forked from sequana/rnaseq
-
Notifications
You must be signed in to change notification settings - Fork 0
/
multiqc_config.yaml
172 lines (141 loc) · 5.37 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
160
161
162
163
164
165
166
167
168
169
170
171
172
#######################################
# Example MultiQC Configuration File
#######################################
# This file can be saved either in the MultiQC installation
# directory, or as ~/.multiqc_config.yaml
# Configuration settings are taken from the following locations, in order:
# - Hardcoded in MultiQC (multiqc/utils/config.py)
# - <installation_dir>/multiqc_config.yaml
# - ~/.multiqc_config.yaml
# - Command line options
# Note that all of the values below are set to the MultiQC defaults.
# It's recommended that you delete any that you don't need.
#------------------------------------------------------------------------------
# TO CHANGE
#-------------------------------------------------------------------------------
# Title to use for the report.
title: "sequana_rnaseq MultiQC summary"
subtitle: "RNA-seq analysis"
intro_text: "Report summarising cleaning (cutadapt section) and mapping (stat/bowtie sections) of your FastQ files, as well as feature counts (featureCounts section) and quick contaminant search (fastq screen section)"
# Add generic information to the top of reports
report_header_info:
- Authors: '<a href="http://github.com/sequana/sequana">Sequana developers</a>'
- Want to know more?: 'See the <a href="http://sequana.readthedocs.io" target="_blank">Sequana</a> and <a href="http://github.com/sequana/sequana_rnaseq/" target="_blank"> sequana_rnaseq pipeline</a> documentation.'
- Citations: 'If you used Sequanix, Sequana, Sequana_coverage tool, or any Sequana pipelines, please see <a href="http://sequana.readthedocs.io">How to cite ?</a> section. In particular, if you use this report in a publication, please cite Sequana.'
- Contact E-mail: ''
# - Project Type: 'Differential gene expression'
#-------------------------------------------------------------------------------
# Prepend sample names with their directory. Useful if analysing the
# sample samples with different parameters.
prepend_dirs: False
# Default output filenames
output_fn_name: multiqc_report.html
data_dir_name: multiqc_data
# Whether to create the parsed data directory in addition to the report
make_data_dir: True
# Cleaning options for sample names. Typically, sample names are detected
# from an input filename. If any of these strings are found, they and any
# text to their right will be discarded.
# For example - file1.fq.gz_trimmed.bam_deduplicated_fastqc.zip
# would be cleaned to 'file1'
# Two options here - fn_clean_exts will replace the defaults,
# extra_fn_clean_exts will append to the defaults
extra_fn_clean_exts:
- .gz
- .fastq
- _R1_.cutadapt
- _R2_.cutadapt
- _R2_001
- _R1_001
- .err
- type: remove
pattern: '.sorted'
- type: regex
pattern: '_S\d+'
# Ignore these files / directories / paths when searching for logs
fn_ignore_files:
- .DS_Store
- slurm*out
- "*.js"
fn_ignore_dirs:
- .sequana
- .snakemake
- multiqc
- logs
# We want to ignore the 3 strand case to use only the final ones in
# post_analysis/feature_counts
fn_ignore_paths:
- "*/feature_counts/*"
# Ignore files larger than this when searcing for logs (bytes)
log_filesize_limit: 5000000
# MultiQC skips a couple of debug messages when searching files as the
# log can get very verbose otherwise. Re-enable here to help debugging.
report_readerrors: False
report_imgskips: False
# Opt-out of remotely checking that you're running the latest version
no_version_check: False
# How to plot graphs. Different templates can override these settings, but
# the default template can use interactive plots (Javascript using HighCharts)
# or flat plots (images, using MatPlotLib). With interactive plots, the report
# can prevent automatically rendering all graphs if there are lots of samples
# to prevent the browser being locked up when the report opens.
plots_force_flat: False # Try to use only flat image graphs
plots_force_interactive: False # Try to use only interactive javascript graphs
plots_flat_numseries: 100 # If neither of the above, use flat if > this number of datasets
num_datasets_plot_limit: 50 # If interactive, don't plot on load if > this number of datasets
max_table_rows: 500 # Swap tables for a beeswarm plot above this
# Overwrite module filename search patterns. See multiqc/utils/search_patterns.yaml
# for the defaults. Remove a default by setting it to null.
sp:
star:
fn: '*Log.final.out'
cutadapt:
fn: 'cutadapt.txt'
fastp:
fn: '*fastp*json'
#rna_seqc/metrics:
# fn: "*metrics.tsv"
#rna_seqc/coverage:
# fn: "*coverage.tsv"
# Overwrite the defaults of which table columns are visible by default
#
read_count_prefix: ''
read_count_multiplier: 1
table_columns_visible:
FastQC:
percent_fails: False
total_sequences: True
percent_gc: False
fastp:
pct_duplication: False
after_filtering_gc_content: False
Bowtie 1:
reads_aligned_percentage: False
reads_aligned: False
picard:
PERCENT_DUPLICATION: False
top_modules:
- fastqc
- fastp
- bowtie1
- bowtie2
- salmon
- star
- featureCounts
module_order:
- fastqc
- fastp
- rseqc
- markduplicates
- picard
- bowtie1
- bowtie2
- salmon
- star
- featureCounts
remove_sections:
- fastqc_status_checks
- fastqc_per_base_n_content
#fastqc_config:
#fastqc_theoretical_gc: 'mm10_genome'
#