diff --git a/CEN/CEN_multiqc_config_v1.0.0.yaml b/CEN/CEN_multiqc_config_v1.0.0.yaml deleted file mode 100644 index a3a9d09..0000000 --- a/CEN/CEN_multiqc_config_v1.0.0.yaml +++ /dev/null @@ -1,394 +0,0 @@ -################################################### -# Eggd MultiQC Configuration File for WES -################################################### - -# This file can be saved either in the MultiQC installation -# directory, or as ~/.multiqc_config.yaml - -# Configuration settings are taken from the following locations, in order: -# - Hardcoded in MultiQC (multiqc/utils/config.py) -# - /multiqc_config.yaml -# - ~/.multiqc_config.yaml -# - Command line options - -# Note that all of the values below are set to the MultiQC defaults. -# It's recommended that you delete any that you don't need. - -################################################################# - -# Title to use for the report. -title: East GLH MultiQC Report -subtitle: Cancer Endocrine Neurology # Grey text below title -# intro_text: null # Set to False to remove, or your own text - -# # Add generic information to the top of reports -# report_header_info: -# - Example Config:: 'This is arbitrary' -# - Another field:: 'Loaded from multiqc_config_example.yaml' -# - Something different:: 'You can put any key-value pairs here' -# - Want to know more?: 'See the MultiQC docs' -# # Specify a custom logo to add to reports (uncomment to use) -# custom_logo: 'link to egglogo.png' # '/path/to/logo.png' -# custom_logo_url: 'https://cuhbioinformatics.atlassian.net/servicedesk/customer/portal/3' # 'https://www.example.com' -# custom_logo_title: 'Bioinformatics Help Desk' # 'Our Institute Name' - -# Default output filenames -output_fn_name: multiqc_report.html -data_dir_name: multiqc_data - -# Prepend sample names with their directory. Useful if analysing the -# sample samples with different parameters. -prepend_dirs: False -# Whether to create the parsed data directory in addition to the report -make_data_dir: True - -# Cleaning options for sample names. Typically, sample names are detected -# from an input filename. If any of these strings are found, they and any -# text to their right will be discarded. -# For example - file1.fq.gz_trimmed.bam_deduplicated_fastqc.zip -# would be cleaned to 'file1' -# Two options here - fn_clean_exts will replace the defaults, -# extra_fn_clean_exts will append to the defaults -extra_fn_clean_exts: - - type: remove - pattern: '_001' - - type: remove - pattern: '.markdup' - - type: remove - pattern: '_markdup' - - type: remove - pattern: '.realigned' - - type: remove - pattern: '_metrics' - - type: remove - pattern: '.Duplication_metrics' - - type: remove - pattern: '.Duplication' - - type: remove - pattern: '.duplication' - - type: remove - pattern: '.AlignmentStat' - - type: remove - pattern: '.GCBias' - - type: remove - pattern: '.InsertSize' - - type: remove - pattern: '.MeanQualityByCycle_metrics' - - type: remove - pattern: '.QualDistribution_metrics' - # - .gz - # - .fastq - # - .fq - # - .bam - # - .sam - # - _fastqc - # - type: replace - # pattern: '.sorted' - # - type: regex - # pattern: '^Sample_\d+' - -# Ignore files larger than this when searcing for logs (bytes) -log_filesize_limit: 5000000000 -# MultiQC skips a couple of debug messages when searching files as the -# log can get very verbose otherwise. Re-enable here to help debugging. -report_readerrors: False -report_imgskips: False -# Opt-out of remotely checking that you're running the latest version -no_version_check: False - -# How to plot graphs. Different templates can override these settings, but -# the default template can use interactive plots (Javascript using HighCharts) -# or flat plots (images, using MatPlotLib). With interactive plots, the report -# can prevent automatically rendering all graphs if there are lots of samples -# to prevent the browser being locked up when the report opens. -plots_force_flat: False # Try to use only flat image graphs -plots_force_interactive: False # Try to use only interactive javascript graphs -plots_flat_numseries: 200 # If neither of the above, use flat if > this number of datasets -num_datasets_plot_limit: 100 # If interactive, don't plot on load if > this number of datasets -max_table_rows: 500 # Swap tables for a beeswarm plot above this - -# Overwrite module