CI
c106022744
Build pipeline: viash-hub.rnaseq.main-g2rlq
Source commit: 1d87dc7c24
Source message: Multiple fixes (#23)
* multiple fixes
* update arguments and add test
* fix biobox module calls
* fix dependency
* add rsem merge counts
* exclude general stats in multiqc report
* output markduplicates metrics
* rename output reference files
165 lines
4.6 KiB
YAML
165 lines
4.6 KiB
YAML
report_comment: >
|
|
This report has been generated by the <a href="https://github.com/viash-hub/rnaseq" </a>
|
|
analysis pipeline.
|
|
report_section_order:
|
|
"rnaseq-methods-description":
|
|
order: -1000
|
|
software_versions:
|
|
order: -1001
|
|
"rnaseq.vsh-summary":
|
|
order: -1002
|
|
|
|
export_plots: true
|
|
disable_version_detection: true
|
|
|
|
# Run only these modules
|
|
run_modules:
|
|
- custom_content
|
|
- fastqc
|
|
- cutadapt
|
|
- fastp
|
|
- sortmerna
|
|
- star
|
|
- rsem
|
|
- salmon
|
|
- kallisto
|
|
- samtools
|
|
- picard
|
|
- preseq
|
|
- rseqc
|
|
- qualimap
|
|
|
|
# Order of modules
|
|
top_modules:
|
|
- "fail_trimming"
|
|
- "fail_mapping"
|
|
- "fail_strand"
|
|
- "star_rsem_deseq2_pca"
|
|
- "star_rsem_deseq2_clustering"
|
|
- "star_salmon_deseq2_pca"
|
|
- "star_salmon_deseq2_clustering"
|
|
- "salmon_deseq2_pca"
|
|
- "salmon_deseq2_clustering"
|
|
- "kallisto_deseq2_pca"
|
|
- "kallisto_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:
|
|
- "*.read_*.fastqc.zip"
|
|
- cutadapt
|
|
- fastp
|
|
- fastqc:
|
|
name: "FastQC (trimmed)"
|
|
info: "This section of the report shows FastQC results after adapter trimming."
|
|
path_filters:
|
|
- "*.trimgalore.read_*.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_extn:
|
|
# - ".mapping_quality"
|
|
# - ".MarkDuplicates_flagstat.output.flagstat"
|
|
# - ".MarkDuplicates_idxstats.output.idxstats"
|
|
# - ".MarkDuplicates_stats.output.txt"
|
|
# - ".genome_sorted_MarkDuplicates.output.bam"
|
|
# - ".genome_sorted_MarkDuplicates"
|
|
- ".read_1"
|
|
- ".read_2"
|
|
|
|
# See https://github.com/ewels/MultiQC_TestData/blob/master/data/custom_content/with_config/table_headerconfig/multiqc_config.yaml
|
|
custom_data:
|
|
fail_trimming:
|
|
section_name: "WARNING: Fail Trimming Check"
|
|
description: "List of samples that failed the minimum trimmed reads threshold specified via the '--min_trimmed_reads' parameter, and hence were ignored for the downstream processing steps."
|
|
plot_type: "table"
|
|
pconfig:
|
|
id: "fail_trimmed_samples_table"
|
|
table_title: "Samples failed trimming threshold"
|
|
namespace: "Samples failed trimming threshold"
|
|
format: "{:.0f}"
|
|
fail_mapping:
|
|
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:
|
|
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}"
|
|
|
|
# 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:
|
|
|
|
fastqc/zip:
|
|
fn: "*.fastqc.zip"
|
|
|
|
cutadapt:
|
|
fn: "*.trimming_report*.txt"
|
|
|
|
fastp:
|
|
fn: "*.fastp_out.json"
|
|
|
|
sortmerna:
|
|
fn: "*sortmerna*.log"
|
|
|
|
star:
|
|
fn: "*.star_align_reads.log.txt"
|
|
|
|
# hisat2:
|
|
# fn: "*.hisat2.summary.log"
|
|
# salmon:
|
|
# fn: "*meta_info.json"
|
|
|
|
preseq:
|
|
fn: "*.lc_extrap.txt"
|
|
|
|
samtools/stats:
|
|
fn: "*_stats.output.txt"
|
|
samtools/flagstat:
|
|
fn: "*_flagstat.output.flagstat"
|
|
samtools/idxstats:
|
|
fn: "*_idxstats.output.idxstats"
|
|
|
|
rseqc/bam_stat:
|
|
fn: "*.mapping_quality.txt"
|
|
rseqc/junction_saturation:
|
|
fn: "*.junction_saturation_plot.r"
|
|
rseqc/junction_annotation:
|
|
fn: "*.junction_annotation.log"
|
|
rseqc/read_duplication_pos:
|
|
fn: "*.duplication_rate_mapping.xls"
|
|
rseqc/read_distribution:
|
|
fn: "*.read_distribution.txt"
|
|
rseqc/infer_experiment:
|
|
fn: "*.strandedness.txt"
|
|
rseqc/inner_distance:
|
|
fn: "*.inner_distance_freq.txt"
|
|
rseqc/tin:
|
|
fn: "*.tin_summary.txt"
|
|
|
|
picard/markdups:
|
|
fn: "*.MarkDuplicates.metrics.txt"
|
|
|
|
skip_versions_section: true
|