Mercurial > repos > iuc > hyphy_absrel
diff hyphy_absrel.xml @ 36:8db8d509d51b draft default tip
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/hyphy/ commit d97b1b98a3a621c93a7ed9e7db16bda47eefcb92
| author | iuc |
|---|---|
| date | Tue, 07 Oct 2025 20:51:45 +0000 |
| parents | 841557158611 |
| children |
line wrap: on
line diff
--- a/hyphy_absrel.xml Thu Mar 02 15:09:44 2023 +0000 +++ b/hyphy_absrel.xml Tue Oct 07 20:51:45 2025 +0000 @@ -8,108 +8,139 @@ <command detect_errors="exit_code"><![CDATA[ @SYMLINK_FILES@ ln -s '$absrel_output' ${input_file}.aBSREL.json && - @HYPHYMPI@ absrel + @HYPHYMP@ absrel --alignment ./$input_file @INPUT_TREE@ --code '$gencodeid' @branch_options@ --output '$absrel_output' --multiple-hits $multiple_hits - $srv + @srv_options@ + --blb $blb + --kill-zero-lengths $kill_zero_lengths > absrel_stdout.md @ERRORS@ ]]></command> <inputs> <expand macro="inputs"/> <expand macro="gencode"/> - <param argument="--multiple-hits" type="select" label="Include support for multiple nucleotide substitutions"> - <option value="None">Use standard models which permit only single nucleotide changes to occur instantly</option> - <option value="Double">Include branch-specific rates for double nucleotide substitutions</option> - <option value="Double+Triple">Include branch-specific rates for double and triple nucleotide substitutions</option> - </param> - <param argument="--srv" type="boolean" truevalue="--srv Yes" falsevalue="" label="Include synonymous rate variation" /> <expand macro="branches"/> + <section name="advanced_options" title="Advanced Options" expanded="false"> + <param argument="--multiple-hits" type="select" label="Include support for multiple nucleotide substitutions" help="Include support for multiple nucleotide substitutions."> + <option value="Double">Include branch-specific rates for double nucleotide substitutions</option> + <option value="Double+Triple">Include branch-specific rates for double and triple nucleotide substitutions</option> + <option value="None" selected="true">Use standard models which permit only single nucleotide changes to occur instantly</option> + </param> + <param argument="--blb" type="float" value="1.0" label="Bag of little bootstrap alignment resampling rate" help="[Advanced option] Bag of Little Bootstraps (BLB) alignment resampling rate (default: 1.0). This parameter controls the fraction of sites to resample for each bootstrap replicate. BLB uses down/upsampling approaches to speed up inference for very long alignments by analyzing subsets of the data."/> + <conditional name="srv_conditional"> + <param name="srv_enabled" type="select" label="Include synonymous rate variation" help="Include synonymous rate variation."> + <option value="true" selected="true">Yes</option> + <option value="false">No</option> + </param> + <when value="true"> + <param argument="--syn-rates" type="integer" value="3" min="1" max="10" label="Synonymous rate classes" help="The number of alpha rate classes to include in the model [1-10, default 3]"/> + </when> + <when value="false"> + </when> + </conditional> + <expand macro="kill_zero_lengths_param"/> + </section> </inputs> <outputs> + <data name="absrel_md_report" format="markdown" from_work_dir="absrel_stdout.md" label="aBSREL Report (Markdown) for ${tool.name} on ${on_string}" /> <data name="absrel_output" format="hyphy_results.json" /> </outputs> <tests> - <test> + <test expect_num_outputs="2"> <param name="input_file" ftype="fasta" value="absrel-in1.fa"/> <param name="input_nhx" ftype="nhx" value="absrel-in1.nhx"/> - <param name="multiple_hits" value="None" /> <output name="absrel_output"> <assert_contents> - <has_size value="10512" delta="100"/> - <has_text text="fits"/> - <has_text text="branch attributes"/> - <has_text text="Full adaptive model"/> - </assert_contents> - </output> - <assert_stdout> - <has_text text="found **2** branches under selection among **5** tested"/> - </assert_stdout> - </test> - <test> - <param name="input_file" ftype="fasta" value="absrel-in1.fa"/> - <param name="input_nhx" ftype="nhx" value="absrel-in1.nhx"/> - <param name="multiple_hits" value="Double" /> - <output name="absrel_output"> - <assert_contents> - <has_size value="11117" delta="100"/> <has_text text="fits"/> <has_text text="branch attributes"/> <has_text text="Full adaptive model"/> </assert_contents> </output> - <assert_stdout> - <has_text text="found **0** branches under