order displayed in report. -# See multiqc/utils/config_defaults.yaml for the defaults. -module_order: - - happy: - module_tag: - - DNA - - 'custom_content' - - verifybamid: - module_tag: - - DNA - - picard: - module_tag: - - DNA - - RNA - - sentieon: - module_tag: - - DNA - - samtools: - module_tag: - - DNA - - RNA - - fastqc: - module_tag: - - RNA - - DNA - - bcl2fastq: - module_tag: - - DNA - -# Overwrite the defaults of which table columns are visible by default -table_columns_visible: - bcl2fastq: False - FastQC: False - Picard: - FOLD_ENRICHMENT: False - verifyBAMID: - CHIPMIX: False - -# Specify order in which table columns are visible in General Statistics -table_columns_placement: - general_stats_table: - mapped_passed: 950 - FREEMIX: 960 - PCT_TARGET_BASES_20X: 970 - percent_duplicates: 980 - PCT_PF_READS_ALIGNED: 990 - summed_median: 1000 - -# Set picard configs: TARGET BASES COVERAGE -picard_config: - general_stats_target_coverage: # should be referred to as 'mqc-generalstats-picard-PCT_TARGET_BASES_20X' - - 20 # for conditional table formatting - -table_cond_formatting_colours: - - blue: '#337ab7' - - lbue: '#5bc0de' - - pass: '#5cb85c' - - warn: '#f0ad4e' - - fail: '#d9534f' - -# Set conditional formatting rules for general stats -table_cond_formatting_rules: - mqc-generalstats-picard-PCT_TARGET_BASES_20X: # Percentage of target bases at 20x - pass: # number in name depends on what is set above - - lt: 101 - warn: - - eq: 98.0 - - lt: 98.0 - fail: - - eq: 95.0 - - lt: 95.0 - mqc-generalstats-verifybamid-FREEMIX: #verifyBamId Contaminntion column in General Stats - pass: - - lt: 2 - warn: - - eq: 2 - - gt: 2 - fail: - - eq: 5 - - gt: 5 -# Set conditional formatting rules for other modules - mean_het_ratio: # vcf_qc mean het ratio column - pass: - - gt: 0 - fail: - - lt: 0.47 - - gt: 0.55 - FOLD_80_BASE_PENALTY: # Picard HSMetrics fold 80 base penalty column - pass: - - lt: 1.30 - warn: - - eq: 1.30 - - gt: 1.30 - FREEMIX: #verifyBamId Contamination column in verifybamid - pass: - - lt: 2 - warn: - - eq: 2 - - gt: 2 - fail: - - eq: 5 - - gt: 5 - METRIC_Recall_indel: # Happy indel Recall outputs - pass: - - gt: 0.830 - - eq: 0.830 - # warn: - # - lt: 0.850 - fail: - - lt: 0.830 - METRIC_Precision_indel: # Happy indel Precision outputs - pass: - - gt: 0.850 - - eq: 0.850 - # warn: - # - lt: 0.620 - fail: - - lt: 0.850 - METRIC_Recall_snp: # Happy snp Recall outputs - pass: - - eq: 1.00 - warn: - - lt: 1.00 - fail: - - lt: 0.990 - METRIC_Precision_snp: # Happy snp Precision outputs - pass: - - eq: 1.000 - warn: - - lt: 1.000 - fail: - - lt: 0.990 - Match_Sexes: # Somalier Matching Sex column - true: - - s_eq: 'pass' - fail: - - s_eq: 'fail' - warn: - - s_eq: 'NA' - original_pedigree_sex: # Somalier Reported sex column - warn: - - s_eq: 'none' - - - # all_columns: - # pass: - # - s_eq: 'pass' - # - s_eq: 'true' - # warn: - # - s_eq: 'warn' - # - s_eq: 'unknown' - # fail: - # - s_eq: 'fail' - # - s_eq: 'false' - -# Add code to include data from custom QC data files -custom_data: - vcf_qc_files: - file_format: 'tsv' - section_name: 'Het-hom analysis' - description: 'This plot comes from vcf_qc files' - plot_type: 'table' - pconfig: - id: 'het-hom_table' - table_title: 'Het-hom' - 'col1_header': 'Sample' - 'col2_header': 'mean het ratio' - 'col3_header': 'mean homo ratio' - 'col4_header': 'het:homo ratio' - 'col5_header': 'X homo:het ratio' -# 'col6_header': 'gender' - headers: - mean het ratio: - format: '{:,.2f}' - mean homo ratio: - format: '{:,.2f}' - het:homo ratio: - format: '{:,.2f}' - X homo:het ratio: - format: '{:,.2f}' -# gender: -# title: 'Inferred sex' - somalier_files: - file_format: 'tsv' - section_name: 'Somalier sex check' - description: 'Checking predicted sex is same as reported' - plot_type: 'table' - pconfig: - id: 'somalier_table' - table_title: 'Sex check' - 'col1_header': 'sample_id' - 'col7_header': 'original_pedigree_sex' - 'col19_header': 'X_depth_mean' - 'col20_header': 'X_n' - 'col21_header': 'X_hom_ref' - 'col22_header': 'X_het' - 'col23_header': 'X_hom_alt' - 'col24_header': 'Y_depth_mean' - 'col25_header': 'Y_n' - 'col26_header': 'Predicted_Sex' - 'col27_header': 'Match_Sexes' - headers: - sample_id: - title: 'Sample ID' - original_pedigree_sex: - title: 'Reported sex' - description: 'Expected sex reported from