2_open(): unable to open file: name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_38_strand.fast5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0\n", + " #004: H5FDsec2.c line 346 in H5FD_sec2_open(): unable to open file: name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_354_strand.fast5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0\n", " major: File accessibilty\n", " minor: Unable to open file\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014833698560:\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205861861120:\n", " #000: H5L.c line 805 in H5Lexists(): not a location\n", " major: Invalid arguments to routine\n", " minor: Inappropriate type\n", " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", " major: Invalid arguments to routine\n", " minor: Bad value\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140014833698560:\n", + "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205861861120:\n", " #000: H5L.c line 805 in H5Lexists(): not a location\n", " major: Invalid arguments to routine\n", " minor: Inappropriate type\n", " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", " major: Invalid arguments to routine\n", " minor: Bad value\n", - "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_38_strand.fast5\n", - "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_192_strand.fast5\n", + "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_354_strand.fast5\n", "[post-run summary] total reads: 21, unparseable: 0, qc fail: 0, could not calibrate: 0, no alignment: 0, bad fast5: 21\n", "Checking arguments\n", "Testing output dir writability\n", @@ -940,12 +1015,12 @@ " args.func(args)\n", " File \"/home/aleg/Programming/NanopolishComp/NanopolishComp/__main__.py\", line 80, in Eventalign_collapse_main\n", " quiet = args.quiet)\n", - " File \"/home/aleg/Programming/NanopolishComp/NanopolishComp/Eventalign_collapse.py\", line 129, in __init__\n", + " File \"/home/aleg/Programming/NanopolishComp/NanopolishComp/Eventalign_collapse.py\", line 148, in __init__\n", " raise E\n", - " File \"/home/aleg/Programming/NanopolishComp/NanopolishComp/Eventalign_collapse.py\", line 119, in __init__\n", + " File \"/home/aleg/Programming/NanopolishComp/NanopolishComp/Eventalign_collapse.py\", line 138, in __init__\n", " raise E\n", "NanopolishComp.common.NanopolishCompError: Traceback (most recent call last):\n", - " File \"/home/aleg/Programming/NanopolishComp/NanopolishComp/Eventalign_collapse.py\", line 152, in _split_reads\n", + " File \"/home/aleg/Programming/NanopolishComp/NanopolishComp/Eventalign_collapse.py\", line 176, in _split_reads\n", " cur_read_id = event_l[idx[\"read_id\"]]\n", "IndexError: list index out of range\n", "\n" @@ -980,11 +1055,11 @@ }, { "cell_type": "code", - "execution_count": 14, + "execution_count": 5, "metadata": { "ExecuteTime": { - "end_time": "2019-05-01T09:30:12.775617Z", - "start_time": "2019-05-01T09:30:12.765015Z" + "end_time": "2019-05-02T09:32:47.744368Z", + "start_time": "2019-05-02T09:32:47.663524Z" } }, "outputs": [], @@ -1008,8 +1083,8 @@ "execution_count": 6, "metadata": { "ExecuteTime": { - "end_time": "2019-05-01T09:26:18.088788Z", - "start_time": "2019-05-01T09:26:18.077388Z" + "end_time": "2019-05-02T09:32:47.769186Z", + "start_time": "2019-05-02T09:32:47.746336Z" } }, "outputs": [ @@ -1092,8 +1167,8 @@ "execution_count": 7, "metadata": { "ExecuteTime": { - "end_time": "2019-05-01T09:26:18.442943Z", - "start_time": "2019-05-01T09:26:18.091265Z" + "end_time": "2019-05-02T09:32:48.110916Z", + "start_time": "2019-05-02T09:32:47.771813Z" }, "scrolled": false }, @@ -1103,25 +1178,10 @@ "output_type": "stream", "text": [ "Checking arguments\n", - "\tTesting input file readability\n", "Testing output dir writability\n", - "\tChecking number of threads\n", - "\tChecking if stat_fields names are valid\n", "Starting to process files\n", - "\t[process_read 1] Starting processing reads\n", - "\t[split_reads] Start reading input file/stream\n", - "\t[process_read 2] Starting processing reads\n", - "\t[process_read 4] Starting processing reads\n", - "\t[write_output] Start rwriting output\n", - "\t[process_read 3] Starting processing reads\n", - "11 reads [00:00, 101.86 reads/s]\t[split_reads] Done\n", - "\t[process_read 3] Done\n", - "\t[process_read 1] Done\n", - "\t[process_read 4] Done\n", - "\t[process_read 2] Done\n", - "21 reads [00:00, 100.25 reads/s]\n", - "\t[write_output] Done\n", - "[Eventalign_collapse] total reads: 21 [82.03 reads/s]\n", + "21 reads [00:00, 83.37 reads/s]\n", + "[Eventalign_collapse] total reads: 21 [78.29 reads/s]\n", "\n" ] }, @@ -1145,11 +1205,11 @@ "YCR030C 1578 2576 1 971 11.487010000000005 23 0 27 38029 29704 \n", "YHR174W 0 839 2 825 9.659210000000002 15 0 14 67734 24231 \n", "YHR174W 218 1309 3 1028 11.06325000000001 36 0 63 91966 30801 \n", - "YHR174W 462 1309 4 818 10.73776000000001 18 0 29 122768 24589 \n", - "YLR441C 173 764 5 554 5.556939999999999 20 0 37 147358 16437 \n", + "YLR441C 173 764 5 554 5.556939999999999 20 0 37 122768 16437 \n", + "YHR174W 462 1309 4 818 10.73776000000001 18 0 29 139206 24589 \n", "YGR192C 1 989 6 927 11.731470000000003 37 0 61 163796 27388 \n", - "YDR500C 9 252 8 231 2.9179100000000027 7 0 14 191185 6751 \n", - "YGR192C 3 995 7 946 12.30464000000001 31 0 50 197937 28123 \n", + "YGR192C 3 995 7 946 12.30464000000001 31 0 50 191185 28123 \n", + "YDR500C 9 252 8 231 2.9179100000000027 7 0 14 219309 6751 \n", "\n" ] } @@ -1159,7 +1219,7 @@ "outdir = \"./output/eventalign_collapse\"\n", "outprefix = \"basic\"\n", "\n", - "Eventalign_collapse (input_fn=input_fn, outdir=outdir, outprefix=outprefix, threads=6, verbose=True)\n", + "Eventalign_collapse (input_fn=input_fn, outdir=outdir, outprefix=outprefix, threads=6)\n", "\n", "head(\"./output/eventalign_collapse/basic_eventalign_collapse.tsv\")\n", "head(\"./output/eventalign_collapse/basic_eventalign_collapse.tsv.idx\")" @@ -1177,8 +1237,8 @@ "execution_count": 8, "metadata": { "ExecuteTime": { - "end_time": "2019-05-01T09:26:18.830954Z", - "start_time": "2019-05-01T09:26:18.446219Z" + "end_time": "2019-05-02T09:32:48.423433Z", + "start_time": "2019-05-02T09:32:48.115915Z" } }, "outputs": [ @@ -1187,25 +1247,10 @@ "output_type": "stream", "text": [ "Checking arguments\n", - "\tTesting input file readability\n", "Testing output dir writability\n", - "\tChecking number of threads\n", - "\tChecking if stat_fields names are valid\n", "Starting to process files\n", - "\t[split_reads] Start reading input file/stream\n", - "\t[process_read 1] Starting processing reads\n", - "\t[process_read 2] Starting processing reads\n", - "\t[process_read 3] Starting processing reads\n", - "\t[write_output] Start rwriting output\n", - "0 reads [00:00, ? reads/s]\t[process_read 4] Starting processing reads\n", - "17 reads [00:00, 69.40 reads/s]\t[split_reads] Done\n", - "\t[process_read 1] Done\n", - "\t[process_read 2] Done\n", - "\t[process_read 4] Done\n", - "\t[process_read 3] Done\n", - "21 reads [00:00, 73.41 reads/s]\n", - "\t[write_output] Done\n", - "[Eventalign_collapse] total reads: 21 [69.34 reads/s]\n", + "21 reads [00:00, 92.53 reads/s]\n", + "[Eventalign_collapse] total reads: 21 [87.47 reads/s]\n", "\n" ] }, @@ -1228,9 +1273,9 @@ "YGR240C 1656 2960 0 1250 13.788570000000009 35 0 54 0 53046 \n", "YCR030C 1578 2576 1 971 11.487010000000005 23 0 27 53047 41374 \n", "YHR174W 0 839 2 825 9.659210000000002 15 0 14 94422 33595 \n", - "YLR441C 173 764 5 554 5.556939999999999 20 0 37 128018 23103 \n", - "YHR174W 218 1309 3 1028 11.06325000000001 36 0 63 151122 43155 \n", - "YHR174W 462 1309 4 818 10.73776000000001 18 0 29 194278 34423 \n", + "YHR174W 218 1309 3 1028 11.06325000000001 36 0 63 128018 43155 \n", + "YHR174W 462 1309 4 818 10.73776000000001 18 0 29 171174 34423 \n", + "YLR441C 173 764 5 554 5.556939999999999 20 0 37 205598 23103 \n", "YGR192C 1 989 6 927 11.731470000000003 37 0 61 228702 38529 \n", "YDR500C 9 252 8 231 2.9179100000000027 7 0 14 267232 9541 \n", "YDR224C 0 389 9 376 4.2840300000000004 8 0 13 276774 15465 \n", @@ -1261,8 +1306,8 @@ "execution_count": 9, "metadata": { "ExecuteTime": { - "end_time": "2019-05-01T09:26:19.177183Z", - "start_time": "2019-05-01T09:26:18.834685Z" + "end_time": "2019-05-02T09:32:48.663769Z", + "start_time": "2019-05-02T09:32:48.425846Z" }, "scrolled": false }, @@ -1271,7 +1316,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "[Eventalign_collapse] total reads: 21 [75.34 reads/s]\n", + "[Eventalign_collapse] total reads: 21 [106.77 reads/s]\n", "\n" ] }, @@ -1299,7 +1344,7 @@ "YLR441C 173 764 5 554 5.556939999999999 20 0 37 205598 23103 \n", "YGR192C 1 989 6 927 11.731470000000003 37 0 61 228702 38529 \n", "YDR500C 9 252 8 231 2.9179100000000027 7 0 14 267232 9541 \n", - "YGR192C 3 995 7 946 12.30464000000001 31 0 50 276774 39493 \n", + "YDR224C 0 389 9 376 4.2840300000000004 8 0 13 276774 15465 \n", "\n" ] } @@ -1324,11 +1369,11 @@ }, { "cell_type": "code", - "execution_count": 13, + "execution_count": 10, "metadata": { "ExecuteTime": { - "end_time": "2019-05-01T09:26:50.792567Z", - "start_time": "2019-05-01T09:26:49.056209Z" + "end_time": "2019-05-02T09:32:50.536323Z", + "start_time": "2019-05-02T09:32:48.666817Z" }, "scrolled": false }, @@ -1337,7 +1382,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "[Eventalign_collapse] total reads: 21 [12.6 reads/s]\n", + "[Eventalign_collapse] total reads: 21 [11.5 reads/s]\n", "\n" ] }, @@ -1345,27 +1390,27 @@ "name": "stdout", "output_type": "stream", "text": [ - "#0\tYGR240C\n", + "#1\tYCR030C\n", "ref_pos\tref_kmer\tnum_events\tdwell_time\tNNNNN_dwell_time\tmismatch_dwell_time\tmean\tstd\tmedian\tmad\tnum_signals\tsamples\n", - "1656\tGAAAA\t1\t0.00266\t0.0\t0.0\t105.49774932861328\t1.1988129615783691\t105.4800033569336\t0.852996826171875\t8\t104.343,106.049,106.617,105.196,105.48,107.47,103.347,105.48\n", - "1657\tAAAAC\t1\t0.00764\t0.0\t0.0\t111.09274291992188\t1.667485237121582\t111.0250015258789\t0.9950027465820312\t23\t112.873,106.617,110.03,114.579,111.736,113.726,111.309,109.745,113.157,109.034,111.025,112.162,112.162,110.172,110.598,110.74,111.025,109.461,110.883,112.02,111.878,110.314,109.887\n", - "1658\tAAACA\t1\t0.00398\t0.0\t0.0\t100.11283111572266\t2.855329990386963\t99.50865173339844\t1.7771987915039062\t12\t100.077,97.5182,98.0869,97.0917,97.5182,99.3665,97.9447,99.6508,100.362,105.764,102.636,105.338\n", - "1659\tAACAA\t1\t0.00432\t0.0\t0.0\t90.71566009521484\t3.648205518722534\t89.12989807128906\t2.2747955322265625\t13\t86.4285,87.1394,86.8551,89.1299,87.9925,91.5468,90.9781,95.2434,95.6699,97.376,89.1299,94.3903,87.4238\n", - "1660\tACAAA\t1\t0.00498\t0.0\t0.0\t81.67988586425781\t2.026559352874756\t81.59459686279297\t1.56390380859375\t15\t81.7368,79.6041,80.7415,82.5898,84.7224,80.8837,86.2864,82.3055,81.5946,79.1776,78.8932,83.3007,79.7463,80.4572,83.1585\n", - "1661\tCAAAG\t1\t0.00564\t0.0\t0.0\t109.75365447998047\t4.070319175720215\t111.16699981689453\t1.8479995727539062\t17\t113.157,111.167,103.347,111.736,111.594,108.892,112.731,111.025,109.319,113.3,110.883,111.736,113.868,111.878,107.897,105.764,97.5182\n", - "1662\tAAAGA\t1\t0.00963\t0.0\t0.0\t117.81983184814453\t3.554028034210205\t118.13400268554688\t2.7009963989257812\t29\t122.399,115.006,115.29,116.996,116.996,109.745,118.276,123.963,121.688,119.555,120.835,121.688,110.456,118.987,118.134,114.721,115.574,120.835,121.83,118.134,118.134,116.57,121.688,112.162,118.418,116.427,116.57,113.584,122.114\n", - "1663\tAAGAT\t1\t0.00299\t0.0\t0.0\t137.0111083984375\t3.2223927974700928\t137.18499755859375\t2.4169921875\t9\t134.768,138.18,131.356,141.592,137.185,137.327,134.057,142.019,136.616\n", + "1578\tCCACC\t1\t0.00365\t0.0\t0.0\t70.06341552734375\t2.593737840652466\t70.67729949951172\t1.4680023193359375\t11\t70.6773,72.1454,71.4114,63.6306,69.2093,69.2093,67.3008,72.5858,69.9433,72.8794,71.705\n", + "1579\tCACCC\t15\t0.09761000000000002\t0.0\t0.0\t74.59468841552734\t3.2702603340148926\t75.08149719238281\t2.4958038330078125\t294\t75.0815,75.8156,79.6326,78.0177,75.3752,77.2837,78.0177,72.2922,76.99,74.7879,75.3752,75.522,75.6688,73.3199,74.9347,77.5773,73.7603,74.3475,72.7326,75.522,77.2837,75.2284,76.6964,78.4581,78.4581,79.7794,76.5496,76.8432,70.2369,70.2369,81.1006,77.8709,74.9347,72.439,75.8156,77.5773,75.9624,77.4305,76.1092,77.2837,64.5114,74.4943,78.4581,77.4305,76.8432,75.0815,76.1092,78.3113,76.5496,75.6688,76.5496,77.4305,78.6049,76.4028,75.8156,77.1368,71.8518,76.4028,75.8156,75.9624,74.9347,78.3113,72.2922,75.6688,75.0815,75.522,75.9624,70.6773,69.9433,69.2093,68.3284,69.3561,69.2093,69.7965,67.888,68.9157,68.622,69.0625,69.7965,73.173,76.1092,74.7879,75.2284,78.3113,76.256,78.3113,77.7241,72.7326,73.6135,78.6049,75.522,75.8156,74.0539,67.3008,72.439,72.2922,67.0072,74.6411,76.1092,75.8156,73.3199,77.2837,70.3837,73.4667,74.7879,76.6964,79.1921,73.3199,76.6964,76.4028,71.1178,76.1092,79.7794,77.7241,77.1368,74.3475,78.6049,78.8985,77.2837,77.7241,70.0901,79.0453,76.1092,73.6135,78.1645,79.0453,75.8156,79.3389,79.0453,77.1368,78.1645,78.3113,77.8709,79.4858,75.8156,76.4028,77.2837,77.4305,79.6326,77.4305,81.8347,76.5496,76.5496,78.8985,74.7879,77.2837,80.2198,75.6688,78.1645,76.99,79.3389,79.0453,71.5582,78.6049,79.7794,78.3113,78.1645,75.3752,76.8432,80.073,78.3113,80.2198,80.073,80.9538,77.5773,77.8709,75.6688,80.807,77.8709,78.0177,79.3389,80.2198,80.2198,76.1092,77.8709,76.5496,76.6964,77.8709,77.1368,75.9624,76.99,72.2922,71.8518,73.9071,68.9157,70.0901,71.8518,75.3752,73.9071,72.1454,73.6135,74.4943,73.173,75.9624,75.0815,74.6411,75.0815,75.2284,74.4943,75.522,76.6964,72.7326,73.7603,74.9347,75.522,74.0539,71.2646,70.3837,72.439,75.522,75.9624,71.705,72.2922,70.8241,71.1178,70.971,74.7879,75.6688,74.6411,72.1454,73.0262,71.4114,73.9071,74.2007,75.0815,74.4943,72.1454,72.8794,72.1454,69.6497,71.5582,72.439,70.6773,69.7965,68.4752,68.7689,73.6135,73.7603,72.2922,71.4114,69.2093,70.2369,73.3199,72.439,71.5582,67.4476,72.8794,72.2922,72.5858,72.439,73.9071,69.6497,72.2922,73.6135,74.4943,73.0262,70.0901,72.439,71.8518,72.1454,71.9986,70.2369,74.0539,70.971,72.1454,71.2646,71.8518,71.1178,71.5582,70.971,69.2093,70.8241,71.4114,71.2646,72.1454,70.5305,69.6497,70.6773,69.9433,72.8794,67.5944,66.7135,70.5305,69.7965,68.622,73.4667,73.7603,76.1092,77.1368,74.3475,75.8156,74.7879,76.8432,75.8156\n", + "1580\tACCCT\t1\t0.00232\t0.0\t0.0\t67.23785400390625\t1.7063778638839722\t67.88800048828125\t2.2021026611328125\t7\t64.9519,65.6859,67.888,68.1816,68.1816,65.6859,70.0901\n", + "1581\tCCCTC\t1\t0.00232\t0.0\t0.0\t72.0615005493164\t1.1475614309310913\t72.58580017089844\t1.0277023315429688\t7\t70.3837,72.5858,70.6773,71.4114,73.0262,73.6135,72.7326\n", + "1582\tCCTCA\t5\t0.0156\t0.0\t0.0\t73.5634994506836\t2.3691813945770264\t73.76029968261719\t1.614898681640625\t47\t75.522,77.8709,75.2284,74.3475,75.9624,76.6964,72.1454,71.1178,71.1178,72.439,76.256,74.0539,73.0262,73.4667,70.6773,71.5582,69.7965,71.1178,68.3284,70.6773,73.6135,69.6497,67.4476,73.7603,74.3475,72.8794,74.0539,73.3199,74.4943,75.522,72.8794,72.5858,71.2646,73.4667,74.3475,74.4943,74.9347,71.9986,72.2922,76.8432,74.9347,76.5496,75.6688,75.2284,75.0815,76.6964,77.7241\n", + "1583\tCTCAA\t1\t0.00398\t0.0\t0.0\t77.58948516845703\t1.5072672367095947\t78.16450500488281\t0.7339935302734375\t12\t74.3475,75.0815,78.3113,78.8985,77.8709,78.3113,76.4028,78.0177,77.1368,78.3113,78.8985,79.4858\n", + "1584\tTCAAG\t1\t0.01096\t0.0\t0.0\t83.52072143554688\t3.1505558490753174\t84.03679656982422\t2.3488998413085938\t33\t88.441,79.9262,81.6879,81.9815,85.0644,86.9729,84.624,81.1006,76.99,79.0453,79.9262,84.0368,92.1112,83.0091,84.1836,80.807,84.0368,85.7985,87.2665,85.6516,83.0091,87.7069,81.2474,84.0368,79.1921,79.6326,87.2665,83.4495,84.0368,83.7432,80.807,84.624,84.7708\n", + "1585\tCAAGG\t1\t0.00232\t0.0\t0.0\t105.23970794677734\t3.632479667663574\t104.2959976196289\t1.7620010375976562\t7\t113.251,102.534,104.296,103.415,106.498,101.36,105.324\n", "\n", "ref_id ref_start ref_end read_id kmers dwell_time NNNNN_kmers mismatch_kmers missing_kmers byte_offset byte_len \n", - "YGR240C 1656 2960 0 1250 13.788570000000009 35 0 54 0 461011 \n", - "YCR030C 1578 2576 1 971 11.487010000000005 23 0 27 461012 376326 \n", - "YHR174W 0 839 2 825 9.659210000000002 15 0 14 837339 317027 \n", - "YHR174W 218 1309 3 1028 11.06325000000001 36 0 63 1154367 372126 \n", + "YCR030C 1578 2576 1 971 11.487010000000005 23 0 27 0 376326 \n", + "YHR174W 0 839 2 825 9.659210000000002 15 0 14 376327 317027 \n", + "YHR174W 218 1309 3 1028 11.06325000000001 36 0 63 693355 372126 \n", + "YGR240C 1656 2960 0 1250 13.788570000000009 35 0 54 1065482 461011 \n", "YLR441C 173 764 5 554 5.556939999999999 20 0 37 1526494 190670 \n", "YHR174W 462 1309 4 818 10.73776000000001 18 0 29 1717165 342528 \n", "YDR500C 9 252 8 231 2.9179100000000027 7 0 14 2059694 93821 \n", "YGR192C 1 989 6 927 11.731470000000003 37 0 61 2153516 376317 \n", - "YGR192C 3 995 7 946 12.30464000000001 31 0 50 2529834 392222 \n", + "YDR224C 0 389 9 376 4.2840300000000004 8 0 13 2529834 141262 \n", "\n" ] } @@ -1393,8 +1438,8 @@ "execution_count": 11, "metadata": { "ExecuteTime": { - "end_time": "2019-05-01T09:26:21.523790Z", - "start_time": "2019-05-01T09:26:21.078127Z" + "end_time": "2019-05-02T09:32:51.031323Z", + "start_time": "2019-05-02T09:32:50.543356Z" }, "scrolled": false }, @@ -1442,20 +1487,6 @@ " \n", " \n", " \n", - " 9\n", - " YDR224C\n", - " 0\n", - " 389\n", - " 9\n", - " 376\n", - " 4.28403\n", - " 8\n", - " 0\n", - " 13\n", - " 316268\n", - " 15465\n", - " \n", - " \n", " 10\n", " YIL117C\n", " 27\n", @@ -1470,6 +1501,20 @@ " 37225\n", " \n", " \n", + " 13\n", + " YPL198W\n", + " 10\n", + " 719\n", + " 13\n", + " 667\n", + " 8.79275\n", + " 30\n", + " 0\n", + " 44\n", + " 409081\n", + " 27943\n", + " \n", + " \n", " 7\n", " YDR500C\n", " 9\n", @@ -1484,32 +1529,32 @@ " 9541\n", " \n", " \n", - " 14\n", - " YDR382W\n", - " 5\n", - " 329\n", - " 14\n", - " 308\n", - " 7.05602\n", - " 13\n", + " 6\n", + " YGR192C\n", + " 1\n", + " 989\n", + " 6\n", + " 927\n", + " 11.73147\n", + " 37\n", " 0\n", - " 16\n", - " 437025\n", - " 13152\n", + " 61\n", + " 228702\n", + " 38529\n", " \n", " \n", - " 13\n", - " YPL198W\n", - " 10\n", - " 719\n", - " 13\n", - " 667\n", - " 8.79275\n", - " 30\n", + " 15\n", + " YLR110C\n", + " 14\n", + " 395\n", + " 15\n", + " 364\n", + " 4.61444\n", + " 9\n", " 0\n", - " 44\n", - " 409081\n", - " 27943\n", + " 17\n", + " 450178\n", + " 15023\n", " \n", " \n", "\n", @@ -1517,18 +1562,18 @@ ], "text/plain": [ " ref_id ref_start ref_end read_id kmers dwell_time NNNNN_kmers \\\n", - "9 YDR224C 0 389 9 376 4.28403 8 \n", "10 YIL117C 27 953 10 889 13.64007 23 \n", - "7 YDR500C 9 252 8 231 2.91791 7 \n", - "14 YDR382W 5 329 14 308 7.05602 13 \n", "13 YPL198W 10 719 13 667 8.79275 30 \n", + "7 YDR500C 9 252 8 231 2.91791 7 \n", + "6 YGR192C 1 989 6 927 11.73147 37 \n", + "15 YLR110C 14 395 15 364 4.61444 9 \n", "\n", " mismatch_kmers missing_kmers byte_offset byte_len \n", - "9 0 13 316268 15465 \n", "10 0 37 331734 37225 \n", + "13 0 44 409081 27943 \n", "7 0 14 267232 9541 \n", - "14 0 16 437025 13152 \n", - "13 0 44 409081 27943 " + "6 0 61 228702 38529 \n", + "15 0 17 450178 15023 " ] }, "metadata": {}, @@ -1538,7 +1583,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "#9\tYDR224C\n" + "#10\tYIL117C\n" ] }, { @@ -1575,25 +1620,25 @@ " \n", " \n", " 0\n", - " 0\n", - " ATGTC\n", - " 1\n", - " 0.00299\n", - " 0.0\n", + " 27\n", + " GGCCT\n", + " 4\n", + " 0.03287\n", + " 0.00498\n", " 0.0\n", - " 24307\n", - " 24316\n", + " 57497\n", + " 57596\n", " \n", " \n", " 1\n", + " 31\n", + " TTCCA\n", " 1\n", - " TGTCT\n", - " 1\n", - " 0.00498\n", - " 0.0\n", + " 0.00398\n", + " 0.00000\n", " 0.0\n", - " 24292\n", - " 24307\n", + " 57485\n", + " 57497\n", " \n", " \n", " ...\n", @@ -1607,48 +1652,48 @@ " ...\n", " \n", " \n", - " 374\n", - " 387\n", - " CAAGC\n", - " 11\n", - " 0.04947\n", - " 0.0\n", + " 887\n", + " 951\n", + " GAGTA\n", + " 3\n", + " 0.01163\n", + " 0.00432\n", " 0.0\n", - " 11435\n", - " 11584\n", + " 16588\n", + " 16623\n", " \n", " \n", - " 375\n", - " 388\n", - " AAGCA\n", - " 1\n", - " 0.00764\n", - " 0.0\n", + " 888\n", + " 952\n", + " AGTAA\n", + " 5\n", + " 0.02590\n", + " 0.00000\n", " 0.0\n", - " 11412\n", - " 11435\n", + " 16510\n", + " 16588\n", " \n", " \n", "\n", - "

