From 313e1a611cff6e91e8b868fada328367de2f8cba Mon Sep 17 00:00:00 2001 From: MatildaAslin Date: Wed, 20 Feb 2019 16:18:07 +0100 Subject: [PATCH 1/4] Separate multiqc config --- nextflow/config/multiqc_flowcell_config.yaml | 24 +++++++++ ...c_config.yaml => multiqc_hwgs_config.yaml} | 26 ++++++---- nextflow/config/multiqc_project_config.yaml | 49 +++++++++++++++++++ 3 files changed, 89 insertions(+), 10 deletions(-) create mode 100644 nextflow/config/multiqc_flowcell_config.yaml rename nextflow/config/{multiqc_config.yaml => multiqc_hwgs_config.yaml} (84%) create mode 100644 nextflow/config/multiqc_project_config.yaml diff --git a/nextflow/config/multiqc_flowcell_config.yaml b/nextflow/config/multiqc_flowcell_config.yaml new file mode 100644 index 0000000..3a2c794 --- /dev/null +++ b/nextflow/config/multiqc_flowcell_config.yaml @@ -0,0 +1,24 @@ +# Config for flowcell Reports + +subtitle: "SNP&SEQ Technology Platform" +intro_text: | + This is a report containing quality control information about your project run at the SNP&SEQ Technology + Platform. If you have any questions, please do not hesitate to contact us at + seq@medsci.uu.se + +custom_logo: 'assets/UU_logo_tranp4f125px.png' +custom_logo_url: 'http://sequencing.se' +custom_logo_title: 'SNP&SEQ Technology Platform' + +table_columns_visible: + FastQC: + percent_duplicates: False + percent_gc: False + total_sequences: False + +top_modules: + - 'bcl2fastq' + - 'interop' + +remove_sections: + - 'fastqc_sequence_counts' diff --git a/nextflow/config/multiqc_config.yaml b/nextflow/config/multiqc_hwgs_config.yaml similarity index 84% rename from nextflow/config/multiqc_config.yaml rename to nextflow/config/multiqc_hwgs_config.yaml index 82431b9..048cba9 100644 --- a/nextflow/config/multiqc_config.yaml +++ b/nextflow/config/multiqc_hwgs_config.yaml @@ -1,5 +1,4 @@ -# QC criteria for NGI Uppsala, based on values in INS-00123 -# Compatible with MultiQC v1.6 +# Config for human whole genome sequencing reports subtitle: "SNP&SEQ Technology Platform" intro_text: | @@ -11,7 +10,6 @@ custom_logo: 'assets/UU_logo_tranp4f125px.png' custom_logo_url: 'http://sequencing.se' custom_logo_title: 'SNP&SEQ Technology Platform' - clarity: name_edit_regex: '^.*.\/(.*)_L00\d_[R|I]\d_001\.fastq\.gz$' @@ -45,8 +43,16 @@ clarity: +table_columns_visible: + FastQC: + percent_duplicates: False + percent_gc: False + total_sequences: False + max_table_rows: 1000 +# QC criteria for NGI Uppsala, based on values in INS-00123 +# Compatible with MultiQC v1.6 table_cond_formatting_rules: mqc-generalstats-qualimap-percentage_aligned: pass: @@ -62,27 +68,27 @@ table_cond_formatting_rules: - lt: 40.5 - gt: 42.1 - mqc-generalstats-qualimap-median_insert_size: + mqc-generalstats-qualimap-median_insert_size: pass: - gt: 317 - - lt: 428 + - lt: 428 fail: - lt: 317 - gt: 428 - mqc-generalstats-qualimap-10_x_pc: + mqc-generalstats-qualimap-10_x_pc: pass: - gt: 91 fail: - lt: 91 - - mqc-generalstats-qualimap-30_x_pc: + + mqc-generalstats-qualimap-30_x_pc: pass: - gt: 58 fail: - lt: 58 - mqc-generalstats-snpeff-Number_of_variants_before_filter: + mqc-generalstats-snpeff-Number_of_variants_before_filter: pass: - gt: 4.8 - lt: 5.3 @@ -90,7 +96,7 @@ table_cond_formatting_rules: - lt: 4.8 - gt: 5.3 - mqc-generalstats-snpeff-Ts_Tv_ratio: + mqc-generalstats-snpeff-Ts_Tv_ratio: pass: - gt: 1.98 - lt: 2.01 diff --git a/nextflow/config/multiqc_project_config.yaml b/nextflow/config/multiqc_project_config.yaml