feat: add container and software versions to multiqc report

.tests/integration/config/config.yaml

@@ -7,7 +7,7 @@ units: "config/units.tsv"
 
 output: "config/output_list.json"
 
-default_container: "docker://hydragenetics/common:0.1.9"
+default_container: "docker://hydragenetics/common:1.11.1"
 
 modules:
   alignment: "v0.6.0"
@@ -30,6 +30,9 @@ reference:
   fasta: "reference/homo_sapiens.fasta"
   fai: "reference/homo_sapiens.fasta.fai"
   genepanels: "reference/genepanels.list"
+  str_panels_dir: "reference/str_panels"
+  str_panels:
+    - "ataxia.list"
   sites: "reference/homo_sapiens.known_indels.vcf.gz"
   wgs_intervals: "reference/homo_sapiens.wgs.interval_list"
   merge_contigs: # contigs to be merged to a single BAM for mark duplicates
@@ -218,7 +221,7 @@ mosdepth_bed:
   extra: ""
 
 multiqc:
-  container: "docker://hydragenetics/multiqc:1.11"
+  container: "docker://hydragenetics/multiqc:1.21"
   reports:
     DNA:
       config: "config/multiqc_config_DNA.yaml"
@@ -355,4 +358,4 @@ verifybamid2:
   svd_mu: "reference/1000g.phase3.100k.b38.vcf.gz.dat.mu"
 
 vt_decompose:
-  container: "docker://hydragenetics/vt:2015.11.10"
+  container: "docker://hydragenetics/vt:2015.11.10"

.tests/integration/config/multiqc_config_DNA.yaml

@@ -69,18 +69,16 @@ table_columns_visible:
     sex_het_ratio: False
     error_sex_check: True
     predicted_sex_sex_check: True
-  Picard:
-    PCT_PF_READS_ALIGNED: False
+  "Picard: HsMetrics":
+    FOLD_ENRICHMENT: False
+    MEDIAN_TARGET_COVERAGE: False
+    PCT_TARGET_BASES_30X: False
+  "Picard: InsertSizeMetrics":
     summed_median: False
     summed_mean: True
+  "Picard: Mark Duplicates":
     PERCENT_DUPLICATION: True
-    MEDIAN_COVERAGE: False
-    MEAN_COVERAGE: False
-    SD_COVERAGE: False
-    PCT_30X: False
-    PCT_TARGET_BASES_30X: False
-    FOLD_ENRICHMENT: False
-  Samtools:
+  "Samtools: stats":
     error_rate: False
     non-primary_alignments: False
     reads_mapped: True
@@ -91,7 +89,7 @@ table_columns_visible:
 
 # Patriks plug in, addera egna columner till general stats
 multiqc_cgs:
-  Picard:
+  "Picard: HsMetrics":
     FOLD_80_BASE_PENALTY:
       title: "Fold80"
       description: "Fold80 penalty from picard hs metrics"
@@ -110,21 +108,13 @@ multiqc_cgs:
       max: 100
       scale: "RdYlGn-rev"
       format: "{:.2%}"
-  Samtools:
+  "Samtools: stats":
     average_quality:
       title: "Average Quality"
       description: "Ratio between the sum of base qualities and total length from Samtools stats"
       min: 0
       max: 60
       scale: "RdYlGn"
-  mosdepth:
-     20_x_pc: #Cant get it to work
-        title: "20x percent"
-        description: "Fraction of genome with at least 20X coverage"
-        max: 100
-        min: 0
-        suffix: "%"
-        scale: "RdYlGn"
 