376 rows × 8 columns

\n", + "

889 rows × 8 columns

\n", "" ], "text/plain": [ " ref_pos ref_kmer num_events dwell_time NNNNN_dwell_time \\\n", - "0 0 ATGTC 1 0.00299 0.0 \n", - "1 1 TGTCT 1 0.00498 0.0 \n", + "0 27 GGCCT 4 0.03287 0.00498 \n", + "1 31 TTCCA 1 0.00398 0.00000 \n", ".. ... ... ... ... ... \n", - "374 387 CAAGC 11 0.04947 0.0 \n", - "375 388 AAGCA 1 0.00764 0.0 \n", + "887 951 GAGTA 3 0.01163 0.00432 \n", + "888 952 AGTAA 5 0.02590 0.00000 \n", "\n", " mismatch_dwell_time start_idx end_idx \n", - "0 0.0 24307 24316 \n", - "1 0.0 24292 24307 \n", + "0 0.0 57497 57596 \n", + "1 0.0 57485 57497 \n", ".. ... ... ... \n", - "374 0.0 11435 11584 \n", - "375 0.0 11412 11435 \n", + "887 0.0 16588 16623 \n", + "888 0.0 16510 16588 \n", "\n", - "[376 rows x 8 columns]" + "[889 rows x 8 columns]" ] }, "metadata": {}, @@ -1658,7 +1703,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "#10\tYIL117C\n" + "#13\tYPL198W\n" ] }, { @@ -1695,25 +1740,25 @@ " \n", " \n", " 0\n", - " 27\n", - " GGCCT\n", - " 4\n", - " 0.03287\n", - " 0.00498\n", + " 10\n", + " AAAAA\n", + " 1\n", + " 0.00697\n", + " 0.00000\n", " 0.0\n", - " 57497\n", - " 57596\n", + " 44620\n", + " 44641\n", " \n", " \n", " 1\n", - " 31\n", - " TTCCA\n", + " 11\n", + " AAAAA\n", " 1\n", - " 0.00398\n", + " 0.01959\n", " 0.00000\n", " 0.0\n", - " 57485\n", - " 57497\n", + " 44561\n", + " 44620\n", " \n", " \n", " ...\n", @@ -1727,48 +1772,48 @@ " ...\n", " \n", " \n", - " 887\n", - " 951\n", - " GAGTA\n", - " 3\n", - " 0.01163\n", - " 0.00432\n", + " 665\n", + " 715\n", + " TGGTT\n", + " 4\n", + " 0.02557\n", + " 0.00797\n", " 0.0\n", - " 16588\n", - " 16623\n", + " 18191\n", + " 18268\n", " \n", " \n", - " 888\n", - " 952\n", - " AGTAA\n", - " 5\n", - " 0.02590\n", + " 666\n", + " 718\n", + " TTAAG\n", + " 1\n", + " 0.01162\n", " 0.00000\n", " 0.0\n", - " 16510\n", - " 16588\n", + " 18156\n", + " 18191\n", " \n", " \n", "\n", - "

889 rows × 8 columns

\n", + "

667 rows × 8 columns

\n", "" ], "text/plain": [ " ref_pos ref_kmer num_events dwell_time NNNNN_dwell_time \\\n", - "0 27 GGCCT 4 0.03287 0.00498 \n", - "1 31 TTCCA 1 0.00398 0.00000 \n", + "0 10 AAAAA 1 0.00697 0.00000 \n", + "1 11 AAAAA 1 0.01959 0.00000 \n", ".. ... ... ... ... ... \n", - "887 951 GAGTA 3 0.01163 0.00432 \n", - "888 952 AGTAA 5 0.02590 0.00000 \n", + "665 715 TGGTT 4 0.02557 0.00797 \n", + "666 718 TTAAG 1 0.01162 0.00000 \n", "\n", " mismatch_dwell_time start_idx end_idx \n", - "0 0.0 57497 57596 \n", - "1 0.0 57485 57497 \n", + "0 0.0 44620 44641 \n", + "1 0.0 44561 44620 \n", ".. ... ... ... \n", - "887 0.0 16588 16623 \n", - "888 0.0 16510 16588 \n", + "665 0.0 18191 18268 \n", + "666 0.0 18156 18191 \n", "\n", - "[889 rows x 8 columns]" + "[667 rows x 8 columns]" ] }, "metadata": {}, @@ -1898,7 +1943,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "#14\tYDR382W\n" + "#6\tYGR192C\n" ] }, { @@ -1935,25 +1980,25 @@ " \n", " \n", " 0\n", - " 5\n", - " ATACT\n", - " 2\n", - " 0.01494\n", + " 1\n", + " TGGTT\n", + " 1\n", + " 0.01461\n", " 0.00000\n", " 0.0\n", - " 48813\n", - " 48858\n", + " 45267\n", + " 45311\n", " \n", " \n", " 1\n", - " 6\n", - " TACTT\n", " 2\n", + " GGTTA\n", + " 1\n", " 0.00631\n", " 0.00000\n", " 0.0\n", - " 48794\n", - " 48813\n", + " 45248\n", + " 45267\n", " \n", " \n", " ...\n", @@ -1967,48 +2012,48 @@ " ...\n", " \n", " \n", - " 306\n", - " 327\n", - " GATTA\n", + " 925\n", + " 987\n", + " GCCAA\n", " 2\n", - " 0.02191\n", + " 0.01992\n", " 0.00000\n", " 0.0\n", - " 27833\n", - " 27899\n", + " 10052\n", + " 10112\n", " \n", " \n", - " 307\n", - " 328\n", - " ATTAA\n", - " 14\n", - " 0.07603\n", - " 0.01029\n", + " 926\n", + " 988\n", + " CCAAG\n", + " 5\n", + " 0.02589\n", + " 0.01228\n", " 0.0\n", - " 27604\n", - " 27833\n", + " 9974\n", + " 10052\n", " \n", " \n", "\n", - "

308 rows × 8 columns

\n", + "

927 rows × 8 columns

\n", "" ], "text/plain": [ " ref_pos ref_kmer num_events dwell_time NNNNN_dwell_time \\\n", - "0 5 ATACT 2 0.01494 0.00000 \n", - "1 6 TACTT 2 0.00631 0.00000 \n", + "0 1 TGGTT 1 0.01461 0.00000 \n", + "1 2 GGTTA 1 0.00631 0.00000 \n", ".. ... ... ... ... ... \n", - "306 327 GATTA 2 0.02191 0.00000 \n", - "307 328 ATTAA 14 0.07603 0.01029 \n", + "925 987 GCCAA 2 0.01992 0.00000 \n", + "926 988 CCAAG 5 0.02589 0.01228 \n", "\n", " mismatch_dwell_time start_idx end_idx \n", - "0 0.0 48813 48858 \n", - "1 0.0 48794 48813 \n", + "0 0.0 45267 45311 \n", + "1 0.0 45248 45267 \n", ".. ... ... ... \n", - "306 0.0 27833 27899 \n", - "307 0.0 27604 27833 \n", + "925 0.0 10052 10112 \n", + "926 0.0 9974 10052 \n", "\n", - "[308 rows x 8 columns]" + "[927 rows x 8 columns]" ] }, "metadata": {}, @@ -2018,7 +2063,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "#13\tYPL198W\n" + "#15\tYLR110C\n" ] }, { @@ -2055,25 +2100,25 @@ " \n", " \n", " 0\n", - " 10\n", - " AAAAA\n", - " 1\n", - " 0.00697\n", - " 0.00000\n", + " 14\n", + " TGTCG\n", + " 2\n", + " 0.00598\n", " 0.0\n", - " 44620\n", - " 44641\n", + " 0.0\n", + " 23697\n", + " 23715\n", " \n", " \n", " 1\n", - " 11\n", - " AAAAA\n", + " 15\n", + " GTCGC\n", " 1\n", - " 0.01959\n", - " 0.00000\n", + " 0.00730\n", " 0.0\n", - " 44561\n", - " 44620\n", + " 0.0\n", + " 23675\n", + " 23697\n", " \n", " \n", " ...\n", @@ -2087,48 +2132,48 @@ " ...\n", " \n", " \n", - " 665\n", - " 715\n", - " TGGTT\n", - " 4\n", - " 0.02557\n", - " 0.00797\n", + " 362\n", + " 393\n", + " TTGTT\n", + " 7\n", + " 0.04217\n", " 0.0\n", - " 18191\n", - " 18268\n", + " 0.0\n", + " 9871\n", + " 9998\n", " \n", " \n", - " 666\n", - " 718\n", - " TTAAG\n", - " 1\n", - " 0.01162\n", - " 0.00000\n", + " 363\n", + " 394\n", + " TGTTG\n", + " 5\n", + " 0.01859\n", " 0.0\n", - " 18156\n", - " 18191\n", + " 0.0\n", + " 9815\n", + " 9871\n", " \n", " \n", "\n", - "

667 rows × 8 columns

\n", + "