new file mode 100644 index 0000000..0ae96d8 --- /dev/null +++ b/nextflow/config/multiqc_project_config.yaml @@ -0,0 +1,49 @@ +# Config for project reports + +subtitle: "SNP&SEQ Technology Platform" +intro_text: | + This is a report containing quality control information about your project run at the SNP&SEQ Technology + Platform. If you have any questions, please do not hesitate to contact us at + seq@medsci.uu.se + +custom_logo: 'assets/UU_logo_tranp4f125px.png' +custom_logo_url: 'http://sequencing.se' +custom_logo_title: 'SNP&SEQ Technology Platform' + +clarity: + name_edit_regex: '^.*.\/(.*)_L00\d_[R|I]\d_001\.fastq\.gz$' + + report_header_info: + Project: + 'Application': + 'Kit for library preparation': + 'DNA library insert size': + 'Sequencing instrument': + 'Read length bp': + 'Project decription': + + # TODO The sample level stats is something that we will need tp specify later. + general_stats: + Sample: + 'Fake Value': +# 'Read Length': +# description: 'Sequencing read length' +# 'Insert size (bp)': +# description: 'Target insert size' +# + # TODO This does not actually work since the Clarity MultiQC module only works with + # MultiQC v1.0, and we are using v1.7 + clarity_module: + Sample: + 'Fake Value': +# 'Read Length': +# description: 'Sequencing read length' +# 'Insert size (bp)': +# description: 'Target insert size' + +table_columns_visible: + FastQC: + percent_duplicates: False + +remove_sections: + - 'fastqc_sequence_counts' From 1691df2ecb9926d39e558c3300c14675ebab568a Mon Sep 17 00:00:00 2001 From: MatildaAslin Date: Wed, 20 Feb 2019 16:20:28 +0100 Subject: [PATCH 2/4] Use specific config --- nextflow/run_multiqc_nextflow.nf | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/nextflow/run_multiqc_nextflow.nf b/nextflow/run_multiqc_nextflow.nf index d937f6e..af8e1bf 100644 --- a/nextflow/run_multiqc_nextflow.nf +++ b/nextflow/run_multiqc_nextflow.nf @@ -36,8 +36,11 @@ Channel params.fastq_screen_config = "config/fastq_screen.conf" fastq_screen_config = file(params.fastq_screen_config) -params.multiqc_config = "config/multiqc_config.yaml" -multiqc_config = file(params.multiqc_config) +params.multiqc_flowcell_config = "config/multiqc_flowcell_config.yaml" +multiqc_flowcell_config = file(params.multiqc_flowcell_config) + +params.multiqc_project_config = "config/multiqc_project_config.yaml" +multiqc_project_config = file(params.multiqc_project_config) fastq_screen_db = file(params.fastq_screen_db) @@ -107,7 +110,7 @@ process MultiQCPerFlowcell { file (fastqscreen:'FastQScreen/*') from fastq_screen_results_for_flowcell.map{ it.get(1) }.collect().ifEmpty([]) file (interop_summary:'Interop_summary/*') from interop_summary_results.collect().ifEmpty([]) file runfolder - file config from multiqc_config + file config from multiqc_flowcell_config file assets from assets output: @@ -141,7 +144,7 @@ process MultiQCPerProject { input: set project, file(fastqc: "*") from fastqc_results_for_project_grouped_by_project set project_fastq_screen, file(fastqc_screen: "*") from fastq_screen_results_for_project_grouped_by_project - file config from multiqc_config + file config from multiqc_project_config file runfolder file assets from assets From dc4ba47a957c1be0f630540f8e21441515ae3de8 Mon Sep 17 00:00:00 2001 From: MatildaAslin Date: Wed, 20 Feb 2019 16:34:31 +0100 Subject: [PATCH 3/4] Add run command to README --- README.md | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/README.md