Mercurial > repos > q2d2 > qiime2__kmerizer__core_metrics
changeset 0:76e30489ad7a draft default tip
planemo upload for repository https://github.com/qiime2/galaxy-tools/tree/main/tools/suite_qiime2__kmerizer commit 64ed09f1f1c680ad8373d261bd6be43a4f8a8d5b
| author | q2d2 |
|---|---|
| date | Sat, 01 Nov 2025 17:26:47 +0000 |
| parents | |
| children | |
| files | qiime2__kmerizer__core_metrics.xml test-data/.gitkeep |
| diffstat | 1 files changed, 164 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/qiime2__kmerizer__core_metrics.xml Sat Nov 01 17:26:47 2025 +0000 @@ -0,0 +1,164 @@ +<?xml version='1.0' encoding='utf-8'?> +<!-- +Copyright (c) 2025, QIIME 2 development team. + +Distributed under the terms of the Modified BSD License. (SPDX: BSD-3-Clause) +--> +<!-- +This tool was automatically generated by: + q2galaxy (version: 2025.10.0) +for: + qiime2 (version: 2025.10.0) +--> +<tool name="qiime2 kmerizer core-metrics" id="qiime2__kmerizer__core_metrics" version="2025.10.1+q2galaxy.2025.10.0" profile="22.05" license="BSD-3-Clause"> + <description>Kmer counting and core diversity metrics (non-phylogenetic)</description> + <xrefs> + <xref type="bio.tools">qiime2</xref> + </xrefs> + <requirements> + <container type="docker">quay.io/qiime2/amplicon:2025.10</container> + </requirements> + <version_command>q2galaxy version kmerizer</version_command> + <command detect_errors="exit_code">q2galaxy run kmerizer core_metrics '$inputs'</command> + <configfiles> + <inputs name="inputs" data_style="staging_path_and_source_path"/> + </configfiles> + <inputs> + <param name="sequences" type="data" format="qza" label="sequences: FeatureData[Sequence | RNASequence | ProteinSequence]" help="[required] Biological sequences to kmerize."> + <options options_filter_attribute="metadata.semantic_type"> + <filter type="add_value" value="FeatureData[ProteinSequence]"/> + <filter type="add_value" value="FeatureData[Sequence]"/> + <filter type="add_value" value="FeatureData[RNASequence]"/> + </options> + <validator type="expression" message="Incompatible type">hasattr(value.metadata, "semantic_type") and value.metadata.semantic_type in ['FeatureData[ProteinSequence]', 'FeatureData[RNASequence]', 'FeatureData[Sequence]']</validator> + </param> + <param name="table" type="data" format="qza" label="table: FeatureTable[Frequency]" help="[required] Frequencies of sequences per sample."> + <options options_filter_attribute="metadata.semantic_type"> + <filter type="add_value" value="FeatureTable[Frequency]"/> + </options> + <validator type="expression" message="Incompatible type">hasattr(value.metadata, "semantic_type") and value.metadata.semantic_type in ['FeatureTable[Frequency]']</validator> + </param> + <param name="sampling_depth" type="integer" min="1" value="" label="sampling_depth: Int % Range(1, None)" help="[required] The total frequency that each sample should be rarefied to prior to computing diversity metrics."/> + <repeat name="metadata" min="1" help="[required] The sample metadata to use in the emperor plots." title="metadata: Metadata"> + <conditional name="__q2galaxy__GUI__conditional__metadata__"> + <param name="type" type="select" label="metadata: Metadata"> + <option value="tsv" selected="true">Metadata from TSV</option> + <option value="qza">Metadata from Artifact</option> + </param> + <when value="tsv"> + <param name="source" type="data" format="tabular,qiime2.tabular" label="Metadata Source"/> + </when> + <when value="qza"> + <param name="source" type="data" format="qza" label="Metadata Source"/> + </when> + </conditional> + </repeat> + <section name="__q2galaxy__GUI__section__extra_opts__" title="Click here for additional options"> + <param name="kmer_size" type="integer" value="16" label="kmer_size: Int" help="[default: 16] Length of kmers to generate."/> + <param name="tfidf" type="boolean" truevalue="__q2galaxy__::literal::True" falsevalue="__q2galaxy__::literal::False" label="tfidf: Bool" help="[default: No] If True, kmers will be scored using TF-IDF and output frequencies will be weighted by scores. If False, kmers are counted without TF-IDF scores."