Skip to content

Commit

Permalink
bio search for SRR now lists fastq urls as a list
Browse files Browse the repository at this point in the history
  • Loading branch information
ialbert committed Apr 4, 2023
1 parent ca69b94 commit b411b9e
Show file tree
Hide file tree
Showing 4 changed files with 31 additions and 9 deletions.
2 changes: 1 addition & 1 deletion biorun/__init__.py
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
#
import sys
# Global package version
VERSION = "1.5.8"
VERSION = "1.5.9"

try:
from signal import signal, SIGPIPE, SIG_DFL
Expand Down
30 changes: 24 additions & 6 deletions biorun/data/search_prjn.json
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,10 @@
"instrument_platform": "ILLUMINA",
"instrument_model": "Illumina HiSeq 2500",
"study_title": "Plasmodium transcription repressor AP2-O3 regulates sex-specific identity of gene expression in female gametocytes [RNA-seq]",
"fastq_ftp": "ftp.sra.ebi.ac.uk/vol1/fastq/SRR125/054/SRR12586154/SRR12586154_1.fastq.gz;ftp.sra.ebi.ac.uk/vol1/fastq/SRR125/054/SRR12586154/SRR12586154_2.fastq.gz",
"fastq_url": [
"https://ftp.sra.ebi.ac.uk/vol1/fastq/SRR125/054/SRR12586154/SRR12586154_1.fastq.gz",
"https://ftp.sra.ebi.ac.uk/vol1/fastq/SRR125/054/SRR12586154/SRR12586154_2.fastq.gz"
],
"info": "2 GB, 2 GB file; 24 million reads; 7.3 billion sequenced bases"
},
{
Expand All @@ -38,7 +41,10 @@
"instrument_platform": "ILLUMINA",
"instrument_model": "Illumina HiSeq 2500",
"study_title": "Plasmodium transcription repressor AP2-O3 regulates sex-specific identity of gene expression in female gametocytes [RNA-seq]",
"fastq_ftp": "ftp.sra.ebi.ac.uk/vol1/fastq/SRR125/055/SRR12586155/SRR12586155_1.fastq.gz;ftp.sra.ebi.ac.uk/vol1/fastq/SRR125/055/SRR12586155/SRR12586155_2.fastq.gz",
"fastq_url": [
"https://ftp.sra.ebi.ac.uk/vol1/fastq/SRR125/055/SRR12586155/SRR12586155_1.fastq.gz",
"https://ftp.sra.ebi.ac.uk/vol1/fastq/SRR125/055/SRR12586155/SRR12586155_2.fastq.gz"
],
"info": "2 GB, 2 GB file; 22 million reads; 6.7 billion sequenced bases"
},
{
Expand All @@ -59,7 +65,10 @@
"instrument_platform": "ILLUMINA",
"instrument_model": "Illumina HiSeq 2500",
"study_title": "Plasmodium transcription repressor AP2-O3 regulates sex-specific identity of gene expression in female gametocytes [RNA-seq]",
"fastq_ftp": "ftp.sra.ebi.ac.uk/vol1/fastq/SRR125/056/SRR12586156/SRR12586156_1.fastq.gz;ftp.sra.ebi.ac.uk/vol1/fastq/SRR125/056/SRR12586156/SRR12586156_2.fastq.gz",
"fastq_url": [
"https://ftp.sra.ebi.ac.uk/vol1/fastq/SRR125/056/SRR12586156/SRR12586156_1.fastq.gz",
"https://ftp.sra.ebi.ac.uk/vol1/fastq/SRR125/056/SRR12586156/SRR12586156_2.fastq.gz"
],
"info": "2 GB, 2 GB file; 26 million reads; 7.9 billion sequenced bases"
},
{
Expand All @@ -80,7 +89,10 @@
"instrument_platform": "ILLUMINA",
"instrument_model": "Illumina HiSeq 2500",
"study_title": "Plasmodium transcription repressor AP2-O3 regulates sex-specific identity of gene expression in female gametocytes [RNA-seq]",