b/README.md index 88d6664..cde7886 100644 --- a/README.md +++ b/README.md @@ -17,3 +17,13 @@ fastq-screen containers, so this is a temporary workaround for that. Here's how - Download fastqc-screen from [here](https://www.bioinformatics.babraham.ac.uk/projects/fastq_screen/fastq_screen_v0.13.0.tar.gz). - Uncompress it - Run `fastq_screen --get_genomes` + + +# How to run the nextflow pipeline +Awesome, you're all set! Let's try generating reports for your favourite runfolder: +``` +cd nextflow +nextflow -c config/nextflow.config run run_multiqc_nextflow.nf \ + --runfolder ~/large_disk/180126_HSX122_0568_BHLFWLBBXX_small/ \ + --fastq_screen_db ~/large_disk/FastQ_Screen_Genomes/ +``` From 852dc31c1b01267534adc8677e1fd7dc1803be0e Mon Sep 17 00:00:00 2001 From: MatildaAslin Date: Thu, 21 Feb 2019 09:27:43 +0100 Subject: [PATCH 4/4] Remove unused config --- nextflow/config/multiqc_hwgs_config.yaml | 105 ----------------------- 1 file changed, 105 deletions(-) delete mode 100644 nextflow/config/multiqc_hwgs_config.yaml diff --git a/nextflow/config/multiqc_hwgs_config.yaml b/nextflow/config/multiqc_hwgs_config.yaml deleted file mode 100644 index 048cba9..0000000 --- a/nextflow/config/multiqc_hwgs_config.yaml +++ /dev/null @@ -1,105 +0,0 @@ -# Config for human whole genome sequencing reports - -subtitle: "SNP&SEQ Technology Platform" -intro_text: | - This is a report containing quality control information about your project run at the SNP&SEQ Technology - Platform. If you have any questions, please do not hesitate to contact us at - seq@medsci.uu.se - -custom_logo: 'assets/UU_logo_tranp4f125px.png' -custom_logo_url: 'http://sequencing.se' -custom_logo_title: 'SNP&SEQ Technology Platform' - -clarity: - name_edit_regex: '^.*.\/(.*)_L00\d_[R|I]\d_001\.fastq\.gz$' - - report_header_info: - Project: - 'Application': - 'Kit for library preparation': - 'DNA library insert size': - 'Sequencing instrument': - 'Read length bp': - 'Project decription': - - # TODO The sample level stats is something that we will need tp specify later. - general_stats: - Sample: - 'Fake Value': -# 'Read Length': -# description: 'Sequencing read length' -# 'Insert size (bp)': -# description: 'Target insert size' -# - # TODO This does not actually work since the Clarity MultiQC module only works with - # MultiQC v1.0, and we are using v1.7 - clarity_module: - Sample: - 'Fake Value': -# 'Read Length': -# description: 'Sequencing read length' -# 'Insert size (bp)': -# description: 'Target insert size' - - - -table_columns_visible: - FastQC: - percent_duplicates: False - percent_gc: False - total_sequences: False - -max_table_rows: 1000 - -# QC criteria for NGI Uppsala, based on values in INS-00123 -# Compatible with MultiQC v1.6 -table_cond_formatting_rules: - mqc-generalstats-qualimap-percentage_aligned: - pass: - - gt: 97.1 - fail: - - lt: 97.1 - - mqc-generalstats-qualimap-avg_gc: - pass: - - gt: 40.5 - - lt: 42.1 - fail: - - lt: 40.5 - - gt: 42.1 - - mqc-generalstats-qualimap-median_insert_size: - pass: - - gt: 317 - - lt: 428 - fail: - - lt: 317 - - gt: 428 - - mqc-generalstats-qualimap-10_x_pc: - pass: - - gt: 91 - fail: - - lt: 91 - - mqc-generalstats-qualimap-30_x_pc: - pass: - - gt: 58 - fail: - - lt: 58 - - mqc-generalstats-snpeff-Number_of_variants_before_filter: - pass: - - gt: 4.8 - - lt: 5.3 - fail: - - lt: 4.8 - - gt: 5.3 - - mqc-generalstats-snpeff-Ts_Tv_ratio: - pass: - - gt: 1.98 - - lt: 2.01 - fail: - - lt: 1.98 - - gt: 2.01