364 rows × 8 columns

\n", "" ], "text/plain": [ " ref_pos ref_kmer num_events dwell_time NNNNN_dwell_time \\\n", - "0 10 AAAAA 1 0.00697 0.00000 \n", - "1 11 AAAAA 1 0.01959 0.00000 \n", + "0 14 TGTCG 2 0.00598 0.0 \n", + "1 15 GTCGC 1 0.00730 0.0 \n", ".. ... ... ... ... ... \n", - "665 715 TGGTT 4 0.02557 0.00797 \n", - "666 718 TTAAG 1 0.01162 0.00000 \n", + "362 393 TTGTT 7 0.04217 0.0 \n", + "363 394 TGTTG 5 0.01859 0.0 \n", "\n", " mismatch_dwell_time start_idx end_idx \n", - "0 0.0 44620 44641 \n", - "1 0.0 44561 44620 \n", + "0 0.0 23697 23715 \n", + "1 0.0 23675 23697 \n", ".. ... ... ... \n", - "665 0.0 18191 18268 \n", - "666 0.0 18156 18191 \n", + "362 0.0 9871 9998 \n", + "363 0.0 9815 9871 \n", "\n", - "[667 rows x 8 columns]" + "[364 rows x 8 columns]" ] }, "metadata": {}, diff --git a/docs/demo/Freq_meth_calculate_usage.ipynb b/docs/demo/Freq_meth_calculate_usage.ipynb index 9088531..ef68547 100644 --- a/docs/demo/Freq_meth_calculate_usage.ipynb +++ b/docs/demo/Freq_meth_calculate_usage.ipynb @@ -169,8 +169,8 @@ "execution_count": 1, "metadata": { "ExecuteTime": { - "end_time": "2019-05-01T13:02:19.149219Z", - "start_time": "2019-05-01T13:02:18.222250Z" + "end_time": "2019-05-02T09:36:28.617634Z", + "start_time": "2019-05-02T09:36:27.566472Z" } }, "outputs": [ @@ -249,9 +249,10 @@ "execution_count": 2, "metadata": { "ExecuteTime": { - "end_time": "2019-05-01T13:02:39.328276Z", - "start_time": "2019-05-01T13:02:19.152991Z" - } + "end_time": "2019-05-02T09:36:48.448839Z", + "start_time": "2019-05-02T09:36:28.620951Z" + }, + "scrolled": false }, "outputs": [ { @@ -284,6 +285,21 @@ "name": "stderr", "output_type": "stream", "text": [ + "Options summary\n", + "\tpackage_name: NanopolishComp\n", + "\tpackage_version: 0.6.1\n", + "\ttimestamp: 2019-05-02 10:36:29.585341\n", + "\tquiet: False\n", + "\tverbose: True\n", + "\tmotif: cpg\n", + "\tsplit_group: False\n", + "\tmin_meth_freq: 0.05\n", + "\tmin_depth: 10\n", + "\tmin_llr: 2.5\n", + "\toutprefix: out\n", + "\toutdir: ./output/freq_meth_calculate/\n", + "\tinput_fn: data/freq_meth_calculate/methylation_calls.tsv\n", + "\n", "## Checking arguments ##\n", "Test input file readability\n", "Testing output dir writability\n", @@ -291,180 +307,175 @@ "Starting to parse file methylation_calls file\n", "\r", "0 lines [00:00, ? lines/s]\r", - "3694 lines [00:00, 36936.86 lines/s]\r", - "7482 lines [00:00, 37212.28 lines/s]\r", - "10734 lines [00:00, 35667.60 lines/s]\r", - "14440 lines [00:00, 36072.69 lines/s]\r", - "18037 lines [00:00, 36040.67 lines/s]\r", - "21625 lines [00:00, 35991.14 lines/s]\r", - "25336 lines [00:00, 36317.90 lines/s]\r", - "28669 lines [00:00, 34892.13 lines/s]\r", - "32294 lines [00:00, 35288.45 lines/s]\r", - "35778 lines [00:01, 35152.49 lines/s]\r", - "39417 lines [00:01, 35514.70 lines/s]\r", - "43273 lines [00:01, 36376.40 lines/s]\r", - "47048 lines [00:01, 36775.78 lines/s]\r", - "50790 lines [00:01, 36966.16 lines/s]\r", - "54468 lines [00:01, 35695.92 lines/s]\r", - "58036 lines [00:01, 35689.11 lines/s]\r", - "61667 lines [00:01, 35871.98 lines/s]\r", - "65444 lines [00:01, 36420.06 lines/s]\r", - "69087 lines [00:01, 35966.06 lines/s]\r", - "72709 lines [00:02, 36040.00 lines/s]\r", - "76315 lines [00:02, 35726.97 lines/s]\r", - "79890 lines [00:02, 35371.23 lines/s]\r", - "83509 lines [00:02, 35611.67 lines/s]\r", - "87072 lines [00:02, 35528.83 lines/s]\r", - "90688 lines [00:02, 35710.92 lines/s]\r", - "94365 lines [00:02, 36016.51 lines/s]\r", - "97983 lines [00:02, 36064.36 lines/s]\r", - "101591 lines [00:02, 33760.63 lines/s]\r", - "105174 lines [00:02, 34353.89 lines/s]\r", - "108792 lines [00:03, 34879.50 lines/s]\r", - "112567 lines [00:03, 35691.17 lines/s]\r", - "116261 lines [00:03, 36054.73 lines/s]\r", - "120017 lines [00:03, 36491.47 lines/s]\r", - "123677 lines [00:03, 36430.93 lines/s]\r", - "127328 lines [00:03, 36100.36 lines/s]\r", - "130959 lines [00:03, 36161.31 lines/s]\r", - "134580 lines [00:03, 33640.59 lines/s]\r", - "138049 lines [00:03, 33423.56 lines/s]\r", - "141674 lines [00:03, 34222.01 lines/s]\r", - "145337 lines [00:04, 34908.34 lines/s]\r", - "148868 lines [00:04, 35026.25 lines/s]\r", - "152514 lines [00:04, 35443.32 lines/s]\r", - "156112 lines [00:04, 35600.85 lines/s]\r", - "159680 lines [00:04, 35429.19 lines/s]\r", - "163270 lines [00:04, 35567.61 lines/s]\r", - "166845 lines [00:04, 35622.11 lines/s]\r", - "170411 lines [00:04, 35273.52 lines/s]\r", - "173942 lines [00:04, 32431.49 lines/s]\r", - "177639 lines [00:05, 33669.34 lines/s]\r", - "181415 lines [00:05, 34799.97 lines/s]\r", - "185157 lines [00:05, 35545.07 lines/s]\r", - "188925 lines [00:05, 36158.67 lines/s]\r", - "192567 lines [00:05, 36218.82 lines/s]\r", - "196207 lines [00:05, 35699.74 lines/s]\r", - "199945 lines [00:05, 36185.90 lines/s]\r", - "203576 lines [00:05, 36182.46 lines/s]\r", - "207305 lines [00:05, 36507.00 lines/s]\r", - "211027 lines [00:05, 36717.97 lines/s]\r", - "214833 lines [00:06, 37109.69 lines/s]\r", - "218549 lines [00:06, 37059.64 lines/s]\r", - "222258 lines [00:06, 36918.24 lines/s]\r", - "225970 lines [00:06, 36977.42 lines/s]\r", - "229670 lines [00:06, 35383.21 lines/s]\r", - "233232 lines [00:06, 35453.12 lines/s]\r", - "236872 lines [00:06, 35730.43 lines/s]\r", - "240454 lines [00:06, 35540.80 lines/s]\r", - "244015 lines [00:06, 35449.02 lines/s]\r", - "247737 lines [00:06, 35960.06 lines/s]\r", - "251443 lines [00:07, 36281.61 lines/s]\r", - "255091 lines [00:07, 36339.07 lines/s]\r", - "258728 lines [00:07, 32742.21 lines/s]\r", - "262144 lines [00:07, 33154.93 lines/s]\r", - "265693 lines [00:07, 33820.17 lines/s]\r", - "269159 lines [00:07, 34065.43 lines/s]\r", - "272821 lines [00:07, 34792.55 lines/s]\r", - "276433 lines [00:07, 35179.58 lines/s]\r", - "280126 lines [00:07, 35684.45 lines/s]\r", - "283709 lines [00:07, 35661.31 lines/s]\r", - "287285 lines [00:08, 33375.47 lines/s]\r", - "290659 lines [00:08, 33333.65 lines/s]\r", - "294302 lines [00:08, 34205.14 lines/s]\r", - "298022 lines [00:08, 35050.44 lines/s]\r", - "301549 lines [00:08, 35071.13 lines/s]\r", - "305118 lines [00:08, 35253.09 lines/s]\r", - "308771 lines [00:08, 35625.90 lines/s]\r", - "312343 lines [00:08, 35633.99 lines/s]\r", - "315943 lines [00:08, 35738.50 lines/s]\r", - "319569 lines [00:09, 35892.24 lines/s]\r", - "323247 lines [00:09, 36151.43 lines/s]\r", - "326981 lines [00:09, 36496.16 lines/s]\r", - "330634 lines [00:09, 31874.39 lines/s]\r", - "334275 lines [00:09, 33110.19 lines/s]\r", - "337674 lines [00:09, 33053.07 lines/s]\r", - "341275 lines [00:09, 33884.76 lines/s]\r", - "344879 lines [00:09, 34502.15 lines/s]\r", - "348424 lines [00:09, 34780.29 lines/s]\r", - "352198 lines [00:09, 35615.65 lines/s]\r", - "355878 lines [00:10, 35961.00 lines/s]\r", - "359819 lines [00:10, 36929.30 lines/s]\r", - "363741 lines [00:10, 37587.85 lines/s]\r", - "367650 lines [00:10, 38025.18 lines/s]\r", - "371688 lines [00:10, 38700.32 lines/s]\r", - "375669 lines [00:10, 39022.03 lines/s]\r", - "379580 lines [00:10, 38665.41 lines/s]\r", - "383454 lines [00:10, 37909.85 lines/s]\r", - "387254 lines [00:10, 37566.73 lines/s]\r", - "391018 lines [00:11, 33373.23 lines/s]\r", - "394447 lines [00:11, 31057.74 lines/s]\r", - "397649 lines [00:11, 30072.43 lines/s]\r", - "400731 lines [00:11, 30017.29 lines/s]\r", - "404120 lines [00:11, 31081.55 lines/s]\r", - "407546 lines [00:11, 31970.25 lines/s]\r", - "410782 lines [00:11, 32008.58 lines/s]\r", - "414132 lines [00:11, 32440.38 lines/s]\r", - "417397 lines [00:11, 31907.29 lines/s]\r", - "420604 lines [00:11, 31911.86 lines/s]\r", - "423807 lines [00:12, 31935.99 lines/s]\r", - "427009 lines [00:12, 28558.08 lines/s]\r", - "429938 lines [00:12, 25030.87 lines/s]\r", - "432571 lines [00:12, 25389.36 lines/s]\r", - "435769 lines [00:12, 27059.71 lines/s]\r", - "439129 lines [00:12, 28737.11 lines/s]\r", - "442252 lines [00:12, 29437.09 lines/s]\r", - "445597 lines [00:12, 30534.80 lines/s]\r", - "449148 lines [00:12, 31867.77 lines/s]\r", - "452498 lines [00:13, 32339.00 lines/s]\r", - "455774 lines [00:13, 27941.41 lines/s]\r", - "458704 lines [00:13, 22947.88 lines/s]\r", - "461241 lines [00:13, 19850.32 lines/s]\r", - "463470 lines [00:13, 16689.86 lines/s]\r", - "465395 lines [00:13, 16843.70 lines/s]\r", - "468681 lines [00:13, 19727.59 lines/s]\r", - "470972 lines [00:14, 20083.04 lines/s]\r", - "473205 lines [00:14, 19638.85 lines/s]\r", - "475328 lines [00:14, 16863.04 lines/s]\r", - "478677 lines [00:14, 19812.92 lines/s]\r", - "482100 lines [00:14, 22675.51 lines/s]\r", - "485442 lines [00:14, 25095.07 lines/s]\r", - "488618 lines [00:14, 26779.94 lines/s]\r", - "491807 lines [00:14, 28129.99 lines/s]\r", - "495278 lines [00:14, 29826.05 lines/s]\r", - "498607 lines [00:15, 30786.46 lines/s]\r", - "502111 lines [00:15, 31943.33 lines/s]\r", - "505407 lines [00:15, 31808.01 lines/s]\r", - "508660 lines [00:15, 28152.30 lines/s]\r", - "511603 lines [00:15, 22895.36 lines/s]\r", - "514142 lines [00:15, 19749.39 lines/s]\r", - "517566 lines [00:15, 22621.03 lines/s]\r", - "520968 lines [00:15, 25147.59 lines/s]\r", - "524491 lines [00:16, 27509.06 lines/s]\r", - "528192 lines [00:16, 29802.64 lines/s]\r", - "531429 lines [00:16, 30348.87 lines/s]\r", - "534646 lines [00:16, 28593.62 lines/s]\r", - "538028 lines [00:16, 29982.41 lines/s]\r", - "541653 lines [00:16, 31621.69 lines/s]\r", - "544925 lines [00:16, 30578.96 lines/s]\r", - "548067 lines [00:16, 30175.37 lines/s]\r", - "551405 lines [00:16, 31068.80 lines/s]\r", - "554561 lines [00:17, 31195.66 lines/s]\r", - "558077 lines [00:17, 32286.50 lines/s]\r", - "561718 lines [00:17, 33420.60 lines/s]\r", - "565178 lines [00:17, 33762.17 lines/s]\r", - "568579 lines [00:17, 33364.23 lines/s]\r", - "572187 lines [00:17, 34133.27 lines/s]\r", - "575719 lines [00:17, 34479.28 lines/s]\r", - "579417 lines [00:17, 35192.23 lines/s]\r", - "582949 lines [00:17, 31020.06 lines/s]\r", - "586151 lines [00:18, 28249.02 lines/s]\r", - "589415 lines [00:18, 29435.73 lines/s]\r", - "592937 lines [00:18, 30959.07 lines/s]\r", - "596121 lines [00:18, 23711.43 lines/s]\r", - "599915 lines [00:18, 26716.08 lines/s]\r", - "603872 lines [00:18, 29599.60 lines/s]\r", - "605248 lines [00:18, 32458.39 lines/s]\n", + "3972 lines [00:00, 39719.66 lines/s]\r", + "7974 lines [00:00, 39807.26 lines/s]\r", + "11925 lines [00:00, 39714.71 lines/s]\r", + "15922 lines [00:00, 39789.10 lines/s]\r", + "19677 lines [00:00, 39088.44 lines/s]\r", + "22922 lines [00:00, 36697.98 lines/s]\r", + "26157 lines [00:00, 29681.15 lines/s]\r", + "29386 lines [00:00, 30416.83 lines/s]\r", + "33098 lines [00:00, 32157.87 lines/s]\r", + "36729 lines [00:01, 33298.15 lines/s]\r", + "40558 lines [00:01, 34651.22 lines/s]\r", + "44481 lines [00:01, 35905.91 lines/s]\r", + "48332 lines [00:01, 36649.03 lines/s]\r", + "52240 lines [00:01, 37344.28 lines/s]\r", + "56156 lines [00:01, 37870.58 lines/s]\r", + "60072 lines [00:01, 38247.05 lines/s]\r", + "64005 lines [00:01, 38563.25 lines/s]\r", + "67892 lines [00:01, 38654.04 lines/s]\r", + "71763 lines [00:01, 38124.82 lines/s]\r", + "75581 lines [00:02, 32395.50 lines/s]\r", + "78974 lines [00:02, 27110.51 lines/s]\r", + "82500 lines [00:02, 29130.13 lines/s]\r", + "85745 lines [00:02, 30047.66 lines/s]\r", + "88911 lines [00:02, 26951.26 lines/s]\r", + "91779 lines [00:02, 26365.74 lines/s]\r", + "95469 lines [00:02, 28833.09 lines/s]\r", + "98741 lines [00:02, 29897.35 lines/s]\r", + "101850 lines [00:03, 25426.34 lines/s]\r", + "105371 lines [00:03, 27733.79 lines/s]\r", + "108346 lines [00:03, 26868.81 lines/s]\r", + "111180 lines [00:03, 21167.71 lines/s]\r", + "114625 lines [00:03, 23935.91 lines/s]\r", + "118268 lines [00:03, 26680.03 lines/s]\r", + "121922 lines [00:03, 29028.45 lines/s]\r", + "125482 lines [00:03, 30730.17 lines/s]\r", + "128940 lines [00:04, 31790.40 lines/s]\r", + "132407 lines [00:04, 32600.32 lines/s]\r", + "135792 lines [00:04, 25016.46 lines/s]\r", + "138648 lines [00:04, 21498.39 lines/s]\r", + "142083 lines [00:04, 24215.84 lines/s]\r", + "144853 lines [00:04, 21830.15 lines/s]\r", + "147989 lines [00:04, 24017.97 lines/s]\r", + "151092 lines [00:04, 25764.01 lines/s]\r", + "154225 lines [00:05, 27214.11 lines/s]\r", + "157125 lines [00:05, 27158.76 lines/s]\r", + "160148 lines [00:05, 28011.78 lines/s]\r", + "163422 lines [00:05, 29279.59 lines/s]\r", + "166932 lines [00:05, 30811.06 lines/s]\r", + "170383 lines [00:05, 31834.16 lines/s]\r", + "173630 lines [00:05, 30157.04 lines/s]\r", + "177112 lines [00:05, 31419.03 lines/s]\r", + "180564 lines [00:05, 32284.12 lines/s]\r", + "183839 lines [00:06, 29498.66 lines/s]\r", + "186868 lines [00:06, 25090.81 lines/s]\r", + "189547 lines [00:06, 23488.05 lines/s]\r", + "192466 lines [00:06, 24948.89 lines/s]\r", + "195084 lines [00:06, 25013.84 lines/s]\r", + "198543 lines [00:06, 27278.88 lines/s]\r", + "201919 lines [00:06, 28944.67 lines/s]\r", + "204926 lines [00:06, 28974.94 lines/s]\r", + "207902 lines [00:06, 29186.25 lines/s]\r", + "210876 lines [00:07, 28575.09 lines/s]\r", + "213838 lines [00:07, 28880.26 lines/s]\r", + "217201 lines [00:07, 30156.07 lines/s]\r", + "220673 lines [00:07, 31391.06 lines/s]\r", + "223851 lines [00:07, 27826.68 lines/s]\r", + "227300 lines [00:07, 29538.19 lines/s]\r", + "230866 lines [00:07, 31141.01 lines/s]\r", + "234699 lines [00:07, 32996.48 lines/s]\r", + "238602 lines [00:07, 34600.63 lines/s]\r", + "242235 lines [00:07, 35099.36 lines/s]\r", + "245936 lines [00:08, 35649.09 lines/s]\r", + "249747 lines [00:08, 36351.39 lines/s]\r", + "253506 lines [00:08, 36714.12 lines/s]\r", + "257204 lines [00:08, 33073.24 lines/s]\r", + "260932 lines [00:08, 34230.86 lines/s]\r", + "264803 lines [00:08, 35459.93 lines/s]\r", + "268469 lines [00:08, 35811.48 lines/s]\r", + "272427 lines [00:08, 36862.49 lines/s]\r", + "276343 lines [00:08, 37521.14 lines/s]\r", + "280266 lines [00:09, 38016.07 lines/s]\r", + "284090 lines [00:09, 37761.02 lines/s]\r", + "287883 lines [00:09, 33629.95 lines/s]\r", + "291342 lines [00:09, 33608.55 lines/s]\r", + "294770 lines [00:09, 33571.47 lines/s]\r", + "298403 lines [00:09, 34353.75 lines/s]\r", + "302015 lines [00:09, 34864.31 lines/s]\r", + "305562 lines [00:09, 35042.38 lines/s]\r", + "309086 lines [00:09, 31551.18 lines/s]\r", + "312530 lines [00:10, 32365.33 lines/s]\r", + "315971 lines [00:10, 32948.88 lines/s]\r", + "319312 lines [00:10, 31673.65 lines/s]\r", + "322522 lines [00:10, 31366.85 lines/s]\r", + "325689 lines [00:10, 30344.76 lines/s]\r", + "328865 lines [00:10, 27638.77 lines/s]\r", + "332249 lines [00:10, 29245.00 lines/s]\r", + "336174 lines [00:10, 31665.71 lines/s]\r", + "339964 lines [00:10, 33307.38 lines/s]\r", + "343558 lines [00:10, 34054.15 lines/s]\r", + "347123 lines [00:11, 34516.28 lines/s]\r", + "350628 lines [00:11, 33981.96 lines/s]\r", + "354201 lines [00:11, 34484.13 lines/s]\r", + "358005 lines [00:11, 35477.81 lines/s]\r", + "362031 lines [00:11, 36788.32 lines/s]\r", + "366050 lines [00:11, 37746.64 lines/s]\r", + "369853 lines [00:11, 37319.53 lines/s]\r", + "373703 lines [00:11, 37664.96 lines/s]\r", + "377485 lines [00:11, 37170.12 lines/s]\r", + "381215 lines [00:12, 36958.38 lines/s]\r", + "384920 lines [00:12, 36086.81 lines/s]\r", + "388540 lines [00:12, 36041.09 lines/s]\r", + "392639 lines [00:12, 37393.68 lines/s]\r", + "396673 lines [00:12, 38231.33 lines/s]\r", + "400856 lines [00:12, 39241.04 lines/s]\r", + "404799 lines [00:12, 38005.94 lines/s]\r", + "408622 lines [00:12, 36691.00 lines/s]\r", + "412317 lines [00:12, 36733.16 lines/s]\r", + "416008 lines [00:12, 36575.74 lines/s]\r", + "419678 lines [00:13, 33549.12 lines/s]\r", + "423204 lines [00:13, 34042.37 lines/s]\r", + "426768 lines [00:13, 34504.83 lines/s]\r", + "430387 lines [00:13, 34993.10 lines/s]\r", + "433910 lines [00:13, 34385.02 lines/s]\r", + "437368 lines [00:13, 34039.32 lines/s]\r", + "440786 lines [00:13, 33517.56 lines/s]\r", + "444283 lines [00:13, 33939.43 lines/s]\r", + "448047 lines [00:13, 34969.31 lines/s]\r", + "451594 lines [00:13, 35115.70 lines/s]\r", + "455457 lines [00:14, 36100.57 lines/s]\r", + "459319 lines [00:14, 36820.52 lines/s]\r", + "463015 lines [00:14, 36781.63 lines/s]\r", + "466952 lines [00:14, 37519.70 lines/s]\r", + "470764 lines [00:14, 37697.68 lines/s]\r", + "474542 lines [00:14, 31041.78 lines/s]\r", + "478141 lines [00:14, 32375.45 lines/s]\r", + "481967 lines [00:14, 33940.30 lines/s]\r", + "485815 lines [00:14, 35183.75 lines/s]\r", + "489820 lines [00:15, 36513.85 lines/s]\r", + "493673 lines [00:15, 37094.94 lines/s]\r", + "497444 lines [00:15, 37215.96 lines/s]\r", + "501417 lines [00:15, 37933.85 lines/s]\r", + "505318 lines [00:15, 38249.40 lines/s]\r", + "509331 lines [00:15, 38792.16 lines/s]\r", + "513252 lines [00:15, 38915.43 lines/s]\r", + "517157 lines [00:15, 38860.38 lines/s]\r", + "521053 lines [00:15, 38880.76 lines/s]\r", + "524964 lines [00:15, 38947.82 lines/s]\r", + "528864 lines [00:16, 38818.64 lines/s]\r", + "532760 lines [00:16, 38858.74 lines/s]\r", + "536696 lines [00:16, 39005.54 lines/s]\r", + "540646 lines [00:16, 39150.28 lines/s]\r", + "544563 lines [00:16, 39153.94 lines/s]\r", + "548480 lines [00:16, 38975.30 lines/s]\r", + "552379 lines [00:16, 38757.84 lines/s]\r", + "556256 lines [00:16, 38555.73 lines/s]\r", + "560113 lines [00:16, 38118.62 lines/s]\r", + "563927 lines [00:16, 37990.75 lines/s]\r", + "567728 lines [00:17, 37973.07 lines/s]\r", + "571689 lines [00:17, 38449.70 lines/s]\r", + "575537 lines [00:17, 38125.34 lines/s]\r", + "579352 lines [00:17, 37955.82 lines/s]\r", + "583150 lines [00:17, 37533.33 lines/s]\r", + "586906 lines [00:17, 37167.12 lines/s]\r", + "590655 lines [00:17, 37263.09 lines/s]\r", + "594384 lines [00:17, 29802.36 lines/s]\r", + "597603 lines [00:17, 30480.09 lines/s]\r", + "600918 lines [00:18, 31233.28 lines/s]\r", + "604362 lines [00:18, 32128.63 lines/s]\r", + "605248 lines [00:18, 33248.80 lines/s]\n", "Read sites summary\n", "\ttotal: 605,248\n", "\tunmethylated: 596,963\n", @@ -473,12 +484,12 @@ "Filtering out positions with low coverage or methylation frequency\n", "\r", " 0%| | 0/340081 [00:00 Date: Wed, 8 May 2019 14:15:04 +0100 Subject: [PATCH 2/4] Create outdir if it does not exist already --- NanopolishComp/Eventalign_collapse.py | 10 ++++++---- NanopolishComp/Freq_meth_calculate.py | 11 ++++++----- NanopolishComp/__main__.py | 4 ++-- NanopolishComp/common.py | 7 +++++++ 4 files changed, 21 insertions(+), 11 deletions(-) diff --git a/NanopolishComp/Eventalign_collapse.py b/NanopolishComp/Eventalign_collapse.py index 6b1bf56..366dd88 100755 --- a/NanopolishComp/Eventalign_collapse.py +++ b/NanopolishComp/Eventalign_collapse.py @@ -50,7 +50,7 @@ def __init__ (self, * input_fn Path to a nanopolish eventalign tsv output file. * outdir - Path to the output folder + Path to the output folder (will be created if it does exist yet) * outprefix text outprefix for all the files generated * max_reads @@ -93,12 +93,14 @@ def __init__ (self, # Verify parameters validity self.log.info ("Checking arguments") + # Try to read input file if not a stream self.log.debug("\tTesting input file readability") if input_fn != 0 and not file_readable (input_fn): raise IOError ("Cannot read input file") - self.log.info("Testing output dir writability") - if not dir_writable (outdir): - raise IOError ("Cannot write output file in indicated folder. Create the output folder if it does not exist yet") + # Try to create output folder + self.log.debug("\tCreating output folder") + mkdir(outdir, exist_ok=True) + # Check other args self.log.debug("\tChecking number of threads") if threads < 3: raise ValueError ("At least 3 threads required") diff --git a/NanopolishComp/Freq_meth_calculate.py b/NanopolishComp/Freq_meth_calculate.py index accd91e..65132f5 100755 --- a/NanopolishComp/Freq_meth_calculate.py +++ b/NanopolishComp/Freq_meth_calculate.py @@ -40,7 +40,7 @@ def __init__ (self, * input_fn Path to a nanopolish call_methylation tsv output file * outdir - Path to the output folder + Path to the output folder (will be created if it does exist yet) * outprefix text outprefix for all the files generated * min_llr @@ -84,12 +84,13 @@ def __init__ (self, # Verify parameters validity self.log.warning ("## Checking arguments ##") - self.log.info("Test input file readability") + # Try to read input file if not a stream + self.log.debug("\tTesting input file readability") if input_fn != 0 and not file_readable (input_fn): raise IOError ("Cannot read input file") - self.log.info("Testing output dir writability") - if not dir_writable (outdir): - raise IOError ("Cannot write output file in indicated folder. Create the output folder if it does not exist yet") + # Try to create output folder + self.log.debug("\tCreating output folder") + mkdir(outdir, exist_ok=True) if motif == "cpg": motif_seq = "CG" diff --git a/NanopolishComp/__main__.py b/NanopolishComp/__main__.py index c3231a0..cd02522 100644 --- a/NanopolishComp/__main__.py +++ b/NanopolishComp/__main__.py @@ -30,7 +30,7 @@ def main(args=None): subparser_ec.set_defaults(func=Eventalign_collapse_main) subparser_ec_io = subparser_ec.add_argument_group("Input/Output options") subparser_ec_io.add_argument("-i", "--input_fn", default=0, help="Path to a nanopolish eventalign tsv output file. If '0' read from std input (default: %(default)s)") - subparser_ec_io.add_argument("-o", "--outdir", type=str, default="./", help="Path to the output folder (default: %(default)s)") + subparser_ec_io.add_argument("-o", "--outdir", type=str, default="./", help="Path to the output folder (will be created if it does exist yet) (default: %(default)s)") subparser_ec_io.add_argument("-p", "--outprefix", type=str, default="out", help="text outprefix for all the files generated (default: %(default)s)") subparser_ec_rp = subparser_ec.add_argument_group("Run parameters options") subparser_ec_rp.add_argument("-s", "--write_samples", default=False, action='store_true', help="If given, will write the raw sample if nanopolish eventalign was ran with --samples option (default: %(default)s)") @@ -44,7 +44,7 @@ def main(args=None): subparser_fm.set_defaults(func=Freq_meth_calculate_main) subparser_fm_io = subparser_fm.add_argument_group("Input/Output options") subparser_fm_io.add_argument("-i", "--input_fn", default=0, help="Path to a nanopolish call_methylation tsv output file. If not specified read from std input") - subparser_fm_io.add_argument("-o", "--outdir", type=str, default="./", help="Path to the output folder (default: %(default)s)") + subparser_fm_io.add_argument("-o", "--outdir", type=str, default="./", help="Path to the output folder (will be created if it does exist yet) (default: %(default)s)") subparser_fm_io.add_argument("-p", "--outprefix", type=str, default="out", help="text outprefix for all the files generated (default: %(default)s)") subparser_fm_fo = subparser_fm.add_argument_group("Filtering options") subparser_fm_fo.add_argument("-l", "--min_llr", type=float, default=2.5, help="Log likelihood ratio threshold (default: %(default)s)") diff --git a/NanopolishComp/common.py b/NanopolishComp/common.py index 5fb9a32..3c052b8 100644 --- a/NanopolishComp/common.py +++ b/NanopolishComp/common.py @@ -23,6 +23,13 @@ def dir_writable (fn, **kwargs): fn = os.path.dirname(fn) return os.path.dirname(fn) and os.access (fn, os.W_OK) +def mkdir (fn, exist_ok=False): + """ Create directory recursivelly. Raise IO error if path exist or if error at creation """ + try: + os.makedirs (fn, exist_ok=exist_ok) + except: + raise NanopolishCompError ("Error creating output folder `{}`".format(fn)) + def numeric_cast_dict (d): """Cast str values to integer or float from a dict """ for k, v in d.items(): From 2232bd66a25c644a39855441423a363cd316007d Mon Sep 17 00:00:00 2001 From: a-slide Date: Wed, 8 May 2019 14:15:17 +0100 Subject: [PATCH 3/4] Update doc --- docs/demo/Eventalign_collapse_usage.ipynb | 1523 +++++++-------------- docs/demo/Freq_meth_calculate_usage.ipynb | 811 ++++++----- 2 files changed, 902 insertions(+), 1432 deletions(-) diff --git a/docs/demo/Eventalign_collapse_usage.ipynb b/docs/demo/Eventalign_collapse_usage.ipynb index 926a373..0d6fdb0 100644 --- a/docs/demo/Eventalign_collapse_usage.ipynb +++ b/docs/demo/Eventalign_collapse_usage.ipynb @@ -132,8 +132,8 @@ "execution_count": 1, "metadata": { "ExecuteTime": { - "end_time": "2019-05-02T09:32:44.181603Z", - "start_time": "2019-05-02T09:32:43.073764Z" + "end_time": "2019-05-08T10:59:10.160569Z", + "start_time": "2019-05-08T10:59:08.905334Z" } }, "outputs": [ @@ -159,7 +159,8 @@ " Path to a nanopolish eventalign tsv output file. If\n", " '0' read from std input (default: 0)\n", " -o OUTDIR, --outdir OUTDIR\n", - " Path to the output folder (default: ./)\n", + " Path to the output folder (will be created if it does\n", + " exist yet) (default: ./)\n", " -p OUTPREFIX, --outprefix OUTPREFIX\n", " text outprefix for all the files generated (default:\n", " out)\n", @@ -218,8 +219,8 @@ "execution_count": 2, "metadata": { "ExecuteTime": { - "end_time": "2019-05-02T09:32:45.417414Z", - "start_time": "2019-05-02T09:32:44.184921Z" + "end_time": "2019-05-08T10:59:11.535593Z", + "start_time": "2019-05-08T10:59:10.164253Z" }, "scrolled": false }, @@ -254,14 +255,40 @@ "name": "stderr", "output_type": "stream", "text": [ + "Options summary\n", + "\tpackage_name: NanopolishComp\n", + "\tpackage_version: 0.6.1\n", + "\ttimestamp: 2019-05-08 11:59:11.239171\n", + "\tquiet: False\n", + "\tverbose: True\n", + "\tthreads: 4\n", + "\tstat_fields: ['mean', 'median', 'num_signals']\n", + "\twrite_samples: False\n", + "\tmax_reads: None\n", + "\toutprefix: out\n", + "\toutdir: ./output/eventalign_collapse/\n", + "\tinput_fn: ./data/eventalign_collapse//nanopolish_reads.tsv\n", + "\n", "Checking arguments\n", - "Testing output dir writability\n", + "\tTesting input file readability\n", + "\tCreating output folder\n", + "\tChecking number of threads\n", + "\tChecking if stat_fields names are valid\n", "Starting to process files\n", + "\t[split_reads] Start reading input file/stream\n", + "\t[process_read 1] Starting processing reads\n", + "\t[process_read 2] Starting processing reads\n", + "\t[write_output] Start rwriting output\n", "\r", "0 reads [00:00, ? reads/s]\r", - "11 reads [00:00, 96.75 reads/s]\r", - "21 reads [00:00, 118.91 reads/s]\n", - "[Eventalign_collapse] total reads: 21 [116.81 reads/s]\n", + "8 reads [00:00, 77.85 reads/s]\r", + "14 reads [00:00, 74.94 reads/s]\t[split_reads] Done\n", + "\t[process_read 1] Done\n", + "\t[process_read 2] Done\n", + "\r", + "21 reads [00:00, 88.36 reads/s]\n", + "\t[write_output] Done\n", + "[Eventalign_collapse] total reads: 21 [86.45 reads/s]\n", "\n" ] } @@ -273,7 +300,7 @@ "source ~/.bashrc\n", "workon Nanopolish_0.11.1\n", "\n", - "NanopolishComp Eventalign_collapse -i ./data/eventalign_collapse//nanopolish_reads.tsv -o ./output/eventalign_collapse/\n", + "NanopolishComp Eventalign_collapse -i ./data/eventalign_collapse//nanopolish_reads.tsv -o ./output/eventalign_collapse/ -v\n", "head ./output/eventalign_collapse/out_eventalign_collapse.tsv\n", "head ./output/eventalign_collapse/out_eventalign_collapse.tsv.idx" ] @@ -290,8 +317,8 @@ "execution_count": 3, "metadata": { "ExecuteTime": { - "end_time": "2019-05-02T09:32:46.592916Z", - "start_time": "2019-05-02T09:32:45.421223Z" + "end_time": "2019-05-08T10:59:12.820574Z", + "start_time": "2019-05-08T10:59:11.538609Z" } }, "outputs": [ @@ -328,7 +355,7 @@ "Options summary\n", "\tpackage_name: NanopolishComp\n", "\tpackage_version: 0.6.1\n", - "\ttimestamp: 2019-05-02 10:32:46.350455\n", + "\ttimestamp: 2019-05-08 11:59:12.535254\n", "\tquiet: False\n", "\tverbose: True\n", "\tthreads: 4\n", @@ -341,7 +368,7 @@ "\n", "Checking arguments\n", "\tTesting input file readability\n", - "Testing output dir writability\n", + "\tCreating output folder\n", "\tChecking number of threads\n", "\tChecking if stat_fields names are valid\n", "Starting to process files\n", @@ -351,13 +378,14 @@ "\t[write_output] Start rwriting output\n", "\r", "0 reads [00:00, ? reads/s]\r", - "12 reads [00:00, 119.55 reads/s]\t[split_reads] Done\n", + "8 reads [00:00, 72.99 reads/s]\r", + "19 reads [00:00, 74.77 reads/s]\t[split_reads] Done\n", "\t[process_read 1] Done\n", "\t[process_read 2] Done\n", "\r", - "21 reads [00:00, 116.86 reads/s]\n", + "21 reads [00:00, 90.18 reads/s]\n", "\t[write_output] Done\n", - "[Eventalign_collapse] total reads: 21 [115.22 reads/s]\n", + "[Eventalign_collapse] total reads: 21 [89.3 reads/s]\n", "\n" ] } @@ -369,7 +397,7 @@ "source ~/.bashrc\n", "workon Nanopolish_0.11.1\n", "\n", - "cat ./data/eventalign_collapse//nanopolish_reads_index.tsv | NanopolishComp Eventalign_collapse -o ./output --verbose\n", + "cat ./data/eventalign_collapse//nanopolish_reads_index.tsv | NanopolishComp Eventalign_collapse -o ./output/eventalign_collapse/ --verbose\n", "head ./output/eventalign_collapse/out_eventalign_collapse.tsv\n", "head ./output/eventalign_collapse/out_eventalign_collapse.tsv.idx" ] @@ -386,10 +414,10 @@ "execution_count": 4, "metadata": { "ExecuteTime": { - "end_time": "2019-05-02T09:32:47.658878Z", - "start_time": "2019-05-02T09:32:46.598203Z" + "end_time": "2019-05-08T12:04:48.915541Z", + "start_time": "2019-05-08T12:04:46.270018Z" }, - "scrolled": true + "scrolled": false }, "outputs": [ { @@ -422,607 +450,22 @@ "name": "stderr", "output_type": "stream", "text": [ - "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_319_strand.fast5\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205845075712:\n", - " #000: H5F.c line 509 in H5Fopen(): unable to open file\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #001: H5Fint.c line 1400 in H5F__open(): unable to open file\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Thu May 2 10:32:47 2019\n", - ", name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_243_strand.fast5', tent_flags = 0\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #003: H5FD.c line 734 in H5FD_open(): open failed\n", - " major: Virtual File Layer\n", - " minor: Unable to initialize object\n", - " #004: H5FDsec2.c line 346 in H5FD_sec2_open(): unable to open file: name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_243_strand.fast5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205845075712:\n", - " #000: H5L.c line 805 in H5Lexists(): not a location\n", - " major: Invalid arguments to routine\n", - " minor: Inappropriate type\n", - " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", - " major: Invalid arguments to routine\n", - " minor: Bad value\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205845075712:\n", - " #000: H5L.c line 805 in H5Lexists(): not a location\n", - " major: Invalid arguments to routine\n", - " minor: Inappropriate type\n", - " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", - " major: Invalid arguments to routine\n", - " minor: Bad value\n", - "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_243_strand.fast5\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205845075712:\n", - " #000: H5F.c line 509 in H5Fopen(): unable to open file\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #001: H5Fint.c line 1400 in H5F__open(): unable to open file\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Thu May 2 10:32:47 2019\n", - ", name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_36_strand.fast5', tent_flags = 0\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #003: H5FD.c line 734 in H5FD_open(): open failed\n", - " major: Virtual File Layer\n", - " minor: Unable to initialize object\n", - " #004: H5FDsec2.c line 346 in H5FD_sec2_open(): unable to open file: name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_36_strand.fast5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205845075712:\n", - " #000: H5L.c line 805 in H5Lexists(): not a location\n", - " major: Invalid arguments to routine\n", - " minor: Inappropriate type\n", - " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", - " major: Invalid arguments to routine\n", - " minor: Bad value\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205845075712:\n", - " #000: H5L.c line 805 in H5Lexists(): not a location\n", - " major: Invalid arguments to routine\n", - " minor: Inappropriate type\n", - " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", - " major: Invalid arguments to routine\n", - " minor: Bad value\n", - "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_36_strand.fast5\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", - " #000: H5F.c line 509 in H5Fopen(): unable to open file\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #001: H5Fint.c line 1400 in H5F__open(): unable to open file\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Thu May 2 10:32:47 2019\n", - ", name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_343_strand.fast5', tent_flags = 0\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #003: H5FD.c line 734 in H5FD_open(): open failed\n", - " major: Virtual File Layer\n", - " minor: Unable to initialize object\n", - " #004: H5FDsec2.c line 346 in H5FD_sec2_open(): unable to open file: name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_343_strand.fast5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", - " #000: H5L.c line 805 in H5Lexists(): not a location\n", - " major: Invalid arguments to routine\n", - " minor: Inappropriate type\n", - " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", - " major: Invalid arguments to routine\n", - " minor: Bad value\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", - " #000: H5L.c line 805 in H5Lexists(): not a location\n", - " major: Invalid arguments to routine\n", - " minor: Inappropriate type\n", - " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", - " major: Invalid arguments to routine\n", - " minor: Bad value\n", - "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_343_strand.fast5\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", - " #000: H5F.c line 509 in H5Fopen(): unable to open file\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #001: H5Fint.c line 1400 in H5F__open(): unable to open file\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Thu May 2 10:32:47 2019\n", - ", name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_237_strand.fast5', tent_flags = 0\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #003: H5FD.c line 734 in H5FD_open(): open failed\n", - " major: Virtual File Layer\n", - " minor: Unable to initialize object\n", - " #004: H5FDsec2.c line 346 in H5FD_sec2_open(): unable to open file: name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_237_strand.fast5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", - " #000: H5L.c line 805 in H5Lexists(): not a location\n", - " major: Invalid arguments to routine\n", - " minor: Inappropriate type\n", - " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", - " major: Invalid arguments to routine\n", - " minor: Bad value\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", - " #000: H5L.c line 805 in H5Lexists(): not a location\n", - " major: Invalid arguments to routine\n", - " minor: Inappropriate type\n", - " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", - " major: Invalid arguments to routine\n", - " minor: Bad value\n", - "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_237_strand.fast5\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205861861120:\n", - " #000: H5F.c line 509 in H5Fopen(): unable to open file\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #001: H5Fint.c line 1400 in H5F__open(): unable to open file\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Thu May 2 10:32:47 2019\n", - ", name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_348_strand.fast5', tent_flags = 0\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #003: H5FD.c line 734 in H5FD_open(): open failed\n", - " major: Virtual File Layer\n", - " minor: Unable to initialize object\n", - " #004: H5FDsec2.c line 346 in H5FD_sec2_open(): unable to open file: name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_348_strand.fast5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205861861120:\n", - " #000: H5L.c line 805 in H5Lexists(): not a location\n", - " major: Invalid arguments to routine\n", - " minor: Inappropriate type\n", - " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", - " major: Invalid arguments to routine\n", - " minor: Bad value\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205861861120:\n", - " #000: H5L.c line 805 in H5Lexists(): not a location\n", - " major: Invalid arguments to routine\n", - " minor: Inappropriate type\n", - " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", - " major: Invalid arguments to routine\n", - " minor: Bad value\n", - "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_348_strand.fast5\n", - "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_108_strand.fast5\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", - " #000: H5F.c line 509 in H5Fopen(): unable to open file\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #001: H5Fint.c line 1400 in H5F__open(): unable to open file\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Thu May 2 10:32:47 2019\n", - ", name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_318_strand.fast5', tent_flags = 0\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #003: H5FD.c line 734 in H5FD_open(): open failed\n", - " major: Virtual File Layer\n", - " minor: Unable to initialize object\n", - " #004: H5FDsec2.c line 346 in H5FD_sec2_open(): unable to open file: name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_318_strand.fast5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", - " #000: H5L.c line 805 in H5Lexists(): not a location\n", - " major: Invalid arguments to routine\n", - " minor: Inappropriate type\n", - " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", - " major: Invalid arguments to routine\n", - " minor: Bad value\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", - " #000: H5L.c line 805 in H5Lexists(): not a location\n", - " major: Invalid arguments to routine\n", - " minor: Inappropriate type\n", - " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", - " major: Invalid arguments to routine\n", - " minor: Bad value\n", - "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_318_strand.fast5\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205845075712:\n", - " #000: H5F.c line 509 in H5Fopen(): unable to open file\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #001: H5Fint.c line 1400 in H5F__open(): unable to open file\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Thu May 2 10:32:47 2019\n", - ", name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_290_strand.fast5', tent_flags = 0\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #003: H5FD.c line 734 in H5FD_open(): open failed\n", - " major: Virtual File Layer\n", - " minor: Unable to initialize object\n", - " #004: H5FDsec2.c line 346 in H5FD_sec2_open(): unable to open file: name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_290_strand.fast5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205845075712:\n", - " #000: H5L.c line 805 in H5Lexists(): not a location\n", - " major: Invalid arguments to routine\n", - " minor: Inappropriate type\n", - " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", - " major: Invalid arguments to routine\n", - " minor: Bad value\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205845075712:\n", - " #000: H5L.c line 805 in H5Lexists(): not a location\n", - " major: Invalid arguments to routine\n", - " minor: Inappropriate type\n", - " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", - " major: Invalid arguments to routine\n", - " minor: Bad value\n", - "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_290_strand.fast5\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205845075712:\n", - " #000: H5F.c line 509 in H5Fopen(): unable to open file\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #001: H5Fint.c line 1400 in H5F__open(): unable to open file\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Thu May 2 10:32:47 2019\n", - ", name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_103_strand.fast5', tent_flags = 0\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #003: H5FD.c line 734 in H5FD_open(): open failed\n", - " major: Virtual File Layer\n", - " minor: Unable to initialize object\n", - " #004: H5FDsec2.c line 346 in H5FD_sec2_open(): unable to open file: name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_103_strand.fast5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205845075712:\n", - " #000: H5L.c line 805 in H5Lexists(): not a location\n", - " major: Invalid arguments to routine\n", - " minor: Inappropriate type\n", - " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", - " major: Invalid arguments to routine\n", - " minor: Bad value\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205845075712:\n", - " #000: H5L.c line 805 in H5Lexists(): not a location\n", - " major: Invalid arguments to routine\n", - " minor: Inappropriate type\n", - " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", - " major: Invalid arguments to routine\n", - " minor: Bad value\n", - "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_103_strand.fast5\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", - " #000: H5F.c line 509 in H5Fopen(): unable to open file\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #001: H5Fint.c line 1400 in H5F__open(): unable to open file\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Thu May 2 10:32:47 2019\n", - ", name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_418_strand.fast5', tent_flags = 0\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #003: H5FD.c line 734 in H5FD_open(): open failed\n", - " major: Virtual File Layer\n", - " minor: Unable to initialize object\n", - " #004: H5FDsec2.c line 346 in H5FD_sec2_open(): unable to open file: name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_418_strand.fast5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", - " #000: H5L.c line 805 in H5Lexists(): not a location\n", - " major: Invalid arguments to routine\n", - " minor: Inappropriate type\n", - " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", - " major: Invalid arguments to routine\n", - " minor: Bad value\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", - " #000: H5L.c line 805 in H5Lexists(): not a location\n", - " major: Invalid arguments to routine\n", - " minor: Inappropriate type\n", - " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", - " major: Invalid arguments to routine\n", - " minor: Bad value\n", - "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_418_strand.fast5\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", - " #000: H5F.c line 509 in H5Fopen(): unable to open file\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #001: H5Fint.c line 1400 in H5F__open(): unable to open file\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Thu May 2 10:32:47 2019\n", - ", name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_191_strand.fast5', tent_flags = 0\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #003: H5FD.c line 734 in H5FD_open(): open failed\n", - " major: Virtual File Layer\n", - " minor: Unable to initialize object\n", - " #004: H5FDsec2.c line 346 in H5FD_sec2_open(): unable to open file: name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_191_strand.fast5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", - " #000: H5L.c line 805 in H5Lexists(): not a location\n", - " major: Invalid arguments to routine\n", - " minor: Inappropriate type\n", - " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", - " major: Invalid arguments to routine\n", - " minor: Bad value\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", - " #000: H5L.c line 805 in H5Lexists(): not a location\n", - " major: Invalid arguments to routine\n", - " minor: Inappropriate type\n", - " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", - " major: Invalid arguments to routine\n", - " minor: Bad value\n", - "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_191_strand.fast5\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", - " #000: H5F.c line 509 in H5Fopen(): unable to open file\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #001: H5Fint.c line 1400 in H5F__open(): unable to open file\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Thu May 2 10:32:47 2019\n", - ", name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_301_strand.fast5', tent_flags = 0\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #003: H5FD.c line 734 in H5FD_open(): open failed\n", - " major: Virtual File Layer\n", - " minor: Unable to initialize object\n", - " #004: H5FDsec2.c line 346 in H5FD_sec2_open(): unable to open file: name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_301_strand.fast5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", - " #000: H5L.c line 805 in H5Lexists(): not a location\n", - " major: Invalid arguments to routine\n", - " minor: Inappropriate type\n", - " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", - " major: Invalid arguments to routine\n", - " minor: Bad value\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", - " #000: H5L.c line 805 in H5Lexists(): not a location\n", - " major: Invalid arguments to routine\n", - " minor: Inappropriate type\n", - " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", - " major: Invalid arguments to routine\n", - " minor: Bad value\n", - "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_301_strand.fast5\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", - " #000: H5F.c line 509 in H5Fopen(): unable to open file\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #001: H5Fint.c line 1400 in H5F__open(): unable to open file\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Thu May 2 10:32:47 2019\n", - ", name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_224_strand.fast5', tent_flags = 0\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #003: H5FD.c line 734 in H5FD_open(): open failed\n", - " major: Virtual File Layer\n", - " minor: Unable to initialize object\n", - " #004: H5FDsec2.c line 346 in H5FD_sec2_open(): unable to open file: name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_224_strand.fast5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", - " #000: H5L.c line 805 in H5Lexists(): not a location\n", - " major: Invalid arguments to routine\n", - " minor: Inappropriate type\n", - " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", - " major: Invalid arguments to routine\n", - " minor: Bad value\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", - " #000: H5L.c line 805 in H5Lexists(): not a location\n", - " major: Invalid arguments to routine\n", - " minor: Inappropriate type\n", - " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", - " major: Invalid arguments to routine\n", - " minor: Bad value\n", - "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_224_strand.fast5\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", - " #000: H5F.c line 509 in H5Fopen(): unable to open file\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #001: H5Fint.c line 1400 in H5F__open(): unable to open file\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Thu May 2 10:32:47 2019\n", - ", name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_410_strand.fast5', tent_flags = 0\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #003: H5FD.c line 734 in H5FD_open(): open failed\n", - " major: Virtual File Layer\n", - " minor: Unable to initialize object\n", - " #004: H5FDsec2.c line 346 in H5FD_sec2_open(): unable to open file: name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_410_strand.fast5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", - " #000: H5L.c line 805 in H5Lexists(): not a location\n", - " major: Invalid arguments to routine\n", - " minor: Inappropriate type\n", - " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", - " major: Invalid arguments to routine\n", - " minor: Bad value\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", - " #000: H5L.c line 805 in H5Lexists(): not a location\n", - " major: Invalid arguments to routine\n", - " minor: Inappropriate type\n", - " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", - " major: Invalid arguments to routine\n", - " minor: Bad value\n", - "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_410_strand.fast5\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", - " #000: H5F.c line 509 in H5Fopen(): unable to open file\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #001: H5Fint.c line 1400 in H5F__open(): unable to open file\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Thu May 2 10:32:47 2019\n", - ", name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_382_strand.fast5', tent_flags = 0\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #003: H5FD.c line 734 in H5FD_open(): open failed\n", - " major: Virtual File Layer\n", - " minor: Unable to initialize object\n", - " #004: H5FDsec2.c line 346 in H5FD_sec2_open(): unable to open file: name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_382_strand.fast5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", - " #000: H5L.c line 805 in H5Lexists(): not a location\n", - " major: Invalid arguments to routine\n", - " minor: Inappropriate type\n", - " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", - " major: Invalid arguments to routine\n", - " minor: Bad value\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", - " #000: H5L.c line 805 in H5Lexists(): not a location\n", - " major: Invalid arguments to routine\n", - " minor: Inappropriate type\n", - " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", - " major: Invalid arguments to routine\n", - " minor: Bad value\n", - "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_382_strand.fast5\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", - " #000: H5F.c line 509 in H5Fopen(): unable to open file\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #001: H5Fint.c line 1400 in H5F__open(): unable to open file\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Thu May 2 10:32:47 2019\n", - ", name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_192_strand.fast5', tent_flags = 0\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #003: H5FD.c line 734 in H5FD_open(): open failed\n", - " major: Virtual File Layer\n", - " minor: Unable to initialize object\n", - " #004: H5FDsec2.c line 346 in H5FD_sec2_open(): unable to open file: name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_192_strand.fast5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", - " #000: H5L.c line 805 in H5Lexists(): not a location\n", - " major: Invalid arguments to routine\n", - " minor: Inappropriate type\n", - " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", - " major: Invalid arguments to routine\n", - " minor: Bad value\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", - " #000: H5L.c line 805 in H5Lexists(): not a location\n", - " major: Invalid arguments to routine\n", - " minor: Inappropriate type\n", - " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", - " major: Invalid arguments to routine\n", - " minor: Bad value\n", - "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_192_strand.fast5\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", - " #000: H5F.c line 509 in H5Fopen(): unable to open file\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #001: H5Fint.c line 1400 in H5F__open(): unable to open file\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Thu May 2 10:32:47 2019\n", - ", name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_113_strand.fast5', tent_flags = 0\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #003: H5FD.c line 734 in H5FD_open(): open failed\n", - " major: Virtual File Layer\n", - " minor: Unable to initialize object\n", - " #004: H5FDsec2.c line 346 in H5FD_sec2_open(): unable to open file: name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_113_strand.fast5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", - " #000: H5L.c line 805 in H5Lexists(): not a location\n", - " major: Invalid arguments to routine\n", - " minor: Inappropriate type\n", - " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", - " major: Invalid arguments to routine\n", - " minor: Bad value\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205853468416:\n", - " #000: H5L.c line 805 in H5Lexists(): not a location\n", - " major: Invalid arguments to routine\n", - " minor: Inappropriate type\n", - " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", - " major: Invalid arguments to routine\n", - " minor: Bad value\n", - "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_113_strand.fast5\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205845075712:\n", - " #000: H5F.c line 509 in H5Fopen(): unable to open file\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #001: H5Fint.c line 1400 in H5F__open(): unable to open file\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Thu May 2 10:32:47 2019\n", - ", name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_382_strand.fast5', tent_flags = 0\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #003: H5FD.c line 734 in H5FD_open(): open failed\n", - " major: Virtual File