Setting the file. One moment. 22
Validate Data
Tech Debt
62
Recruiting Pipeline
71
Vendor Check
125
Zoom Meeting SDK Web
88
Vendor Review
181
Create An Asset
Video Sdk/web
This file
- Number
- 2.10
- Position
- 10 of 21
- Type
- YAML
- Size
- 4 KB
- Lines
- 147
scripts/config/pipelines/rnaseq.yaml
YAML·147 lines·4 KB
11
releases
:
"https://github.com/nf-core/rnaseq/releases"
12
13data_types:
14 - RNA-seq
15 - mRNA-seq
16 - bulk RNA-seq
17
18detection_hints:
19 filename:
20 - rna
21 - rnaseq
22 - mrna
23 - expression
24 directory:
25 - rnaseq
26 - rna
27 - expression
28 - transcriptome
29
30samplesheet:
31 input_types:
32 - fastq
33
34 columns:
35 - name: sample
36 required: true
37 type: string
38 inference: filename
39 description: "Sample identifier"
40
41 - name: fastq_1
42 required: true
43 type: path
44 inference: auto
45 description: "Absolute path to R1 FASTQ"
46
47 - name: fastq_2
48 required: false
49 type: path
50 inference: auto
51 description: "Absolute path to R2 FASTQ (empty for single-end)"
52
53 - name: strandedness
54 required: true
55 type: enum
56 allowed:
57 - auto
58 - forward
59 - reverse
60 - unstranded
61 default: "auto"
62 inference: default
63 description: "Library strandedness (auto recommended)"
64
65decision_points:
66 - parameter: genome
67 prompt: "Which reference genome matches your organism?"
68 options:
69 - value: GRCh38
70 label: "Human GRCh38/hg38 (recommended for human)"
71 description: "Latest human reference assembly"
72 - value: GRCh37
73 label: "Human GRCh37/hg19 (legacy)"
74 description: "Older human reference for compatibility"
75 - value: mm10
76 label: "Mouse mm10/GRCm38"
77 description: "Mouse reference genome"
78 - value: BDGP6
79 label: "Drosophila BDGP6"
80 description: "Fruit fly reference"
81 default: GRCh38
82 recommendation: "Default to GRCh38 for human samples"
83
84 - parameter: aligner
85 prompt: "Which alignment strategy would you prefer?"
86 options:
87 - value: star_salmon
88 label: "STAR + Salmon (recommended)"
89 description: "Most accurate, standard for differential expression"
90 - value: star_rsem
91 label: "STAR + RSEM"
92 description: "Better for isoform-level quantification"
93 - value: hisat2
94 label: "HISAT2"
95 description: "Lower memory requirements, faster"
96 default: star_salmon
97 recommendation: "Use star_salmon unless memory-constrained or need isoforms"
98
99test_profile:
100 command: "nextflow run nf-core/rnaseq -r 3.22.2 -profile test,docker --outdir test_rnaseq"
101 duration: "15 minutes"
102 success_indicators:
103 - "test_rnaseq/multiqc/multiqc_report.html"
104 log_pattern: "Pipeline completed successfully"
105
106run_command:
107 template: |
108 nextflow run nf-core/rnaseq \
109 -r 3.22.2 \
110 -profile docker \
111 --input {samplesheet} \
112 --outdir {outdir} \
113 --genome {genome} \
114 --aligner {aligner} \
115 -resume
116
117outputs:
118 primary:
119 - path: "star_salmon/salmon.merged.gene_counts.tsv"
120 description: "Raw gene counts for DESeq2/edgeR"
121 - path: "star_salmon/salmon.merged.gene_tpm.tsv"
122 description: "TPM normalized expression values"
123 - path: "star_salmon/*.bam"
124 description: "Aligned reads"
125
126 validation:
127 - file: "multiqc/multiqc_report.html"
128 check: exists
129 description: "QC report must exist"
130 - file: "star_salmon/salmon.merged.gene_counts.tsv"
131 check: non_empty
132 description: "Count matrix must have data"
133
134resources:
135 min_memory: "8.GB"
136 recommended_memory: "32.GB"
137 min_cpus: 4
138 recommended_cpus: 8
139 disk_space: "100.GB"
140
141troubleshooting:
142 - error: "STAR index fails"
143 fix: "Increase memory with --max_memory '64.GB' or provide pre-built --star_index"
144 - error: "Low alignment rate"
145 fix: "Verify genome matches species; check FastQC for adapter contamination"
146 - error: "Strandedness detection fails"
147 fix: "Specify explicitly with --strandedness reverse (or forward/unstranded)"