Mercurial > repos > iuc > qualifilter
view qualifilter.xml @ 0:b694fab47ac7 draft default tip
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/qualifilter commit c1d08b00ccb4837dd592970d2000f5fffe695e9f
| author | iuc |
|---|---|
| date | Mon, 15 Dec 2025 14:04:25 +0000 |
| parents | |
| children |
line wrap: on
line source
<tool id="qualifilter" name="QualiFilter" version="@TOOL_VERSION@@VERSION_SUFFIX@" profile="@PROFILE@"> <description>Report QC metrics and sample pass/fail based on user-defined thresholds</description> <macros> <import>macros.xml</import> </macros> <requirements> <requirement type="package" version="1.0.0">qualifilter</requirement> </requirements> <version_command>echo @TOOL_VERSION@</version_command> <command detect_errors="exit_code" ><![CDATA[ qualifilter --input '$input_file' --attributes '$attributes' --thresholds "{\"Total_reads\": ${total_reads}, \"Coverage_gte_10x_pct\": ${coverage_gte_10x_pct}, \"Contam_pct\": ${contam_max}}" --round '${round}' $derive_reads #if $config --config '$config' #end if --outdir . > qualifilter.log 2>&1 ]]></command> <inputs> <param name="input_file" type="data" format="tabular" label="Input summary file" /> <param argument="--attributes" type="select" multiple="true" optional="true" label="QC metrics to include" help="Select which metrics to include in the output. Leave empty to include all."> <option value="Sample">Sample</option> <option value="Total_reads">Total reads</option> <option value="Mapped_reads">Mapped reads</option> <option value="Mapping_pct">Mapping %</option> <option value="Median_depth">Median depth</option> <option value="Coverage_gte_10x_pct">Coverage ≥10x %</option> <option value="GC_pct">GC %</option> <option value="Kraken_top1_pct">Kraken top1 %</option> <option value="Kraken_unclassified_pct">Kraken unclassified %</option> <option value="Contam_pct">Contamination %</option> <option value="QC_status">QC status</option> <option value="Total_reads_pass">Total reads pass</option> <option value="Coverage_gte_10x_pct_pass">Coverage at ≥10x pass</option> <option value="Contam_pct_pass">Contamination pass</option> <option value="MTB_reads">MTB reads</option> <option value="Unclassified_reads">Unclassified reads</option> </param> <param name="total_reads" type="float" value="1000000" min="0" label="Minimum total reads" help="Minimum number of sequencing reads required for a sample to pass QC (commonly ≥1M for microbial WGS)." /> <param name="coverage_gte_10x_pct" type="float" value="90" min="0" max="100" label="Minimum coverage pct at ≥10x depth" help="Percentage of the genome covered at ≥10x depth. Values ≥90% are generally considered good quality." /> <param name="contam_max" type="float" value="5" min="0" max="100" label="Maximum contamination %" help="Maximum proportion of reads not belonging to the target organism (typically ≤5%)." /> <param name="round" type="integer" value="2" min="0" label="Rounding precision" help="Number of decimal places used to round numeric values in the output." /> <param name="config" type="data" format="yaml" optional="true" label="Optional config file" help="Provide a YAML or JSON config file to override default allowed columns and rename map. Only advanced users need this." /> <param argument="--derive_reads" type="boolean" truevalue="--derive_reads" falsevalue="" label="Derive MTB/unclassified reads" /> </inputs> <outputs> <data name="qc_matrix_tsv" format="tsv" label="QC Matrix (TSV)" from_work_dir="QC_matrix.tsv" /> <data name="qc_matrix_csv" format="csv" label="QC Matrix (CSV)" from_work_dir="QC_matrix.csv" /> <data name="log" format="txt" label="QualiFilter Log" from_work_dir="qualifilter.log" /> </outputs> <tests> <test expect_num_outputs="3"> <param name="input_file" value="qc_matrix.tabular" ftype="tabular"/> <param name="attributes" value="Sample,Total_reads,Mapped_reads,Mapping_pct,Median_depth,Coverage_gte_10x_pct,GC_pct,Kraken_top1_pct,Kraken_unclassified_pct,Contam_pct,QC_status,Total_reads_pass,Coverage_gte_10x_pct_pass,Contam_pct_pass,MTB_reads,Unclassified_reads" /> <param