Skip to content

Commit 94e9b50

Browse files
ahmigahmig
authored
refactor: update file names to avoid wildcard issues (#35)
* refactor: update file names to avoid wildcard issues * style: apply snakefmt
1 parent 29d75e5 commit 94e9b50

1 file changed

Lines changed: 85 additions & 70 deletions

File tree

‎workflow/rules/vaf.smk‎

Lines changed: 85 additions & 70 deletions
Original file line numberDiff line numberDiff line change
@@ -1,23 +1,25 @@
11
rule snps_to_ancestor:
22
threads: 2
33
retries: 3
4-
shadow: "minimal"
5-
conda: "../envs/var_calling.yaml"
4+
shadow:
5+
"minimal"
6+
conda:
7+
"../envs/var_calling.yaml"
68
params:
7-
mpileup_depth = config["VC"]["MAX_DEPTH"],
8-
mpileup_quality = 0,
9-
ivar_quality = config["VC"]["MIN_QUALITY"],
10-
ivar_freq = config["VC"]["MIN_FREQ"],
11-
ivar_depth = config["VC"]["MIN_DEPTH"],
9+
mpileup_depth=config["VC"]["MAX_DEPTH"],
10+
mpileup_quality=0,
11+
ivar_quality=config["VC"]["MIN_QUALITY"],
12+
ivar_freq=config["VC"]["MIN_FREQ"],
13+
ivar_depth=config["VC"]["MIN_DEPTH"],
1214
input:
13-
reference_fasta = OUTDIR/f"{OUTPUT_NAME}.ancestor.fasta",
14-
bam = get_input_bam,
15-
gff = OUTDIR/"reference.gff3"
15+
reference_fasta=OUTDIR / f"{OUTPUT_NAME}.ancestor.fasta",
16+
bam=get_input_bam,
17+
gff=OUTDIR / "reference.gff3",
1618
output:
17-
tsv = temp(OUTDIR/"vaf"/"{sample}.tsv"),
18-
reference_fasta_renamed = temp(OUTDIR/"vaf"/"{sample}.reference.fasta"),
19+
tsv=temp(OUTDIR / "vaf" / "vc" / "{sample}.tsv"),
20+
reference_fasta_renamed=temp(OUTDIR / "vaf" / "{sample}.reference.fasta"),
1921
log:
20-
LOGDIR / "snps_to_ancestor" / "{sample}.log.txt"
22+
LOGDIR / "snps_to_ancestor" / "{sample}.log.txt",
2123
shell:
2224
"""
2325
set -e
@@ -55,65 +57,70 @@ rule snps_to_ancestor:
5557

5658
rule mask_tsv:
5759
threads: 1
58-
conda: "../envs/biopython.yaml"
60+
conda:
61+
"../envs/biopython.yaml"
5962
params:
60-
mask_class = ["mask"]
61-
input:
62-
tsv = OUTDIR/"vaf"/"{sample}.tsv",
63-
vcf = lambda wildcards: select_problematic_vcf()
63+
mask_class=["mask"],
64+
input:
65+
tsv=OUTDIR / "vaf" / "vc" / "{sample}.tsv",
66+
vcf=lambda wildcards: select_problematic_vcf(),
6467
output:
65-
masked_tsv = temp(OUTDIR/"vaf"/"{sample}.masked.tsv")
68+
masked_tsv=temp(OUTDIR / "vaf" / "masked" / "{sample}.tsv"),
6669
log:
67-
LOGDIR / "mask_tsv" / "{sample}.log.txt"
70+
LOGDIR / "mask_tsv" / "{sample}.log.txt",
6871
script:
6972
"../scripts/mask_tsv.py"
7073

7174

7275
rule filter_tsv:
7376
threads: 1
74-
conda: "../envs/renv.yaml"
77+
conda:
78+
"../envs/renv.yaml"
7579
params:
76-
min_depth = 20,
77-
min_alt_rv = 2,
78-
min_alt_dp = 2,
79-
input:
80-
tsv = OUTDIR/"vaf"/"{sample}.masked.tsv"
80+
min_depth=20,
81+
min_alt_rv=2,
82+
min_alt_dp=2,
83+
input:
84+
tsv=OUTDIR / "vaf" / "masked" / "{sample}.tsv",
8185
output:
82-
filtered_tsv = temp(OUTDIR/"vaf"/"{sample}.masked.prefiltered.tsv")
86+
filtered_tsv=temp(OUTDIR / "vaf" / "filtered" / "{sample}.tsv"),
8387
log:
84-
LOGDIR / "filter_tsv" / "{sample}.log.txt"
88+
LOGDIR / "filter_tsv" / "{sample}.log.txt",
8589
script:
8690
"../scripts/filter_tsv.R"
8791