 # Galler alla kolumner oberoende pa module!
 table_columns_placement:
@@ -152,15 +142,18 @@ table_columns_placement:
     error_sex_check: 701
     predicted_sex_sex_check: 702
     family_id: 703
-  Picard:
+  "Picard: HsMetrics":
     PCT_SELECTED_BASES: 801
     FOLD_80_BASE_PENALTY: 802
     PCT_PF_READS_ALIGNED: 888
+    ZERO_CVG_TARGETS_PCT: 888
+  "Picard: InsertSizeMetrics":
     summed_median: 888
-    PERCENT_DUPLICATION: 803
     summed_mean: 804
+  "Picard: Mark Duplicates":
+    PERCENT_DUPLICATION: 803
+  Picard:
     STANDARD_DEVIATION: 805
-    ZERO_CVG_TARGETS_PCT: 888
     MEDIAN_COVERAGE: 888
     MEAN_COVERAGE: 888
     SD_COVERAGE: 888

.tests/integration/config/output_list.json

@@ -13,8 +13,9 @@
   "results/{sample}/cnv_sv/{sample}.svdb_merged.filtered.vcf.gz": {"name": "_copy_svdb_merged_filtered_vcf", "file": "annotate/vep_svdb/{sample}_N.merged.svdb_query.vep_annotated.filtered.vcf.gz", "types": ["N"]},
   "results/{sample}/{sample}.upd_regions.bed": {"name": "_copy_upd_regions_bed", "file": "cnv_sv/upd/{sample}_N.upd_regions.bed", "types": ["N"]},
   "results/{sample}/{sample}.contamination.html": {"name": "_copy_haplochack_contamination_report", "file": "mitochondrial/haplocheck/{sample}_N.contamination.html", "types": ["N"]},
-  "results/{sample}/{sample}.expansionhunter_stranger.vcf.gz": {"name": "_copy_stranger_vcf", "file": "cnv_sv/stranger/{sample}_N.stranger.vcf.gz", "types": ["N"]},
-  "results/{sample}/{sample}.expansionhunter_stranger.bed": {"name": "_copy_stranger_bed", "file": "cnv_sv/stranger/{sample}_N.stranger.bed", "types": ["N"]},
+  "results/{sample}/expansionhunter/{sample}.expansionhunter_stranger.vcf.gz": {"name": "_copy_stranger_vcf", "file": "cnv_sv/stranger/{sample}_N.stranger.vcf.gz", "types": ["N"]},
+  "results/{sample}/expansionhunter/{sample}.expansionhunter_stranger.bed": {"name": "_copy_stranger_bed", "file": "cnv_sv/stranger/{sample}_N.stranger.bed", "types": ["N"]},
+  "results/{sample}/expansionhunter/{sample}.expansionhunter_stranger_{panel}.bed": {"name": "_copy_stranger_bed_panel", "file": "cnv_sv/stranger/{sample}_N_{panel}.stranger.bed", "types": ["N"]},
   "results/{sample}/{sample}.coverage_analysis.xlsx": {"name": "_copy_coverage_excel", "file": "qc/create_cov_excel/{sample}_N.coverage.xlsx", "types": ["N"]},
   "results/{sample}/SMNCopyNumberCaller/{sample}.smn_charts.pdf": {"name": "_copy_smn_pdf", "file": "cnv_sv/smn_charts/smn_{sample}_N.pdf", "types": ["N"]},
   "results/{sample}/SMNCopyNumberCaller/{sample}.smn_caller.tsv": {"name": "_copy_smn_tsv", "file": "cnv_sv/smn_caller/{sample}_N.tsv", "types": ["N"]},
@@ -25,5 +26,6 @@
   "results/{sample}/{sample}_N.cram": {"name": "_copy_samtools_cram", "file": "compression/samtools_view/{sample}_N.cram", "types": ["N"]},
   "results/{sample}/{sample}_N.cram.crai": {"name": "_copy_samtools_crai", "file": "compression/samtools_view/{sample}_N.cram.crai", "types": ["N"]},
   "results/{sample}/spring/{sample}_{type}_{flowcell}_{lane}_{barcode}.spring":  {"name": "_copy_spring", "file": "compression/spring/{sample}_{type}_{flowcell}_{lane}_{barcode}.spring", "types": ["N"]},
+  "results/peddy.html": {"name": "_copy_peddy_html", "file": "qc/peddy/peddy.html", "types": ["N"]},
   "results/multiqc_DNA.html": {"name": "_copy_multiqc_html", "file": "qc/multiqc/multiqc_DNA.html", "types": ["N"]}
 }

