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
- 2.9
- Position
- 9 of 21
- Type
- YAML
- Size
- 5 KB
- Lines
- 187
scripts/config/pipelines/atacseq.yaml
YAML·187 lines·5 KB
11
releases
:
"https://github.com/nf-core/atacseq/releases"
12
13data_types:
14 - ATAC-seq
15 - chromatin accessibility
16 - open chromatin
17
18detection_hints:
19 filename:
20 - atac
21 - atacseq
22 - chromatin
23 - accessibility
24 directory:
25 - atac
26 - atacseq
27 - chromatin
28 - epigenome
29 - epigenetics
30
31samplesheet:
32 input_types:
33 - fastq
34
35 columns:
36 - name: sample
37 required: true
38 type: string
39 inference: filename
40 description: "Condition/group identifier (replicates share same name)"
41
42 - name: fastq_1
43 required: true
44 type: path
45 inference: auto
46 description: "Absolute path to R1 FASTQ"
47
48 - name: fastq_2
49 required: true
50 type: path
51 inference: auto
52 description: "Absolute path to R2 FASTQ (paired-end required)"
53
54 - name: replicate
55 required: true
56 type: integer
57 default: 1
58 inference: filename
59 description: "Replicate number (integer)"
60
61decision_points:
62 - parameter: genome
63 prompt: "Which reference genome matches your organism?"
64 options:
65 - value: GRCh38
66 label: "Human GRCh38/hg38 (recommended)"
67 description: "Latest human reference"
68 - value: GRCh37
69 label: "Human GRCh37/hg19 (legacy)"
70 description: "Older human reference"
71 - value: mm10
72 label: "Mouse mm10"
73 description: "Mouse reference genome"
74 default: GRCh38
75 recommendation: "Default to GRCh38 for human samples"
76
77 - parameter: read_length
78 prompt: "What is the read length of your sequencing data?"
79 options:
80 - value: 50
81 label: "50 bp"
82 description: "Short reads"
83 - value: 75
84 label: "75 bp"
85 description: "Standard length"
86 - value: 100
87 label: "100 bp"
88 description: "Common for modern sequencers"
89 - value: 150
90 label: "150 bp"
91 description: "Long reads"
92 default: 50
93 recommendation: "Check FASTQ files or sequencing report for exact length"
94
95 - parameter: narrow_peak
96 prompt: "What type of peaks are you expecting?"
97 options:
98 - value: "true"
99 label: "Narrow peaks (default for ATAC-seq)"
100 description: "Standard ATAC-seq open chromatin regions"
101 - value: "false"
102 label: "Broad peaks"
103 description: "For histone marks or broader accessibility regions"
104 default: "true"
105 recommendation: "Use narrow peaks for standard ATAC-seq"
106
107test_profile:
108 command: "nextflow run nf-core/atacseq -r 2.1.2 -profile test,docker --outdir test_atacseq"
109 duration: "15 minutes"
110 success_indicators:
111 - "test_atacseq/multiqc/multiqc_report.html"
112 log_pattern: "Pipeline completed successfully"
113
114run_command:
115 template: |
116 nextflow run nf-core/atacseq \
117 -r 2.1.2 \
118 -profile docker \
119 --input {samplesheet} \
120 --outdir {outdir} \
121 --genome {genome} \
122 --read_length {read_length} \
123 -resume
124
125outputs:
126 primary:
127 - path: "bwa/mergedLibrary/*.mLb.mkD.sorted.bam"
128 description: "Filtered, deduplicated alignments"
129 - path: "bwa/mergedLibrary/bigwig/*.bigWig"
130 description: "Coverage tracks for genome browsers"
131 - path: "macs2/narrowPeak/*.narrowPeak"
132 description: "Peak calls (BED format)"
133 - path: "macs2/narrowPeak/consensus/consensus_peaks.bed"
134 description: "Consensus peaks across replicates"
135
136 validation:
137 - file: "multiqc/multiqc_report.html"
138 check: exists
139 description: "QC report must exist"
140 - file: "macs2/narrowPeak"
141 check: exists
142 description: "Peak calls directory"
143
144quality_metrics:
145 - name: mapped_reads
146 good: ">80%"
147 acceptable: "60-80%"
148 poor: "<60%"
149 - name: mitochondrial
150 good: "<20%"
151 acceptable: "20-40%"
152 poor: ">40%"
153 - name: duplicates
154 good: "<30%"
155 acceptable: "30-50%"
156 poor: ">50%"
157 - name: frip
158 good: ">30%"
159 acceptable: "15-30%"
160 poor: "<15%"
161 - name: tss_enrichment
162 good: ">6"
163 acceptable: "4-6"
164 poor: "<4"
165
166resources:
167 min_memory: "8.GB"
168 recommended_memory: "32.GB"
169 min_cpus: 4
170 recommended_cpus: 8
171 disk_space: "100.GB"
172
173troubleshooting:
174 - error: "Low FRiP score"
175 fix: "Check library complexity in plotFingerprint. May indicate over-transposition or low quality"
176 - error: "Few peaks called"
177 fix: "Lower threshold with --macs_qvalue 0.1 or use --narrow_peak false for broader peaks"
178 - error: "High duplicates"
179 fix: "Normal for low-input samples. Pipeline removes by default. Consider deeper sequencing"
180 - error: "High mitochondrial reads"
181 fix: "Sample quality issue. Pipeline filters mito by default (--keep_mito false)"
182
183replicate_patterns:
184 - "_rep(\\d+)"
185 - "_R(\\d+)_"
186 - "_(\\d+)$"
187 - "_replicate(\\d+)"