forked from genome/analysis-workflows
-
Notifications
You must be signed in to change notification settings - Fork 0
/
somatic_exome_gathered.cwl
244 lines (243 loc) · 11.1 KB
/
somatic_exome_gathered.cwl
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
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
#!/usr/bin/env cwl-runner
cwlVersion: v1.0
class: Workflow
label: "gathered exome alignment and somatic variant detection"
requirements:
- class: SchemaDefRequirement
types:
- $import: ../types/labelled_file.yml
- $import: ../types/sequence_data.yml
- $import: ../types/vep_custom_annotation.yml
- class: SubworkflowFeatureRequirement
- class: StepInputExpressionRequirement
inputs:
reference:
type:
- string
- File
secondaryFiles: [.fai, ^.dict, .amb, .ann, .bwt, .pac, .sa]
tumor_sequence:
type: ../types/sequence_data.yml#sequence_data[]
tumor_cram_name:
type: string?
default: 'tumor.cram'
normal_sequence:
type: ../types/sequence_data.yml#sequence_data[]
normal_cram_name:
type: string?
default: 'normal.cram'
mills:
type: File
secondaryFiles: [.tbi]
known_indels:
type: File
secondaryFiles: [.tbi]
dbsnp_vcf:
type: File
secondaryFiles: [.tbi]
bqsr_intervals:
type: string[]
bait_intervals:
type: File
target_intervals:
type: File
per_base_intervals:
type: ../types/labelled_file.yml#labelled_file[]
per_target_intervals:
type: ../types/labelled_file.yml#labelled_file[]
summary_intervals:
type: ../types/labelled_file.yml#labelled_file[]
omni_vcf:
type: File
secondaryFiles: [.tbi]
picard_metric_accumulation_level:
type: string
qc_minimum_mapping_quality:
type: int?
default: 0
qc_minimum_base_quality:
type: int?
default: 0
interval_list:
type: File
cosmic_vcf:
type: File?
secondaryFiles: [.tbi]
panel_of_normals_vcf:
type: File?
secondaryFiles: [.tbi]
strelka_cpu_reserved:
type: int?
default: 8
mutect_scatter_count:
type: int
mutect_artifact_detection_mode:
type: boolean
mutect_max_alt_allele_in_normal_fraction:
type: float?
mutect_max_alt_alleles_in_normal_count:
type: int?
varscan_strand_filter:
type: int?
default: 0
varscan_min_coverage:
type: int?
default: 8
varscan_min_var_freq:
type: float?
default: 0.05
varscan_p_value:
type: float?
default: 0.99
varscan_max_normal_freq:
type: float?
pindel_insert_size:
type: int
default: 400
docm_vcf:
type: File
secondaryFiles: [.tbi]
filter_docm_variants:
type: boolean?
default: true
vep_cache_dir:
type: string?
vep_ensembl_assembly:
type: string
doc: "genome assembly to use in vep. Examples: GRCh38 or GRCm38"
vep_ensembl_version:
type: string
doc: "ensembl version - Must be present in the cache directory. Example: 95"
vep_ensembl_species:
type: string
doc: "ensembl species - Must be present in the cache directory. Examples: homo_sapiens or mus_musculus"
synonyms_file:
type: File?
annotate_coding_only:
type: boolean?
hgvs_annotation:
type: boolean?
vep_pick:
type:
- "null"
- type: enum
symbols: ["pick", "flag_pick", "pick_allele", "per_gene", "pick_allele_gene", "flag_pick_allele", "flag_pick_allele_gene"]
cle_vcf_filter:
type: boolean
default: false
variants_to_table_fields:
type: string[]
default: [CHROM,POS,ID,REF,ALT,set,AC,AF]
variants_to_table_genotype_fields:
type: string[]
default: [GT,AD]
vep_to_table_fields:
type: string[]
default: [HGVSc,HGVSp]
vep_custom_annotations:
type: ../types/vep_custom_annotation.yml#vep_custom_annotation[]
doc: "custom type, check types directory for input format"
output_dir:
type: string
somalier_vcf:
type: File
tumor_sample_name:
type: string
normal_sample_name:
type: string
known_variants:
type: File?
