From d6db04503e0fe2d643a7f34cb915a708f490de1e Mon Sep 17 00:00:00 2001 From: Sofia Stamouli <91951607+sofstam@users.noreply.github.com> Date: Thu, 15 Dec 2022 17:04:45 +0100 Subject: [PATCH] Configuration of multiqc report --- assets/multiqc_config.yml | 207 +++++++++++++++++++++++++++++++++++++- 1 file changed, 205 insertions(+), 2 deletions(-) diff --git a/assets/multiqc_config.yml b/assets/multiqc_config.yml index e4a04a9..865879b 100644 --- a/assets/multiqc_config.yml +++ b/assets/multiqc_config.yml @@ -19,11 +19,20 @@ custom_logo_title: "nf-core/taxprofiler" run_modules: - fastqc - adapterRemoval + - bbduk + - prinseqplusplus - fastp + - filtlong - bowtie2 + - minimap2 - samtools - kraken + - kaiju + - metaphlan + - diamond - malt + - motus + - porechop - custom_content #extra_fn_clean_exts: @@ -36,16 +45,41 @@ top_modules: name: "FastQC (pre-Trimming)" path_filters: - "*raw_*fastqc.zip" + - "fastqc": + name: "Falco (pre-Trimming)" + path_filters: + - "*_raw_falco_*_report.html" - "fastp" - "adapterRemoval" + - "porechop" - "fastqc": name: "FastQC (post-Trimming)" path_filters: - - "*raw_*processed.zip" + - "*_processed_*fastqc.zip" + - "fastqc": + name: "Falco (post-Trimming)" + path_filters: + - "*_processed_falco_*_report.html" + - "bbduk" + - "prinseqplusplus" + - "filtlong" + - "bowtie2": + name: "bowtie2" + - "samtools": + name: "Samtools Stats" - "kraken": name: "Kraken" path_filters: - - "*.kraken2.report.txt" + - "*.kraken2.kraken2.report.txt" + - "kraken": + name: "Bracken" + anchor: "bracken" + target: "Bracken" + doi: "10.7717/peerj-cs.104" + info: "Estimates species abundances in metagenomics samples by probabilistically re-distributing reads in the taxonomic tree." + extra: "Note: plot title will say Kraken2 due to the first step of bracken producing the same output format as Kraken. Abundance information is currently not supported in MultiQC." + path_filters: + - "*.bracken.kraken2.report.txt" - "kraken": name: "Centrifuge" anchor: "centrifuge" @@ -55,3 +89,172 @@ top_modules: extra: "Note: plot title will say Kraken2 due to Centrifuge producing the same output format as Kraken. If activated, see the actual Kraken2 results in the section above." path_filters: - "*.centrifuge.txt" + - "malt": + name: "MALT" + - "diamond" + - "kaiju": + name: "Kaiju" + - "motus" + +#It is not possible to set placement for custom kraken and centrifuge columns. + +table_columns_placement: + FastQC (pre-Trimming): + total_sequences: 100 + avg_sequence_length: 110 + percent_duplicates: 120 + percent_gc: 130 + percent_fails: 140 + Falco (pre-Trimming): + total_sequences: 200 + avg_sequence_length: 210 + percent_duplicates: 220 + percent_gc: 230 + percent_fails: 240 + fastp: + pct_adapter: 300 + pct_surviving: 310 + pct_duplication: 320 + after_filtering_gc_content: 330 + after_filtering_q30_rate: 340 + after_filtering_q30_bases: 350 + Adapter Removal: + aligned_total: 360 + percent_aligned: 370 + percent_collapsed: 380 + percent_discarded: 390 + FastQC (post-Trimming): + total_sequences: 400 + avg_sequence_length: 410 + percent_duplicates: 420 + percent_gc: 430 + percent_fails: 440 + Falco (post-Trimming): + total_sequences: 500 + avg_sequence_length: 510 + percent_duplicates: 520 + percent_gc: 530 + percent_fails: 540 + bowtie2: + overall_alignment_rate: 600 + Samtools Stats: + raw_total_sequences: 700 + reads_mapped: 710 + reads_mapped_percent: 720 + reads_properly_paired_percent: 730 + non-primary_alignments: 740 + reads_MQ0_percent: 750 + error_rate: 760 + MALT: + Num. of queries: 1000 + Total reads: 1100 + Mappability: 1200 + Assig. Taxonomy: 1300 + Taxonomic assignment success: 1400 + Kaiju: + assigned: 2000 + "% Assigned": 2100 + "% Unclassified": 2200 + +table_columns_visible: + FastQC (pre-Trimming): + total_sequences: True + avg_sequence_length: True + percent_duplicates: True + percent_gc: True + percent_fails: False + Falco (pre-Trimming): + total_sequences: True + avg_sequence_length: True + percent_duplicates: True + percent_gc: True + percent_fails: False + fastp: + pct_adapter: True + pct_surviving: True + pct_duplication: False + after_filtering_gc_content: False + after_filtering_q30_rate: False + after_filtering_q30_bases: False + Adapter Removal: + aligned_total: True + percent_aligned: True + percent_collapsed: True + percent_discarded: False + FastQC (post-Trimming): + total_sequences: True + avg_sequence_length: True + percent_duplicates: False + percent_gc: False + percent_fails: False + Falco (post-Trimming): + total_sequences: True + avg_sequence_length: True + percent_duplicates: False + percent_gc: False + percent_fails: False + bowtie2: + overall_alignment_rate: True + Samtools Stats: + raw_total_sequences: True + reads_mapped: True + reads_mapped_percent: True + reads_properly_paired_percent: False + non-primary_alignments: False + reads_MQ0_percent: False + error_rate: False + Kraken: + "% Unclassified": True + "% Top 5": False + Bracken: + "% Unclassified": True + "% Top 5": False + Centrifuge: + "% Unclassified": True + "% Top 5": False + MALT: + Num. of queries: True + Total reads: True + Mappability: True + Assig. Taxonomy: False + Taxonomic assignment success: True + Kaiju: + assigned: False + "% Assigned": False + "% Unclassified": True +table_columns_name: + FastQC (pre-Trimming): + total_sequences: "Nr. Input Reads" + avg_sequence_length: "Length Input Reads" + percent_gc: "% GC Input Reads" + percent_duplicates: "% Dups Input Reads" + percent_fails: "% Failed Input Reads" + Falco (pre-Trimming): + total_sequences: "Nr. Input Reads" + avg_sequence_length: "Length Input Reads" + percent_gc: "% GC Input Reads" + percent_duplicates: "% Dups Input Reads" + percent_fails: "% Failed Input Reads" + FastQC (post-Trimming): + total_sequences: "Nr. Processed Reads" + avg_sequence_length: "Length Processed Reads" + percent_gc: "% GC Processed Reads" + percent_duplicates: "% Dups Processed Reads" + percent_fails: "%Failed Processed Reads" + Falco (post-Trimming): + total_sequences: "Nr. Processed Reads" + avg_sequence_length: "Length Processed Reads" + percent_gc: "% GC Processed Reads" + percent_duplicates: "% Dups Processed Reads" + percent_fails: "%Failed Processed Reads" + Samtools Stats: + raw_total_sequences: "Nr. Reads Into Mapping" + reads_mapped: "Nr. Mapped Reads" + reads_mapped_percent: "% Mapped Reads" + + +extra_fn_clean_exts: + - ".kraken2.kraken2.report.txt" + - ".centrifuge.txt" + - ".bracken.kraken2.report.txt" + - ".settings"