config/config.yaml

@@ -32,6 +32,9 @@ reference:
   genepanels: "/beegfs-storage/projects/wp3/Reference_files/Manifest/Clinical_research_exome/Gene_panels/genepanels_WGS.list"
   sites: "/beegfs-storage/data/ref_genomes/GRCh38/GRCmasked/Homo_sapiens_assembly38.known_indels.vcf.gz"
   wgs_intervals: "/beegfs-storage/data/ref_genomes/GRCh38/GRCmasked/homo_sapiens.hg38.wgs.interval_list"
+  str_panels_dir: "config/str_panels"
+  str_panels:
+    - "ataxia.list"
   merge_contigs: # contigs to be merged to a single BAM for mark duplicates
     - ".*_random"
     - "chrUn_.*"
@@ -217,7 +220,7 @@ mosdepth_bed:
   extra: ""
 
 multiqc:
-  container: "docker://hydragenetics/multiqc:1.11"
+  container: "docker://hydragenetics/multiqc:1.21"
   reports:
     DNA:
       config: "config/multiqc_config_DNA.yaml"

config/multiqc_config_DNA.yaml

@@ -3,7 +3,7 @@ subtitle: "Reference used: GRCh38"
 intro_text: "The MultiQC report summarise analysis results from WGS data that been analysed by the pipeline Poirot_RD-WGS (https://github.com/clinical-genomics-uppsala/Poirot_RD-WGS)."
 
 report_header_info:
-  - Contact E-mail: "jessika.nordin@scilifelab.uu.se"
+  - Contact E-mail: "igp-klinsek-bioinfo@lists.uu.se"
   - Application Type: "Bioinformatic analysis of WGS for rare diseases"
 
 show_analysis_paths: True
@@ -12,32 +12,20 @@ decimalPoint_format: ','
 
 extra_fn_clean_exts: ##from this until end
     - '.dup'
-    - '_N'
     - type: regex
       pattern: '_fastq[12]'
 #    - '_S'
 extra_fn_clean_trim:
   - 'Sample_VE-3297_'
-#fn_ignore_dirs:
-#fn_ignore_files:
 
-#top_modules:
-#    - "samtools"
-#    - "picard"
-#    - "fastqc"
-
-
-# https://github.com/ewels/MultiQC/blob/master/docs/customisation.md
-
-
-custom_content: # Not working
-  order:
-    - fastqc
-    - fastp
-    - mosdepth
-    - peddy
-    - samtools
-    - picard
+module_order:
+  - fastqc
+  - fastp
+  - verifybamid
+  - mosdepth
+  - peddy
+  - samtools
+  - picard
 
 table_columns_visible:
   FastQC:
@@ -70,19 +58,25 @@ table_columns_visible:
     sex_het_ratio: False
     error_sex_check: True
     predicted_sex_sex_check: True
-  Picard:
-    TOTAL_READS: False
-    PCT_PF_READS_ALIGNED: False
+  "Picard: HsMetrics":
+    FOLD_ENRICHMENT: False
+    MEDIAN_TARGET_COVERAGE: False
+    PCT_TARGET_BASES_30X: False
+  "Picard: InsertSizeMetrics":
     summed_median: False
     summed_mean: True
+  "Picard: Mark Duplicates":
     PERCENT_DUPLICATION: True
+  "Picard: WGSMetrics":
+    STANDARD_DEVIATION: False
     MEDIAN_COVERAGE: False
     MEAN_COVERAGE: False
     SD_COVERAGE: False
     PCT_30X: False
     PCT_TARGET_BASES_30X: False
     FOLD_ENRICHMENT: False
-  Samtools:
+
+  "Samtools: stats":
     error_rate: False
     non-primary_alignments: False
     reads_mapped: True
@@ -93,10 +87,10 @@ table_columns_visible:
 
