workflows/quality_control

Description

A subworkflow for the final quality control stage of the nf-core/rnaseq pipeline.

Type

nextflow_script

Run this component

Run the following command to execute this component with Nextflow:

cat > params.yaml <<'EOM'  
id: "run"  
strandedness: [ "unstranded" ]  
gtf_group_features: [ "gene_id" ]  
gtf_extra_attributes: [ "gene_name" ]  
skip_qc: [ false ]  
skip_align: [ false ]  
skip_preseq: [ false ]  
extra_preseq_args: [ "-verbose -bam -seed 1" ]  
featurecounts_group_type: [ "gene_biotype" ]  
featurecounts_feature_type: [ "exon" ]  
biotypes_header: [ "src/assets/multiqc/biotypes_header.txt" ]  
rseqc_modules:  
  [  
    "bam_stat,inner_distance,infer_experiment,junction_annotation,junction_sa\  
      turation,read_distribution,read_duplication"  
  ]  
sample_size: [ 200000 ]  
lower_bound_size: [ -250 ]  
upper_bound_size: [ 250 ]  
step_size: [ 5 ]  
map_qual: [ 30 ]  
min_intron: [ 50 ]  
min_splice_read: [ 1 ]  
sampling_percentile_lower_bound: [ 5 ]  
sampling_percentile_upper_bound: [ 100 ]  
sampling_percentile_step: [ 5 ]  
read_count_upper_limit: [ 500 ]  
minimum_coverage: [ 10 ]  
tin_sample_size: [ 100 ]  
output_format: [ "html" ]  
pr_bases: [ 100 ]  
tr_bias: [ 1000 ]  
algorithm: [ "uniquely-mapped-reads" ]  
sequencing_protocol: [ "non-strand-specific" ]  
java_memory_size: [ "4G" ]  
pca_header_multiqc: [ "src/assets/multiqc/deseq2_pca_header.txt" ]  
clustering_header_multiqc: [ "src/assets/multiqc/deseq2_clustering_header.txt" ]  
extra_deseq2_args: [ "--id_col 1 --sample_suffix '' --outprefix deseq2 --count_col 3" ]  
extra_deseq2_args2: [ "star_salmon" ]  
preseq_output: "$id.$key.preseq_output"  
bamstat_output: "$id.$key.bamstat_output"  
strandedness_output: "$id.$key.strandedness_output"  
inner_dist_output_stats: "$id.$key.inner_dist_output_stats"  
inner_dist_output_dist: "$id.$key.inner_dist_output_dist"  
inner_dist_output_freq: "$id.$key.inner_dist_output_freq"  
inner_dist_output_plot: "$id.$key.inner_dist_output_plot"  
inner_dist_output_plot_r: "$id.$key.inner_dist_output_plot_r"  
junction_annotation_output_log: "$id.$key.junction_annotation_output_log"  
junction_annotation_output_plot_r: "$id.$key.junction_annotation_output_plot_r"  
junction_annotation_output_junction_bed: "$id.$key.junction_annotation_output_junction_bed"  
junction_annotation_output_junction_interact: "$id.$key.junction_annotation_output_junction_interact"  
junction_annotation_output_junction_sheet: "$id.$key.junction_annotation_output_junction_sheet"  
junction_annotation_output_splice_events_plot: "$id.$key.junction_annotation_output_splice_events_plot"  
junction_annotation_output_splice_junctions_plot: "$id.$key.junction_annotation_output_splice_junctions_plot"  