Layer\n", - " minor: Unable to initialize object\n", - " #004: H5FDsec2.c line 346 in H5FD_sec2_open(): unable to open file: name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_382_strand.fast5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205845075712:\n", - " #000: H5L.c line 805 in H5Lexists(): not a location\n", - " major: Invalid arguments to routine\n", - " minor: Inappropriate type\n", - " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", - " major: Invalid arguments to routine\n", - " minor: Bad value\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205845075712:\n", - " #000: H5L.c line 805 in H5Lexists(): not a location\n", - " major: Invalid arguments to routine\n", - " minor: Inappropriate type\n", - " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", - " major: Invalid arguments to routine\n", - " minor: Bad value\n", - "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_382_strand.fast5\n", - "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_38_strand.fast5\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205861861120:\n", - " #000: H5F.c line 509 in H5Fopen(): unable to open file\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #001: H5Fint.c line 1400 in H5F__open(): unable to open file\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #002: H5Fint.c line 1546 in H5F_open(): unable to open file: time = Thu May 2 10:32:47 2019\n", - ", name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_354_strand.fast5', tent_flags = 0\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - " #003: H5FD.c line 734 in H5FD_open(): open failed\n", - " major: Virtual File Layer\n", - " minor: Unable to initialize object\n", - " #004: H5FDsec2.c line 346 in H5FD_sec2_open(): unable to open file: name = './data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_354_strand.fast5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0\n", - " major: File accessibilty\n", - " minor: Unable to open file\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205861861120:\n", - " #000: H5L.c line 805 in H5Lexists(): not a location\n", - " major: Invalid arguments to routine\n", - " minor: Inappropriate type\n", - " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", - " major: Invalid arguments to routine\n", - " minor: Bad value\n", - "HDF5-DIAG: Error detected in HDF5 (1.10.4) thread 140205861861120:\n", - " #000: H5L.c line 805 in H5Lexists(): not a location\n", - " major: Invalid arguments to routine\n", - " minor: Inappropriate type\n", - " #001: H5Gloc.c line 246 in H5G_loc(): invalid object ID\n", - " major: Invalid arguments to routine\n", - " minor: Bad value\n", - "[warning] fast5 file is unreadable and will be skipped: ./data/fast5//20180625_FAH77625_MN23126_sequencing_run_S1_57529_read_10_ch_354_strand.fast5\n", - "[post-run summary] total reads: 21, unparseable: 0, qc fail: 0, could not calibrate: 0, no alignment: 0, bad fast5: 21\n", "Checking arguments\n", - "Testing output dir writability\n", "Starting to process files\n", - "\n", - "An error occured. All processes were killed\n", - "\n", - "Traceback (most recent call last):\n", - " File \"/home/aleg/.virtualenvs/Nanopolish_0.11.1/bin/NanopolishComp\", line 11, in \n", - " load_entry_point('NanopolishComp', 'console_scripts', 'NanopolishComp')()\n", - " File \"/home/aleg/Programming/NanopolishComp/NanopolishComp/__main__.py\", line 65, in main\n", - " args.func(args)\n", - " File \"/home/aleg/Programming/NanopolishComp/NanopolishComp/__main__.py\", line 80, in Eventalign_collapse_main\n", - " quiet = args.quiet)\n", - " File \"/home/aleg/Programming/NanopolishComp/NanopolishComp/Eventalign_collapse.py\", line 148, in __init__\n", - " raise E\n", - " File \"/home/aleg/Programming/NanopolishComp/NanopolishComp/Eventalign_collapse.py\", line 138, in __init__\n", - " raise E\n", - "NanopolishComp.common.NanopolishCompError: Traceback (most recent call last):\n", - " File \"/home/aleg/Programming/NanopolishComp/NanopolishComp/Eventalign_collapse.py\", line 176, in _split_reads\n", - " cur_read_id = event_l[idx[\"read_id\"]]\n", - "IndexError: list index out of range\n", + "\r", + "0 reads [00:00, ? reads/s]\r", + "1 reads [00:00, 4.50 reads/s]\r", + "2 reads [00:00, 4.64 reads/s]\r", + "4 reads [00:00, 4.96 reads/s]\r", + "7 reads [00:00, 5.31 reads/s]\r", + "8 reads [00:00, 5.48 reads/s]\r", + "10 reads [00:00, 5.85 reads/s]\r", + "12 reads [00:01, 6.26 reads/s]\r", + "15 reads [00:01, 6.73 reads/s]\r", + "18 reads [00:01, 7.25 reads/s][post-run summary] total reads: 21, unparseable: 0, qc fail: 0, could not calibrate: 0, no alignment: 0, bad fast5: 0\n", + "\r", + "21 reads [00:01, 7.84 reads/s]\n", + "[Eventalign_collapse] total reads: 21 [14.06 reads/s]\n", "\n" ] } @@ -1034,7 +477,12 @@ "source ~/.bashrc\n", "workon Nanopolish_0.11.1\n", "\n", - "nanopolish eventalign -t 4 --samples --scale-events --print-read-name --reads ./data/eventalign_collapse//reads.fastq --bam ./data/eventalign_collapse//aligned_reads.bam --genome ./data/eventalign_collapse//reference.fa | NanopolishComp Eventalign_collapse -o ./output\n", + "nanopolish eventalign -t 4 --samples --scale-events --print-read-name \\\n", + " --reads ./data/eventalign_collapse/reads.fastq \\\n", + " --bam ./data/eventalign_collapse/aligned_reads.bam \\\n", + " --genome ./data/eventalign_collapse/reference.fa | \\\n", + " NanopolishComp Eventalign_collapse -o ./output\n", + " \n", "head ./output/eventalign_collapse/out_eventalign_collapse.tsv\n", "head ./output/eventalign_collapse/out_eventalign_collapse.tsv.idx" ] @@ -1058,8 +506,8 @@ "execution_count": 5, "metadata": { "ExecuteTime": { - "end_time": "2019-05-02T09:32:47.744368Z", - "start_time": "2019-05-02T09:32:47.663524Z" + "end_time": "2019-05-08T10:59:13.946027Z", + "start_time": "2019-05-08T10:59:13.856226Z" } }, "outputs": [], @@ -1083,8 +531,8 @@ "execution_count": 6, "metadata": { "ExecuteTime": { - "end_time": "2019-05-02T09:32:47.769186Z", - "start_time": "2019-05-02T09:32:47.746336Z" + "end_time": "2019-05-08T10:59:13.960817Z", + "start_time": "2019-05-08T10:59:13.947533Z" } }, "outputs": [ @@ -1105,7 +553,7 @@ "\n", "* **outdir** *: str (default = ./)*\n", "\n", - "Path to the output folder\n", + "Path to the output folder (will be created if it does exist yet)\n", "\n", "* **outprefix** *: str (default = out)*\n", "\n", @@ -1167,8 +615,8 @@ "execution_count": 7, "metadata": { "ExecuteTime": { - "end_time": "2019-05-02T09:32:48.110916Z", - "start_time": "2019-05-02T09:32:47.771813Z" + "end_time": "2019-05-08T10:59:14.251288Z", + "start_time": "2019-05-08T10:59:13.962928Z" }, "scrolled": false }, @@ -1178,10 +626,9 @@ "output_type": "stream", "text": [ "Checking arguments\n", - "Testing output dir writability\n", "Starting to process files\n", - "21 reads [00:00, 83.37 reads/s]\n", - "[Eventalign_collapse] total reads: 21 [78.29 reads/s]\n", + "21 reads [00:00, 99.56 reads/s] \n", + "[Eventalign_collapse] total reads: 21 [90.56 reads/s]\n", "\n" ] }, @@ -1205,11 +652,11 @@ "YCR030C 1578 2576 1 971 11.487010000000005 23 0 27 38029 29704 \n", "YHR174W 0 839 2 825 9.659210000000002 15 0 14 67734 24231 \n", "YHR174W 218 1309 3 1028 11.06325000000001 36 0 63 91966 30801 \n", - "YLR441C 173 764 5 554 5.556939999999999 20 0 37 122768 16437 \n", - "YHR174W 462 1309 4 818 10.73776000000001 18 0 29 139206 24589 \n", + "YHR174W 462 1309 4 818 10.73776000000001 18 0 29 122768 24589 \n", + "YLR441C 173 764 5 554 5.556939999999999 20 0 37 147358 16437 \n", "YGR192C 1 989 6 927 11.731470000000003 37 0 61 163796 27388 \n", - "YGR192C 3 995 7 946 12.30464000000001 31 0 50 191185 28123 \n", - "YDR500C 9 252 8 231 2.9179100000000027 7 0 14 219309 6751 \n", + "YDR500C 9 252 8 231 2.9179100000000027 7 0 14 191185 6751 \n", + "YGR192C 3 995 7 946 12.30464000000001 31 0 50 197937 28123 \n", "\n" ] } @@ -1237,8 +684,8 @@ "execution_count": 8, "metadata": { "ExecuteTime": { - "end_time": "2019-05-02T09:32:48.423433Z", - "start_time": "2019-05-02T09:32:48.115915Z" + "end_time": "2019-05-08T10:59:14.549256Z", + "start_time": "2019-05-08T10:59:14.254417Z" } }, "outputs": [ @@ -1247,10 +694,9 @@ "output_type": "stream", "text": [ "Checking arguments\n", - "Testing output dir writability\n", "Starting to process files\n", - "21 reads [00:00, 92.53 reads/s]\n", - "[Eventalign_collapse] total reads: 21 [87.47 reads/s]\n", + "21 reads [00:00, 94.30 reads/s]\n", + "[Eventalign_collapse] total reads: 21 [82.25 reads/s]\n", "\n" ] }, @@ -1278,7 +724,7 @@ "YLR441C 173 764 5 554 5.556939999999999 20 0 37 205598 23103 \n", "YGR192C 1 989 6 927 11.731470000000003 37 0 61 228702 38529 \n", "YDR500C 9 252 8 231 2.9179100000000027 7 0 14 267232 9541 \n", - "YDR224C 0 389 9 376 4.2840300000000004 8 0 13 276774 15465 \n", + "YGR192C 3 995 7 946 12.30464000000001 31 0 50 276774 39493 \n", "\n" ] } @@ -1306,8 +752,8 @@ "execution_count": 9, "metadata": { "ExecuteTime": { - "end_time": "2019-05-02T09:32:48.663769Z", - "start_time": "2019-05-02T09:32:48.425846Z" + "end_time": "2019-05-08T10:59:14.841773Z", + "start_time": "2019-05-08T10:59:14.555193Z" }, "scrolled": false }, @@ -1316,7 +762,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "[Eventalign_collapse] total reads: 21 [106.77 reads/s]\n", + "[Eventalign_collapse] total reads: 21 [86.98 reads/s]\n", "\n" ] }, @@ -1339,12 +785,12 @@ "YGR240C 1656 2960 0 1250 13.788570000000009 35 0 54 0 53046 \n", "YCR030C 1578 2576 1 971 11.487010000000005 23 0 27 53047 41374 \n", "YHR174W 0 839 2 825 9.659210000000002 15 0 14 94422 33595 \n", - "YHR174W 462 1309 4 818 10.73776000000001 18 0 29 128018 34423 \n", - "YHR174W 218 1309 3 1028 11.06325000000001 36 0 63 162442 43155 \n", + "YHR174W 218 1309 3 1028 11.06325000000001 36 0 63 128018 43155 \n", + "YHR174W 462 1309 4 818 10.73776000000001 18 0 29 171174 34423 \n", "YLR441C 173 764 5 554 5.556939999999999 20 0 37 205598 23103 \n", "YGR192C 1 989 6 927 11.731470000000003 37 0 61 228702 38529 \n", "YDR500C 9 252 8 231 2.9179100000000027 7 0 14 267232 9541 \n", - "YDR224C 0 389 9 376 4.2840300000000004 8 0 13 276774 15465 \n", + "YGR192C 3 995 7 946 12.30464000000001 31 0 50 276774 39493 \n", "\n" ] } @@ -1372,8 +818,8 @@ "execution_count": 10, "metadata": { "ExecuteTime": { - "end_time": "2019-05-02T09:32:50.536323Z", - "start_time": "2019-05-02T09:32:48.666817Z" + "end_time": "2019-05-08T10:59:16.615547Z", + "start_time": "2019-05-08T10:59:14.844207Z" }, "scrolled": false }, @@ -1382,7 +828,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "[Eventalign_collapse] total reads: 21 [11.5 reads/s]\n", + "[Eventalign_collapse] total reads: 21 [12.19 reads/s]\n", "\n" ] }, @@ -1390,27 +836,27 @@ "name": "stdout", "output_type": "stream", "text": [ - "#1\tYCR030C\n", + "#2\tYHR174W\n", "ref_pos\tref_kmer\tnum_events\tdwell_time\tNNNNN_dwell_time\tmismatch_dwell_time\tmean\tstd\tmedian\tmad\tnum_signals\tsamples\n", - "1578\tCCACC\t1\t0.00365\t0.0\t0.0\t70.06341552734375\t2.593737840652466\t70.67729949951172\t1.4680023193359375\t11\t70.6773,72.1454,71.4114,63.6306,69.2093,69.2093,67.3008,72.5858,69.9433,72.8794,71.705\n", - "1579\tCACCC\t15\t0.09761000000000002\t0.0\t0.0\t74.59468841552734\t3.2702603340148926\t75.08149719238281\t2.4958038330078125\t294\t75.0815,75.8156,79.6326,78.0177,75.3752,77.2837,78.0177,72.2922,76.99,74.7879,75.3752,75.522,75.6688,73.3199,74.9347,77.5773,73.7603,74.3475,72.7326,75.522,77.2837,75.2284,76.6964,78.4581,78.4581,79.7794,76.5496,76.8432,70.2369,70.2369,81.1006,77.8709,74.9347,72.439,75.8156,77.5773,75.9624,77.4305,76.1092,77.2837,64.5114,74.4943,78.4581,77.4305,76.8432,75.0815,76.1092,78.3113,76.5496,75.6688,76.5496,77.4305,78.6049,76.4028,75.8156,77.1368,71.8518,76.4028,75.8156,75.9624,74.9347,78.3113,72.2922,75.6688,75.0815,75.522,75.9624,70.6773,69.9433,69.2093,68.3284,69.3561,69.2093,69.7965,67.888,68.9157,68.622,69.0625,69.7965,73.173,76.1092,74.7879,75.2284,78.3113,76.256,78.3113,77.7241,72.7326,73.6135,78.6049,75.522,75.8156,74.0539,67.3008,72.439,72.2922,67.0072,74.6411,76.1092,75.8156,73.3199,77.2837,70.3837,73.4667,74.7879,76.6964,79.1921,73.3199,76.6964,76.4028,71.1178,76.1092,79.7794,77.7241,77.1368,74.3475,78.6049,78.8985,77.2837,77.7241,70.0901,79.0453,76.1092,73.6135,78.1645,79.0453,75.8156,79.3389,79.0453,77.1368,78.1645,78.3113,77.8709,79.4858,75.8156,76.4028,77.2837,77.4305,79.6326,77.4305,81.8347,76.5496,76.5496,78.8985,74.7879,77.2837,80.2198,75.6688,78.1645,76.99,79.3389,79.0453,71.5582,78.6049,79.7794,78.3113,78.1645,75.3752,76.8432,80.073,78.3113,80.2198,80.073,80.9538,77.5773,77.8709,75.6688,80.807,77.8709,78.0177,79.3389,80.2198,80.2198,76.1092,77.8709,76.5496,76.6964,77.8709,77.1368,75.9624,76.99,72.2922,71.8518,73.9071,68.9157,70.0901,71.8518,75.3752,73.9071,72.1454,73.6135,74.4943,73.173,75.9624,75.0815,74.6411,75.0815,75.2284,74.4943,75.522,76.6964,72.7326,73.7603,74.9347,75.522,74.0539,71.2646,70.3837,72.439,75.522,75.9624,71.705,72.2922,70.8241,71.1178,70.971,74.7879,75.6688,74.6411,72.1454,73.0262,71.4114,73.9071,74.2007,75.0815,74.4943,72.1454,72.8794,72.1454,69.6497,71.5582,72.439,70.6773,69.7965,68.4752,68.7689,73.6135,73.7603,72.2922,71.4114,69.2093,70.2369,73.3199,72.439,71.5582,67.4476,72.8794,72.2922,72.5858,72.439,73.9071,69.6497,72.2922,73.6135,74.4943,73.0262,70.0901,72.439,71.8518,72.1454,71.9986,70.2369,74.0539,70.971,72.1454,71.2646,71.8518,71.1178,71.5582,70.971,69.2093,70.8241,71.4114,71.2646,72.1454,70.5305,69.6497,70.6773,69.9433,72.8794,67.5944,66.7135,70.5305,69.7965,68.622,73.4667,73.7603,76.1092,77.1368,74.3475,75.8156,74.7879,76.8432,75.8156\n", - "1580\tACCCT\t1\t0.00232\t0.0\t0.0\t67.23785400390625\t1.7063778638839722\t67.88800048828125\t2.2021026611328125\t7\t64.9519,65.6859,67.888,68.1816,68.1816,65.6859,70.0901\n", - "1581\tCCCTC\t1\t0.00232\t0.0\t0.0\t72.0615005493164\t1.1475614309310913\t72.58580017089844\t1.0277023315429688\t7\t70.3837,72.5858,70.6773,71.4114,73.0262,73.6135,72.7326\n", - "1582\tCCTCA\t5\t0.0156\t0.0\t0.0\t73.5634994506836\t2.3691813945770264\t73.76029968261719\t1.614898681640625\t47\t75.522,77.8709,75.2284,74.3475,75.9624,76.6964,72.1454,71.1178,71.1178,72.439,76.256,74.0539,73.0262,73.4667,70.6773,71.5582,69.7965,71.1178,68.3284,70.6773,73.6135,69.6497,67.4476,73.7603,74.3475,72.8794,74.0539,73.3199,74.4943,75.522,72.8794,72.5858,71.2646,73.4667,74.3475,74.4943,74.9347,71.9986,72.2922,76.8432,74.9347,76.5496,75.6688,75.2284,75.0815,76.6964,77.7241\n", - "1583\tCTCAA\t1\t0.00398\t0.0\t0.0\t77.58948516845703\t1.5072672367095947\t78.16450500488281\t0.7339935302734375\t12\t74.3475,75.0815,78.3113,78.8985,77.8709,78.3113,76.4028,78.0177,77.1368,78.3113,78.8985,79.4858\n", - "1584\tTCAAG\t1\t0.01096\t0.0\t0.0\t83.52072143554688\t3.1505558490753174\t84.03679656982422\t2.3488998413085938\t33\t88.441,79.9262,81.6879,81.9815,85.0644,86.9729,84.624,81.1006,76.99,79.0453,79.9262,84.0368,92.1112,83.0091,84.1836,80.807,84.0368,85.7985,87.2665,85.6516,83.0091,87.7069,81.2474,84.0368,79.1921,79.6326,87.2665,83.4495,84.0368,83.7432,80.807,84.624,84.7708\n", - "1585\tCAAGG\t1\t0.00232\t0.0\t0.0\t105.23970794677734\t3.632479667663574\t104.2959976196289\t1.7620010375976562\t7\t113.251,102.534,104.296,103.415,106.498,101.36,105.324\n", + "0\tATGGC\t1\t0.01096\t0.0\t0.0\t86.3893051147461\t3.8192403316497803\t85.67970275878906\t2.618194580078125\t33\t96.4434,93.5342,94.5524,87.1342,85.6797,86.6978,85.0978,91.0615,89.316,84.0797,82.916,82.3342,89.316,84.3706,84.3706,85.8251,81.4615,83.0615,85.9706,85.0978,80.7342,82.4796,93.0979,88.0069,82.916,85.3887,84.0797,86.5524,84.3706,82.3342,88.2979,88.2979,85.9706\n", + "1\tTGGCT\t4\t0.03253\t0.0\t0.0\t104.78181457519531\t6.572873592376709\t106.18900299072266\t3.9269943237304688\t98\t104.007,96.1524,106.189,99.0615,108.371,102.407,107.498,100.662,113.462,106.189,111.28,111.28,112.298,102.989,101.971,109.68,106.916,109.243,106.916,103.28,101.825,110.553,112.443,105.898,101.098,99.0615,105.462,102.843,100.516,107.643,109.098,107.789,113.316,109.098,110.116,108.807,106.916,112.443,114.916,110.843,109.098,111.716,103.862,110.262,109.098,105.171,109.68,108.807,112.589,111.425,123.498,110.116,108.371,110.843,111.134,110.843,96.007,94.5524,97.8979,90.6251,94.9888,97.0252,93.9706,104.589,109.971,106.48,108.807,101.389,103.716,96.8797,89.7524,97.4615,98.0434,86.8433,104.443,103.716,102.407,107.207,102.989,93.6797,103.571,104.007,100.08,103.862,109.68,106.625,101.534,97.3161,103.571,97.607,88.7342,109.534,106.771,113.025,108.807,93.2433,108.952,91.207\n", + "2\tGGCTG\t1\t0.00465\t0.0\t0.0\t96.55765533447266\t6.874111652374268\t97.75244903564453\t5.382049560546875\t14\t105.752,98.9161,98.7706,96.7343,95.5706,100.08,105.607,96.4434,88.5888,101.68,85.6797,104.589,88.1524,85.2433\n", + "3\tGCTGT\t5\t0.0385\t0.0\t0.0\t81.69342803955078\t5.14208984375\t80.29779815673828\t1.5273017883300781\t116\t94.1161,90.6251,93.2433,81.316,105.316,87.716,95.7161,90.3342,98.0434,86.116,87.716,107.789,96.2979,83.4978,84.2251,83.3524,79.5705,80.8796,79.1342,78.116,80.4433,80.5887,79.4251,79.2796,81.6069,77.9705,81.6069,81.7524,81.4615,80.4433,86.9888,79.5705,81.316,77.5342,82.6251,77.9705,82.1887,77.6796,80.7342,83.6433,77.9705,78.4069,80.0069,80.1524,80.4433,80.7342,80.2978,84.9524,78.5524,81.316,80.2978,82.1887,81.6069,77.6796,81.0251,78.4069,79.4251,80.4433,79.8615,82.1887,79.8615,80.0069,78.6978,80.7342,80.5887,78.5524,78.8433,79.4251,82.6251,80.0069,77.5342,80.0069,77.5342,83.7887,84.0797,83.0615,82.1887,81.6069,80.8796,81.316,80.0069,78.9887,82.7706,84.516,81.4615,80.5887,79.2796,78.9887,78.4069,80.5887,80.2978,83.7887,78.4069,78.116,79.5705,78.5524,79.4251,79.2796,81.0251,78.8433,78.9887,78.5524,80.1524,77.9705,78.2614,80.8796,78.4069,79.2796,78.2614,79.716,77.6796,79.4251,77.6796,78.6978,77.3887,76.9523\n", + "4\tCTGTC\t1\t0.00232\t0.0\t0.0\t102.4487075805664\t1.5290673971176147\t103.57099914550781\t0.2910003662109375\t7\t103.571,103.716,103.862,101.243,100.371,103.862,100.516\n", + "5\tTGTCT\t4\t0.019249999999999996\t0.0\t0.0\t107.04158020019531\t5.813553810119629\t107.64350128173828\t2.5454978942871094\t58\t113.462,109.534,107.789,112.298,110.116,112.153,109.243,111.862,107.352,112.88,103.716,102.262,103.571,101.971,104.007,104.152,99.6434,104.88,109.971,109.825,114.625,105.898,107.062,88.7342,105.462,112.589,108.516,114.771,106.916,111.716,110.116,106.334,108.08,107.207,110.262,110.116,105.898,109.825,108.08,106.771,107.207,108.08,107.498,114.48,116.807,107.062,109.68,105.607,110.407,110.553,106.189,105.025,109.389,104.88,86.6978,103.425,88.2979,97.4615\n", + "6\tGTCTC\t2\t0.00797\t0.0\t0.0\t76.83718872070312\t2.1963260173797607\t76.87960052490234\t1.1636505126953125\t24\t78.5524,75.6432,75.7887,79.4251,82.3342,77.3887,79.4251,77.8251,76.9523,78.4069,76.9523,77.8251,76.6614,78.9887,76.6614,76.8069,75.7887,71.8614,74.7705,74.6251,77.3887,76.8069,74.3341,72.8796\n", + "7\tTCTCT\t1\t0.00232\t0.0\t0.0\t80.0484619140625\t1.0306347608566284\t80.00689697265625\t0.727294921875\t7\t78.6978,79.2796,79.2796,80.0069,81.4615,81.6069,80.0069\n", "\n", "ref_id ref_start ref_end read_id kmers dwell_time NNNNN_kmers mismatch_kmers missing_kmers byte_offset byte_len \n", - "YCR030C 1578 2576 1 971 11.487010000000005 23 0 27 0 376326 \n", - "YHR174W 0 839 2 825 9.659210000000002 15 0 14 376327 317027 \n", - "YHR174W 218 1309 3 1028 11.06325000000001 36 0 63 693355 372126 \n", - "YGR240C 1656 2960 0 1250 13.788570000000009 35 0 54 1065482 461011 \n", + "YHR174W 0 839 2 825 9.659210000000002 15 0 14 0 317027 \n", + "YCR030C 1578 2576 1 971 11.487010000000005 23 0 27 317028 376326 \n", + "YGR240C 1656 2960 0 1250 13.788570000000009 35 0 54 693355 461011 \n", + "YHR174W 218 1309 3 1028 11.06325000000001 36 0 63 1154367 372126 \n", "YLR441C 173 764 5 554 5.556939999999999 20 0 37 1526494 190670 \n", - "YHR174W 462 1309 4 818 10.73776000000001 18 0 29 1717165 342528 \n", - "YDR500C 9 252 8 231 2.9179100000000027 7 0 14 2059694 93821 \n", - "YGR192C 1 989 6 927 11.731470000000003 37 0 61 2153516 376317 \n", - "YDR224C 0 389 9 376 4.2840300000000004 8 0 13 2529834 141262 \n", + "YDR500C 9 252 8 231 2.9179100000000027 7 0 14 1717165 93821 \n", + "YHR174W 462 1309 4 818 10.73776000000001 18 0 29 1810987 342528 \n", + "YGR192C 3 995 7 946 12.30464000000001 31 0 50 2153516 392222 \n", + "YDR224C 0 389 9 376 4.2840300000000004 8 0 13 2545739 141262 \n", "\n" ] } @@ -1433,13 +879,131 @@ "## Using the index to random access a specific entry in the file" ] }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Random access with standard library " + ] + }, { "cell_type": "code", - "execution_count": 11, + "execution_count": 2, "metadata": { "ExecuteTime": { - "end_time": "2019-05-02T09:32:51.031323Z", - "start_time": "2019-05-02T09:32:50.543356Z" + "end_time": "2019-05-08T12:57:21.157813Z", + "start_time": "2019-05-08T12:57:21.111872Z" + }, + "scrolled": false + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "RANDOM INDEX LINES\n", + "ref_id ref_start ref_end read_id kmers dwell_time NNNNN_kmers mismatch_kmers missing_kmers byte_offset byte_len\n", + "-------- ----------- --------- --------- ------- ------------ ------------- ---------------- --------------- ------------- ----------\n", + "YMR116C 180 950 16 740 9.30597 20 0 30 482785 30690\n", + "YLR110C 14 395 15 364 4.61444 9 0 17 450178 15023\n", + "YGR240C 1656 2960 0 1250 13.7886 35 0 54 0 53046\n", + "YGR192C 3 995 7 946 12.3046 31 0 50 276774 39493\n", + "YHR174W 462 1309 4 818 10.7378 18 0 29 171174 34423\n", + "\n", + "#16\tYMR116C\n", + " ref_pos ref_kmer num_events dwell_time NNNNN_dwell_time mismatch_dwell_time start_idx end_idx\n", + "--------- ---------- ------------ ------------ ------------------ --------------------- ----------- ---------\n", + " 180 TTCAA 3 0.06408 0 0 41362 41555\n", + " 181 TCAAG 1 0.00598 0 0 41344 41362\n", + " 182 CAAGG 2 0.00963 0 0 41315 41344\n", + " 183 AAGGG 1 0.00697 0 0 41294 41315\n", + " 184 AGGGT 1 0.00199 0 0 41288 41294\n", + "\n", + "#15\tYLR110C\n", + " ref_pos ref_kmer num_events dwell_time NNNNN_dwell_time mismatch_dwell_time start_idx end_idx\n", + "--------- ---------- ------------ ------------ ------------------ --------------------- ----------- ---------\n", + " 14 TGTCG 2 0.00598 0 0 23697 23715\n", + " 15 GTCGC 1 0.0073 0 0 23675 23697\n", + " 16 TCGCT 1 0.00564 0 0 23658 23675\n", + " 17 CGCTT 1 0.00398 0 0 23646 23658\n", + " 18 GCTTC 2 0.01328 0 0 23606 23646\n", + "\n", + "#0\tYGR240C\n", + " ref_pos ref_kmer num_events dwell_time NNNNN_dwell_time mismatch_dwell_time start_idx end_idx\n", + "--------- ---------- ------------ ------------ ------------------ --------------------- ----------- ---------\n", + " 1656 GAAAA 1 0.00266 0 0 63446 63454\n", + " 1657 AAAAC 1 0.00764 0 0 63423 63446\n", + " 1658 AAACA 1 0.00398 0 0 63411 63423\n", + " 1659 AACAA 1 0.00432 0 0 63398 63411\n", + " 1660 ACAAA 1 0.00498 0 0 63383 63398\n", + "\n", + "#7\tYGR192C\n", + " ref_pos ref_kmer num_events dwell_time NNNNN_dwell_time mismatch_dwell_time start_idx end_idx\n", + "--------- ---------- ------------ ------------ ------------------ --------------------- ----------- ---------\n", + " 3 GTTAG 1 0.00564 0 0 55070 55087\n", + " 4 TTAGA 1 0.0073 0 0 55048 55070\n", + " 5 TAGAG 1 0.01162 0 0 55013 55048\n", + " 6 AGAGT 1 0.00465 0 0 54999 55013\n", + " 7 GAGTT 3 0.01128 0 0 54965 54999\n", + "\n", + "#4\tYHR174W\n", + " ref_pos ref_kmer num_events dwell_time NNNNN_dwell_time mismatch_dwell_time start_idx end_idx\n", + "--------- ---------- ------------ ------------ ------------------ --------------------- ----------- ---------\n", + " 462 TTGAA 2 0.00797 0 0 42640 42664\n", + " 463 TGAAC 1 0.00531 0 0 42624 42640\n", + " 464 GAACG 3 0.01726 0 0 42572 42624\n", + " 465 AACGG 5 0.02423 0 0 42499 42572\n", + " 466 ACGGT 1 0.00764 0 0 42476 42499\n" + ] + } + ], + "source": [ + "output_fn = \"./output/eventalign_collapse/stats_eventalign_collapse.tsv\"\n", + "index_fn = \"./output/eventalign_collapse/stats_eventalign_collapse.tsv.idx\"\n", + "\n", + "# Imports\n", + "import csv\n", + "from tabulate import tabulate\n", + "from random import sample\n", + "from itertools import islice\n", + "\n", + "# read index file and select random lines\n", + "index_list = []\n", + "with open (index_fn) as fp:\n", + " for l in csv.DictReader(fp, delimiter='\\t'):\n", + " index_list.append(l)\n", + "random_index = sample(index_list, k=5)\n", + "print (\"RANDOM INDEX LINES\")\n", + "print (tabulate(random_index, headers=\"keys\"))\n", + "\n", + "# Open the collapsed event align file\n", + "with open (output_fn) as fp:\n", + " for index in random_index:\n", + " # Access the header corresponding to the randomly selected index line using seek \n", + " fp.seek(0) # Return to file start\n", + " fp.seek(int(index[\"byte_offset\"])) # Move to the offset indicated in the index file\n", + " print (\"\\n\" + fp.readline().rstrip()) # Print read header\n", + " # Get 5 first lines and print then\n", + " data_list = []\n", + " for l in islice(csv.DictReader(fp, delimiter='\\t'), 5):\n", + " data_list.append(l)\n", + " print (tabulate(data_list, headers=\"keys\"))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Random access with pandas " + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": { + "ExecuteTime": { + "end_time": "2019-05-08T12:56:26.210616Z", + "start_time": "2019-05-08T12:56:25.679506Z" }, "scrolled": false }, @@ -1475,11 +1039,7 @@ " ref_id\n", " ref_start\n", " ref_end\n", - " read_id\n", - " kmers\n", - " dwell_time\n", - " NNNNN_kmers\n", - " mismatch_kmers\n", + " ...\n", " missing_kmers\n", " byte_offset\n", " byte_len\n", @@ -1487,93 +1047,69 @@ " \n", " \n", " \n", - " 10\n", - " YIL117C\n", - " 27\n", - " 953\n", - " 10\n", - " 889\n", - " 13.64007\n", - " 23\n", - " 0\n", - " 37\n", - " 331734\n", - " 37225\n", - " \n", - " \n", - " 13\n", - " YPL198W\n", - " 10\n", - " 719\n", - " 13\n", - " 667\n", - " 8.79275\n", - " 30\n", - " 0\n", - " 44\n", - " 409081\n", - " 27943\n", - " \n", - " \n", - " 7\n", - " YDR500C\n", - " 9\n", - " 252\n", - " 8\n", - " 231\n", - " 2.91791\n", - " 7\n", - " 0\n", - " 14\n", - " 267232\n", - " 9541\n", + " 14\n", + " YDR382W\n", + " 5\n", + " 329\n", + " ...\n", + " 16\n", + " 437025\n", + " 13152\n", " \n", " \n", " 6\n", " YGR192C\n", " 1\n", " 989\n", - " 6\n", - " 927\n", - " 11.73147\n", - " 37\n", - " 0\n", + " ...\n", " 61\n", " 228702\n", " 38529\n", " \n", " \n", - " 15\n", - " YLR110C\n", - " 14\n", - " 395\n", - " 15\n", - " 364\n", - " 4.61444\n", - " 9\n", - " 0\n", - " 17\n", - " 450178\n", - " 15023\n", + " 1\n", + " YCR030C\n", + " 1578\n", + " 2576\n", + " ...\n", + " 27\n", + " 53047\n", + " 41374\n", + " \n", + " \n", + " 5\n", + " YLR441C\n", + " 173\n", + " 764\n", + " ...\n", + " 37\n", + " 205598\n", + " 23103\n", + " \n", + " \n", + " 12\n", + " YLR293C\n", + " 1\n", + " 654\n", + " ...\n", + " 43\n", + " 382914\n", + " 26166\n", " \n", " \n", "\n", + "

