-
Notifications
You must be signed in to change notification settings - Fork 666
/
multiqc_config.yaml
159 lines (144 loc) · 4.54 KB
/
multiqc_config.yaml
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
report_comment: >
This report has been generated by the <a href="https://github.com/nf-core/rnaseq" target="_blank">nf-core/rnaseq</a>
analysis pipeline. For information about how to interpret these results, please see the
<a href="https://nf-co.re/rnaseq" target="_blank">documentation</a>.
report_section_order:
software_versions:
order: -1000
nf-core-rnaseq-summary:
order: -1001
export_plots: true
# Run only these modules
run_modules:
- custom_content
- fastqc
- cutadapt
- sortmerna
- star
- hisat2
- rsem
- salmon
- samtools
- picard
- preseq
- rseqc
- qualimap
# Order of modules
top_modules:
- 'fail_mapped_samples'
- 'fail_strand_check'
- 'star_rsem_deseq2_pca'
- 'star_rsem_deseq2_clustering'
- 'star_salmon_deseq2_pca'
- 'star_salmon_deseq2_clustering'
- 'salmon_deseq2_pca'
- 'salmon_deseq2_clustering'
- 'biotype_counts'
- 'dupradar'
module_order:
- fastqc:
name: 'FastQC (raw)'
info: 'This section of the report shows FastQC results before adapter trimming.'
path_filters:
- './fastqc/*.zip'
- cutadapt
- fastqc:
name: 'FastQC (trimmed)'
info: 'This section of the report shows FastQC results after adapter trimming.'
path_filters:
- './trimgalore/fastqc/*.zip'
# Don't show % Dups in the General Stats table (we have this from Picard)
table_columns_visible:
fastqc:
percent_duplicates: False
extra_fn_clean_exts:
- '.umi_dedup'
- '_val'
# Customise the module search patterns to speed up execution time
# - Skip module sub-tools that we are not interested in
# - Replace file-content searching with filename pattern searching
# - Don't add anything that is the same as the MultiQC default
# See https://multiqc.info/docs/#optimise-file-search-patterns for details
sp:
cutadapt:
fn: '*trimming_report.txt'
sortmerna:
fn: '*.sortmerna.log'
hisat2:
fn: '*.hisat2.summary.log'
salmon/meta:
fn: 'meta_info.json'
preseq:
fn: '*.ccurve.txt'
samtools/stats:
fn: '*.stats'
samtools/flagstat:
fn: '*.flagstat'
samtools/idxstats:
fn: '*.idxstats*'
rseqc/bam_stat:
fn: '*.bam_stat.txt'
rseqc/gene_body_coverage:
skip: true
rseqc/junction_annotation:
fn: '*.junction_annotation.log'
rseqc/read_gc:
skip: true
rseqc/read_distribution:
fn: '*.read_distribution.txt'
rseqc/infer_experiment:
fn: '*.infer_experiment.txt'
rseqc/tin:
fn: '*.tin.txt'
picard/markdups:
fn: '*.MarkDuplicates.metrics.txt'
picard/alignment_metrics:
skip: true
picard/basedistributionbycycle:
skip: true
picard/gcbias:
skip: true
picard/hsmetrics:
skip: true
picard/insertsize:
skip: true
picard/oxogmetrics:
skip: true
picard/pcr_metrics:
skip: true
picard/quality_by_cycle:
skip: true
picard/quality_score_distribution:
skip: true
picard/quality_yield_metrics:
skip: true
picard/rnaseqmetrics:
skip: true
picard/rrbs_metrics:
skip: true
picard/sam_file_validation:
skip: true
picard/variant_calling_metrics:
skip: true
picard/wgs_metrics:
skip: true
# See https://github.com/ewels/MultiQC_TestData/blob/master/data/custom_content/with_config/table_headerconfig/multiqc_config.yaml
custom_data:
fail_mapped_samples:
section_name: 'WARNING: Fail Alignment Check'
description: "List of samples that failed the STAR minimum mapped reads threshold specified via the '--min_mapped_reads' parameter, and hence were ignored for the downstream processing steps."
plot_type: 'table'
pconfig:
id: 'fail_mapped_samples_table'
table_title: 'Samples failed mapping threshold'
namespace: 'Samples failed mapping threshold'
format: '{:.2f}'
fail_strand_check:
section_name: 'WARNING: Fail Strand Check'
description: "List of samples that failed the strandedness check between that provided in the samplesheet and calculated by the <a href='http://rseqc.sourceforge.net/#infer-experiment-py'>RSeQC infer_experiment.py</a> tool."
plot_type: 'table'
pconfig:
id: 'fail_strand_check_table'
table_title: 'Samples failed strandedness check'
namespace: 'Samples failed strandedness check'
format: '{:.2f}'