junction_saturation_output_plot_r: "$id.$key.junction_saturation_output_plot_r"  
junction_saturation_output_plot: "$id.$key.junction_saturation_output_plot"  
read_distribution_output: "$id.$key.read_distribution_output"  
read_duplication_output_duplication_rate_plot_r: "$id.$key.read_duplication_output_duplication_rate_plot_r"  
read_duplication_output_duplication_rate_plot: "$id.$key.read_duplication_output_duplication_rate_plot"  
read_duplication_output_duplication_rate_mapping: "$id.$key.read_duplication_output_duplication_rate_mapping"  
read_duplication_output_duplication_rate_sequence: "$id.$key.read_duplication_output_duplication_rate_sequence"  
tin_output_summary: "$id.$key.tin_output_summary"  
tin_output_metrics: "$id.$key.tin_output_metrics"  
dupradar_output_dupmatrix: "$id.$key.dupradar_output_dupmatrix"  
dupradar_output_dup_intercept_mqc: "$id.$key.dupradar_output_dup_intercept_mqc"  
dupradar_output_duprate_exp_boxplot: "$id.$key.dupradar_output_duprate_exp_boxplot"  
dupradar_output_duprate_exp_densplot: "$id.$key.dupradar_output_duprate_exp_densplot"  
dupradar_output_duprate_exp_denscurve_mqc: "$id.$key.dupradar_output_duprate_exp_denscurve_mqc"  
dupradar_output_expression_histogram: "$id.$key.dupradar_output_expression_histogram"  
dupradar_output_intercept_slope: "$id.$key.dupradar_output_intercept_slope"  
qualimap_output_pdf: "$id.$key.qualimap_output_pdf"  
qualimap_output_dir: "$id.$key.qualimap_output_dir"  
deseq2_output: "$id.$key.deseq2_output"  
deseq2_output_pseudo: "$id.$key.deseq2_output_pseudo"  
multiqc_report: "$id.$key.multiqc_report"  
multiqc_data: "$id.$key.multiqc_data"  
multiqc_plots: "$id.$key.multiqc_plots"  
featurecounts: "$id.$key.featurecounts"  
featurecounts_summary: "$id.$key.featurecounts_summary"  
featurecounts_multiqc: "$id.$key.featurecounts_multiqc"  
featurecounts_rrna_multiqc: "$id.$key.featurecounts_rrna_multiqc"  
tpm_gene: "$id.$key.tpm_gene"  
counts_gene: "$id.$key.counts_gene"  
counts_gene_length_scaled: "$id.$key.counts_gene_length_scaled"  
counts_gene_scaled: "$id.$key.counts_gene_scaled"  
tpm_transcript: "$id.$key.tpm_transcript"  
counts_transcript: "$id.$key.counts_transcript"  
quant_merged_summarizedexperiment: "$id.$key.quant_merged_summarizedexperiment"  
pseudo_tpm_gene: "$id.$key.pseudo_tpm_gene"  
pseudo_counts_gene: "$id.$key.pseudo_counts_gene"  
pseudo_counts_gene_length_scaled: "$id.$key.pseudo_counts_gene_length_scaled"  
pseudo_counts_gene_scaled: "$id.$key.pseudo_counts_gene_scaled"  
pseudo_tpm_transcript: "$id.$key.pseudo_tpm_transcript"  
pseudo_counts_transcript: "$id.$key.pseudo_counts_transcript"  
pseudo_quant_merged_summarizedexperiment: "$id.$key.pseudo_quant_merged_summarizedexperiment"  
publish_dir: "output/"  
EOM