secondaryFiles: [.tbi]
doc: "Previously discovered variants to be flagged in this pipelines's output vcf"
outputs:
final_outputs:
type: string[]
outputSource: gatherer/gathered_files
steps:
somatic_exome:
run: somatic_exome.cwl
in:
reference: reference
tumor_sequence: tumor_sequence
tumor_cram_name: tumor_cram_name
normal_sequence: normal_sequence
normal_cram_name: normal_cram_name
mills: mills
known_indels: known_indels
dbsnp_vcf: dbsnp_vcf
bqsr_intervals: bqsr_intervals
bait_intervals: bait_intervals
target_intervals: target_intervals
per_base_intervals: per_base_intervals
per_target_intervals: per_target_intervals
summary_intervals: summary_intervals
omni_vcf: omni_vcf
picard_metric_accumulation_level: picard_metric_accumulation_level
qc_minimum_mapping_quality: qc_minimum_mapping_quality
qc_minimum_base_quality: qc_minimum_base_quality
interval_list: interval_list
cosmic_vcf: cosmic_vcf
panel_of_normals_vcf: panel_of_normals_vcf
strelka_cpu_reserved: strelka_cpu_reserved
mutect_scatter_count: mutect_scatter_count
mutect_artifact_detection_mode: mutect_artifact_detection_mode
mutect_max_alt_allele_in_normal_fraction: mutect_max_alt_allele_in_normal_fraction
mutect_max_alt_alleles_in_normal_count: mutect_max_alt_alleles_in_normal_count
varscan_strand_filter: varscan_strand_filter
varscan_min_coverage: varscan_min_coverage
varscan_min_var_freq: varscan_min_var_freq
varscan_p_value: varscan_p_value
varscan_max_normal_freq: varscan_max_normal_freq
pindel_insert_size: pindel_insert_size
docm_vcf: docm_vcf
vep_cache_dir: vep_cache_dir
vep_ensembl_assembly: vep_ensembl_assembly
vep_ensembl_version: vep_ensembl_version
vep_ensembl_species: vep_ensembl_species
synonyms_file: synonyms_file
annotate_coding_only: annotate_coding_only
hgvs_annotation: hgvs_annotation
vep_pick: vep_pick
cle_vcf_filter: cle_vcf_filter
variants_to_table_fields: variants_to_table_fields
variants_to_table_genotype_fields: variants_to_table_genotype_fields
vep_to_table_fields: vep_to_table_fields
vep_custom_annotations: vep_custom_annotations
somalier_vcf: somalier_vcf
tumor_sample_name: tumor_sample_name
normal_sample_name: normal_sample_name
known_variants: known_variants
out:
[tumor_cram, tumor_mark_duplicates_metrics, tumor_insert_size_metrics, tumor_alignment_summary_metrics, tumor_hs_metrics, tumor_per_target_coverage_metrics, tumor_per_base_coverage_metrics, tumor_per_base_hs_metrics, tumor_summary_hs_metrics, tumor_flagstats, tumor_verify_bam_id_metrics, tumor_verify_bam_id_depth, normal_cram, normal_mark_duplicates_metrics, normal_insert_size_metrics, normal_alignment_summary_metrics, normal_hs_metrics, normal_per_target_coverage_metrics, normal_per_target_hs_metrics, normal_per_base_coverage_metrics, normal_per_base_hs_metrics, normal_summary_hs_metrics, normal_flagstats, normal_verify_bam_id_metrics, normal_verify_bam_id_depth, mutect_unfiltered_vcf, mutect_filtered_vcf, strelka_unfiltered_vcf, strelka_filtered_vcf, varscan_unfiltered_vcf, varscan_filtered_vcf, pindel_unfiltered_vcf, pindel_filtered_vcf, docm_filtered_vcf, final_vcf, final_filtered_vcf, final_tsv, vep_summary, tumor_snv_bam_readcount_tsv, tumor_indel_bam_readcount_tsv, normal_snv_bam_readcount_tsv, normal_indel_bam_readcount_tsv, somalier_concordance_metrics, somalier_concordance_statistics]
gatherer:
run: ../tools/gatherer.cwl
in:
output_dir: output_dir
all_files:
source: [somatic_exome/tumor_cram, somatic_exome/tumor_mark_duplicates_metrics, somatic_exome/tumor_insert_size_metrics, somatic_exome/tumor_alignment_summary_metrics, somatic_exome/tumor_hs_metrics, somatic_exome/tumor_per_target_coverage_metrics, somatic_exome/tumor_per_base_coverage_metrics, somatic_exome/tumor_per_base_hs_metrics, somatic_exome/tumor_summary_hs_metrics, somatic_exome/tumor_flagstats, somatic_exome/tumor_verify_bam_id_metrics, somatic_exome/tumor_verify_bam_id_depth, somatic_exome/normal_cram, somatic_exome/normal_mark_duplicates_metrics, somatic_exome/normal_insert_size_metrics, somatic_exome/normal_alignment_summary_metrics, somatic_exome/normal_hs_metrics, somatic_exome/normal_per_target_coverage_metrics, somatic_exome/normal_per_target_hs_metrics, somatic_exome/normal_per_base_coverage_metrics, somatic_exome/normal_per_base_hs_metrics, somatic_exome/normal_summary_hs_metrics, somatic_exome/normal_flagstats, somatic_exome/normal_verify_bam_id_metrics, somatic_exome/normal_verify_bam_id_depth, somatic_exome/mutect_unfiltered_vcf, somatic_exome/mutect_filtered_vcf, somatic_exome/strelka_unfiltered_vcf, somatic_exome/strelka_filtered_vcf, somatic_exome/varscan_unfiltered_vcf, somatic_exome/varscan_filtered_vcf, somatic_exome/pindel_unfiltered_vcf, somatic_exome/pindel_filtered_vcf, somatic_exome/docm_filtered_vcf, somatic_exome/final_vcf, somatic_exome/final_filtered_vcf, somatic_exome/final_tsv, somatic_exome/vep_summary, somatic_exome/tumor_snv_bam_readcount_tsv, somatic_exome/tumor_indel_bam_readcount_tsv, somatic_exome/normal_snv_bam_readcount_tsv, somatic_exome/normal_indel_bam_readcount_tsv]
valueFrom: ${
function flatten(inArr, outArr) {
var arrLen = inArr.length;
for (var i = 0; i < arrLen; i++) {
if (Array.isArray(inArr[i])) {
flatten(inArr[i], outArr);
}
else {
outArr.push(inArr[i]);
}
}
return outArr;
}
var no_secondaries = flatten(self, []);
var all_files = [];
var arrLen = no_secondaries.length;
for (var i = 0; i < arrLen; i++) {
all_files.push(no_secondaries[i]);
var secondaryLen = no_secondaries[i].secondaryFiles.length;
for (var j = 0; j < secondaryLen; j++) {
all_files.push(no_secondaries[i].secondaryFiles[j]);
}
}
return all_files;
}
out: [gathered_files]