Skip to content

Commit

Permalink
Revert "macros parameters"
Browse files Browse the repository at this point in the history
This reverts commit 940613d.
Back before macros when tests passed
  • Loading branch information
hugolefeuvre committed Nov 22, 2024
1 parent 940613d commit 09e0d94
Show file tree
Hide file tree
Showing 3 changed files with 87 additions and 62 deletions.
49 changes: 0 additions & 49 deletions tools/mmseqs2/macro.xml
Original file line number Diff line number Diff line change
Expand Up @@ -30,53 +30,4 @@
<citation type="doi">10.1093/bioinformatics/btab184</citation>
</citations>
</xml>
<xml name="prefilter_common_parameters">
<param argument="--add-self-matches" type="boolean" checked="false" truevalue="1" falsevalue="0" label="Artificially add entries of queries with themselves (for clustering)" help=""/>
<param argument="-k" name="kmer_length" type="integer" min="0" value="0" label="k-mer length" help="(0: automatically set to optimum)"/>
<param argument="--mask" type="select" label="Mask sequences in k-mer stage" help="">
<option value="0">Without low complexity masking</option>
<option value="1" selected="true">With low complexity masking</option>
</param>
<param argument="--mask-prob" type="float" min="0" value="0.9" label="Mask sequences if probablity is above threshold" help=""/>
<param argument="--mask-lower-case" type="select" label="Mask lower case letters" help="">
<option value="0" selected="true">Include region</option>
<option value="1">Exclude region</option>
</param>
</xml>
<xml name="align_common_parameters">
<param argument="-a" name="convertalis" type="boolean" checked="false" truevalue="1" falsevalue="0" label="Add backtrace string" help="Convert to alignments with mmseqs convertalis module"/>
<param argument="--alignment-output-mode" type="select" label="Alignment mode : How to compute the alignment" help="" >
<option value="0" selected="true">Automatic</option>
<option value="1">Only score and end_pos</option>
<option value="2">Also start_pos and cov</option>
<option value="3">Also seq.id</option>
<option value="4">Only ungapped alignment</option>
<option value="5">score only (output) cluster format</option>
</param>
<param argument="--wrapped-scoring" type="boolean" checked="false" truevalue="1" falsevalue="0" label="Double the (nucleotide) query sequence during the scoring process" help="Allow wrapped diagonal scoring around end and start"/>
<param argument="--min-aln-len" type="integer" min="0" value="0" label="Minimum alignment length" help=""/>
<param argument="--seq-id-mode" type="select" label="Sequence identity mode" help="" >
<option value="0" selected="true">Alignment length</option>
<option value="1">Shorter</option>
<option value="2">Longer sequence</option>
</param>
<param argument="--alt-ali" type="integer" min="0" value="0" label="Number of alternative alignments to show" help=""/>
<param argument="--score-bias" type="float" value="0" label="Score bias when computing Smith-Waterman alignment" help=""/>
<param argument="--realign" type="boolean" checked="false" truevalue="1" falsevalue="0" label="Compute more conservative, shorter alignments" help="Scores and E-values not changed"/>
<param argument="--realign-score-bias" type="float" value="-0.200" label="Additional bias when computing realignment" help=""/>
<param argument="--realign-max-seqs" type="integer" min="0" value="2147483647" label="Maximum number of results to return in realignment" help=""/>
<param argument="--corr-score-weight" type="float" value="0" label="Weight of backtrace correlation score that is added to the alignment score" help=""/>
</xml>
<xml name="common_section">
<section name="common" title="Common">
<param argument="--max-seq-len" type="integer" min="0" value="65535" optional="true" label="Maximum sequence length" help=""/>
</section>
</xml>
<xml name="expert_common_parameters">
<param argument="--filter-hits" type="boolean" checked="false" truevalue="1" falsevalue="0" label="Filter hits by seq.id. and coverage" help=""/>
<param argument="--sort-results" type="select" label="Sort results" help="">
<option value="0" selected="true">No sorting</option>
<option value="1">Sort by E-value (Alignment) or seq.id. (Hamming)</option>
</param>
</xml>
</macros>