nextflow run https://packages.viash-hub.com/vsh/rnaseq.git \  
  -revision v0.1.1 \  
  -main-script target/nextflow/workflows/quality_control/main.nf \  
  -params-file params.yaml

Input

Name	Type & Properties	Description
--id	string required	ID of the sample
--strandedness	string	Sample strand-specificity. Must be one of unstranded, forward, reverse
--paired	boolean	Paired-end reads?
--genome_bam	file	Input genome BAM file
--genome_bam_index	file	Genome BAM index file
--gene_bed	file	Path to BED file containing gene intervals. This will be created from the GTF file if not specified.
--gtf	file	GTF file
--gtf_group_features	string	Define the attribute type used to group features in the GTF file when running Salmon.
--gtf_extra_attributes	string	By default, the pipeline uses the gene_name field to obtain additional gene identifiers from the input GTF file when running Salmon.
--quant_out_dir	file	Directory containing Salmon quantification results.
--quant_results_file	file	Salmon quantification file.
--pseudo_quant_out_dir	file	Directory containing quantification results for pseudo alignment.
--pseudo_salmon_quant_results_file	file	Quantification file from Salmon for pseudo alignment.
--pseudo_kallisto_quant_results_file	file	Quantification file from Kallisto for pseudo alignment.
--aligner	string	Method used for alognment and qqunatification.
--pseudo_aligner	string	Method used for pseudo alignment and quantification.
--rsem_counts_gene	file	Expression counts on gene level
--rsem_counts_transcripts	file	Expression counts on transcript level
--skip_qc	boolean
--skip_biotype_qc	boolean
--skip_align	boolean
--skip_pseudo_align	boolean
--skip_preseq	boolean
--extra_preseq_args	string
--featurecounts_group_type	string	The attribute type used to group feature types in the GTF file when generating the biotype plot with featureCounts.
--featurecounts_feature_type	string	By default, the pipeline assigns reads based on the 'exon' attribute within the GTF file.
--gencode	boolean	Specify if the GTF annotation is in GENCODE format.
--biotypes_header	file
--biotype	string	Biotype value to use while appending entries to GTF file when additional fasta file is provided.
--extra_featurecounts_args	string	Extra arguments to pass to featureCounts command in addition to defaults defined by the pipeline
--rseqc_modules	string multiple	Specify the RSeQC modules to run_wf
--sample_size	integer	Numer of reads sampled from SAM/BAM file to infer experiment and calculate inner distance, default = 200000.
--lower_bound_size	integer	Lower bound of inner distance (bp). This option is used for ploting histograme, default = -250.
--upper_bound_size	integer	Upper bound of inner distance (bp). This option is used for ploting histograme, default = 250.
--step_size	integer	Step size (bp) of histograme of inner distance. This option is used for plotting histogram, default = 5.
--map_qual	integer	Minimum mapping quality (phred scaled) to determine uniquely mapped reads, default = 30.
--min_intron	integer	Minimum intron length (bp) to call a junction, default = 50.
--min_splice_read	integer	Minimum number of supporting reads to call a junction, default = 1.
--sampling_percentile_lower_bound	integer	Read sampling for junction saturation starts from this percentile, must be an integer between 0 and 100, default = 5.
--sampling_percentile_upper_bound	integer	Read sampling for junction saturation ends at this percentile, must be an integer between 0 and 100, default = 5.
--sampling_percentile_step	integer	Read sampling for junction saturation frequency in %. Smaller value means more sampling times. Must be an integer between 0 and 100, default = 5.
--read_count_upper_limit	integer	Upper limit of reads' occurence to determine read duplication. Only used for plotting, default = 500 (times).
--minimum_coverage	integer	Minimum number of reads mapped to a transcript to determin tin, default = 10.
--tin_sample_size	integer	Number of equal-spaced nucleotide positions picked from mRNA. Note, if this number is larger than the length of mRNA (L), it will be halved until it's smaller than L (default = 100)
--subtract_background	boolean_true	Set flag to subtract background noise (estimated from intronic reads) to determine tin. Only use this option if there are substantial intronic reads.
--output_format	string	Format of the qualimap output report (PDF or HTML, default is HTML)
--pr_bases	integer	Number of upstream/downstream nucleotide bases to compute 5'-3' bias for qualimap (default = 100).
--tr_bias	integer	Number of top highly expressed transcripts to compute 5'-3' bias for qualimap (default = 1000).
--algorithm	string	Counting algorithm for qualimap (uniquely-mapped-reads (default) or proportional).
--sequencing_protocol	string	Sequencing library protocol for qualimap (strand-specific-forward, strand-specific-reverse or non-strand-specific (default)).
--sorted	boolean_true	Setting this flag indicates that the input file is already sorted by name. If flag is not set, additional sorting by name will be performed for qualimap. Only requiredfor paired-end analysis.
--java_memory_size	string	maximum Java heap memory size for qualimap, default = 4G.
--skip_deseq2_qc	boolean
--pca_header_multiqc	file
--clustering_header_multiqc	file
--deseq2_vst	boolean	Use vst transformation instead of rlog with DESeq2
--extra_deseq2_args	string
--extra_deseq2_args2	string
--multiqc_custom_config	file
--multiqc_title	string
--multiqc_methods_description	file
--passed_trimmed_reads	boolean
--num_trimmed_reads	double
--passed_mapping	boolean
--percent_mapped	double
--fastqc_zip_1	file
--fastqc_zip_2	file
--trim_zip_1	file
--trim_zip_2	file
--trim_log_1	file
--trim_log_2	file
--sortmerna_multiqc	file
--star_multiqc	file
--rsem_multiqc	file
--genome_bam_stats	file
--genome_bam_flagstat	file
--genome_bam_idxstats	file
--markduplicates_multiqc	file
--pseudo_multiqc	file

