Skills › Knowledge Work Plugins › nextflow-development › sarek.yaml
sarek.yaml
233 lines · bio-research/skills/nextflow-development/scripts/config/pipelines/sarek.yaml at 2574e29
1name: sarek
2version: "3.7.1"
3description: "Variant calling for WGS/WES data (germline and somatic)"
5# Documentation and source - NOTE: Update version in URLs when upgrading pipeline
6urls:
7 documentation: "https://nf-co.re/sarek/{version}/"
8 parameters: "https://nf-co.re/sarek/{version}/parameters/"
9 output_docs: "https://nf-co.re/sarek/{version}/docs/output/"
10 github: "https://github.com/nf-core/sarek"
11 releases: "https://github.com/nf-core/sarek/releases"
13data_types:
14 - WGS
15 - WES
16 - whole genome sequencing
17 - whole exome sequencing
18 - tumor-normal
19 - germline
20 - somatic
22detection_hints:
23 filename:
24 - tumor
25 - normal
26 - germline
27 - wgs
28 - wes
29 - exome
30 - dna
31 - variant
32 directory:
33 - variant
34 - wgs
35 - wes
36 - exome
37 - germline
38 - somatic
40samplesheet:
41 input_types:
42 - fastq
43 - bam
44 - cram
46 columns:
47 - name: patient
48 required: true
49 type: string
50 inference: filename
51 description: "Patient/subject identifier for grouping samples"
53 - name: sample
54 required: true
55 type: string
56 inference: filename
57 description: "Sample identifier (e.g., tumor, normal)"
59 - name: lane
60 required: false
61 type: string
62 default: "L001"
63 inference: filename
64 description: "Sequencing lane"
66 - name: fastq_1
67 required: true
68 type: path
69 inference: auto
70 condition: "input_type == 'fastq'"
71 description: "Absolute path to R1 FASTQ"
73 - name: fastq_2
74 required: false
75 type: path
76 inference: auto
77 condition: "input_type == 'fastq'"
78 description: "Absolute path to R2 FASTQ"
80 - name: bam
81 required: true
82 type: path
83 inference: auto
84 condition: "input_type in ['bam', 'cram']"
85 description: "Absolute path to BAM/CRAM file"
87 - name: bai
88 required: true
89 type: path
90 inference: auto
91 condition: "input_type in ['bam', 'cram']"
92 description: "Absolute path to BAM/CRAM index"
94 - name: status
95 required: false
96 type: integer
97 allowed:
98 - 0
99 - 1
100 default: 0
101 inference: filename
102 description: "0=normal, 1=tumor (critical for somatic calling)"
104decision_points:
105 - parameter: genome
106 prompt: "Which reference genome should be used?"
107 options:
108 - value: GRCh38
109 label: "Human GRCh38/hg38 (recommended)"
110 description: "Latest human reference with most annotation support"
111 - value: GRCh37
112 label: "Human GRCh37/hg19 (legacy)"
113 description: "For compatibility with older datasets"
114 - value: mm10
115 label: "Mouse mm10"
116 description: "Mouse reference genome"
117 default: GRCh38
118 recommendation: "Default to GRCh38 for human data"
120 - parameter: tools
121 prompt: "What type of variant calling do you need?"
122 options:
123 - value: "haplotypecaller,snpeff"
124 label: "Germline variants (single samples)"
125 description: "For finding inherited variants in normal samples"
126 condition: "no tumor samples detected"
127 - value: "mutect2,strelka,snpeff"
128 label: "Somatic variants (tumor-normal pairs)"
129 description: "For finding cancer mutations with matched normal"
130 condition: "tumor-normal pairs detected"
131 - value: "haplotypecaller,deepvariant,snpeff"
132 label: "Germline with DeepVariant"
133 description: "Higher accuracy germline calling (requires GPU)"
134 - value: "mutect2,manta,snpeff"
135 label: "Somatic with structural variants"
136 description: "Comprehensive tumor analysis including SVs"
137 default: "haplotypecaller,snpeff"
138 recommendation: "Use somatic tools if tumor/normal pairs detected, otherwise germline"
140 - parameter: wes
141 prompt: "Is this whole exome sequencing (WES) data?"
142 options:
143 - value: "false"
144 label: "No - Whole Genome Sequencing (WGS)"
145 description: "Full genome coverage"
146 - value: "true"
147 label: "Yes - Whole Exome Sequencing (WES)"
148 description: "Requires --intervals BED file"
149 default: "false"
150 recommendation: "If WES, user must provide intervals BED file"
152test_profile:
153 command: "nextflow run nf-core/sarek -r 3.7.1 -profile test,docker --outdir test_sarek"
154 duration: "20 minutes"
155 success_indicators:
156 - "test_sarek/multiqc/multiqc_report.html"
157 log_pattern: "Pipeline completed successfully"
159run_command:
160 template: |
161 nextflow run nf-core/sarek \
162 -r 3.7.1 \
163 -profile docker \
164 --input {samplesheet} \
165 --outdir {outdir} \
166 --genome {genome} \
167 --tools {tools} \
168 -resume
170 wes_template: |
171 nextflow run nf-core/sarek \
172 -r 3.7.1 \
173 -profile docker \
174 --input {samplesheet} \
175 --outdir {outdir} \
176 --genome {genome} \
177 --tools {tools} \
178 --wes \
179 --intervals {intervals} \
180 -resume
182outputs:
183 primary:
184 - path: "preprocessing/recalibrated/*.recal.bam"
185 description: "Analysis-ready BAM files"
186 - path: "variant_calling/*/*.vcf.gz"
187 description: "Variant call files"
188 - path: "annotation/snpeff/*.ann.vcf.gz"
189 description: "Annotated variants"
191 validation:
192 - file: "multiqc/multiqc_report.html"
193 check: exists
194 description: "QC report must exist"
195 - file: "preprocessing/recalibrated"
196 check: exists
197 description: "Recalibrated BAMs directory"
199resources:
200 min_memory: "16.GB"
201 recommended_memory: "64.GB"
202 wgs_memory: "128.GB"
203 min_cpus: 4
204 recommended_cpus: 16
205 disk_space: "500.GB"
207troubleshooting:
208 - error: "BQSR fails"
209 fix: "Check known sites available for genome. Skip with --skip_bqsr for non-standard references"
210 - error: "Mutect2 no variants"
211 fix: "Verify tumor/normal pairing in samplesheet (check status column: 0=normal, 1=tumor)"
212 - error: "Out of memory"
213 fix: "--max_memory '128.GB' for WGS data"
214 - error: "DeepVariant GPU issues"
215 fix: "Ensure NVIDIA Docker runtime configured, or use CPU mode"
217tumor_normal_keywords:
218 tumor:
219 - tumor
220 - tumour
221 - met
222 - metastasis
223 - primary
224 - cancer
225 - malignant
226 normal:
227 - normal
228 - germline
229 - blood
230 - pbmc
231 - control
232 - healthy
233 - matched