Merge pull request #480 from genomic-medicine-sweden/multiqc_update

feat: updated multiqc for version info

config/config.yaml

@@ -223,7 +223,7 @@ msisensor_pro:
   extra: "-c 50"
 
 multiqc:
-  container: "docker://hydragenetics/multiqc:1.11"
+  container: "docker://hydragenetics/multiqc:1.21"
   reports:
     DNA:
       config: "config/reports/multiqc_config_dna.yaml"
@@ -239,7 +239,7 @@ multiqc:
         - "qc/samtools_stats/{sample}_{type}.samtools-stats.txt"
         - "qc/gatk_calculate_contamination/{sample}_{type}.contamination.table"
     DNA_umi:
-      config: "config/multiqc_config_dna.yaml"
+      config: "config/reports/multiqc_config_dna.yaml"
       included_unit_types: ["N", "T"]
       deduplication: ["umi"]
       qc_files:

config/reports/multiqc_config_dna.yaml

@@ -19,7 +19,7 @@ custom_data:
   contamination_table:
     file_format: "tsv"
     section_name: "Contamination"
-    description: "This data comes from files acommpanied by a mutliqc_config_dna.yaml file for configuration"
+    description: "This data comes from files accompanied by a multiqc_config_dna.yaml file for configuration"
     plot_type: "generalstats"
     pconfig:
       - contamination:
@@ -31,18 +31,19 @@ sp:
     fn: "*.contamination.table"
 
 table_columns_visible:
-  Picard:
-    PCT_PF_READS_ALIGNED: True
+  "Picard: HsMetrics":
     FOLD_ENRICHMENT: False
     PCT_TARGET_BASES_30X: False
-    summed_median: False
+  "Picard: InsertSizeMetrics":
+    summed_median: True
     summed_mean: False
+  "Picard: Mark Duplicates":
     PERCENT_DUPLICATION: True
-  Samtools:
+  "Samtools: stats":
     error_rate: False
     non-primary_alignments: False
-    reads_mapped: False
-    reads_mapped_percent: False
+    reads_mapped: True
+    reads_mapped_percent: True
     reads_properly_paired_percent: False
     reads_MQ0_percent: False
     raw_total_sequences: False
@@ -54,23 +55,25 @@ table_columns_visible:
     total_sequences: False
 
 multiqc_cgs:
-  Picard:
-    PF_READS_ALIGNED:
+  "Samtools: stats":
+    reads_mapped:
       title: "M Aligned reads"
-      description: "Number of million reads in bam from Picard"
+      description: "Number of million reads in bam from Samtools stats"
       format: "{:.1f}"
       shared_key: "read_count"
+  "Picard: Mark Duplicates":
     PERCENT_DUPLICATION:
       title: "Duplicates [%]"
       description: "Duplicates [%] from Picard stats (MarkDuplicates)"
-      min: 0
-      max: 0.4
+      min: 0.2
+      max: 0.6
       scale: "RdYlGn-rev"
       format: "{:.1%}"
+  "Picard: HsMetrics":
     PCT_SELECTED_BASES:
       title: "Bases on exon target [%]"
       description: "Bases on exon target [%] from Picard"
-      min: 0.5
+      min: 0.3
       max: 0.7
       scale: "RdYlGn"
       format: "{:.1%}"
@@ -102,25 +105,12 @@ multiqc_cgs:
     MEDIAN_TARGET_COVERAGE:
       title: "Median exon target coverage"
       description: "Median exon target coverage from picard"
-    MEDIAN_INSERT_SIZE:
-      title: "Median insert size"
-      description: "Median insert size from Picard"
-      min: 70
-      max: 200
-      scale: "RdYlGn"
-      format: "{:.1f}"
-    STANDARD_DEVIATION:
-      title: "Insert size s.d."
-      description: "Insert size standard deviation from Picard"
-      min: 0
-      max: 150
-      scale: "RdYlGn-rev"
       format: "{:.1f}"
     AT_DROPOUT:
       title: "AT-dropout [%]"
       description: "AT-dropout [%] from Picard"
       min: 0
-      max: 5
+      max: 10
       scale: "RdYlGn-rev"
       format: "{:.3f}"
     GC_DROPOUT:
@@ -134,7 +124,7 @@ multiqc_cgs:
       title: "Target bases with zero coverage [%]"
       description: "Target bases with zero coverage [%] from Picard"
       min: 0
-      max: 0.05
+      max: 0.1
       scale: "RdYlGn-rev"
       format: "{:.2%}"
     FOLD_80_BASE_PENALTY:
@@ -144,21 +134,31 @@ multiqc_cgs:
       max: 3
       scale: "RdYlGn-rev"
       format: "{:.1f}"
+  "Picard: InsertSizeMetrics":
+    summed_median:
+      title: "Median insert size"
+      description: "Median insert size from Picard"
+      min: 70
+      max: 200
+      scale: "RdYlGn"
+      format: "{:.1f}"
 