Name

Type & Properties

--id

string

required

--strandedness

string

--paired

boolean

--genome_bam

file

--genome_bam_index

file

--gene_bed

file

--gtf

file

--gtf_group_features

string

--gtf_extra_attributes

string

--quant_out_dir

file

--quant_results_file

file

--pseudo_quant_out_dir

file

--pseudo_salmon_quant_results_file

file

--pseudo_kallisto_quant_results_file

file

--aligner

string

--pseudo_aligner

string

--rsem_counts_gene

file

--rsem_counts_transcripts

file

--skip_qc

boolean

--skip_biotype_qc

boolean

--skip_align

boolean

--skip_pseudo_align

boolean

--skip_preseq

boolean

--extra_preseq_args

string

--featurecounts_group_type

string

--featurecounts_feature_type

string

--gencode

boolean

--biotypes_header

file

--biotype

string

--extra_featurecounts_args

string

--rseqc_modules

string

multiple

--sample_size

integer

--lower_bound_size

integer

--upper_bound_size

integer

--step_size

integer

--map_qual

integer

--min_intron

integer

--min_splice_read

integer

--sampling_percentile_lower_bound

integer

--sampling_percentile_upper_bound

integer

--sampling_percentile_step

integer

--read_count_upper_limit

integer

--minimum_coverage

integer

--tin_sample_size

integer

--subtract_background

boolean_true

--output_format

string

--pr_bases

integer

--tr_bias

integer

--algorithm

string

--sequencing_protocol

string

--sorted

boolean_true

--java_memory_size

string

--skip_deseq2_qc

boolean

--pca_header_multiqc

file

--clustering_header_multiqc

file

--deseq2_vst

boolean

--extra_deseq2_args

string

--extra_deseq2_args2

string

--multiqc_custom_config

file

--multiqc_title

string

--multiqc_methods_description

file

--passed_trimmed_reads

boolean

--num_trimmed_reads

double

--passed_mapping

boolean

--percent_mapped

double

--fastqc_zip_1

file

--fastqc_zip_2

file

--trim_zip_1

file

--trim_zip_2

file

--trim_log_1

file

--trim_log_2

file

--sortmerna_multiqc

file

--star_multiqc

file

--rsem_multiqc

file

--genome_bam_stats

file

--genome_bam_flagstat

file

--genome_bam_idxstats

file

--markduplicates_multiqc

file

--pseudo_multiqc

file

Output

Name	Type & Properties	Description
--preseq_output	file output
--bamstat_output	file output	Path to output file (txt) of mapping quality statistics
--strandedness_output	file output	Path to output report (txt) of inferred strandedness
--inner_dist_output_stats	file output	output file (txt) with summary statistics of inner distances of paired reads
--inner_dist_output_dist	file output	output file (txt) with inner distances of all paired reads
--inner_dist_output_freq	file output	output file (txt) with frequencies of inner distances of all paired reads
--inner_dist_output_plot	file output	output file (pdf) with histogram plot of of inner distances of all paired reads
--inner_dist_output_plot_r	file output	output file (R) with script of histogram plot of of inner distances of all paired reads
--junction_annotation_output_log	file output	output log of junction annotation script
--junction_annotation_output_plot_r	file output	R script to generate splice_junction and splice_events plot
--junction_annotation_output_junction_bed	file output	junction annotation file (bed format)
--junction_annotation_output_junction_interact	file output	interact file (bed format) of junctions. Can be uploaded to UCSC genome browser or converted to bigInteract (using bedToBigBed program) for visualization.
--junction_annotation_output_junction_sheet	file output	junction annotation file (xls format)
--junction_annotation_output_splice_events_plot	file output	plot of splice events (pdf)
--junction_annotation_output_splice_junctions_plot	file output	plot of junctions (pdf)
--junction_saturation_output_plot_r	file output	r script to generate junction_saturation_plot plot
--junction_saturation_output_plot	file output	plot of junction saturation (pdf
--read_distribution_output	file output	output file (txt) of read distribution analysis.
--read_duplication_output_duplication_rate_plot_r	file output	R script for generating duplication rate plot
--read_duplication_output_duplication_rate_plot	file output	duplication rate plot (pdf)
--read_duplication_output_duplication_rate_mapping	file output	Summary of mapping-based read duplication
--read_duplication_output_duplication_rate_sequence	file output	Summary of sequencing-based read duplication
--tin_output_summary	file output	summary statistics (txt) of calculated TIN metrics
--tin_output_metrics	file output	file with TIN metrics (xls)
--dupradar_output_dupmatrix	file output	path to output file (txt) of duplicate tag counts
--dupradar_output_dup_intercept_mqc	file output	path to output file (txt) of multiqc intercept value DupRadar
--dupradar_output_duprate_exp_boxplot	file output	path to output file (pdf) of distribution of expression box plot
--dupradar_output_duprate_exp_densplot	file output	path to output file (pdf) of 2D density scatter plot of duplicate tag counts
--dupradar_output_duprate_exp_denscurve_mqc	file output	path to output file (pdf) of density curve of gene duplication multiqc
--dupradar_output_expression_histogram	file output	path to output file (pdf) of distribution of RPK values per gene histogram
--dupradar_output_intercept_slope	file output
--qualimap_output_pdf	file output
--qualimap_output_dir	file output
--deseq2_output	file output
--deseq2_output_pseudo	file output
--multiqc_report	file output
--multiqc_data	file output
--multiqc_plots	file output
--featurecounts	file output
--featurecounts_summary	file output
--featurecounts_multiqc	file output
--featurecounts_rrna_multiqc	file output
--tpm_gene	file output
--counts_gene	file output
--counts_gene_length_scaled	file output
--counts_gene_scaled	file output
--tpm_transcript	file output
--counts_transcript	file output
--quant_merged_summarizedexperiment	file output
--pseudo_tpm_gene	file output
--pseudo_counts_gene	file output
--pseudo_counts_gene_length_scaled	file output
--pseudo_counts_gene_scaled	file output
--pseudo_tpm_transcript	file output
--pseudo_counts_transcript	file output
--pseudo_quant_merged_summarizedexperiment	file output

