-
Notifications
You must be signed in to change notification settings - Fork 41
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request #135 from Daniel-VM/dev
Implementation of KmerFinder subworkflow Custom Quast, and Custom MultiQC Reports
- Loading branch information
Showing
38 changed files
with
1,845 additions
and
333 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,166 @@ | ||
| report_comment: > | ||
| This report has been generated by the <a href="https://github.com/nf-core/bacass/releases/tag/dev" target="_blank">nf-core/bacass</a> | ||
| analysis pipeline. For information about how to interpret these results, please see the | ||
| <a href="https://nf-co.re/bacass/dev/docs/output" target="_blank">documentation</a>. | ||
| data_format: "yaml" | ||
|
|
||
| max_table_rows: 10000 | ||
|
|
||
| run_modules: | ||
| - custom_content | ||
| - fastqc | ||
| - fastp | ||
| - nanostat | ||
| - porechop | ||
| - pycoqc | ||
| - kraken2 | ||
| - quast | ||
| - prokka | ||
| - bakta | ||
|
|
||
| exclude_modules: | ||
| - general_stats | ||
|
|
||
| module_order: | ||
| - fastqc: | ||
| name: "PREPROCESS: FastQC (raw reads)" | ||
| info: "This section of the report shows FastQC results for the raw reads before adapter trimming." | ||
| path_filters: | ||
| - "./fastqc/*.zip" | ||
| - fastp: | ||
| name: "PREPROCESS: fastp (adapter trimming)" | ||
| info: "This section of the report shows fastp results for reads after adapter and quality trimming." | ||
| path_filters: | ||
| - "./fastp/*.json" | ||
| - nanostat: | ||
| name: "PREPROCESS: Nanoplot" | ||
| info: "This section of the report shows Nanoplot results for nanopore sequencing data." | ||
| path_filters: | ||
| - "./nanoplot/*.txt" | ||
| - porechop: | ||
| name: "PREPROCESS: Porechop" | ||
| info: "This section of the report shows Porechop results for reads after adapter trimming." | ||
| path_filters: | ||
| - "./porechop/*.log" | ||
| - pycoqc: | ||
| name: "PREPROCESS: PycoQC" | ||
| info: "This section of the report shows PycoQC results for quality control of long-read sequencing data." | ||
| path_filters: | ||
| - "./pycoqc/*.txt" | ||
| - kraken2: | ||
| name: "CONTAMINATION ANALYSIS: Kraken 2" | ||
| info: "This section of the report shows Kraken 2 classification results for reads after adapter trimming with fastp." | ||
| path_filters: | ||
| - ".*kraken2_*/*report.txt" | ||
| - quast: | ||
| name: "ASSEMBLY: Quast" | ||
| info: "This section of the report shows Quast QC results for assembled genomes with Unicycler." | ||
| path_filters: | ||
| - "./quast/*/report.tsv" | ||
| - prokka: | ||
| name: "ANNOTATION: Prokka" | ||
| info: "This section of the report shows Prokka annotation results for reads after adapter trimming and quality trimming." | ||
| path_filters: | ||
| - "./prokka/*.txt" | ||
| - bakta: | ||
| name: "ANNOTATION: Bakta" | ||
| info: "This section of the report shows Bakta mapping and annotation results for reads after adapter trimming." | ||
| path_filters: | ||
| - "./bakta/*.txt" | ||
|
|
||
| report_section_order: | ||
| fastqc: | ||
| after: general_stats | ||
| fastp: | ||
| after: general_stats | ||
| nanostat: | ||
| after: general_stats | ||
| porechop: | ||
| before: nanostat | ||
| kraken2: | ||
| after: general_stats | ||
| quast: | ||
| after: general_stats | ||
| prokka: | ||
| before: nf-core-bacass-methods-description | ||
| bakta: | ||
| before: nf-core-bacass-methods-description | ||
| nf-core-bacass-methods-description: | ||
| order: -1000 | ||
| software_versions: | ||
| order: -1001 | ||
| nf-core-bacass-summary: | ||
| order: -1002 | ||
|
|
||
| custom_data: | ||
| summary_assembly_metrics: | ||
| section_name: "De novo assembly metrics (shorts & long reads)" | ||
| description: "generated by nf-core/bacass" | ||
| plot_type: "table" | ||
| headers: | ||
| "Sample": | ||
| description: "Input sample names" | ||
| format: "{:,.0f}" | ||
| "# Input short reads": | ||
| description: "Total number of input reads in raw fastq files" | ||
| format: "{:,.0f}" | ||