selection among **5** tested"/> - </assert_stdout> + <output name="absrel_md_report"> + <assert_contents> + <has_text text="found **1** branches under selection among **5** tested"/> + </assert_contents> + </output> </test> - <test> + <test expect_num_outputs="2"> <param name="input_file" ftype="fasta" value="absrel-in1.fa"/> <param name="input_nhx" ftype="nhx" value="absrel-in1.nhx"/> - <param name="multiple_hits" value="Double" /> - <param name="srv" value="true" /> + <section name="advanced_options"> + <param name="multiple_hits" value="Double" /> + </section> <output name="absrel_output"> <assert_contents> - <has_size value="23396" delta="100"/> <has_text text="fits"/> <has_text text="branch attributes"/> <has_text text="Full adaptive model"/> </assert_contents> </output> - <assert_stdout> - <has_text text="found **0** branches under selection among **5** tested"/> - </assert_stdout> + <output name="absrel_md_report"> + <assert_contents> + <has_text text="found **0** branches under selection among **5** tested"/> + <has_text text="Branch-level rate at which 2 nucleotides are changed instantly"/> + </assert_contents> + </output> </test> + <test expect_num_outputs="2"> + <param name="input_file" ftype="fasta" value="absrel-in1.fa"/> + <param name="input_nhx" ftype="nhx" value="absrel-in1.nhx"/> + <section name="advanced_options"> + <param name="multiple_hits" value="Double" /> + <conditional name="srv_conditional"> + <param name="srv_enabled" value="true" /> + </conditional> + </section> + <output name="absrel_output"> + <assert_contents> + <has_text text="fits"/> + <has_text text="branch attributes"/> + <has_text text="Full adaptive model"/> + </assert_contents> + </output> + <output name="absrel_md_report"> + <assert_contents> + <has_text text="found **0** branches under selection among **5** tested"/> + <has_text text="Branch-level rate at which 2 nucleotides are changed instantly"/> + <has_text text="The following rate distribution for site-to-site **synonymous** rate variation was inferred"/> + </assert_contents> + </output> + </test> </tests> <help><![CDATA[ +aBSREL: Adaptive Branch-Site Random Effects Likelihood +====================================================== -aBSREL : Adaptive Branch-Site Random Effects Likelihood -======================================================= +**What question does this method answer?** + +aBSREL (adaptive Branch-Site Random Effects Likelihood) is a powerful method for detecting episodic positive selection. It identifies instances where a proportion of sites along specific branches or lineages of a phylogeny have undergone positive selection. -What question does this method answer? --------------------------------------- +**Recommended Applications** -Is some proportion of sites is subject to positive selection along specific branches or lineages of a phylogeny? +1. **Detecting Episodic Diversifying Selection:** Ideal for exploratory testing to find evidence of lineage-specific positive diversifying selection in alignments of various sizes. +2. **Targeted Branch Testing:** Suitable for targeted testing of branches hypothesized to be under positive selection, even in alignments that would be computationally prohibitive for older branch-site models. -Recommended Applications ------------------------- +**Methodology** -1. Exploratory testing for evidence of lineage-specific positive diversifying selection in small to medium sized alignments (up to 100 sequences). -2. Targeted testing of branches selected a priori for positive diversifying selection, including alignments with prohibitive runtimes under older branch-site models (up to 1,000 sequences) +aBSREL is an adaptive branch-site random effects likelihood model that allows the dN/dS ratio to vary across sites and branches. The key innovation of aBSREL is its adaptive nature: it infers the optimal number of dN/dS rate classes for each branch, providing a more nuanced and powerful test for positive selection compared to traditional fixed-rate models. + +**The Intuition** -Brief description ------------------ +Imagine a gene evolving across a phylogeny. On some branches, the gene might be under strong purifying selection, with most non-synonymous mutations being deleterious. On other branches, the gene might be evolving neutrally. And on a few key branches, the gene might be under positive selection, with non-synonymous mutations providing a fitness advantage. + +Traditional