8892

8993
rule tsv_to_vcf:
9094
threads: 1
91-
conda: "../envs/biopython.yaml"
95+
conda:
96+
"../envs/biopython.yaml"
9297
params:
93-
ref_name = config["ALIGNMENT_REFERENCE"],
94-
input:
95-
tsv = OUTDIR/"vaf"/"{sample}.masked.prefiltered.tsv",
98+
ref_name=config["ALIGNMENT_REFERENCE"],
99+
input:
100+
tsv=OUTDIR / "vaf" / "filtered" / "{sample}.tsv",
96101
output:
97-
vcf = temp(OUTDIR/"vaf"/"{sample}.vcf")
102+
vcf=temp(OUTDIR / "vaf" / "vcf" / "{sample}.vcf"),
98103
log:
99-
LOGDIR / "tsv_to_vcf" / "{sample}.log.txt"
104+
LOGDIR / "tsv_to_vcf" / "{sample}.log.txt",
100105
script:
101106
"../scripts/tsv_to_vcf.py"
102107

103108

104109
rule variants_effect:
105110
threads: 1
106-
shadow: "minimal"
107-
conda: "../envs/snpeff.yaml"
111+
shadow:
112+
"minimal"
113+
conda:
114+
"../envs/snpeff.yaml"
108115
params:
109-
ref_name = config["ALIGNMENT_REFERENCE"],
110-
snpeff_data_dir = (BASE_PATH / "config" / "snpeff").resolve()
116+
ref_name=config["ALIGNMENT_REFERENCE"],
117+
snpeff_data_dir=(BASE_PATH / "config" / "snpeff").resolve(),
111118
input:
112-
vcf = OUTDIR/"vaf"/"{sample}.vcf"
119+
vcf=OUTDIR / "vaf" / "vcf" / "{sample}.vcf",
113120
output:
114-
ann_vcf = OUTDIR/"vaf"/"{sample}.annotated.vcf"
121+
ann_vcf=OUTDIR / "vaf" / "annotated" / "{sample}.vcf",
115122
log:
116-
LOGDIR / "variants_effect" / "{sample}.log.txt"
123+
LOGDIR / "variants_effect" / "{sample}.log.txt",
117124
retries: 2
118125
shell:
119126
"""
@@ -133,74 +140,82 @@ rule variants_effect:
133140

134141
rule extract_vcf_fields:
135142
threads: 1
136-
conda: "../envs/snpeff.yaml"
143+
conda:
144+
"../envs/snpeff.yaml"
137145
params:
138-
extract_columns = [f"'{col}'" for col in config["ANNOTATION"]["SNPEFF_COLS"].values()],
139-
sep = ",",
146+
extract_columns=[
147+
f"'{col}'" for col in config["ANNOTATION"]["SNPEFF_COLS"].values()
148+
],
149+
sep=",",
140150
input:
141-
vcf = OUTDIR/"vaf"/"{sample}.annotated.vcf"
151+
vcf=OUTDIR / "vaf" / "annotated" / "{sample}.vcf",
142152
output:
143-
tsv = OUTDIR/"vaf"/"{sample}.vcf_fields.tsv"
153+
tsv=OUTDIR / "vaf" / "fields" / "{sample}.tsv",
144154
log:
145-
LOGDIR / "tsv_to_vcf" / "{sample}.log.txt"
155+
LOGDIR / "tsv_to_vcf" / "{sample}.log.txt",
146156
shell:
147157
"SnpSift extractFields -e 'NA' -s {params.sep:q} {input.vcf:q} {params.extract_columns} >{output.tsv:q} 2>{log:q}"
148158