filename' - X_depth_mean: - title: 'X_depth_mean' - description: 'Mean depth on X chromosome' - X_n: - title: 'X total' - description: 'Total variant calls on X chromosome' - format: '{:,.0f}' - X_hom_ref: - title: 'X_hom_ref' - description: 'Homozygous ref variant calls on X chromosome' - format: '{:,.0f}' - X_het: - title: 'X_het' - description: 'Heterozygosity variant calls on X chromosome' - format: '{:,.0f}' - X_hom_alt: - title: 'X_hom_alt' - description: 'Homozygous alt variant calls on X chromosome' - format: '{:,.0f}' - Y_depth_mean: - title: 'Y_depth_mean' - description: 'Mean depth on Y chromosome' - Y_n: - title: 'Y_n' - description: 'Total variant calls on Y chromosome' - format: '{:,.0f}' - Predicted_Sex: - title: 'Predicted sex' - description: 'Predicted sex based on thresholds on X_het' - Match_Sexes: - title: 'Matching sex' - description: 'Whether reported and predicted sex of sample match' - -# Overwrite module filename search patterns. See multiqc/utils/search_patterns.yaml -# for the defaults. Remove a default by setting it to null. -sp: - fastqc/data: - fn: '*.stats-fastqc.txt' - #picard/alignment_metrics: - sentieon/alignment_metrics: - fn: '*.AlignmentStat_metrics.txt' - shared: true - #picard/insertsize: - sentieon/insertsize: - fn: '*.InsertSize_metrics.txt' - shared: true - picard/markdups: - fn: '*.Duplication_metrics.txt' - shared: true - #picard/gcbias: - sentieon/gcbias: - fn: '*.GCBias_metrics.txt' - shared: true - picard/quality_by_cycle: - fn: '*.MeanQualityByCycle_metrics.txt' - shared: true - picard/quality_score_distribution: - fn: '*.QualDistribution_metrics.txt' - shared: true - verifybamid/selfsm: - fn: '*.selfSM' - samtools/flagstat: - contents: 'in total (QC-passed reads + QC-failed reads)' - shared: true - vcf_qc_files: - fn: '*.vcf.QC' - happy_snp: - fn: '*snp.csv' - happy_indel: - fn: '*indel.csv' - somalier_files: - fn: '*_somalier.samples.tsv' - -# Remove plots from HTML report -# remove_sections: - -exclude_modules: - - somalier diff --git a/CEN/CEN_multiqc_config_v2.0.0.yaml b/CEN/CEN_multiqc_config_v2.0.0.yaml deleted file mode 100644 index 8e19d3a..0000000 --- a/CEN/CEN_multiqc_config_v2.0.0.yaml +++ /dev/null @@ -1,435 +0,0 @@ -################################################### -# Eggd MultiQC Configuration File for CEN -################################################### - -# This file can be saved either in the MultiQC installation -# directory, or as ~/.multiqc_config.yaml - -# Configuration settings are taken from the following locations, in order: -# - Hardcoded in MultiQC (multiqc/utils/config.py) -# - /multiqc_config.yaml -# - ~/.multiqc_config.yaml -# - Command line options - -# Note that all of the values below are set to the MultiQC defaults. -# It's recommended that you delete any that you don't need. - -################################################################# - -# Title to use for the report. -title: East GLH MultiQC Report -subtitle: Cancer Endocrine Neurology # Grey text below title -# intro_text: null # Set to False to remove, or your own text - -# # Add generic information to the top of reports -# report_header_info: -# - Example Config:: 'This is arbitrary' -# - Another field:: 'Loaded from multiqc_config_example.yaml' -# - Something different:: 'You can put any key-value pairs here' -# - Want to know more?: 'See the MultiQC docs' -# # Specify a custom logo to add to reports (uncomment to use) -# custom_logo: 'link to egglogo.png' # '/path/to/logo.png' -# custom_logo_url: 'https://cuhbioinformatics.atlassian.net/servicedesk/customer/portal/3' # 'https://www.example.com' -# custom_logo_title: 'Bioinformatics Help Desk' # 'Our Institute Name' - -# Default output filenames -output_fn_name: multiqc_report.html -data_dir_name: multiqc_data - -# Prepend sample names with their directory. Useful if analysing the -# sample samples with different parameters. -prepend_dirs: False -# Whether to create the parsed data directory in addition to the report -make_data_dir: True - -# Cleaning options for sample names. Typically, sample names are detected -# from an input filename. If any of these strings are found, they and any -# text to their right will be discarded. -# For example - file1.fq.gz_trimmed.bam_deduplicated_fastqc.zip -# would be cleaned to 'file1' -# Two options here - fn_clean_exts will replace