"fastq_ftp": "ftp.sra.ebi.ac.uk/vol1/fastq/SRR125/057/SRR12586157/SRR12586157_1.fastq.gz;ftp.sra.ebi.ac.uk/vol1/fastq/SRR125/057/SRR12586157/SRR12586157_2.fastq.gz",
"fastq_url": [
"https://ftp.sra.ebi.ac.uk/vol1/fastq/SRR125/057/SRR12586157/SRR12586157_1.fastq.gz",
"https://ftp.sra.ebi.ac.uk/vol1/fastq/SRR125/057/SRR12586157/SRR12586157_2.fastq.gz"
],
"info": "2 GB, 2 GB file; 24 million reads; 7.1 billion sequenced bases"
},
{
Expand All @@ -101,7 +113,10 @@
"instrument_platform": "ILLUMINA",
"instrument_model": "Illumina HiSeq 2500",
"study_title": "Plasmodium transcription repressor AP2-O3 regulates sex-specific identity of gene expression in female gametocytes [RNA-seq]",
"fastq_ftp": "ftp.sra.ebi.ac.uk/vol1/fastq/SRR125/058/SRR12586158/SRR12586158_1.fastq.gz;ftp.sra.ebi.ac.uk/vol1/fastq/SRR125/058/SRR12586158/SRR12586158_2.fastq.gz",
"fastq_url": [
"https://ftp.sra.ebi.ac.uk/vol1/fastq/SRR125/058/SRR12586158/SRR12586158_1.fastq.gz",
"https://ftp.sra.ebi.ac.uk/vol1/fastq/SRR125/058/SRR12586158/SRR12586158_2.fastq.gz"
],
"info": "2 GB, 2 GB file; 24 million reads; 7.3 billion sequenced bases"
},
{
Expand All @@ -122,7 +137,10 @@
"instrument_platform": "ILLUMINA",
"instrument_model": "Illumina HiSeq 2500",
"study_title": "Plasmodium transcription repressor AP2-O3 regulates sex-specific identity of gene expression in female gametocytes [RNA-seq]",
"fastq_ftp": "ftp.sra.ebi.ac.uk/vol1/fastq/SRR125/059/SRR12586159/SRR12586159_1.fastq.gz;ftp.sra.ebi.ac.uk/vol1/fastq/SRR125/059/SRR12586159/SRR12586159_2.fastq.gz",
"fastq_url": [
"https://ftp.sra.ebi.ac.uk/vol1/fastq/SRR125/059/SRR12586159/SRR12586159_1.fastq.gz",
"https://ftp.sra.ebi.ac.uk/vol1/fastq/SRR125/059/SRR12586159/SRR12586159_2.fastq.gz"
],
"info": "2 GB, 2 GB file; 28 million reads; 8.5 billion sequenced bases"
}
]
5 changes: 4 additions & 1 deletion biorun/data/search_srr.json
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,10 @@
"instrument_platform": "ILLUMINA",
"instrument_model": "Illumina HiSeq 2500",
"study_title": "Zaire ebolavirus Genome sequencing",
"fastq_ftp": "ftp.sra.ebi.ac.uk/vol1/fastq/SRR197/006/SRR1972976/SRR1972976_1.fastq.gz;ftp.sra.ebi.ac.uk/vol1/fastq/SRR197/006/SRR1972976/SRR1972976_2.fastq.gz",
"fastq_url": [
"https://ftp.sra.ebi.ac.uk/vol1/fastq/SRR197/006/SRR1972976/SRR1972976_1.fastq.gz",
"https://ftp.sra.ebi.ac.uk/vol1/fastq/SRR197/006/SRR1972976/SRR1972976_2.fastq.gz"
],
"info": "699 MB, 606 MB file; 8 million reads; 1.7 billion sequenced bases"
}
]
3 changes: 2 additions & 1 deletion biorun/search.py
Original file line number Diff line number Diff line change
Expand Up @@ -162,7 +162,8 @@ def add_field(entry):
entry["bio_error"] = f"invalid data: {exc}"

info = f"{bytes_val} file; {count_val} reads; {base_val} sequenced bases"

entry['fastq_url'] = [ f"https://{u}" for u in entry['fastq_ftp'].split(";") ]
del entry['fastq_ftp']
entry["info"] = info

return entry
Expand Down

0 comments on commit b411b9e

Please sign in to comment.