-
Notifications
You must be signed in to change notification settings - Fork 3
/
Snakefile_donorid
executable file
·183 lines (161 loc) · 6.27 KB
/
Snakefile_donorid
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
"""
Snakefile for cardelino donor ID for the single-cell fibroblast project
Author: Davis McCarthy
Affiliation: EMBL-EBI
Run from run directory
Run: snakemake -s Snakefile_donorid --jobs 2000 --latency-wait 30 --cluster-config cluster.json --cluster 'bsub -J {cluster.name} -q {cluster.queue} -n {cluster.n} -R "rusage[mem={cluster.memory}]" -M {cluster.memory} -o {cluster.output} -e {cluster.error}'
Davis McCarthy, 31 May 2018
"""
import glob
import os
from subprocess import run
import subprocess
import pandas as pd
import re
HIPSCI_VCF = 'references/hipsci.wec.gtarray.HumanCoreExome.imputed_phased.20170327.genotypes.allchr.fibro_samples_v2_filt_vars_sorted_oa.vcf.gz'
## read in input dirs and cell VCF files
run_dirs = glob.glob('data/raw/22*')
vcfs = glob.glob('data/raw/22*/cells_merged_donor_id.vcf.gz')
cell_vcf_files = {}
## define output files
donorid_csvs = []
sce_files = []
for run in run_dirs:
donorid_csvs.append('{}/donor_id_all_cardelino_v2.csv'.format(run))
crams_all = glob.glob('{}/cram/*.cram'.format(run))
# SAMPLES = [os.path.basename(w).replace('.cram', '') for w in crams_all]
fastq_all = glob.glob('fastq/*_1.fastq')
SAMPLES = [os.path.basename(w).replace('_1.fastq', '') for w in fastq_all]
cell_vcf_files[os.path.basename(run)] = expand('{run}/vcf/{sample}/{sample}.filtered.vcf.gz', run = run, sample=SAMPLES)
sce_files.append('{}/sces/sce.salmon.GRCh37.preqc_gene.rds'.format(run))
rule all:
input:
donorid_csvs,
'data/raw/sce_merged_donors_cardelino_donorid_unstim_qc_filt.rds'
rule merge_cell_vcfs:
input:
files=lambda wildcards: cell_vcf_files[wildcards.run]
output:
vcf='data/raw/{run}/cells_merged_donor_id.vcf.gz',
files=temp('data/raw/{run}/cell_merge_donor_id_filelist.txt')
params:
dir='data/raw/{run}/vcf'
conda:
"envs/myenv.yaml"
singularity:
"docker://davismcc/fibroblast-clonality"
shell:
"""
set +euo pipefail
ls -1 {params.dir}/*/*.filtered.vcf.gz | grep -v clone_id > {output.files}
bcftools merge -O z -l {output.files} -o {output.vcf}
set -euo pipefail
"""
rule index_cells_vcf:
input:
sc_vcf='data/raw/{run}/cells_merged_donor_id.vcf.gz'
output:
'data/raw/{run}/cells_merged_donor_id.vcf.gz.csi'
conda:
"envs/myenv.yaml"
singularity:
"docker://davismcc/fibroblast-clonality"
shell:
"""
set +euo pipefail
bcftools index {input.sc_vcf}
set -euo pipefail
"""
rule filter_cells_vcf:
input:
sc_vcf='data/raw/{run}/cells_merged_donor_id.vcf.gz',
sc_idx='data/raw/{run}/cells_merged_donor_id.vcf.gz.csi'
output:
vcf='data/raw/{run}/cells_merged_donor_id_filt.vcf.gz',
idx='data/raw/{run}/cells_merged_donor_id_filt.vcf.gz.csi'
conda:
"envs/myenv.yaml"
singularity:
"docker://davismcc/fibroblast-clonality"