5 rows × 11 columns

\n", "" ], "text/plain": [ - " ref_id ref_start ref_end read_id kmers dwell_time NNNNN_kmers \\\n", - "10 YIL117C 27 953 10 889 13.64007 23 \n", - "13 YPL198W 10 719 13 667 8.79275 30 \n", - "7 YDR500C 9 252 8 231 2.91791 7 \n", - "6 YGR192C 1 989 6 927 11.73147 37 \n", - "15 YLR110C 14 395 15 364 4.61444 9 \n", + " ref_id ref_start ref_end ... missing_kmers byte_offset byte_len\n", + "14 YDR382W 5 329 ... 16 437025 13152\n", + "6 YGR192C 1 989 ... 61 228702 38529\n", + "1 YCR030C 1578 2576 ... 27 53047 41374\n", + "5 YLR441C 173 764 ... 37 205598 23103\n", + "12 YLR293C 1 654 ... 43 382914 26166\n", "\n", - " mismatch_kmers missing_kmers byte_offset byte_len \n", - "10 0 37 331734 37225 \n", - "13 0 44 409081 27943 \n", - "7 0 14 267232 9541 \n", - "6 0 61 228702 38529 \n", - "15 0 17 450178 15023 " + "[5 rows x 11 columns]" ] }, "metadata": {}, @@ -1583,7 +1119,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "#10\tYIL117C\n" + "#14\tYDR382W\n" ] }, { @@ -1610,8 +1146,7 @@ " ref_pos\n", " ref_kmer\n", " num_events\n", - " dwell_time\n", - " NNNNN_dwell_time\n", + " ...\n", " mismatch_dwell_time\n", " start_idx\n", " end_idx\n", @@ -1620,80 +1155,68 @@ " \n", " \n", " 0\n", - " 27\n", - " GGCCT\n", - " 4\n", - " 0.03287\n", - " 0.00498\n", + " 5\n", + " ATACT\n", + " 2\n", + " ...\n", " 0.0\n", - " 57497\n", - " 57596\n", + " 48813\n", + " 48858\n", " \n", " \n", " 1\n", - " 31\n", - " TTCCA\n", - " 1\n", - " 0.00398\n", - " 0.00000\n", + " 6\n", + " TACTT\n", + " 2\n", + " ...\n", " 0.0\n", - " 57485\n", - " 57497\n", + " 48794\n", + " 48813\n", " \n", " \n", - " ...\n", - " ...\n", - " ...\n", - " ...\n", - " ...\n", - " ...\n", - " ...\n", - " ...\n", + " 2\n", + " 7\n", + " ACTTA\n", + " 4\n", " ...\n", + " 0.0\n", + " 48741\n", + " 48794\n", " \n", " \n", - " 887\n", - " 951\n", - " GAGTA\n", - " 3\n", - " 0.01163\n", - " 0.00432\n", + " 3\n", + " 8\n", + " CTTAG\n", + " 1\n", + " ...\n", " 0.0\n", - " 16588\n", - " 16623\n", + " 48709\n", + " 48741\n", " \n", " \n", - " 888\n", - " 952\n", - " AGTAA\n", - " 5\n", - " 0.02590\n", - " 0.00000\n", + " 4\n", + " 9\n", + " TTAGC\n", + " 1\n", + " ...\n", " 0.0\n", - " 16510\n", - " 16588\n", + " 48681\n", + " 48709\n", " \n", " \n", "\n", - "