 table_columns_placement:
-  Picard:
-    PF_READS_ALIGNED: 900
-    PCT_PF_READS_ALIGNED: 910
+  "Samtools: stats":
+    reads_mapped: 900
+    reads_mapped_percent: 910
+  "Picard: Mark Duplicates":
     PERCENT_DUPLICATION: 920
+  "Picard: HsMetrics":
     PCT_SELECTED_BASES: 930
     PCT_USABLE_BASES_ON_TARGET: 940
     PCT_TARGET_BASES_100X: 950
-    PCT_TARGET_BASES_500X: 960
-    MEAN_TARGET_COVERAGE: 970
-    MEDIAN_TARGET_COVERAGE: 980
-    MEDIAN_INSERT_SIZE: 990
-    STANDARD_DEVIATION: 1000
-    AT_DROPOUT: 1010
-    GC_DROPOUT: 1020
-    ZERO_CVG_TARGETS_PCT: 1030
-    FOLD_80_BASE_PENALTY: 1040
+    PCT_TARGET_BASES_500X: 955
+    MEAN_TARGET_COVERAGE: 960
+    MEDIAN_TARGET_COVERAGE: 970
+    AT_DROPOUT: 1000
+    GC_DROPOUT: 1010
+    ZERO_CVG_TARGETS_PCT: 1020
+    FOLD_80_BASE_PENALTY: 1030
+  "Picard: InsertSizeMetrics":
+    summed_median: 980

config/reports/multiqc_config_rna.yaml

@@ -22,14 +22,15 @@ custom_content:
     - picard
 
 table_columns_visible:
-  Picard:
-    PCT_PF_READS_ALIGNED: True
+  "Picard: HsMetrics":
     FOLD_ENRICHMENT: False
     PCT_TARGET_BASES_30X: False
+  "Picard: InsertSizeMetrics":
     summed_median: False
     summed_mean: False
+  "Picard: Mark Duplicates":
     PERCENT_DUPLICATION: True
-  Samtools:
+  "Samtools: stats":
     error_rate: False
     non-primary_alignments: False
     reads_mapped: False
@@ -45,19 +46,21 @@ table_columns_visible:
     total_sequences: False
 