/> + <conditional name="__q2galaxy__GUI__conditional__max_df__"> + <param name="__q2galaxy__GUI__select__" type="select" label="max_df: Float % Range(0, 1, inclusive_end=True) | Int" help="[default: 1.0] Ignore kmers that have a frequency strictly higher than the given threshold. If float, the parameter represents a proportion of sequences, if an integer it represents an absolute count."> + <option value="__q2galaxy__::control::Float X Range(0__comma__ 1__comma__ inclusive_end=True)" selected="true">Provide a value (Float % Range(0, 1, inclusive_end=True))</option> + <option value="__q2galaxy__::control::Int">Provide a value (Int)</option> + </param> + <when value="__q2galaxy__::control::Float X Range(0__comma__ 1__comma__ inclusive_end=True)"> + <param name="max_df" type="float" min="0" max="1" value="1.0" label="max_df: Float % Range(0, 1, inclusive_end=True)" help="[default: 1.0] Ignore kmers that have a frequency strictly higher than the given threshold. If float, the parameter represents a proportion of sequences, if an integer it represents an absolute count."/> + </when> + <when value="__q2galaxy__::control::Int"> + <param name="max_df" type="integer" value="" label="max_df: Int" help="[required] Ignore kmers that have a frequency strictly higher than the given threshold. If float, the parameter represents a proportion of sequences, if an integer it represents an absolute count."/> + </when> + </conditional> + <conditional name="__q2galaxy__GUI__conditional__min_df__"> + <param name="__q2galaxy__GUI__select__" type="select" label="min_df: Float % Range(0, 1) | Int" help="[default: 1] Ignore kmers that have a frequency strictly lower than the given threshold. If float, the parameter represents a proportion of sequences, if an integer it represents an absolute count."> + <option value="__q2galaxy__::control::Float X Range(0__comma__ 1)">Provide a value (Float % Range(0, 1))</option> + <option value="__q2galaxy__::control::Int" selected="true">Provide a value (Int)</option> + </param> + <when value="__q2galaxy__::control::Float X Range(0__comma__ 1)"> + <param name="min_df" type="float" min="0" max="0.999999" value="" label="min_df: Float % Range(0, 1)" help="[required] Ignore kmers that have a frequency strictly lower than the given threshold. If float, the parameter represents a proportion of sequences, if an integer it represents an absolute count."/> + </when> + <when value="__q2galaxy__::control::Int"> + <param name="min_df" type="integer" value="1" label="min_df: Int" help="[default: 1] Ignore kmers that have a frequency strictly lower than the given threshold. If float, the parameter represents a proportion of sequences, if an integer it represents an absolute count."/> + </when> + </conditional> + <param name="max_features" type="integer" optional="true" label="max_features: Int" help="[optional] If not None, build a vocabulary that only considers the top max_features ordered by frequency (or TF-IDF score)."/> + <param name="with_replacement" type="boolean" truevalue="__q2galaxy__::literal::True" falsevalue="__q2galaxy__::literal::False" label="with_replacement: Bool" help="[default: No] Rarefy with replacement by sampling from the multinomial distribution instead of rarefying without replacement."/> + <conditional name="__q2galaxy__GUI__conditional__n_jobs__"> + <param name="__q2galaxy__GUI__select__" type="select" label="n_jobs: Int % Range(1, None) | Str % Choices('auto')" help="[default: 1] [beta methods only] - The number of concurrent jobs to use in performing this calculation. May not exceed the number of available physical cores. If n_jobs = 'auto', one job will be launched for each identified CPU core on the host."> + <option value="auto">auto (Str)</option> + <option value="__q2galaxy__::control::Int X Range(1__comma__ None)" selected="true">Provide a value (Int % Range(1, None))</option> + </param> + <when value="auto"> + <param name="n_jobs" type="hidden" value="auto"/> + </when> + <when value="__q2galaxy__::control::Int X Range(1__comma__ None)"> + <param name="n_jobs" type="integer" min="1" value="1" label="n_jobs: Int % Range(1, None)" help="[default: 1] [beta methods only] - The number of concurrent jobs to use in performing this calculation. May not exceed the number of available physical cores. If n_jobs = 'auto', one job will be launched for each identified CPU core on the host."