889 rows × 8 columns

\n", + "

5 rows × 8 columns

\n", "" ], "text/plain": [ - " ref_pos ref_kmer num_events dwell_time NNNNN_dwell_time \\\n", - "0 27 GGCCT 4 0.03287 0.00498 \n", - "1 31 TTCCA 1 0.00398 0.00000 \n", - ".. ... ... ... ... ... \n", - "887 951 GAGTA 3 0.01163 0.00432 \n", - "888 952 AGTAA 5 0.02590 0.00000 \n", - "\n", - " mismatch_dwell_time start_idx end_idx \n", - "0 0.0 57497 57596 \n", - "1 0.0 57485 57497 \n", - ".. ... ... ... \n", - "887 0.0 16588 16623 \n", - "888 0.0 16510 16588 \n", + " ref_pos ref_kmer num_events ... mismatch_dwell_time start_idx end_idx\n", + "0 5 ATACT 2 ... 0.0 48813 48858\n", + "1 6 TACTT 2 ... 0.0 48794 48813\n", + "2 7 ACTTA 4 ... 0.0 48741 48794\n", + "3 8 CTTAG 1 ... 0.0 48709 48741\n", + "4 9 TTAGC 1 ... 0.0 48681 48709\n", "\n", - "[889 rows x 8 columns]" + "[5 rows x 8 columns]" ] }, "metadata": {}, @@ -1703,7 +1226,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "#13\tYPL198W\n" + "#6\tYGR192C\n" ] }, { @@ -1730,8 +1253,7 @@ " ref_pos\n", " ref_kmer\n", " num_events\n", - " dwell_time\n", - " NNNNN_dwell_time\n", + " ...\n", " mismatch_dwell_time\n", " start_idx\n", " end_idx\n", @@ -1740,80 +1262,68 @@ " \n", " \n", " 0\n", - " 10\n", - " AAAAA\n", " 1\n", - " 0.00697\n", - " 0.00000\n", + " TGGTT\n", + " 1\n", + " ...\n", " 0.0\n", - " 44620\n", - " 44641\n", + " 45267\n", + " 45311\n", " \n", " \n", " 1\n", - " 11\n", - " AAAAA\n", + " 2\n", + " GGTTA\n", " 1\n", - " 0.01959\n", - " 0.00000\n", + " ...\n", " 0.0\n", - " 44561\n", - " 44620\n", + " 45248\n", + " 45267\n", " \n", " \n", - " ...\n", - " ...\n", - " ...\n", - " ...\n", - " ...\n", - " ...\n", - " ...\n", - " ...\n", + " 2\n", + " 3\n", + " GTTAG\n", + " 1\n", " ...\n", + " 0.0\n", + " 45223\n", + " 45248\n", " \n", " \n", - " 665\n", - " 715\n", - " TGGTT\n", + " 3\n", + " 4\n", + " TTAGA\n", " 4\n", - " 0.02557\n", - " 0.00797\n", + " ...\n", " 0.0\n", - " 18191\n", - " 18268\n", + " 45159\n", + " 45223\n", " \n", " \n", - " 666\n", - " 718\n", - " TTAAG\n", - " 1\n", - " 0.01162\n", - " 0.00000\n", + " 4\n", + " 5\n", + " TAGAG\n", + " 2\n", + " ...\n", " 0.0\n", - " 18156\n", - " 18191\n", + " 45137\n", + " 45159\n", " \n", " \n", "\n", - "

667 rows × 8 columns

\n", + "

5 rows × 8 columns

\n", "" ], "text/plain": [ - " ref_pos ref_kmer num_events dwell_time NNNNN_dwell_time \\\n", - "0 10 AAAAA 1 0.00697 0.00000 \n", - "1 11 AAAAA 1 0.01959 0.00000 \n", - ".. ... ... ... ... ... \n", - "665 715 TGGTT 4 0.02557 0.00797 \n", - "666 718 TTAAG 1 0.01162 0.00000 \n", - "\n", - " mismatch_dwell_time start_idx end_idx \n", - "0 0.0 44620 44641 \n", - "1 0.0 44561 44620 \n", - ".. ... ... ... \n", - "665 0.0 18191 18268 \n", - "666 0.0 18156 18191 \n", + " ref_pos ref_kmer num_events ... mismatch_dwell_time start_idx end_idx\n", + "0 1 TGGTT 1 ... 0.0 45267 45311\n", + "1 2 GGTTA 1 ... 0.0 45248 45267\n", + "2 3 GTTAG 1 ... 0.0 45223 45248\n", + "3 4 TTAGA 4 ... 0.0 45159 45223\n", + "4 5 TAGAG 2 ... 0.0 45137 45159\n", "\n", - "[667 rows x 8 columns]" + "[5 rows x 8 columns]" ] }, "metadata": {}, @@ -1823,7 +1333,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "#8\tYDR500C\n" + "#1\tYCR030C\n" ] }, { @@ -1850,8 +1360,7 @@ " ref_pos\n", " ref_kmer\n", " num_events\n", - " dwell_time\n", - " NNNNN_dwell_time\n", + " ...\n", " mismatch_dwell_time\n", " start_idx\n", " end_idx\n", @@ -1860,80 +1369,68 @@ " \n", " \n", " 0\n", - " 9\n", - " GGTAC\n", - " 2\n", - " 0.01095\n", - " 0.00000\n", + " 1578\n", + " CCACC\n", + " 1\n", + " ...\n", " 0.0\n", - " 22637\n", - " 22670\n", + " 47517\n", + " 47528\n", " \n", " \n", " 1\n", - " 10\n", - " GTACT\n", - " 1\n", - " 0.00631\n", - " 0.00000\n", + " 1579\n", + " CACCC\n", + " 15\n", + " ...\n", " 0.0\n", - " 22618\n", - " 22637\n", + " 47223\n", + " 47517\n", " \n", " \n", - " ...\n", - " ...\n", - " ...\n", - " ...\n", - " ...\n", - " ...\n", - " ...\n", - " ...\n", + " 2\n", + " 1580\n", + " ACCCT\n", + " 1\n", " ...\n", + " 0.0\n", + " 47216\n", + " 47223\n", " \n", " \n", - " 229\n", - " 248\n", - " TAAGG\n", - " 2\n", - " 0.01560\n", - " 0.01228\n", + " 3\n", + " 1581\n", + " CCCTC\n", + " 1\n", + " ...\n", " 0.0\n", - " 13899\n", - " 13946\n", + " 47209\n", + " 47216\n", " \n", " \n", - " 230\n", - " 251\n", - " GGCTA\n", - " 1\n", - " 0.00598\n", - " 0.00000\n", + " 4\n", + " 1582\n", + " CCTCA\n", + " 5\n", + " ...\n", " 0.0\n", - " 13881\n", - " 13899\n", + " 47162\n", + " 47209\n", " \n", " \n", "\n", - "

231 rows × 8 columns

\n", + "

5 rows × 8 columns

\n", "" ], "text/plain": [ - " ref_pos ref_kmer num_events dwell_time NNNNN_dwell_time \\\n", - "0 9 GGTAC 2 0.01095 0.00000 \n", - "1 10 GTACT 1 0.00631 0.00000 \n", - ".. ... ... ... ... ... \n", - "229 248 TAAGG 2 0.01560 0.01228 \n", - "230 251 GGCTA 1 0.00598 0.00000 \n", + " ref_pos ref_kmer num_events ... mismatch_dwell_time start_idx end_idx\n", + "0 1578 CCACC 1 ... 0.0 47517 47528\n", + "1 1579 CACCC 15 ... 0.0 47223 47517\n", + "2 1580 ACCCT 1 ... 0.0 47216 47223\n", + "3 1581 CCCTC 1 ... 0.0 47209 47216\n", + "4 1582 CCTCA 5 ... 0.0 47162 47209\n", "\n", - " mismatch_dwell_time start_idx end_idx \n", - "0 0.0 22637 22670 \n", - "1 0.0 22618 22637 \n", - ".. ... ... ... \n", - "229 0.0 13899 13946 \n", - "230 0.0 13881 13899 \n", - "\n", - "[231 rows x 8 columns]" + "[5 rows x 8 columns]" ] }, "metadata": {}, @@ -1943,7 +1440,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "#6\tYGR192C\n" + "#5\tYLR441C\n" ] }, { @@ -1970,8 +1467,7 @@ " ref_pos\n", " ref_kmer\n", " num_events\n", - " dwell_time\n", - " NNNNN_dwell_time\n", + " ...\n", " mismatch_dwell_time\n", " start_idx\n", " end_idx\n", @@ -1980,80 +1476,68 @@ " \n", " \n", " 0\n", - " 1\n", - " TGGTT\n", - " 1\n", - " 0.01461\n", - " 0.00000\n", + " 173\n", + " AGATG\n", + " 4\n", + " ...\n", " 0.0\n", - " 45267\n", - " 45311\n", + " 27161\n", + " 27241\n", " \n", " \n", " 1\n", - " 2\n", - " GGTTA\n", + " 174\n", + " GATGC\n", " 1\n", - " 0.00631\n", - " 0.00000\n", + " ...\n", " 0.0\n", - " 45248\n", - " 45267\n", + " 27150\n", + " 27161\n", " \n", " \n", - " ...\n", - " ...\n", - " ...\n", - " ...\n", - " ...\n", - " ...\n", - " ...\n", - " ...\n", + " 2\n", + " 175\n", + " ATGCT\n", + " 1\n", " ...\n", + " 0.0\n", + " 27105\n", + " 27150\n", " \n", " \n", - " 925\n", - " 987\n", - " GCCAA\n", - " 2\n", - " 0.01992\n", - " 0.00000\n", + " 3\n", + " 178\n", + " CTTTG\n", + " 1\n", + " ...\n", " 0.0\n", - " 10052\n", - " 10112\n", + " 27078\n", + " 27105\n", " \n", " \n", - " 926\n", - " 988\n", - " CCAAG\n", - " 5\n", - " 0.02589\n", - " 0.01228\n", + " 4\n", + " 179\n", + " TTTGA\n", + " 1\n", + " ...\n", " 0.0\n", - " 9974\n", - " 10052\n", + " 27061\n", + " 27078\n", " \n", " \n", "\n", - "

927 rows × 8 columns

\n", + "

5 rows × 8 columns

\n", "" ], "text/plain": [ - " ref_pos ref_kmer num_events dwell_time NNNNN_dwell_time \\\n", - "0 1 TGGTT 1 0.01461 0.00000 \n", - "1 2 GGTTA 1 0.00631 0.00000 \n", - ".. ... ... ... ... ... \n", - "925 987 GCCAA 2 0.01992 0.00000 \n", - "926 988 CCAAG 5 0.02589 0.01228 \n", - "\n", - " mismatch_dwell_time start_idx end_idx \n", - "0 0.0 45267 45311 \n", - "1 0.0 45248 45267 \n", - ".. ... ... ... \n", - "925 0.0 10052 10112 \n", - "926 0.0 9974 10052 \n", + " ref_pos ref_kmer num_events ... mismatch_dwell_time start_idx end_idx\n", + "0 173 AGATG 4 ... 0.0 27161 27241\n", + "1 174 GATGC 1 ... 0.0 27150 27161\n", + "2 175 ATGCT 1 ... 0.0 27105 27150\n", + "3 178 CTTTG 1 ... 0.0 27078 27105\n", + "4 179 TTTGA 1 ... 0.0 27061 27078\n", "\n", - "[927 rows x 8 columns]" + "[5 rows x 8 columns]" ] }, "metadata": {}, @@ -2063,7 +1547,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "#15\tYLR110C\n" + "#12\tYLR293C\n" ] }, { @@ -2090,8 +1574,7 @@ " ref_pos\n", " ref_kmer\n", " num_events\n", - " dwell_time\n", - " NNNNN_dwell_time\n", + " ...\n", " mismatch_dwell_time\n", " start_idx\n", " end_idx\n", @@ -2100,80 +1583,68 @@ " \n", " \n", " 0\n", - " 14\n", - " TGTCG\n", - " 2\n", - " 0.00598\n", - " 0.0\n", + " 1\n", + " TGTCT\n", + " 1\n", + " ...\n", " 0.0\n", - " 23697\n", - " 23715\n", + " 81520\n", + " 81535\n", " \n", " \n", " 1\n", - " 15\n", - " GTCGC\n", - " 1\n", - " 0.00730\n", - " 0.0\n", + " 2\n", + " GTCTG\n", + " 2\n", + " ...\n", " 0.0\n", - " 23675\n", - " 23697\n", + " 81436\n", + " 81520\n", " \n", " \n", - " ...\n", - " ...\n", - " ...\n", - " ...\n", - " ...\n", - " ...\n", - " ...\n", - " ...\n", + " 2\n", + " 3\n", + " TCTGC\n", + " 2\n", " ...\n", + " 0.0\n", + " 81371\n", + " 81436\n", " \n", " \n", - " 362\n", - " 393\n", - " TTGTT\n", - " 7\n", - " 0.04217\n", - " 0.0\n", + " 3\n", + " 4\n", + " CTGCC\n", + " 1\n", + " ...\n", " 0.0\n", - " 9871\n", - " 9998\n", + " 81361\n", + " 81371\n", " \n", " \n", - " 363\n", - " 394\n", - " TGTTG\n", + " 4\n", " 5\n", - " 0.01859\n", - " 0.0\n", + " TGCCC\n", + " 1\n", + " ...\n", " 0.0\n", - " 9815\n", - " 9871\n", + " 81351\n", + " 81361\n", " \n", " \n", "\n", - "

364 rows × 8 columns

\n", + "