 # Patriks plug in, addera egna columner till general stats
 multiqc_cgs:
-  Picard:
+  "Picard: HsMetrics":
     FOLD_80_BASE_PENALTY:
       title: "Fold80"
-      description: "Fold80 penalty from picard WGS metrics"
+      description: "Fold80 penalty from picard hs metrics"
       min: 1
       max: 3
       scale: "RdYlGn-rev"
@@ -112,26 +106,13 @@ multiqc_cgs:
       max: 100
       scale: "RdYlGn-rev"
       format: "{:.2%}"
-    TOTAL_READS:
-      title: "Total Reads"
-      description: "Total read in BAM file from Picard"
-      scale: "RdYlGn-rev"
-      format: "{:.1f}"
-  Samtools:
+  "Samtools: stats":
     average_quality:
       title: "Average Quality"
       description: "Ratio between the sum of base qualities and total length from Samtools stats"
       min: 0
       max: 60
       scale: "RdYlGn"
-  mosdepth:
-     20_x_pc: #Cant get it to work
-        title: "20x percent"
-        description: "Fraction of genome with at least 20X coverage"
-        max: 100
-        min: 0
-        suffix: "%"
-        scale: "RdYlGn"
 
 # Galler alla kolumner oberoende pa module!
 table_columns_placement:
@@ -143,7 +124,7 @@ table_columns_placement:
     20_x_pc: 603
     30_x_pc: 604
     50_x_pc: 605
-  Samtools:
+  "Samtools: stats":
     raw_total_sequences: 500
     reads_mapped: 501
     reads_mapped_percent: 502
@@ -159,16 +140,18 @@ table_columns_placement:
     error_sex_check: 701
     predicted_sex_sex_check: 702
     family_id: 703
-  Picard:
-    TOTAL_READS: 800
+  "Picard: HsMetrics":
     PCT_SELECTED_BASES: 801
     FOLD_80_BASE_PENALTY: 802
     PCT_PF_READS_ALIGNED: 888
+    ZERO_CVG_TARGETS_PCT: 888
+  "Picard: InsertSizeMetrics":
     summed_median: 888
-    PERCENT_DUPLICATION: 803
     summed_mean: 804
+  "Picard: Mark Duplicates":
+    PERCENT_DUPLICATION: 803
+  "Picard: WGSMetrics":
     STANDARD_DEVIATION: 805
-    ZERO_CVG_TARGETS_PCT: 888
     MEDIAN_COVERAGE: 888
     MEAN_COVERAGE: 888
     SD_COVERAGE: 888