the defaults, -# extra_fn_clean_exts will append to the defaults -extra_fn_clean_exts: - - type: remove - pattern: '_001' - - type: remove - pattern: '.markdup' - - type: remove - pattern: '_markdup' - - type: remove - pattern: '.realigned' - - type: remove - pattern: '_metrics' - - type: remove - pattern: '.Duplication_metrics' - - type: remove - pattern: '.Duplication' - - type: remove - pattern: '.duplication' - - type: remove - pattern: '.AlignmentStat' - - type: remove - pattern: '.GCBias' - - type: remove - pattern: '.InsertSize' - - type: remove - pattern: '.MeanQualityByCycle_metrics' - - type: remove - pattern: '.QualDistribution_metrics' - # - .gz - # - .fastq - # - .fq - # - .bam - # - .sam - # - _fastqc - # - type: replace - # pattern: '.sorted' - # - type: regex - # pattern: '^Sample_\d+' - -# Ignore files larger than this when searcing for logs (bytes) -log_filesize_limit: 5000000000 -# MultiQC skips a couple of debug messages when searching files as the -# log can get very verbose otherwise. Re-enable here to help debugging. -report_readerrors: False -report_imgskips: False -# Opt-out of remotely checking that you're running the latest version -no_version_check: False - -# How to plot graphs. Different templates can override these settings, but -# the default template can use interactive plots (Javascript using HighCharts) -# or flat plots (images, using MatPlotLib). With interactive plots, the report -# can prevent automatically rendering all graphs if there are lots of samples -# to prevent the browser being locked up when the report opens. -plots_force_flat: False # Try to use only flat image graphs -plots_force_interactive: False # Try to use only interactive javascript graphs -plots_flat_numseries: 200 # If neither of the above, use flat if > this number of datasets -num_datasets_plot_limit: 100 # If interactive, don't plot on load if > this number of datasets -max_table_rows: 500 # Swap tables for a beeswarm plot above this - -# Overwrite module order displayed in report. -# See multiqc/utils/config_defaults.yaml for the defaults. -module_order: - - happy: - module_tag: - - DNA - - 'custom_content' - - verifybamid: - module_tag: - - DNA - - picard: - module_tag: - - DNA - - sentieon: - module_tag: - - DNA - - samtools: - module_tag: - - DNA - - fastqc: - module_tag: - - RNA - - bcl2fastq: - module_tag: - - DNA - -# Overwrite the defaults of which table columns are visible by default -table_columns_visible: - bcl2fastq: False - FastQC: False - Picard: - FOLD_ENRICHMENT: False - verifyBAMID: - CHIPMIX: False - -# Specify order in which table columns are visible in General Statistics -table_columns_placement: - general_stats_table: - mapped_passed: 950 - FREEMIX: 960 - PCT_TARGET_BASES_20X: 970 - percent_duplicates: 980 - PCT_PF_READS_ALIGNED: 990 - summed_median: 1000 - -# Set picard configs: TARGET BASES COVERAGE -picard_config: - general_stats_target_coverage: # should be referred to as 'mqc-generalstats-picard-PCT_TARGET_BASES_20X' - - 20 # for conditional table formatting - -table_cond_formatting_colours: - - blue: '#337ab7' - - lbue: '#5bc0de' - - pass: '#5cb85c' - - warn: '#f0ad4e' - - fail: '#d9534f' - -# Set conditional formatting rules for general stats -table_cond_formatting_rules: - mqc-generalstats-picard-PCT_TARGET_BASES_20X: # Percentage of target bases at 20x - pass: # number in name depends on what is set above - - lt: 101 - warn: - - eq: 98.0 - - lt: 98.0 - fail: - - eq: 95.0 - - lt: 95.0 - mqc-generalstats-verifybamid-FREEMIX: #verifyBamId Contaminntion column in General Stats - pass: - - lt: 2 - warn: - - eq: 2 - - gt: 2 - fail: - - eq: 5 - - gt: 5 -# Set conditional formatting rules for other modules - mean_het_ratio: # vcf_qc mean het ratio column - pass: - - gt: 0 - fail: - - lt: 0.47 - - gt: 0.55 - FOLD_80_BASE_PENALTY: # Picard HSMetrics fold 80 base penalty column - pass: - - lt: 1.30 - warn: - - eq: 1.30 - - gt: 1.30 - FREEMIX: #verifyBamId Contamination column in verifybamid - pass: - - lt: 2 - warn: - - eq: 2 - - gt: 2 - fail: - - eq: 5 - - gt: 5 - METRIC_Recall_indel: # Happy indel Recall outputs - pass: - - gt: 0.830 - - eq: 0.830 - # warn: - # - lt: 0.850 - fail: - - lt: 0.830 - METRIC_Precision_indel: # Happy indel Precision outputs - pass: - - gt: 0.850 - - eq: 0.850 - # warn: - # - lt: 0.620 - fail: - - lt: 