| "# Trimmed short reads (fastp)": | ||
| description: "Total number of reads remaining after adapter/quality trimming with fastp" | ||
| format: "{:,.0f}" | ||
| "# Input long reads": | ||
| description: "Total number of input reads in raw fastq files" | ||
| format: "{:,.0f}" | ||
| "# Median long reads lenght": | ||
| description: "Median read lenght (bp)" | ||
| format: "{:,.0f}" | ||
| "# Median long reads quality": | ||
| description: "Median read quality (Phred scale)" | ||
| format: "{:,.0f}" | ||
| "# Contigs (hybrid assembly)": | ||
| description: "Total number of contigs calculated by QUAST" | ||
| format: "{:,.0f}" | ||
| "# Largest contig (hybrid assembly)": | ||
| description: "Size of largest contig calculated by QUAST" | ||
| format: "{:,.0f}" | ||
| "# N50 (hybrid assembly)": | ||
| description: "N50 metric for de novo assembly as calculated by QUAST" | ||
| format: "{:,.0f}" | ||
| "# % Genome fraction (hybrid assembly)": | ||
| description: "% genome fraction calculated by QUAST" | ||
| format: "{:,.2f}" | ||
| "# Best hit (Kmerfinder)": | ||
| description: "Specie name of the best hit from Kmerfinder (using short reads)" | ||
| format: "{:,.0f}" | ||
| "# Best hit assembly ID (Kmerfinder)": | ||
| description: "Assembly ID of the best hit from Kmerfinder (using short reads)" | ||
| format: "{:,.0f}" | ||
| "# Best hit query coverage (Kmerfinder)": | ||
| description: "Query coverage value of the best hit from Kmerfinder (using short reads)" | ||
| format: "{:,.0f}" | ||
| "# Best hit depth (Kmerfinder)": | ||
| description: "Depth of the best hit from Kmerfinder (using short reads)" | ||
| format: "{:,.0f}" | ||
| "# Second hit (Kmerfinder)": | ||
| description: "Specie name of the second hit from Kmerfinder (using short reads)" | ||
| format: "{:,.0f}" | ||
| "# Second hit assembly ID (Kmerfinder)": | ||
| description: "Assembly ID of the second hit from Kmerfinder (using short reads)" | ||
| format: "{:,.0f}" | ||
| "# Second hit query coverage (Kmerfinder)": | ||
| description: "Query coverage value of the second hit from Kmerfinder (using short reads)" | ||
| format: "{:,.0f}" | ||
| "# Second hit depth (Kmerfinder)": | ||
| description: "Depth of the second hit from Kmerfinder (using short reads)" | ||
| format: "{:,.0f}" | ||
|
|
||
| export_plots: true | ||
|
|
||
| # # Customise the module search patterns to speed up execution time | ||
| # # - Skip module sub-tools that we are not interested in | ||
| # # - Replace file-content searching with filename pattern searching | ||
| # # - Don't add anything that is the same as the MultiQC default | ||
| # # See https://multiqc.info/docs/#optimise-file-search-patterns for details | ||
| sp: | ||
| fastp: | ||
| fn: "*.fastp.json" |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,140 @@ | ||
| report_comment: > | ||
| This report has been generated by the <a href="https://github.com/nf-core/bacass/releases/tag/dev" target="_blank">nf-core/bacass</a> | ||
| analysis pipeline. For information about how to interpret these results, please see the | ||
| <a href="https://nf-co.re/bacass/dev/docs/output" target="_blank">documentation</a>. | ||
| data_format: "yaml" | ||
|
|
||
| max_table_rows: 10000 | ||
|
|
||
| run_modules: | ||
| - custom_content | ||
| - nanostat | ||
| - porechop | ||
| - pycoqc | ||
| - kraken2 | ||
| - quast | ||
| - prokka | ||
| - bakta | ||
|
|
||
| exclude_modules: | ||
| - general_stats | ||
|
|
||
| module_order: | ||
| - nanostat: | ||
| name: "PREPROCESS: Nanoplot" | ||
| info: "This section of the report shows Nanoplot results for nanopore sequencing data." | ||
| path_filters: | ||
| - "./nanoplot/*.txt" | ||
| - porechop: | ||
| name: "PREPROCESS: Porechop" | ||
| info: "This section of the report shows Porechop results for reads after adapter trimming." | ||
| path_filters: | ||
| - "./porechop/*.log" | ||
| - pycoqc: | ||
| name: "PREPROCESS: PycoQC" | ||
| info: "This section of the report shows PycoQC results for quality control of long-read sequencing data." | ||