name="total_reads" value="1000000" /> <param name="coverage_gte_10x_pct" value="90" /> <param name="contam_max" value="5" /> <param name="round" value="2" /> <param name="derive_reads" value="true" /> <output name="qc_matrix_tsv" file="QC_matrix.tsv" /> <output name="qc_matrix_csv" file="QC_matrix.csv" /> <output name="log" file="qualifilter.log" /> </test> </tests> <help><![CDATA[ **What it does** This tool extracts sequencing quality control (QC) metrics from a MultiQC tabular summary (.tabular) file and generates a consolidated QC matrix containing only the metrics of interest. It summarizes key metrics including Total reads, Mapped reads, Coverage percentage, and Contamination. Each sample is automatically evaluated against user-defined QC thresholds (provided as a JSON string) to assign a QC Pass/Fail status. **Input** - A MultiQC-generated .tabular file containing per-sample QC metrics - User-defined thresholds for Total reads, Coverage >=10x percentage, Maximum contamination percentage - You can specify which QC metrics to include in the output using the --attributes option (comma-separated list). If left empty, all available metrics will be included automatically - Optionally, a YAML or JSON config file can be provided to customize allowed columns and rename mappings **Available metrics / attributes** - Sample - unique identifier for each sample - Total_reads - total number of sequencing reads - Mapped_reads - reads mapped to the reference genome - Median_depth - median sequencing coverage across the genome - Coverage_gte_10x_pct - percentage of the genome covered at >=10x depth - GC_pct - GC content percentage of reads - Kraken_top1_pct - percentage of reads assigned to the top taxonomic hit by Kraken - Kraken_unclassified_pct - percentage of reads unclassified by Kraken - Contam_pct - estimated contamination percentage - QC_status - Pass/Fail status of the sample based on thresholds - MTB_reads (optional, derived if --derive_reads is selected) - reads assigned to the target organism - Unclassified_reads (optional, derived if --derive_reads is selected) - reads that could not be classified **Output** - A summarized QC matrix in TSV format - A summarized QC matrix in CSV format - Both outputs include Pass/Fail status for each sample based on the threshold evaluation **Threshold behavior** - Thresholds are provided as a JSON-formatted string. Example: {"Total_reads": 1000000, "Coverage_gte_10x_pct": 90, "Contam_pct": 5} **Optional configuration file** - An optional YAML or JSON configuration file can be supplied for advanced use cases where the default behavior needs to be customized. This file allows users to: - Define custom allowed columns - Rename columns in the output matrix Example YAML:: allowed_columns: - Sample - Total_reads - Coverage_gte_10x_pct - Contam_pct rename_map: qualimap_bamqc-total_reads: Total_reads qualimap_bamqc-mapped_reads: Mapped_reads qualimap_bamqc-percentage_aligned: Mapping_pct qualimap_bamqc-median_coverage: Median_depth **Additional Notes** - Read count fields (Total_reads, Mapped_reads) are automatically scaled if MultiQC reports them in millions (e.g., Qualimap output). No action is required - If no QC metric attributes are selected, the tool includes all available columns - Derived read metrics (MTB_reads, Unclassified_reads) are calculated only when the relevant option is enabled - Default thresholds: Total reads >= 1000000, Coverage >=10x percentage >= 90, Contamination percentage <= 5 - Rounding precision for numeric metrics can be adjusted (default is 2 decimal places) - The tool generates a log file documenting the processing steps and any issues encountered ]]></help> <citations> <citation type="bibtex"> @misc{bntozini2025, author = {Buhle Ntozini}, year = {2025}, title = {QualiFilter: QC matrix extractor and decision tool}, publisher = {GitHub}, journal = {GitHub repository}, url = {https://github.com/buhlentozini/QualiFilter} } </citation> </citations> </tool>