0.850 - METRIC_Recall_snp: # Happy snp Recall outputs - pass: - - eq: 1.00 - warn: - - lt: 1.00 - fail: - - lt: 0.990 - METRIC_Precision_snp: # Happy snp Precision outputs - pass: - - eq: 1.000 - warn: - - lt: 1.000 - fail: - - lt: 0.990 - Match_Sexes: # Somalier Matching Sex column - true: - - s_eq: 'pass' - fail: - - s_eq: 'fail' - warn: - - s_eq: 'NA' - original_pedigree_sex: # Somalier Reported sex column - warn: - - s_eq: 'none' - FOLD_ENRICHMENT: # Picard HSMetrics fold enrichment column - pass: - - gt: 1350 - - lt: 1650 - fail: - - lt: 1350 - - eq: 1350 - - eq: 1650 - - gt: 1650 - - - # all_columns: - # pass: - # - s_eq: 'pass' - # - s_eq: 'true' - # warn: - # - s_eq: 'warn' - # - s_eq: 'unknown' - # fail: - # - s_eq: 'fail' - # - s_eq: 'false' - -# Add code to include data from custom QC data files -custom_data: - vcf_qc_files: - file_format: 'tsv' - section_name: 'Het-hom analysis' - description: 'This plot comes from vcf_qc files' - plot_type: 'table' - pconfig: - id: 'het-hom_table' - table_title: 'Het-hom' - 'col1_header': 'Sample' - 'col2_header': 'mean het ratio' - 'col3_header': 'mean homo ratio' - 'col4_header': 'het:homo ratio' - 'col5_header': 'X homo:het ratio' - # 'col6_header': 'gender' - headers: - mean het ratio: - format: '{:,.2f}' - mean homo ratio: - format: '{:,.2f}' - het:homo ratio: - format: '{:,.2f}' - X homo:het ratio: - format: '{:,.2f}' - # gender: - # title: 'Inferred sex' - somalier_files: - file_format: 'tsv' - section_name: 'Somalier sex check' - description: 'Checking predicted sex is same as reported' - plot_type: 'table' - pconfig: - id: 'somalier_table' - table_title: 'Sex check' - 'col1_header': 'sample_id' - 'col7_header': 'original_pedigree_sex' - 'col19_header': 'X_depth_mean' - 'col20_header': 'X_n' - 'col21_header': 'X_hom_ref' - 'col22_header': 'X_het' - 'col23_header': 'X_hom_alt' - 'col24_header': 'Y_depth_mean' - 'col25_header': 'Y_n' - 'col26_header': 'Predicted_Sex' - 'col27_header': 'Match_Sexes' - headers: - sample_id: - title: 'Sample ID' - original_pedigree_sex: - title: 'Reported sex' - description: 'Expected sex reported from filename' - X_depth_mean: - title: 'X_depth_mean' - description: 'Mean depth on X chromosome' - X_n: - title: 'X total' - description: 'Total variant calls on X chromosome' - format: '{:,.0f}' - X_hom_ref: - title: 'X_hom_ref' - description: 'Homozygous ref variant calls on X chromosome' - format: '{:,.0f}' - X_het: - title: 'X_het' - description: 'Heterozygosity variant calls on X chromosome' - format: '{:,.0f}' - X_hom_alt: - title: 'X_hom_alt' - description: 'Homozygous alt variant calls on X chromosome' - format: '{:,.0f}' - Y_depth_mean: - title: 'Y_depth_mean' - description: 'Mean depth on Y chromosome' - Y_n: - title: 'Y_n' - description: 'Total variant calls on Y chromosome' - format: '{:,.0f}' - Predicted_Sex: - title: 'Predicted sex' - description: 'Predicted sex based on thresholds on X_het' - Match_Sexes: - title: 'Matching sex' - description: 'Whether reported and predicted sex of sample match' - -# Overwrite module filename search patterns. See multiqc/utils/search_patterns.yaml -# for the defaults. Remove a default by setting it to null. -sp: - bcl2fastq: - fn: 'Stats.json' - fastqc/data: - fn: '*.stats-fastqc.txt' - sentieon/alignment_metrics: - fn: '*.AlignmentStat_metrics.txt' - shared: true - sentieon/markdups: - fn: '*.Duplication_metrics.txt' - shared: true - sentieon/gcbias: - fn: '*.GCBias_metrics.txt' - shared: true - sentieon/insertsize: - fn: '*.InsertSize_metrics.txt' - shared: true - picard/hsmetrics: - fn: '*.hsmetrics.tsv' - shared: true - picard/pcr_metrics: - fn: '*.pertarget_coverage.tsv' - shared: true - picard/quality_by_cycle: - fn: '*.MeanQualityByCycle_metrics.txt' - shared: true - picard/quality_score_distribution: - fn: '*.QualDistribution_metrics.txt' - shared: true - verifybamid/selfsm: - fn: '*.selfSM' - samtools/flagstat: - fn: '*.flagstat' - contents: 'in total (QC-passed reads + QC-failed reads)' - shared: true - happy: - fn: "*.summary.csv" - contents: "Type,Filter,TRUTH" - vcf_qc_files: - fn: '*.vcf.QC' - somalier_files: - fn: '*_somalier.samples.tsv' - -# Remove plots from HTML report -# remove_sections: - -# Remove module sections from HTML report -exclude_modules: - - somalier - -# Specify location and file extensions of QC metrics