| path_filters: | ||
| - "./pycoqc/*.txt" | ||
| - kraken2: | ||
| name: "CONTAMINATION ANALYSIS: Kraken 2" | ||
| info: "This section of the report shows Kraken 2 classification results for reads after adapter trimming with fastp." | ||
| path_filters: | ||
| - ".*kraken2_*/*report.txt" | ||
| - quast: | ||
| name: "ASSEMBLY: Quast" | ||
| info: "This section of the report shows Quast QC results for assembled genomes with Unicycler." | ||
| path_filters: | ||
| - "./quast/*/report.tsv" | ||
| - prokka: | ||
| name: "ANNOTATION: Prokka" | ||
| info: "This section of the report shows Prokka annotation results for reads after adapter trimming and quality trimming." | ||
| path_filters: | ||
| - "./prokka/*.txt" | ||
| - bakta: | ||
| name: "ANNOTATION: Bakta" | ||
| info: "This section of the report shows Bakta mapping and annotation results for reads after adapter trimming." | ||
| path_filters: | ||
| - "./bakta/*.txt" | ||
|
|
||
| report_section_order: | ||
| nanostat: | ||
| after: general_stats | ||
| porechop: | ||
| before: nanostat | ||
| kraken2: | ||
| after: general_stats | ||
| quast: | ||
| after: general_stats | ||
| prokka: | ||
| before: nf-core-bacass-methods-description | ||
| bakta: | ||
| before: nf-core-bacass-methods-description | ||
| nf-core-bacass-methods-description: | ||
| order: -1000 | ||
| software_versions: | ||
| order: -1001 | ||
| nf-core-bacass-summary: | ||
| order: -1002 | ||
|
|
||
| custom_data: | ||
| summary_assembly_metrics: | ||
| section_name: "De novo assembly metrics (long-reads)" | ||
| description: "generated by nf-core/bacass" | ||
| plot_type: "table" | ||
| headers: | ||
| "Sample": | ||
| description: "Input sample names" | ||
| format: "{:,.0f}" | ||
| "# Input reads": | ||
| description: "Total number of input reads in raw fastq files" | ||
| format: "{:,.0f}" | ||
| "# Median read lenght": | ||
| description: "Median read lenght (bp)" | ||
| format: "{:,.0f}" | ||
| "# Median read quality": | ||
| description: "Median read quality (Phred scale)" | ||
| format: "{:,.0f}" | ||
| "# Contigs": | ||
| description: "Total number of contigs calculated by QUAST" | ||
| format: "{:,.0f}" | ||
| "# Largest contig": | ||
| description: "Size of largest contig calculated by QUAST" | ||
| format: "{:,.0f}" | ||
| "# N50": | ||
| description: "N50 metric for de novo assembly as calculated by QUAST" | ||
| format: "{:,.0f}" | ||
| "# % Genome fraction": | ||
| description: "% genome fraction calculated by QUAST" | ||
| format: "{:,.2f}" | ||
| "# Best hit (Kmerfinder)": | ||
| description: "Specie name of the best hit from Kmerfinder" | ||
| format: "{:,.0f}" | ||
| "# Best hit assembly ID (Kmerfinder)": | ||
| description: "Assembly ID of the best hit from Kmerfinder" | ||
| format: "{:,.0f}" | ||
| "# Best hit query coverage (Kmerfinder)": | ||
| description: "Query coverage value of the best hit from Kmerfinder" | ||
| format: "{:,.0f}" | ||
| "# Best hit depth (Kmerfinder)": | ||
| description: "Depth of the best hit from Kmerfinder" | ||
| format: "{:,.0f}" | ||
| "# Second hit (Kmerfinder)": | ||
| description: "Specie name of the second hit from Kmerfinder" | ||
| format: "{:,.0f}" | ||
| "# Second hit assembly ID (Kmerfinder)": | ||
| description: "Assembly ID of the second hit from Kmerfinder" | ||
| format: "{:,.0f}" | ||
| "# Second hit query coverage (Kmerfinder)": | ||
| description: "Query coverage value of the second hit from Kmerfinder" | ||
| format: "{:,.0f}" | ||
| "# Second hit depth (Kmerfinder)": | ||
| description: "Depth of the second hit from Kmerfinder" | ||
| format: "{:,.0f}" | ||
|
|
||
| export_plots: true | ||
| # # Customise the module search patterns to speed up execution time | ||
| # # - Skip module sub-tools that we are not interested in | ||
| # # - Replace file-content searching with filename pattern searching | ||
| # # - Don't add anything that is the same as the MultiQC default | ||
| # # See https://multiqc.info/docs/#optimise-file-search-patterns for details |
Oops, something went wrong.