5 rows × 8 columns

\n", "" ], "text/plain": [ - " ref_pos ref_kmer num_events dwell_time NNNNN_dwell_time \\\n", - "0 14 TGTCG 2 0.00598 0.0 \n", - "1 15 GTCGC 1 0.00730 0.0 \n", - ".. ... ... ... ... ... \n", - "362 393 TTGTT 7 0.04217 0.0 \n", - "363 394 TGTTG 5 0.01859 0.0 \n", - "\n", - " mismatch_dwell_time start_idx end_idx \n", - "0 0.0 23697 23715 \n", - "1 0.0 23675 23697 \n", - ".. ... ... ... \n", - "362 0.0 9871 9998 \n", - "363 0.0 9815 9871 \n", + " ref_pos ref_kmer num_events ... mismatch_dwell_time start_idx end_idx\n", + "0 1 TGTCT 1 ... 0.0 81520 81535\n", + "1 2 GTCTG 2 ... 0.0 81436 81520\n", + "2 3 TCTGC 2 ... 0.0 81371 81436\n", + "3 4 CTGCC 1 ... 0.0 81361 81371\n", + "4 5 TGCCC 1 ... 0.0 81351 81361\n", "\n", - "[364 rows x 8 columns]" + "[5 rows x 8 columns]" ] }, "metadata": {}, @@ -2184,11 +1655,12 @@ "output_fn = \"./output/eventalign_collapse/stats_eventalign_collapse.tsv\"\n", "index_fn = \"./output/eventalign_collapse/stats_eventalign_collapse.tsv.idx\"\n", "\n", - "# Import the index in a pandas dataframe (because it is simple)\n", - "import pandas as pd \n", - "index_df = pd.read_csv (index_fn, sep=\"\\t\")\n", + "# Imports\n", + "import pandas as pd\n", + "pd.set_option('display.max_columns', 6)\n", "\n", - "# Select random lines\n", + "# read index file and select random lines\n", + "index_df = pd.read_csv (index_fn, sep=\"\\t\")\n", "random_lines = index_df.sample(5)\n", "print (\"Random index lines\")\n", "display (random_lines)\n", @@ -2201,9 +1673,8 @@ " fp.seek(0) # Return to file start\n", " fp.seek(read.byte_offset) # Move to the offset indicated in the index file\n", " print (fp.readline().rstrip()) # Print read header\n", - " df = pd.read_csv (fp, nrows=read.kmers, sep=\"\\t\") # Read lines corresponding to the read\n", - " with pd.option_context(\"display.max_rows\",4): # display first and last lines\n", - " display(df)" + " df = pd.read_csv (fp, nrows=5, sep=\"\\t\") # Read lines corresponding to the read\n", + " display(df)" ] } ], diff --git a/docs/demo/Freq_meth_calculate_usage.ipynb b/docs/demo/Freq_meth_calculate_usage.ipynb index ef68547..23f798f 100644 --- a/docs/demo/Freq_meth_calculate_usage.ipynb +++ b/docs/demo/Freq_meth_calculate_usage.ipynb @@ -166,11 +166,11 @@ }, { "cell_type": "code", - "execution_count": 1, + "execution_count": 9, "metadata": { "ExecuteTime": { - "end_time": "2019-05-02T09:36:28.617634Z", - "start_time": "2019-05-02T09:36:27.566472Z" + "end_time": "2019-05-08T11:50:06.436703Z", + "start_time": "2019-05-08T11:50:05.441542Z" } }, "outputs": [ @@ -197,7 +197,8 @@ " Path to a nanopolish call_methylation tsv output file.\n", " If not specified read from std input\n", " -o OUTDIR, --outdir OUTDIR\n", - " Path to the output folder (default: ./)\n", + " Path to the output folder (will be created if it does\n", + " exist yet) (default: ./)\n", " -p OUTPREFIX, --outprefix OUTPREFIX\n", " text outprefix for all the files generated (default:\n", " out)\n", @@ -246,11 +247,11 @@ }, { "cell_type": "code", - "execution_count": 2, + "execution_count": 11, "metadata": { "ExecuteTime": { - "end_time": "2019-05-02T09:36:48.448839Z", - "start_time": "2019-05-02T09:36:28.620951Z" + "end_time": "2019-05-08T11:52:10.999583Z", + "start_time": "2019-05-08T11:51:51.857073Z" }, "scrolled": false }, @@ -288,7 +289,7 @@ "Options summary\n", "\tpackage_name: NanopolishComp\n", "\tpackage_version: 0.6.1\n", - "\ttimestamp: 2019-05-02 10:36:29.585341\n", + "\ttimestamp: 2019-05-08 12:51:52.765199\n", "\tquiet: False\n", "\tverbose: True\n", "\tmotif: cpg\n", @@ -301,181 +302,180 @@ "\tinput_fn: data/freq_meth_calculate/methylation_calls.tsv\n", "\n", "## Checking arguments ##\n", - "Test input file readability\n", - "Testing output dir writability\n", + "\tTesting input file readability\n", + "\tCreating output folder\n", "## Parsing methylation_calls file ##\n", "Starting to parse file methylation_calls file\n", "\r", "0 lines [00:00, ? lines/s]\r", - "3972 lines [00:00, 39719.66 lines/s]\r", - "7974 lines [00:00, 39807.26 lines/s]\r", - "11925 lines [00:00, 39714.71 lines/s]\r", - "15922 lines [00:00, 39789.10 lines/s]\r", - "19677 lines [00:00, 39088.44 lines/s]\r", - "22922 lines [00:00, 36697.98 lines/s]\r", - "26157 lines [00:00, 29681.15 lines/s]\r", - "29386 lines [00:00, 30416.83 lines/s]\r", - "33098 lines [00:00, 32157.87 lines/s]\r", - "36729 lines [00:01, 33298.15 lines/s]\r", - "40558 lines [00:01, 34651.22 lines/s]\r", - "44481 lines [00:01, 35905.91 lines/s]\r", - "48332 lines [00:01, 36649.03 lines/s]\r", - "52240 lines [00:01, 37344.28 lines/s]\r", - "56156 lines [00:01, 37870.58 lines/s]\r", - "60072 lines [00:01, 38247.05 lines/s]\r", - "64005 lines [00:01, 38563.25 lines/s]\r", - "67892 lines [00:01, 38654.04 lines/s]\r", - "71763 lines [00:01, 38124.82 lines/s]\r", - "75581 lines [00:02, 32395.50 lines/s]\r", - "78974 lines [00:02, 27110.51 lines/s]\r", - "82500 lines [00:02, 29130.13 lines/s]\r", - "85745 lines [00:02, 30047.66 lines/s]\r", - "88911 lines [00:02, 26951.26 lines/s]\r", - "91779 lines [00:02, 26365.74 lines/s]\r", - "95469 lines [00:02, 28833.09 lines/s]\r", - "98741 lines [00:02, 29897.35 lines/s]\r", - "101850 lines [00:03, 25426.34 lines/s]\r", - "105371 lines [00:03, 27733.79 lines/s]\r", - "108346 lines [00:03, 26868.81 lines/s]\r", - "111180 lines [00:03, 21167.71 lines/s]\r", - "114625 lines [00:03, 23935.91 lines/s]\r", - "118268 lines [00:03, 26680.03 lines/s]\r", - "121922 lines [00:03, 29028.45 lines/s]\r", - "125482 lines [00:03, 30730.17 lines/s]\r", - "128940 lines [00:04, 31790.40 lines/s]\r", - "132407 lines [00:04, 32600.32 lines/s]\r", - "135792 lines [00:04, 25016.46 lines/s]\r", - "138648 lines [00:04, 21498.39 lines/s]\r", - "142083 lines [00:04, 24215.84 lines/s]\r", - "144853 lines [00:04, 21830.15 lines/s]\r", - "147989 lines [00:04, 24017.97 lines/s]\r", - "151092 lines [00:04, 25764.01 lines/s]\r", - "154225 lines [00:05, 27214.11 lines/s]\r", - "157125 lines [00:05, 27158.76 lines/s]\r", - "160148 lines [00:05, 28011.78 lines/s]\r", - "163422 lines [00:05, 29279.59 lines/s]\r", - "166932 lines [00:05, 30811.06 lines/s]\r", - "170383 lines [00:05, 31834.16 lines/s]\r", - "173630 lines [00:05, 30157.04 lines/s]\r", - "177112 lines [00:05, 31419.03 lines/s]\r", - "180564 lines [00:05, 32284.12 lines/s]\r", - "183839 lines [00:06, 29498.66 lines/s]\r", - "186868 lines [00:06, 25090.81 lines/s]\r", - "189547 lines [00:06, 23488.05 lines/s]\r", - "192466 lines [00:06, 24948.89 lines/s]\r", - "195084 lines [00:06, 25013.84 lines/s]\r", - "198543 lines [00:06, 27278.88 lines/s]\r", - "201919 lines [00:06, 28944.67 lines/s]\r", - "204926 lines [00:06, 28974.94 lines/s]\r", - "207902 lines [00:06, 29186.25 lines/s]\r", - "210876 lines [00:07, 28575.09 lines/s]\r", - "213838 lines [00:07, 28880.26 lines/s]\r", - "217201 lines [00:07, 30156.07 lines/s]\r", - "220673 lines [00:07, 31391.06 lines/s]\r", - "223851 lines [00:07, 27826.68 lines/s]\r", - "227300 lines [00:07, 29538.19 lines/s]\r", - "230866 lines [00:07, 31141.01 lines/s]\r", - "234699 lines [00:07, 32996.48 lines/s]\r", - "238602 lines [00:07, 34600.63 lines/s]\r", - "242235 lines [00:07, 35099.36 lines/s]\r", - "245936 lines [00:08, 35649.09 lines/s]\r", - "249747 lines [00:08, 36351.39 lines/s]\r", - "253506 lines [00:08, 36714.12 lines/s]\r", - "257204 lines [00:08, 33073.24 lines/s]\r", - "260932 lines [00:08, 34230.86 lines/s]\r", - "264803 lines [00:08, 35459.93 lines/s]\r", - "268469 lines [00:08, 35811.48 lines/s]\r", - "272427 lines [00:08, 36862.49 lines/s]\r", - "276343 lines [00:08, 37521.14 lines/s]\r", - "280266 lines [00:09, 38016.07 lines/s]\r", - "284090 lines [00:09, 37761.02 lines/s]\r", - "287883 lines [00:09, 33629.95 lines/s]\r", - "291342 lines [00:09, 33608.55 lines/s]\r", - "294770 lines [00:09, 33571.47 lines/s]\r", - "298403 lines [00:09, 34353.75 lines/s]\r", - "302015 lines [00:09, 34864.31 lines/s]\r", - "305562 lines [00:09, 35042.38 lines/s]\r", - "309086 lines [00:09, 31551.18 lines/s]\r", - "312530 lines [00:10, 32365.33 lines/s]\r", - "315971 lines [00:10, 32948.88 lines/s]\r", - "319312 lines [00:10, 31673.65 lines/s]\r", - "322522 lines [00:10, 31366.85 lines/s]\r", - "325689 lines [00:10, 30344.76 lines/s]\r", - "328865 lines [00:10, 27638.77 lines/s]\r", - "332249 lines [00:10, 29245.00 lines/s]\r", - "336174 lines [00:10, 31665.71 lines/s]\r", - "339964 lines [00:10, 33307.38 lines/s]\r", - "343558 lines [00:10, 34054.15 lines/s]\r", - "347123 lines [00:11, 34516.28 lines/s]\r", - "350628 lines [00:11, 33981.96 lines/s]\r", - "354201 lines [00:11, 34484.13 lines/s]\r", - "358005 lines [00:11, 35477.81 lines/s]\r", - "362031 lines [00:11, 36788.32 lines/s]\r", - "366050 lines [00:11, 37746.64 lines/s]\r", - "369853 lines [00:11, 37319.53 lines/s]\r", - "373703 lines [00:11, 37664.96 lines/s]\r", - "377485 lines [00:11, 37170.12 lines/s]\r", - "381215 lines [00:12, 36958.38 lines/s]\r", - "384920 lines [00:12, 36086.81 lines/s]\r", - "388540 lines [00:12, 36041.09 lines/s]\r", - "392639 lines [00:12, 37393.68 lines/s]\r", - "396673 lines [00:12, 38231.33 lines/s]\r", - "400856 lines [00:12, 39241.04 lines/s]\r", - "404799 lines [00:12, 38005.94 lines/s]\r", - "408622 lines [00:12, 36691.00 lines/s]\r", - "412317 lines [00:12, 36733.16 lines/s]\r", - "416008 lines [00:12, 36575.74 lines/s]\r", - "419678 lines [00:13, 33549.12 lines/s]\r", - "423204 lines [00:13, 34042.37 lines/s]\r", - "426768 lines [00:13, 34504.83 lines/s]\r", - "430387 lines [00:13, 34993.10 lines/s]\r", - "433910 lines [00:13, 34385.02 lines/s]\r", - "437368 lines [00:13, 34039.32 lines/s]\r", - "440786 lines [00:13, 33517.56 lines/s]\r", - "444283 lines [00:13, 33939.43 lines/s]\r", - "448047 lines [00:13, 34969.31 lines/s]\r", - "451594 lines [00:13, 35115.70 lines/s]\r", - "455457 lines [00:14, 36100.57 lines/s]\r", - "459319 lines [00:14, 36820.52 lines/s]\r", - "463015 lines [00:14, 36781.63 lines/s]\r", - "466952 lines [00:14, 37519.70 lines/s]\r", - "470764 lines [00:14, 37697.68 lines/s]\r", - "474542 lines [00:14, 31041.78 lines/s]\r", - "478141 lines [00:14, 32375.45 lines/s]\r", - "481967 lines [00:14, 33940.30 lines/s]\r", - "485815 lines [00:14, 35183.75 lines/s]\r", - "489820 lines [00:15, 36513.85 lines/s]\r", - "493673 lines [00:15, 37094.94 lines/s]\r", - "497444 lines [00:15, 37215.96 lines/s]\r", - "501417 lines [00:15, 37933.85 lines/s]\r", - "505318 lines [00:15, 38249.40 lines/s]\r", - "509331 lines [00:15, 38792.16 lines/s]\r", - "513252 lines [00:15, 38915.43 lines/s]\r", - "517157 lines [00:15, 38860.38 lines/s]\r", - "521053 lines [00:15, 38880.76 lines/s]\r", - "524964 lines [00:15, 38947.82 lines/s]\r", - "528864 lines [00:16, 38818.64 lines/s]\r", - "532760 lines [00:16, 38858.74 lines/s]\r", - "536696 lines [00:16, 39005.54 lines/s]\r", - "540646 lines [00:16, 39150.28 lines/s]\r", - "544563 lines [00:16, 39153.94 lines/s]\r", - "548480 lines [00:16, 38975.30 lines/s]\r", - "552379 lines [00:16, 38757.84 lines/s]\r", - "556256 lines [00:16, 38555.73 lines/s]\r", - "560113 lines [00:16, 38118.62 lines/s]\r", - "563927 lines [00:16, 37990.75 lines/s]\r", - "567728 lines [00:17, 37973.07 lines/s]\r", - "571689 lines [00:17, 38449.70 lines/s]\r", - "575537 lines [00:17, 38125.34 lines/s]\r", - "579352 lines [00:17, 37955.82 lines/s]\r", - "583150 lines [00:17, 37533.33 lines/s]\r", - "586906 lines [00:17, 37167.12 lines/s]\r", - "590655 lines [00:17, 37263.09 lines/s]\r", - "594384 lines [00:17, 29802.36 lines/s]\r", - "597603 lines [00:17, 30480.09 lines/s]\r", - "600918 lines [00:18, 31233.28 lines/s]\r", - "604362 lines [00:18, 32128.63 lines/s]\r", - "605248 lines [00:18, 33248.80 lines/s]\n", + "3372 lines [00:00, 33717.94 lines/s]\r", + "7149 lines [00:00, 34838.21 lines/s]\r", + "10719 lines [00:00, 35087.64 lines/s]\r", + "14524 lines [00:00, 35925.41 lines/s]\r", + "18273 lines [00:00, 36378.56 lines/s]\r", + "21966 lines [00:00, 36541.96 lines/s]\r", + "25638 lines [00:00, 36594.83 lines/s]\r", + "29024 lines [00:00, 34807.15 lines/s]\r", + "32549 lines [00:00, 34936.32 lines/s]\r", + "36011 lines [00:01, 34840.02 lines/s]\r", + "39521 lines [00:01, 34915.98 lines/s]\r", + "43365 lines [00:01, 35902.09 lines/s]\r", + "47290 lines [00:01, 36843.77 lines/s]\r", + "51090 lines [00:01, 37180.46 lines/s]\r", + "54797 lines [00:01, 36649.63 lines/s]\r", + "58456 lines [00:01, 36208.79 lines/s]\r", + "62074 lines [00:01, 36003.85 lines/s]\r", + "65673 lines [00:01, 35564.70 lines/s]\r", + "69230 lines [00:01, 35433.86 lines/s]\r", + "72774 lines [00:02, 35125.90 lines/s]\r", + "76288 lines [00:02, 33329.14 lines/s]\r", + "79641 lines [00:02, 32917.36 lines/s]\r", + "82948 lines [00:02, 32123.71 lines/s]\r", + "86509 lines [00:02, 33095.04 lines/s]\r", + "89967 lines [00:02, 33526.76 lines/s]\r", + "93434 lines [00:02, 33861.11 lines/s]\r", + "97091 lines [00:02, 34629.28 lines/s]\r", + "100566 lines [00:02, 32572.17 lines/s]\r", + "104045 lines [00:02, 33205.88 lines/s]\r", + "107392 lines [00:03, 32238.25 lines/s]\r", + "110641 lines [00:03, 30385.51 lines/s]\r", + "113719 lines [00:03, 29811.26 lines/s]\r", + "116739 lines [00:03, 29924.42 lines/s]\r", + "119753 lines [00:03, 29431.38 lines/s]\r", + "122900 lines [00:03, 30013.75 lines/s]\r", + "126380 lines [00:03, 31303.59 lines/s]\r", + "129681 lines [00:03, 31796.05 lines/s]\r", + "133489 lines [00:03, 33450.50 lines/s]\r", + "137286 lines [00:04, 34687.89 lines/s]\r", + "140792 lines [00:04, 34581.21 lines/s]\r", + "144478 lines [00:04, 35228.50 lines/s]\r", + "148216 lines [00:04, 35846.02 lines/s]\r", + "151819 lines [00:04, 33562.97 lines/s]\r", + "155218 lines [00:04, 33559.23 lines/s]\r", + "158905 lines [00:04, 34488.01 lines/s]\r", + "162605 lines [00:04, 35204.41 lines/s]\r", + "166148 lines [00:04, 34490.05 lines/s]\r", + "169616 lines [00:04, 34116.24 lines/s]\r", + "173042 lines [00:05, 31750.62 lines/s]\r", + "176854 lines [00:05, 33425.59 lines/s]\r", + "180743 lines [00:05, 34895.42 lines/s]\r", + "184287 lines [00:05, 35041.00 lines/s]\r", + "187931 lines [00:05, 35448.90 lines/s]\r", + "191689 lines [00:05, 36061.83 lines/s]\r", + "195458 lines [00:05, 36533.48 lines/s]\r", + "199193 lines [00:05, 36774.05 lines/s]\r", + "202929 lines [00:05, 36946.08 lines/s]\r", + "206734 lines [00:05, 37269.30 lines/s]\r", + "210468 lines [00:06, 36914.51 lines/s]\r", + "214165 lines [00:06, 35872.09 lines/s]\r", + "217763 lines [00:06, 34527.99 lines/s]\r", + "221234 lines [00:06, 31747.01 lines/s]\r", + "224466 lines [00:06, 29450.81 lines/s]\r", + "227545 lines [00:06, 29838.26 lines/s]\r", + "230837 lines [00:06, 30699.90 lines/s]\r", + "234000 lines [00:06, 30972.52 lines/s]\r", + "237628 lines [00:06, 32393.47 lines/s]\r", + "241160 lines [00:07, 33217.50 lines/s]\r", + "244517 lines [00:07, 33321.34 lines/s]\r", + "247872 lines [00:07, 32573.76 lines/s]\r", + "251149 lines [00:07, 32209.47 lines/s]\r", + "254385 lines [00:07, 31406.15 lines/s]\r", + "257541 lines [00:07, 27011.37 lines/s]\r", + "260500 lines [00:07, 27736.23 lines/s]\r", + "263547 lines [00:07, 28503.23 lines/s]\r", + "266465 lines [00:07, 28663.42 lines/s]\r", + "269396 lines [00:08, 28853.53 lines/s]\r", + "272479 lines [00:08, 29414.55 lines/s]\r", + "275544 lines [00:08, 29773.08 lines/s]\r", + "278541 lines [00:08, 29553.85 lines/s]\r", + "281607 lines [00:08, 29876.61 lines/s]\r", + "284683 lines [00:08, 29085.97 lines/s]\r", + "288244 lines [00:08, 30776.14 lines/s]\r", + "291918 lines [00:08, 32350.32 lines/s]\r", + "295598 lines [00:08, 33566.61 lines/s]\r", + "299361 lines [00:08, 34688.60 lines/s]\r", + "303023 lines [00:09, 35245.86 lines/s]\r", + "306955 lines [00:09, 36374.55 lines/s]\r", + "310678 lines [00:09, 36625.21 lines/s]\r", + "314363 lines [00:09, 36261.65 lines/s]\r", + "318088 lines [00:09, 36551.49 lines/s]\r", + "321792 lines [00:09, 36695.31 lines/s]\r", + "325617 lines [00:09, 37147.19 lines/s]\r", + "329339 lines [00:09, 31990.27 lines/s]\r", + "332945 lines [00:09, 33110.54 lines/s]\r", + "336655 lines [00:10, 34211.11 lines/s]\r", + "340373 lines [00:10, 35046.83 lines/s]\r", + "344143 lines [00:10, 35802.25 lines/s]\r", + "347851 lines [00:10, 36173.74 lines/s]\r", + "351632 lines [00:10, 36648.07 lines/s]\r", + "355327 lines [00:10, 36736.28 lines/s]\r", + "359181 lines [00:10, 37259.25 lines/s]\r", + "363200 lines [00:10, 38091.18 lines/s]\r", + "367269 lines [00:10, 38834.93 lines/s]\r", + "371289 lines [00:10, 39234.54 lines/s]\r", + "375274 lines [00:11, 39414.93 lines/s]\r", + "379438 lines [00:11, 40055.02 lines/s]\r", + "383642 lines [00:11, 40629.66 lines/s]\r", + "387841 lines [00:11, 41025.02 lines/s]\r", + "391956 lines [00:11, 41061.65 lines/s]\r", + "396067 lines [00:11, 40880.09 lines/s]\r", + "400159 lines [00:11, 40765.90 lines/s]\r", + "404238 lines [00:11, 39454.07 lines/s]\r", + "408195 lines [00:11, 38780.00 lines/s]\r", + "412084 lines [00:11, 38326.58 lines/s]\r", + "415925 lines [00:12, 37540.12 lines/s]\r", + "419689 lines [00:12, 37406.68 lines/s]\r", + "423483 lines [00:12, 37564.15 lines/s]\r", + "427245 lines [00:12, 37316.43 lines/s]\r", + "430981 lines [00:12, 37310.27 lines/s]\r", + "434715 lines [00:12, 37284.63 lines/s]\r", + "438495 lines [00:12, 37435.54 lines/s]\r", + "442261 lines [00:12, 37500.58 lines/s]\r", + "446013 lines [00:12, 37433.72 lines/s]\r", + "449758 lines [00:12, 36125.29 lines/s]\r", + "453461 lines [00:13, 36389.73 lines/s]\r", + "457289 lines [00:13, 36936.57 lines/s]\r", + "461135 lines [00:13, 37379.93 lines/s]\r", + "464962 lines [00:13, 37642.19 lines/s]\r", + "468732 lines [00:13, 37379.28 lines/s]\r", + "472474 lines [00:13, 37341.27 lines/s]\r", + "476211 lines [00:13, 30920.47 lines/s]\r", + "479833 lines [00:13, 32338.41 lines/s]\r", + "483505 lines [00:13, 33537.91 lines/s]\r", + "487161 lines [00:14, 34385.71 lines/s]\r", + "490833 lines [00:14, 35053.11 lines/s]\r", + "494517 lines [00:14, 35568.39 lines/s]\r", + "498120 lines [00:14, 35386.04 lines/s]\r", + "501703 lines [00:14, 35516.11 lines/s]\r", + "505278 lines [00:14, 35341.14 lines/s]\r", + "508896 lines [00:14, 35588.65 lines/s]\r", + "512638 lines [00:14, 36116.99 lines/s]\r", + "516260 lines [00:14, 36015.36 lines/s]\r", + "519869 lines [00:14, 35910.01 lines/s]\r", + "523582 lines [00:15, 36266.32 lines/s]\r", + "527214 lines [00:15, 35415.97 lines/s]\r", + "531044 lines [00:15, 36232.15 lines/s]\r", + "534678 lines [00:15, 34902.47 lines/s]\r", + "538186 lines [00:15, 34520.34 lines/s]\r", + "541652 lines [00:15, 34054.68 lines/s]\r", + "545391 lines [00:15, 34990.15 lines/s]\r", + "549065 lines [00:15, 35495.33 lines/s]\r", + "552626 lines [00:15, 34344.66 lines/s]\r", + "556322 lines [00:15, 35088.21 lines/s]\r", + "559917 lines [00:16, 35339.70 lines/s]\r", + "563617 lines [00:16, 35821.22 lines/s]\r", + "567209 lines [00:16, 34874.87 lines/s]\r", + "570792 lines [00:16, 35155.71 lines/s]\r", + "574317 lines [00:16, 33441.09 lines/s]\r", + "577694 lines [00:16, 33537.36 lines/s]\r", + "581065 lines [00:16, 30567.57 lines/s]\r", + "584572 lines [00:16, 31790.60 lines/s]\r", + "588180 lines [00:16, 32965.62 lines/s]\r", + "591650 lines [00:17, 33463.26 lines/s]\r", + "595034 lines [00:17, 27365.42 lines/s]\r", + "598554 lines [00:17, 29322.83 lines/s]\r", + "601862 lines [00:17, 30355.94 lines/s]\r", + "605248 lines [00:17, 34539.19 lines/s]\n", "Read sites summary\n", "\ttotal: 605,248\n", "\tunmethylated: 596,963\n", @@ -484,12 +484,12 @@ "Filtering out positions with low coverage or methylation frequency\n", "\r", " 0%| | 0/340081 [00:00 Date: Wed, 8 May 2019 14:15:30 +0100 Subject: [PATCH 4/4] Bump version number --- NanopolishComp/__init__.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/NanopolishComp/__init__.py b/NanopolishComp/__init__.py index 927d6c1..df57568 100755 --- a/NanopolishComp/__init__.py +++ b/NanopolishComp/__init__.py @@ -1,7 +1,7 @@ # -*- coding: utf-8 -*- # Define self package variable -__version__ = "0.6.1" +__version__ = "0.6.2" __description__ = 'NanopolishComp is a Python3 package for downstream analyses of Nanopolish output files' # Collect info in a dictionary for setup.py