-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathdenovoSNP_calling.smk
147 lines (136 loc) · 6.61 KB
/
denovoSNP_calling.smk
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
configfile: "configDenovo.yaml"
import pandas as pd
import os
df = pd.read_csv(os.path.join(config["barcodes"]), sep='\t', dtype="object").set_index('Sample')
SAMPLES = df.index
rule all:
input:
RTGsummary=expand("{out_dir}/RTG{score}/{sample}/summary.txt",sample=SAMPLES,out_dir=config["output_dir"],score=config["score_field"]),
rule sort:
input:
expand("{in_dir}/alignment/{{sample}}_trimmed_filt_merged.1_bismark_bt2_pe.bam",in_dir=config["input_dir"])
output:
temp(expand("{tmp}/{{sample}}_sorted.bam",tmp=config["tmp_dir"]))
shell:
"samtools sort {input} > {output}"
rule depth:
input:
expand("{tmp}/{{sample}}_sorted.bam",tmp=config["tmp_dir"])
output:
temp(expand("{tmp}/{{sample}}.depth",tmp=config["tmp_dir"]))
shell:
"samtools depth {input} | awk '$3>0{{print $1,$2-1,$2,$3}}' | sed 's/ /\t/g' > {output}"
rule liftOverDepth:
input:
depth=expand("{tmp}/{{sample}}.depth",tmp=config["tmp_dir"]),
consensus=expand("{tmp}/consensus.bam",tmp=config["tmp_dir"]),
output:
expand("{tmp}/{{sample}}liftOver.depth",tmp=config["tmp_dir"])
shell:
"python src/liftover_bed.py {input.consensus} {input.depth} > {output}"
rule subset:
input:
refIn="data/snp-calls/refAll.vcf.gz",
depthIn=expand("{tmp}/{{sample}}liftOver.depth",tmp=config["tmp_dir"]),
output:
sampleSpecificRef=expand("{tmp}/{{sample}}Ref.vcf.gz",tmp=config["tmp_dir"])
shell:
"""
cat <(bcftools view -h {input.refIn}) <(bedtools intersect -a {input.refIn} -b {input.depthIn} -u) | \
bgzip -c > {output.sampleSpecificRef}
"""
rule normalize:
input:
SNPs=expand("{tmp}/liftoverAdam.vcf.gz",tmp=config["tmp_dir"]),
ref=expand("{ref}",ref=config["ref_truth"])
output:
norm=expand("{tmp}/normalisedAdam.vcf.gz",tmp=config["tmp_dir"])
shell:
"bcftools norm --check-ref s -f {input.ref} {input.SNPs} > {output.norm}"
rule filter:
input:
norm=expand("{tmp}/normalisedAdam.vcf.gz",tmp=config["tmp_dir"])
output:
filt=expand("{out}/vcfs/{{sample}}.vcf.gz",out=config["output_dir"])
params:
sample="{sample}"
shell:
"""cat <(bcftools view -h -s {params.sample} -V indels,mnps,ref,bnd,other {input.norm}) <(bcftools view -s {params.sample} -V indels,mnps,ref,bnd,other {input.norm} | awk '$0~"^#" || ($10~"^1/1" || $10~"^1/0" || $10~"^0/1")' )| bgzip -c > {output.filt}"""
rule tabix_filter:
input:
filt=expand("{out}/vcfs/{{sample}}.vcf.gz",out=config["output_dir"])
output:
filt=expand("{out}/vcfs/{{sample}}.vcf.gz.tbi",out=config["output_dir"])
shell:
"bcftools tabix {input.filt}"
rule referenceFormat:
input:
ref=expand("{ref}",ref=config["ref"])
output:
refSDF=directory(expand("{ref}.sdf",ref=config["ref"]))
shell:
"rtg format -o {output.refSDF} {input.ref}"
rule tabixRef:
input:
sampleSpecificRef=expand("{tmp}/{{sample}}Ref.vcf.gz",tmp=config["tmp_dir"])
output:
sampleSpecificTabix=temp(expand("{tmp}/{{sample}}Ref.vcf.gz.tbi",tmp=config["tmp_dir"]))
shell:
"bcftools tabix {input.sampleSpecificRef} -f"