branch-site models test for positive selection by fitting a model with a fixed number of dN/dS rate classes to each branch. This can be problematic because the evolutionary process is not always so uniform. Some branches might have a simple evolutionary history that can be described by one or two dN/dS rates, while others might have a more complex history that requires more rate classes. -aBSREL (Adaptive branch-site random effects likelihood) uses an adaptive -random effects branch-site model framework to test whether each branch -has evolved under positive selection, using a procedure which infers an -optimal number of rate categories per branch. +aBSREL addresses this by starting with a simple model for each branch and incrementally adding more rate classes until the model fit no longer improves. This "adaptive" approach allows the model to tailor itself to the complexity of the evolutionary process on each branch, leading to a more accurate and powerful test for positive selection. + +**The Test** +For each branch, aBSREL performs a likelihood ratio test to determine if a model that allows for positive selection (i.e., a dN/dS ratio > 1) is a significantly better fit than a model that does not. The p-values from these tests are then corrected for multiple testing to identify branches that show statistically significant evidence of positive selection. -Input ------ +**Input** 1. A *FASTA* sequence alignment. 2. A phylogenetic tree in the *Newick* format @@ -117,8 +148,7 @@ Note: the names of sequences in the alignment must match the names of the sequences in the tree. -Output ------- +**Output** A JSON file with analysis results (http://hyphy.org/resources/json-fields.pdf). @@ -127,31 +157,48 @@ A custom visualization module for viewing these results is available (see http://vision.hyphy.org/aBSREL for an example) -Further reading ---------------- +**Further reading** http://hyphy.org/methods/selection-methods/#absrel -Tool options ------------- +**Tool options** :: + --alignment [required] An in-frame codon alignment in one of the formats supported by HyPhy - --code Which genetic code to use + --tree [conditionally required] A phylogenetic tree (optionally annotated with {}) + + --code Which genetic code to use (see tool form for available options) --branches Which branches should be tested for selection? - All [default] : test all branches + All [default] + Internal + Leaves + Unlabeled branches + Custom : Enter a branch label - Internal : test only internal branches (suitable for - intra-host pathogen evolution for example, where terminal branches - may contain polymorphism data) + --multiple-hits Include support for multiple nucleotide substitutions + Double : Include branch-specific rates for double nucleotide substitutions + Double+Triple : Include branch-specific rates for double and triple nucleotide substitutions + None [default] : Use standard models which permit only single nucleotide changes to occur instantly - Leaves: test only terminal (leaf) branches + --srv Include synonymous rate variation (default: No) + If Yes, then: + --syn-rates The number alpha rate classes to include in the model [1-10, default 3] + + --blb [Advanced option] Bag of Little Bootstraps (BLB) alignment resampling rate (default: 1.0). This parameter controls the fraction of sites to resample for each bootstrap replicate. BLB uses down/upsampling approaches to speed up inference for very long alignments by analyzing subsets of the data. For more details, see https://www.nature.com/articles/s43588-021-00129-5. + + --output Write the resulting JSON to this file (default is to save to the same path as the alignment file + 'ABSREL.json') - Unlabeled: if the Newick string is labeled using the {} notation, - test only branches without explicit labels - (see http://hyphy.org/tutorials/phylotree/) + + + --kill-zero-lengths Automatically delete internal zero-length branches for computational efficiency + Yes [default] : Automatically delete internal zero-length branches for computational efficiency (will not affect results otherwise) + Constrain : Keep zero-length branches, but constrain their values to 0 + No : Keep all branches + + --save-fit Save full adaptive aBSREL model fit to this file (default is not to save) @@ -159,4 +206,4 @@ <expand macro="citations"> <citation type="doi">10.1093/molbev/msv022</citation> </expand> -</tool> +</tool> \ No newline at end of file