shell:
"""
set +euo pipefail
bcftools filter -Oz -i'F_MISSING<0.97 && MAF>0.01 && QUAL>20' -o {output.vcf} {input.sc_vcf}
bcftools index {output.vcf}
set -euo pipefail
"""
rule filter_hipsci_overlap_variants:
input:
sc_vcf='data/raw/{run}/cells_merged_donor_id_filt.vcf.gz',
sc_vcf_idx='data/raw/{run}/cells_merged_donor_id_filt.vcf.gz.csi',
hipsci_vcf=HIPSCI_VCF
output:
lst=temp('data/raw/{run}/variant_list.txt'),
tmp=temp('data/raw/{run}/tmp.vcf.gz'),
vcf=temp('data/raw/{run}/filtered.hipsci.overlap.vcf.gz'),
csi=temp('data/raw/{run}/filtered.hipsci.overlap.vcf.gz.csi')
conda:
"envs/myenv.yaml"
singularity:
"docker://davismcc/fibroblast-clonality"
shell:
"""
set +euo pipefail
echo -e "1\\t1\\tA\\tC" > {output.lst}
bcftools view -O v {input.sc_vcf} | grep -v ^# | awk \'{{sub(/chr/,""); print $1"\\t"$2"\\t"$4"\\t"$5}}\' >> {output.lst}
bcftools view -o {output.tmp} -O z -l 9 -R {output.lst} {input.hipsci_vcf}
vcf-sort {output.tmp} | bgzip -c > {output.vcf}
bcftools index {output.vcf}
set -euo pipefail
"""
rule identify_donor_multicell:
input:
sc_vcf='data/raw/{run}/cells_merged_donor_id_filt.vcf.gz',
sc_idx='data/raw/{run}/cells_merged_donor_id_filt.vcf.gz.csi',
hipsci_vcf='data/raw/{run}/filtered.hipsci.overlap.vcf.gz',
hipsci_vcf_idx='data/raw/{run}/filtered.hipsci.overlap.vcf.gz.csi'
output:
'data/raw/{run}/donor_id_all_cardelino_v2.csv'
params:
prefix='data/raw/{run}/donor_id_all_cardelino_v2'
singularity:
"docker://davismcc/r-singlecell-img"
shell:
'Rscript src/R/identify_donor_cardelino_multicell.R '
'--input_file "{input.sc_vcf}" '
'--donor_vcf {input.hipsci_vcf} '
'--output_prefix "{params.prefix}" '
rule sce_merge_and_qc:
input:
donorid_files=donorid_csvs,
sces=sce_files,
meta1='metadata/cell_metadata.csv',
meta2='metadata/data_processing_metadata.tsv'
output:
'data/raw/sce_merged_donors_cardelino_donorid_unstim_qc_filt.rds',
'data/raw/sce_merged_donors_cardelino_donorid_all_qc_filt.rds',
'figures/qc/donor_id_all_nvars_vs_total_counts.png',
'data/raw/sce_merge_qc.html'
singularity:
"docker://davismcc/r-singlecell-img"
shell:
"""
R -e "rmarkdown::render(input = 'src/Rmd/merge_lane_data_cardelino_donorid.Rmd', output_file = 'sce_merge_qc.html', output_dir = 'data/raw/', output_format = 'html_document')"
"""
rule get_donor_sce:
input:
'data/raw/sce_merged_donors_cardelino_donorid_unstim_qc_filt.rds'
output:
html = 'reports/donor_sces/sce.{donor}.html',
rds = 'data/sces/sce_{donor}_qc.rds',
cell_list='data/raw/donor-cell-lists/{donor}.qc-pass.cells.txt',
bam_list='data/raw/donor-cell-lists/{donor}.qc-pass.bams.txt'
singularity:
"docker://davismcc/r-singlecell-img"
shell:
'{rscript_cmd} '
'src/R/compile_report.R -i {input} -o {output.html} '
'--results_out {output.rds} '
'--template src/Rmd/sce_qc_per_donor.Rmd '
'--title "Save donor SCE object: {wildcards.donor}" '
'--donor {wildcards.donor} --to_working_dir ../../ '