config/output_list.json

@@ -13,8 +13,9 @@
   "results/{sample}/cnv_sv/{sample}.svdb_merged.filtered.vcf.gz": {"name": "_copy_svdb_merged_filtered_vcf", "file": "annotate/vep_svdb/{sample}_N.merged.svdb_query.vep_annotated.filtered.vcf.gz", "types": ["N"]},
   "results/{sample}/{sample}.upd_regions.bed": {"name": "_copy_upd_regions_bed", "file": "cnv_sv/upd/{sample}_N.upd_regions.bed", "types": ["N"]},
   "results/{sample}/{sample}.contamination.html": {"name": "_copy_haplochack_contamination_report", "file": "mitochondrial/haplocheck/{sample}_N.contamination.html", "types": ["N"]},
-  "results/{sample}/{sample}.expansionhunter_stranger.vcf.gz": {"name": "_copy_stranger_vcf", "file": "cnv_sv/stranger/{sample}_N.stranger.vcf.gz", "types": ["N"]},
-  "results/{sample}/{sample}.expansionhunter_stranger.bed": {"name": "_copy_stranger_bed", "file": "cnv_sv/stranger/{sample}_N.stranger.bed", "types": ["N"]},
+  "results/{sample}/expansionhunter/{sample}.expansionhunter_stranger.vcf.gz": {"name": "_copy_stranger_vcf", "file": "cnv_sv/stranger/{sample}_N.stranger.vcf.gz", "types": ["N"]},
+  "results/{sample}/expansionhunter/{sample}.expansionhunter_stranger.bed": {"name": "_copy_stranger_bed", "file": "cnv_sv/stranger/{sample}_N.stranger.bed", "types": ["N"]},
+  "results/{sample}/expansionhunter/{sample}.expansionhunter_stranger_{panel}.bed": {"name": "_copy_stranger_bed_panel", "file": "cnv_sv/stranger/{sample}_N_{panel}.stranger.bed", "types": ["N"]},
   "results/{sample}/{sample}.coverage_analysis.xlsx": {"name": "_copy_coverage_excel", "file": "qc/create_cov_excel/{sample}_N.coverage.xlsx", "types": ["N"]},
   "results/{sample}/SMNCopyNumberCaller/{sample}.smn_charts.pdf": {"name": "_copy_smn_pdf", "file": "cnv_sv/smn_charts/smn_{sample}_N.pdf", "types": ["N"]},
   "results/{sample}/SMNCopyNumberCaller/{sample}.smn_caller.tsv": {"name": "_copy_smn_tsv", "file": "cnv_sv/smn_caller/{sample}_N.tsv", "types": ["N"]},

config/sample_order.tsv

@@ -0,0 +1,25 @@
+Sample Order	Sample Name
+sample_001	D22-07608
+sample_002	D24-03890
+sample_003	D24-03891
+sample_004	D24-03892
+sample_005	D20-05240
+sample_006	D23-09349
+sample_007	D23-09384
+sample_008	D24-01401
+sample_009	D24-01640
+sample_010	D24-02504
+sample_011	D24-03945
+sample_012	D24-03888
+sample_013	D24-03946
+sample_014	D24-03889
+sample_015	D24-03952
+sample_016	D23-08138
+sample_017	D24-03982
+sample_018	D24-04023
+sample_019	D24-04029
+sample_020	D24-04028
+sample_021	D24-03986
+sample_022	D24-03987
+sample_023	D24-03985
+sample_024	D24-04082

config/sample_replacement.tsv

@@ -0,0 +1,24 @@
+D22-07608	sample_001
+D24-03890	sample_002
+D24-03891	sample_003
+D24-03892	sample_004
+D20-05240	sample_005
+D23-09349	sample_006
+D23-09384	sample_007
+D24-01401	sample_008
+D24-01640	sample_009
+D24-02504	sample_010
+D24-03945	sample_011
+D24-03888	sample_012
+D24-03946	sample_013
+D24-03889	sample_014
+D24-03952	sample_015
+D23-08138	sample_016
+D24-03982	sample_017
+D24-04023	sample_018
+D24-04029	sample_019
+D24-04028	sample_020
+D24-03986	sample_021
+D24-03987	sample_022
+D24-03985	sample_023
+D24-04082	sample_024

config/str_panels/ataxia.list

@@ -0,0 +1,15 @@
+ATN1
+ATXN1
+ATXN10
+ATXN2
+ATXN3
+ATXN7
+ATXN8OS
+BEAN1
+CACNA1A
+DAB1
+FGF14
+FXN
+NOP56
+PPP2R2B
+TBP

docs/requirements.txt

@@ -1,6 +1,6 @@
 jinja2<3.1.0
 mkdocs==1.4.2
-pymdown-extensions==9.10
+pymdown-extensions==10.0
 mkdocs-schema-reader==0.11.1
 mkdocs-simple-hooks==0.1.5
 mdx_spanner==0.0.5

requirements.txt

@@ -1,4 +1,4 @@
-hydra-genetics==1.11.1
+hydra-genetics==3.0.0
 pandas>=1.3.1
 pulp<2.8
 snakemake==7.26.0