to be downloaded -# to the workstation by the app: -dx_sp: - primary: - fastqc: - - '*.stats-fastqc.txt' - sentieon/sample: - - '*.AlignmentStat_metrics.txt' - - '*.Duplication_metrics.txt' - - '*.GCBias_metrics.txt' - - '*.InsertSize_metrics.txt' - # - '*.MeanQualityByCycle_metrics.txt' - # - '*.QualDistribution_metrics.txt' - picard/QC: - - '*.hsmetrics.tsv' - - '*.pertarget_coverage.tsv' - verifybamid/QC: - - '*.selfSM' - # - '*.depthSM' - samtools: - - '*.flagstat' - vcf_qc: - - '*.vcf.QC' - secondary: - somalier_relate2multiqc: - - '*_somalier.samples.tsv' - vcfeval_hap.py: - - "*.summary.csv" diff --git a/CEN/CEN_multiqc_config_v2.1.0.yaml b/CEN/CEN_multiqc_config_v2.1.0.yaml deleted file mode 100644 index 3fb4551..0000000 --- a/CEN/CEN_multiqc_config_v2.1.0.yaml +++ /dev/null @@ -1,447 +0,0 @@ -################################################### -# Eggd MultiQC Configuration File for CEN -################################################### - -# This file can be saved either in the MultiQC installation -# directory, or as ~/.multiqc_config.yaml - -# Configuration settings are taken from the following locations, in order: -# - Hardcoded in MultiQC (multiqc/utils/config.py) -# - /multiqc_config.yaml -# - ~/.multiqc_config.yaml -# - Command line options - -# Note that all of the values below are set to the MultiQC defaults. -# It's recommended that you delete any that you don't need. - -################################################################# - -# Title to use for the report. -title: East GLH MultiQC Report -subtitle: Cancer Endocrine Neurology # Grey text below title -# intro_text: null # Set to False to remove, or your own text - -# # Add generic information to the top of reports -# report_header_info: -# - Example Config:: 'This is arbitrary' -# - Another field:: 'Loaded from multiqc_config_example.yaml' -# - Something different:: 'You can put any key-value pairs here' -# - Want to know more?: 'See the MultiQC docs' -# # Specify a custom logo to add to reports (uncomment to use) -# custom_logo: 'link to egglogo.png' # '/path/to/logo.png' -# custom_logo_url: 'https://cuhbioinformatics.atlassian.net/servicedesk/customer/portal/3' # 'https://www.example.com' -# custom_logo_title: 'Bioinformatics Help Desk' # 'Our Institute Name' - -# Default output filenames -output_fn_name: multiqc_report.html -data_dir_name: multiqc_data - -# Prepend sample names with their directory. Useful if analysing the -# sample samples with different parameters. -prepend_dirs: False -# Whether to create the parsed data directory in addition to the report -make_data_dir: True - -# Cleaning options for sample names. Typically, sample names are detected -# from an input filename. If any of these strings are found, they and any -# text to their right will be discarded. -# For example - file1.fq.gz_trimmed.bam_deduplicated_fastqc.zip -# would be cleaned to 'file1' -# Two options here - fn_clean_exts will replace the defaults, -# extra_fn_clean_exts will append to the defaults -extra_fn_clean_exts: - - type: remove - pattern: '_001' - - type: remove - pattern: '.markdup' - - type: remove - pattern: '_markdup' - - type: remove - pattern: '.realigned' - - type: remove - pattern: '_metrics' - - type: remove - pattern: '.Duplication_metrics' - - type: remove - pattern: '.Duplication' - - type: remove - pattern: '.duplication' - - type: remove - pattern: '.AlignmentStat' - - type: remove - pattern: '.GCBias' - - type: remove - pattern: '.InsertSize' - - type: remove - pattern: '.MeanQualityByCycle_metrics' - - type: remove - pattern: '.QualDistribution_metrics' - # - .gz - # - .fastq - # - .fq - # - .bam - # - .sam - # - _fastqc - # - type: replace - # pattern: '.sorted' - # - type: regex - # pattern: '^Sample_\d+' - -# Ignore files larger than this when searcing for logs (bytes) -log_filesize_limit: 5000000000 -# MultiQC skips a couple of debug messages when searching files as the -# log can get very verbose otherwise. Re-enable here to help debugging. -report_readerrors: False -report_imgskips: False -# Opt-out of remotely checking that you're running the latest version -no_version_check: False - -# How to plot graphs. Different templates can override these settings, but -# the default template can use interactive plots (Javascript using HighCharts) -# or flat plots (images, using