Name

Type & Properties

--preseq_output

file

output

--bamstat_output

file

output

--strandedness_output

file

output

--inner_dist_output_stats

file

output

--inner_dist_output_dist

file

output

--inner_dist_output_freq

file

output

--inner_dist_output_plot

file

output

--inner_dist_output_plot_r

file

output

--junction_annotation_output_log

file

output

--junction_annotation_output_plot_r

file

output

--junction_annotation_output_junction_bed

file

output

--junction_annotation_output_junction_interact

file

output

--junction_annotation_output_junction_sheet

file

output

--junction_annotation_output_splice_events_plot

file

output

--junction_annotation_output_splice_junctions_plot

file

output

--junction_saturation_output_plot_r

file

output

--junction_saturation_output_plot

file

output

--read_distribution_output

file

output

--read_duplication_output_duplication_rate_plot_r

file

output

--read_duplication_output_duplication_rate_plot

file

output

--read_duplication_output_duplication_rate_mapping

file

output

--read_duplication_output_duplication_rate_sequence

file

output

--tin_output_summary

file

output

--tin_output_metrics

file

output

--dupradar_output_dupmatrix

file

output

--dupradar_output_dup_intercept_mqc

file

output

--dupradar_output_duprate_exp_boxplot

file

output

--dupradar_output_duprate_exp_densplot

file

output

--dupradar_output_duprate_exp_denscurve_mqc

file

output

--dupradar_output_expression_histogram

file

output

--dupradar_output_intercept_slope

file

output

--qualimap_output_pdf

file

output

--qualimap_output_dir

file

output

--deseq2_output

file

output

--deseq2_output_pseudo

file

output

--multiqc_report

file

output

--multiqc_data

file

output

--multiqc_plots

file

output

--featurecounts

file

output

--featurecounts_summary

file

output

--featurecounts_multiqc

file

output

--featurecounts_rrna_multiqc

file

output

--tpm_gene

file

output

--counts_gene

file

output

--counts_gene_length_scaled

file

output

--counts_gene_scaled

file

output

--tpm_transcript

file

output

--counts_transcript

file

output

--quant_merged_summarizedexperiment

file

output

--pseudo_tpm_gene

file

output

--pseudo_counts_gene

file

output

--pseudo_counts_gene_length_scaled

file

output

--pseudo_counts_gene_scaled

file

output

--pseudo_tpm_transcript

file

output

--pseudo_counts_transcript

file

output

--pseudo_quant_merged_summarizedexperiment

file

output