rule rtg:
input:
sampleSpecificRef=expand("{tmp}/{{sample}}Ref.vcf.gz",tmp=config["tmp_dir"]),
sampleSpecificTabix=expand("{tmp}/{{sample}}Ref.vcf.gz.tbi",tmp=config["tmp_dir"]),
filt=expand("{out}/vcfs/{{sample}}.vcf.gz",out=config["output_dir"]),
tabix=expand("{out}/vcfs/{{sample}}.vcf.gz.tbi",out=config["output_dir"]),
refSDF=expand("{ref}.sdf",ref=config["ref_truth"])
params:
outDirTemp=expand("{out}/RTG/{{sample}}temp/",out=config["output_dir"]),
outDir=expand("{out}/RTG{score}/{{sample}}/",out=config["output_dir"],score=config["score_field"]),
sample="{sample}",
vcfScoreField=config["score_field"]
output:
summary=expand("{out}/RTG{score}/{{sample}}/summary.txt",out=config["output_dir"],score=config["score_field"]),
fp=expand("{out}/RTG{score}/{{sample}}/fp.vcf.gz",out=config["output_dir"],score=config["score_field"]),
fn=expand("{out}/RTG{score}/{{sample}}/fn.vcf.gz",out=config["output_dir"],score=config["score_field"]),
tp=expand("{out}/RTG{score}/{{sample}}/tp.vcf.gz",out=config["output_dir"],score=config["score_field"]),
weighted_roc=expand("{out}/RTG{score}/{{sample}}/weighted_roc.tsv.gz",out=config["output_dir"],score=config["score_field"]),
shell:
"""
mkdir {params.outDir} -p
rtg vcfeval -b {input.sampleSpecificRef} -c {input.filt} -t {input.refSDF} -o {params.outDirTemp} \
--sample={params.sample} \
--vcf-score-field={params.vcfScoreField} \
--evaluation-regions={input.high_confidence}
mv {params.outDirTemp}/* {params.outDir}
rm -r {params.outDirTemp}
"""
rule rtg_squash:
input:
sampleSpecificRef=expand("{tmp}/{{sample}}Ref.vcf.gz",tmp=config["tmp_dir"]),
sampleSpecificTabix=expand("{tmp}/{{sample}}Ref.vcf.gz.tbi",tmp=config["tmp_dir"]),
filt=expand("{out}/vcfs/{{sample}}.vcf.gz",out=config["output_dir"]),
tabix=expand("{out}/vcfs/{{sample}}.vcf.gz.tbi",out=config["output_dir"]),
refSDF=expand("{ref}.sdf",ref=config["ref_truth"])
params:
outDirTemp=expand("{out}/RTGSquash/{{sample}}temp/",out=config["output_dir"]),
outDir=expand("{out}/RTGSquash{score}/{{sample}}/",out=config["output_dir"],score=config["score_field"]),
sample="{sample}",
vcfScoreField=config["score_field"]
output:
summary=expand("{out}/RTGSquash{score}/{{sample}}/summary.txt",out=config["output_dir"],score=config["score_field"]),
fp=expand("{out}/RTGSquash{score}/{{sample}}/fp.vcf.gz",out=config["output_dir"],score=config["score_field"]),
fn=expand("{out}/RTGSquash{score}/{{sample}}/fn.vcf.gz",out=config["output_dir"],score=config["score_field"]),
tp=expand("{out}/RTGSquash{score}/{{sample}}/tp.vcf.gz",out=config["output_dir"],score=config["score_field"]),
weighted_roc=expand("{out}/RTGSquash{score}/{{sample}}/weighted_roc.tsv.gz",out=config["output_dir"],score=config["score_field"]),
shell:
"""
mkdir {params.outDir} -p
rtg vcfeval -b {input.sampleSpecificRef} -c {input.filt} -t {input.refSDF} -o {params.outDirTemp} \
--sample={params.sample} \
--vcf-score-field={params.vcfScoreField} \
--evaluation-regions={input.high_confidence} \
--squash-ploidy
mv {params.outDirTemp}/* {params.outDir}
rm -r {params.outDirTemp}
"""