MatPlotLib). With interactive plots, the report -# can prevent automatically rendering all graphs if there are lots of samples -# to prevent the browser being locked up when the report opens. -plots_force_flat: False # Try to use only flat image graphs -plots_force_interactive: True # Try to use only interactive javascript graphs -plots_flat_numseries: 200 # If neither of the above, use flat if > this number of datasets -num_datasets_plot_limit: 100 # If interactive, don't plot on load if > this number of datasets -max_table_rows: 500 # Swap tables for a beeswarm plot above this - -# Overwrite module order displayed in report. -# See multiqc/utils/config_defaults.yaml for the defaults. -module_order: - - happy: - module_tag: - - DNA - - 'custom_content' - - verifybamid: - info: "detects sample contamination." - module_tag: - - DNA - - picard: - module_tag: - - DNA - - sentieon: - module_tag: - - DNA - - samtools: - module_tag: - - DNA - - fastqc: - module_tag: - - RNA - - bcl2fastq: - module_tag: - - DNA - -# Overwrite the defaults of which table columns are visible by default -table_columns_visible: - bcl2fastq: False - FastQC: False - Picard: - FOLD_ENRICHMENT: False - verifyBAMID: - CHIPMIX: False - -# Specify order in which table columns are visible in General Statistics -table_columns_placement: - general_stats_table: - mapped_passed: 950 - FREEMIX: 960 - PCT_TARGET_BASES_20X: 970 - percent_duplicates: 980 - PCT_PF_READS_ALIGNED: 990 - summed_median: 1000 - -# Set picard configs: TARGET BASES COVERAGE -picard_config: - general_stats_target_coverage: # should be referred to as 'mqc-generalstats-picard-PCT_TARGET_BASES_20X' - - 20 # for conditional table formatting - -table_cond_formatting_colours: - - blue: '#337ab7' - - lbue: '#5bc0de' - - pass: '#5cb85c' - - warn: '#f0ad4e' - - fail: '#d9534f' - -# Set conditional formatting rules for general stats -table_cond_formatting_rules: - mqc-generalstats-picard-PCT_TARGET_BASES_20X: # Percentage of target bases at 20x - pass: # number in name depends on what is set above - - lt: 101 - warn: - - eq: 98.0 - - lt: 98.0 - fail: - - eq: 95.0 - - lt: 95.0 - mqc-generalstats-verifybamid-FREEMIX: #verifyBamId Contaminntion column in General Stats - pass: - - lt: 2 - warn: - - eq: 2 - - gt: 2 - fail: - - eq: 5 - - gt: 5 -# Set conditional formatting rules for other modules - mean_het_ratio: # vcf_qc mean het ratio column - pass: - - gt: 0 - fail: - - lt: 0.47 - - gt: 0.55 - FOLD_80_BASE_PENALTY: # Picard HSMetrics fold 80 base penalty column - pass: - - lt: 1.30 - warn: - - eq: 1.30 - - gt: 1.30 - FREEMIX: #verifyBamId Contamination column in verifybamid - pass: - - lt: 2 - warn: - - eq: 2 - - gt: 2 - fail: - - eq: 5 - - gt: 5 - METRIC_Recall_indel: # Happy indel Recall outputs - pass: - - gt: 0.830 - - eq: 0.830 - # warn: - # - lt: 0.850 - fail: - - lt: 0.830 - METRIC_Precision_indel: # Happy indel Precision outputs - pass: - - gt: 0.850 - - eq: 0.850 - # warn: - # - lt: 0.620 - fail: - - lt: 0.850 - METRIC_Recall_snp: # Happy snp Recall outputs - pass: - - eq: 1.00 - warn: - - lt: 1.00 - fail: - - lt: 0.990 - METRIC_Precision_snp: # Happy snp Precision outputs - pass: - - eq: 1.000 - warn: - - lt: 1.000 - fail: - - lt: 0.990 - Match_Sexes: # Somalier Matching Sex column - true: - - s_eq: 'pass' - fail: - - s_eq: 'fail' - warn: - - s_eq: 'NA' - original_pedigree_sex: # Somalier Reported sex column - warn: - - s_eq: 'none' - FOLD_ENRICHMENT: # Picard HSMetrics fold enrichment column - pass: - - gt: 1350 - - lt: 1750 - warn: - - eq: 1750 - - gt: 1750 - fail: - - lt: 1350 - - eq: 1350 - - eq: 1800 - - gt: 1800 - - # all_columns: - # pass: - # - s_eq: 'pass' - # - s_eq: 'true' - # warn: - # - s_eq: 'warn' - # - s_eq: 'unknown' - # fail: - # - s_eq: 'fail' - # - s_eq: 'false' - -# Add code to include data from custom QC data files -custom_data: - vcf_qc_files: - file_format: 'tsv' - section_name: 'Het-hom analysis' - description: 'This plot comes from vcf_qc files' - plot_type: 'table' - pconfig: - id: 'het-hom_table' - table_title: 'Het-hom' - 'col1_header': 'Sample' - 'col2_header': 'mean het ratio' - 'col3_header': 'mean homo ratio' - 'col4_header': 'het:homo ratio' - 'col5_header': 'X homo:het ratio' - # 'col6_header': 'gender' - headers: - mean het ratio: - format: '{:,.2f}' - mean homo ratio: - format: '{:,.2f}' - het:homo