 multiqc_cgs:
-  Picard:
-    PF_READS_ALIGNED:
+  "Samtools: stats":
+    reads_mapped:
       title: "M Aligned reads"
-      description: "Number of million reads in bam from Picard"
+      description: "Number of million reads in bam from Samtools stats"
       format: "{:.1f}"
       shared_key: "read_count"
+  "Picard: Mark Duplicates":
     PERCENT_DUPLICATION:
       title: "Duplicates [%]"
       description: "Duplicates [%] from Picard stats (MarkDuplicates)"
       min: 0
       max: 0.4
       scale: "RdYlGn-rev"
       format: "{:.1%}"
+  "Picard: HsMetrics":
     PCT_SELECTED_BASES:
       title: "Bases on target [%]"
       description: "Bases on target [%] from Picard"
@@ -67,7 +70,6 @@ multiqc_cgs:
       format: "{:.1%}"
     PCT_USABLE_BASES_ON_TARGET:
       title: "Usable bases [%]"
-      format: "{:.0%}"
       description: "Bases aligned, on target, and dedup [%] from Picard"
       min: 0.1
       max: 0.7
@@ -87,20 +89,7 @@ multiqc_cgs:
     MEDIAN_TARGET_COVERAGE:
       title: "Median target coverage"
       description: "Median target coverage from picard"
-    MEDIAN_INSERT_SIZE:
-      title: "Median insert size"
-      description: "Median insert size from Picard"
-      min: 70
-      max: 200
-      scale: "RdYlGn"
       format: "{:.1f}"
-    STANDARD_DEVIATION:
-      title: "Insert size s.d."
-      description: "Insert size standard deviation from Picard"
-      min: 0
-      max: 150
-      scale: "RdYlGn-rev"
-      format: "{:.1%}"
     AT_DROPOUT:
       title: "AT-dropout [%]"
       description: "AT-dropout [%] from Picard"
@@ -129,22 +118,39 @@ multiqc_cgs:
       max: 10
       scale: "RdYlGn-rev"
       format: "{:.1f}"
+  "Picard: InsertSizeMetrics":
+    MEDIAN_INSERT_SIZE:
+      title: "Median insert size"
+      description: "Median insert size from Picard"
+      min: 70
+      max: 200
+      scale: "RdYlGn"
+      format: "{:.1f}"
+    STANDARD_DEVIATION:
+      title: "Insert size s.d."
+      description: "Insert size standard deviation from Picard"
+      min: 0
+      max: 150
+      scale: "RdYlGn-rev"
+      format: "{:.1%}"
 
 table_columns_placement:
-  Picard:
-    PF_READS_ALIGNED: 900
-    PCT_PF_READS_ALIGNED: 901
-    PERCENT_DUPLICATION: 902
-    PCT_PF_READS_ALIGNED: 910
+  "Samtools: stats":
+    reads_mapped: 900
+    reads_mapped_percent: 910
+  "Picard: Mark Duplicates":
     PERCENT_DUPLICATION: 920
+  "Picard: HsMetrics":
     PCT_SELECTED_BASES: 930
     PCT_USABLE_BASES_ON_TARGET: 940
     PCT_TARGET_BASES_100X: 950
     MEAN_TARGET_COVERAGE: 960
     MEDIAN_TARGET_COVERAGE: 970
-    MEDIAN_INSERT_SIZE: 980
-    STANDARD_DEVIATION: 990
     AT_DROPOUT: 1000
     GC_DROPOUT: 1010
     ZERO_CVG_TARGETS_PCT: 1020
     FOLD_80_BASE_PENALTY: 1030
+  "Picard: InsertSizeMetrics":
+    MEDIAN_INSERT_SIZE: 980
+    STANDARD_DEVIATION: 990
+

workflow/Snakefile

@@ -297,7 +297,7 @@ use rule * from filtering exclude all as filtering_*
 
 module qc:
     snakefile:
-        get_module_snakefile(config, "hydra-genetics/qc", path="workflow/Snakefile", tag="v0.3.0")
+        get_module_snakefile(config, "hydra-genetics/qc", path="workflow/Snakefile", tag="v0.5.0")
     config:
         config
 
@@ -329,14 +329,6 @@ use rule samtools_stats from qc as qc_samtools_stats with:
 
 
 use rule samtools_stats from qc as qc_samtools_stats_rna with:
-    input:
-        bam="alignment/samtools_merge_bam/{sample}_{type}.bam",
-    params:
-        extra="%s -t %s"
-        % (
-            config.get("samtools_stats", {}).get("extra", ""),
-            config.get("reference", {}).get("design_bed_rna", ""),
-        ),
     wildcard_constraints:
         type="R",
 

workflow/schemas/singularity.schema.yaml

@@ -257,7 +257,7 @@ properties:
         type: string
         description: name or path to a default docker/singularity container
         pattern: >-
-            hydragenetics/multiqc:1\.11$|hydragenetics_multiqc_1\.11\.sif$
+            hydragenetics/multiqc:1\.21$|hydragenetics_multiqc_1\.21\.sif$
       required:
         - container