149159

150160
rule format_vcf_fields_longer:
151-
conda: "../envs/renv.yaml"
161+
conda:
162+
"../envs/renv.yaml"
152163
params:
153-
sample = "{sample}",
154-
colnames_mapping = config["ANNOTATION"]["SNPEFF_COLS"],
155-
filter_include = config["ANNOTATION"]["FILTER_INCLUDE"],
156-
filter_exclude = config["ANNOTATION"]["FILTER_EXCLUDE"],
157-
variant_name_pattern = lambda wildcards: config["ANNOTATION"]["VARIANT_NAME_PATTERN"], # lambda to deactivate automatic wildcard expansion in pattern
158-
sep = ",",
164+
sample="{sample}",
165+
colnames_mapping=config["ANNOTATION"]["SNPEFF_COLS"],
166+
filter_include=config["ANNOTATION"]["FILTER_INCLUDE"],
167+
filter_exclude=config["ANNOTATION"]["FILTER_EXCLUDE"],
168+
variant_name_pattern=lambda wildcards: config["ANNOTATION"][
169+
"VARIANT_NAME_PATTERN"
170+
], # lambda to deactivate automatic wildcard expansion in pattern
171+
sep=",",
159172
input:
160-
tsv = OUTDIR/"vaf"/"{sample}.vcf_fields.tsv",
173+
tsv=OUTDIR / "vaf" / "fields" / "{sample}.tsv",
161174
output:
162-
tsv = OUTDIR/"vaf"/"{sample}.vcf_fields.longer.tsv",
175+
tsv=OUTDIR / "vaf" / "fields_longer" / "{sample}.tsv",
163176
log:
164-
LOGDIR / "format_vcf_fields_longer" / "{sample}.log.txt"
177+
LOGDIR / "format_vcf_fields_longer" / "{sample}.log.txt",
165178
script:
166179
"../scripts/format_vcf_fields_longer.R"
167180

168181

169182
rule concat_vcf_fields:
170183
params:
171-
sep = "\t",
184+
sep="\t",
172185
input:
173-
expand(OUTDIR/"vaf"/"{sample}.vcf_fields.longer.tsv", sample=iter_samples()),
186+
expand(OUTDIR / "vaf" / "fields_longer" / "{sample}.tsv", sample=iter_samples()),
174187
output:
175-
OUTDIR/f"{OUTPUT_NAME}.vcf_fields.longer.tsv",
188+
OUTDIR / f"{OUTPUT_NAME}.vcf_fields.longer.tsv",
176189
run:
177190
import pandas as pd
178191
from functools import reduce
192+
179193
reduce(
180194
lambda a, b: pd.concat((a, b), axis="rows", ignore_index=True),
181-
(pd.read_csv(path, sep=params.sep) for path in input)
195+
(pd.read_csv(path, sep=params.sep) for path in input),
182196
).to_csv(output[0], sep=params.sep, index=False)
183197

184198

185199
rule merge_annotation:
186200
threads: 1
187-
conda: "../envs/renv.yaml"
201+
conda:
202+
"../envs/renv.yaml"
188203
params:
189-
sample = "{sample}",
190-
ref_name = config["ALIGNMENT_REFERENCE"],
204+
sample="{sample}",
205+
ref_name=config["ALIGNMENT_REFERENCE"],
191206
input:
192-
tsv = OUTDIR/"vaf"/"{sample}.masked.prefiltered.tsv",
193-
annot = OUTDIR/"vaf"/"{sample}.vcf_fields.longer.tsv",
207+
tsv=OUTDIR / "vaf" / "filtered" / "{sample}.tsv",
208+
annot=OUTDIR / "vaf" / "fields_longer" / "{sample}.tsv",
194209
output:
195-
tsv = OUTDIR/"vaf"/"{sample}.variants.tsv"
210+
tsv=OUTDIR / "vaf" / "variants" / "{sample}.tsv",
196211
log:
197-
LOGDIR / "merge_annotation" / "{sample}.log.txt"
212+
LOGDIR / "merge_annotation" / "{sample}.log.txt",
198213
script:
199214
"../scripts/merge_annotation.R"
200215

201216

202217
use rule concat_vcf_fields as concat_variants with:
203218
input:
204-
expand(OUTDIR/"vaf"/"{sample}.variants.tsv", sample=iter_samples()),
219+
expand(OUTDIR / "vaf" / "variants" / "{sample}.tsv", sample=iter_samples()),
205220
output:
206-
OUTDIR/f"{OUTPUT_NAME}.variants.tsv",
221+
OUTDIR / f"{OUTPUT_NAME}.variants.tsv",

0 commit comments

Comments
 (0)