ratio: - format: '{:,.2f}' - X homo:het ratio: - format: '{:,.2f}' - # gender: - # title: 'Inferred sex' - somalier_files: - file_format: 'tsv' - section_name: 'Somalier sex check' - description: 'Checking predicted sex is same as reported' - plot_type: 'table' - pconfig: - id: 'somalier_table' - table_title: 'Sex check' - 'col1_header': 'sample_id' - 'col7_header': 'original_pedigree_sex' - 'col19_header': 'X_depth_mean' - 'col20_header': 'X_n' - 'col21_header': 'X_hom_ref' - 'col22_header': 'X_het' - 'col23_header': 'X_hom_alt' - 'col24_header': 'Y_depth_mean' - 'col25_header': 'Y_n' - 'col26_header': 'Predicted_Sex' - 'col27_header': 'Match_Sexes' - headers: - sample_id: - title: 'Sample ID' - original_pedigree_sex: - title: 'Reported sex' - description: 'Expected sex reported from filename' - X_depth_mean: - title: 'X_depth_mean' - description: 'Mean depth on X chromosome' - X_n: - title: 'X total' - description: 'Total variant calls on X chromosome' - format: '{:,.0f}' - X_hom_ref: - title: 'X_hom_ref' - description: 'Homozygous ref variant calls on X chromosome' - format: '{:,.0f}' - X_het: - title: 'X_het' - description: 'Heterozygosity variant calls on X chromosome' - format: '{:,.0f}' - X_hom_alt: - title: 'X_hom_alt' - description: 'Homozygous alt variant calls on X chromosome' - format: '{:,.0f}' - Y_depth_mean: - title: 'Y_depth_mean' - description: 'Mean depth on Y chromosome' - Y_n: - title: 'Y_n' - description: 'Total variant calls on Y chromosome' - format: '{:,.0f}' - Predicted_Sex: - title: 'Predicted sex' - description: 'Predicted sex based on thresholds on X_het' - Match_Sexes: - title: 'Matching sex' - description: 'Whether reported and predicted sex of sample match' - -# Add a fixed scale of the Y-axis on the Picard GC bias plot -custom_plot_config: - sentieon_gcbias_plot: - yCeiling: 100 - -# Overwrite module filename search patterns. See multiqc/utils/search_patterns.yaml -# for the defaults. Remove a default by setting it to null. -sp: - bcl2fastq: - fn: 'Stats.json' - fastqc/data: - fn: '*.stats-fastqc.txt' - sentieon/alignment_metrics: - fn: '*.AlignmentStat_metrics.txt' - shared: true - sentieon/markdups: - fn: '*.Duplication_metrics.txt' - shared: true - sentieon/gcbias: - fn: '*.GCBias_metrics.txt' - shared: true - sentieon/insertsize: - fn: '*.InsertSize_metrics.txt' - shared: true - picard/hsmetrics: - fn: '*.hsmetrics.tsv' - shared: true - picard/pcr_metrics: - fn: '*.pertarget_coverage.tsv' - shared: true - picard/quality_by_cycle: - fn: '*.MeanQualityByCycle_metrics.txt' - shared: true - picard/quality_score_distribution: - fn: '*.QualDistribution_metrics.txt' - shared: true - verifybamid/selfsm: - fn: '*.selfSM' - samtools/flagstat: - fn: '*.flagstat' - contents: 'in total (QC-passed reads + QC-failed reads)' - shared: true - happy: - fn: "*.summary.csv" - contents: "Type,Filter,TRUTH" - vcf_qc_files: - fn: '*.vcf.QC' - somalier_files: - fn: '*_somalier.samples.tsv' - -# Remove plots from HTML report -# remove_sections: - -# Remove module sections from HTML report -exclude_modules: - - somalier - -# Specify location and file extensions of QC metrics to be downloaded -# to the workstation by the app: -dx_sp: - primary: - fastqc: - - '*.stats-fastqc.txt' - sentieon/sample: - - '*.AlignmentStat_metrics.txt' - - '*.Duplication_metrics.txt' - - '*.GCBias_metrics.txt' - - '*.InsertSize_metrics.txt' - # - '*.MeanQualityByCycle_metrics.txt' - # - '*.QualDistribution_metrics.txt' - picard/QC: - - '*.hsmetrics.tsv' - - '*.pertarget_coverage.tsv' - verifybamid/QC: - - '*.selfSM' - # - '*.depthSM' - samtools: - - '*.flagstat' - vcf_qc: - - '*.vcf.QC' - somalier_relate2multiqc: - - '*_somalier.samples.tsv' - vcfeval_hap.py: - - "*.summary.csv" - secondary: - somalier_relate2multiqc: - - '*_somalier.samples.tsv' - vcfeval_hap.py: - - "*.summary.csv" diff --git a/CEN/CEN_multiqc_config_v2.2.0.yaml b/CEN/CEN_multiqc_config_v2.3.0.yaml similarity index 99% rename from CEN/CEN_multiqc_config_v2.2.0.yaml rename to CEN/CEN_multiqc_config_v2.3.0.yaml index 1c6ff9b..822dc69 100644 --- a/CEN/CEN_multiqc_config_v2.2.0.yaml +++ b/CEN/CEN_multiqc_config_v2.3.0.yaml @@ -470,6 +470,8 @@ dx_sp: - '*_somalier.samples.tsv' vcfeval_hap.py: - "*.summary.csv" + sex_check: + - "*_mqc.json" secondary: somalier_relate2multiqc: - '*_somalier.samples.tsv'