/> + </when> + </conditional> + <param name="pc_dimensions" type="integer" value="3" label="pc_dimensions: Int" help="[default: 3] Number of principal coordinate dimensions to keep for plotting."/> + <conditional name="__q2galaxy__GUI__conditional__color_by__" label="color_by: Str"> + <param name="__q2galaxy__GUI__select__" type="select" label="color_by: Str" help="[optional] Categorical measure from the input Metadata that should be used for color-coding the scatterplot."> + <option value="__q2galaxy__::control::default" selected="true">None (Use default behavior)</option> + <option value="__q2galaxy__::control::provide">Provide a value</option> + </param> + <when value="__q2galaxy__::control::default"> + <param name="color_by" type="hidden" value="__q2galaxy__::literal::None"/> + </when> + <when value="__q2galaxy__::control::provide"> + <param name="color_by" type="text"> + <sanitizer> + <valid initial="string.printable"/> + </sanitizer> + </param> + </when> + </conditional> + <param name="norm" type="select" label="norm: Str % Choices('None', 'l1', 'l2')" display="radio"> + <option value="None" selected="true">None</option> + <option value="l1">l1</option> + <option value="l2">l2</option> + </param> + </section> + </inputs> + <outputs> + <data name="rarefied_table" format="qza" label="${tool.name} on ${on_string}: rarefied_table.qza" from_work_dir="rarefied_table.qza"/> + <data name="kmer_table" format="qza" label="${tool.name} on ${on_string}: kmer_table.qza" from_work_dir="kmer_table.qza"/> + <data name="observed_features_vector" format="qza" label="${tool.name} on ${on_string}: observed_features_vector.qza" from_work_dir="observed_features_vector.qza"/> + <data name="shannon_vector" format="qza" label="${tool.name} on ${on_string}: shannon_vector.qza" from_work_dir="shannon_vector.qza"/> + <data name="jaccard_distance_matrix" format="qza" label="${tool.name} on ${on_string}: jaccard_distance_matrix.qza" from_work_dir="jaccard_distance_matrix.qza"/> + <data name="bray_curtis_distance_matrix" format="qza" label="${tool.name} on ${on_string}: bray_curtis_distance_matrix.qza" from_work_dir="bray_curtis_distance_matrix.qza"/> + <data name="jaccard_pcoa_results" format="qza" label="${tool.name} on ${on_string}: jaccard_pcoa_results.qza" from_work_dir="jaccard_pcoa_results.qza"/> + <data name="bray_curtis_pcoa_results" format="qza" label="${tool.name} on ${on_string}: bray_curtis_pcoa_results.qza" from_work_dir="bray_curtis_pcoa_results.qza"/> + <data name="scatterplot" format="qzv" label="${tool.name} on ${on_string}: scatterplot.qzv" from_work_dir="scatterplot.qzv"/> + </outputs> + <tests/> + <help> +QIIME 2: kmerizer core-metrics +============================== +Kmer counting and core diversity metrics (non-phylogenetic) + + +Outputs: +-------- +:rarefied_table.qza: The resulting rarefied feature table. +:kmer_table.qza: Frequencies of kmers per sample. +:observed_features_vector.qza: Vector of Observed Kmers values by sample. +:shannon_vector.qza: Vector of Shannon diversity values by sample. +:jaccard_distance_matrix.qza: Matrix of Jaccard distances between pairs of samples. +:bray_curtis_distance_matrix.qza: Matrix of Bray-Curtis dissimilarities between pairs of samples. +:jaccard_pcoa_results.qza: PCoA matrix computed from Jaccard distances between samples. +:bray_curtis_pcoa_results.qza: PCoA matrix computed from Bray-Curtis dissimilarities between samples. +:scatterplot.qzv: Scatterplot of results. Axes can be selected to display alpha diversity results or PCoA coordinates computed from Jaccard or Bray-Curtis. + +| + +Description: +------------ +Generate kmer counts from sequences and apply a collection of diversity metrics (non-phylogenetic) to compare samples. + + +| + +</help> + <citations> + <citation type="doi">10.1038/s41587-019-0209-9</citation> + </citations> +</tool>