45 changes: 41 additions & 4 deletions tools/mmseqs2/mmseqs2_easy_linclust_clustering.xml
Original file line number Diff line number Diff line change
Expand Up @@ -131,24 +131,55 @@ mmseqs easy-linclust
</param>
<param argument="-c" name="cov" type="float" min="0" value="0.800" label="List matches above this fraction of aligned (covered) residues" help=""/>
<section name="prefilter" title="Pre-filter">
<expand macro="prefilter_common_parameters" />
<param argument="--add-self-matches" type="boolean" checked="false" truevalue="1" falsevalue="0" label="Artificially add entries of queries with themselves (for clustering)" help=""/>
<param argument="-k" name="kmer_length" type="integer" min="0" value="0" label="k-mer length" help="(0: automatically set to optimum)"/>
<param argument="--mask" type="select" label="Mask sequences in k-mer stage" help="">
<option value="0">Without low complexity masking</option>
<option value="1" selected="true">With low complexity masking</option>
</param>
<param argument="--mask-prob" type="float" min="0" value="0.9" label="Mask sequences if probablity is above threshold" help=""/>
<param argument="--mask-lower-case" type="select" label="Mask lower case letters" help="">
<option value="0" selected="true">Include region</option>
<option value="1">Exclude region</option>
</param>
<param argument="--spaced-kmer-mode" type="select" label="Spaced k-mer mode" help="">
<option value="0" selected="true">Use consecutive positions in k-mers</option>
<option value="1">Use spaced k-mers</option>
</param>
</section>
<section name="align" title="Align">
<expand macro="align_common_parameters" />
<param argument="-a" name="convertalis" type="boolean" checked="false" truevalue="1" falsevalue="0" label="Add backtrace string" help="Convert to alignments with mmseqs convertalis module"/>
<param argument="--alignment-mode" type="select" label="Alignment mode : How to compute the alignment" help="" >
<option value="0" selected="true">Automatic</option>
<option value="1">Only score and end_pos</option>
<option value="2">Also start_pos and cov</option>
<option value="3">Also seq.id</option>
<option value="4">Only ungapped alignment</option>
</param>
<param argument="--alignment-output-mode" type="select" label="Alignment mode : How to compute the alignment" help="" >
<option value="0" selected="true">Automatic</option>
<option value="1">Only score and end_pos</option>
<option value="2">Also start_pos and cov</option>
<option value="3">Also seq.id</option>
<option value="4">Only ungapped alignment</option>
<option value="5">score only (output) cluster format</option>
</param>
<param argument="--wrapped-scoring" type="boolean" checked="false" truevalue="1" falsevalue="0" label="Double the (nucleotide) query sequence during the scoring process" help="Allow wrapped diagonal scoring around end and start"/>
<param argument="-e" name="evalue" type="float" min="0" value="1.000E-03" label="E-value threshold" help="List matches below this E-value"/>
<param argument="--min-aln-len" type="integer" min="0" value="0" label="Minimum alignment length" help=""/>
<param argument="--seq-id-mode" type="select" label="Sequence identity mode" help="" >
<option value="0" selected="true">Alignment length</option>
<option value="1">Shorter</option>
<option value="2">Longer sequence</option>
</param>
<param argument="--alt-ali" type="integer" min="0" value="0" label="Show up to this many alternative alignments" help=""/>
<param argument="--max-rejected" type="integer" min="0" value="2147483647" optional="true" label="Maximum rejected alignments before alignment calculation for a query is stopped" help=""/>
<param argument="--max-accept" type="integer" min="0" value="2147483647" optional="true" label="Maximum accepted alignments before alignment calculation for a query is stopped" help=""/>
<param argument="--score-bias" type="float" value="0" label="Score bias when computing Smith-Waterman alignment" help=""/>
<param argument="--realign" type="boolean" checked="false" truevalue="1" falsevalue="0" label="Compute more conservative, shorter alignments" help="Scores and E-values not changed"/>
<param argument="--realign-score-bias" type="float" value="-0.200" label="Additional bias when computing realignment" help=""/>
<param argument="--realign-max-seqs" type="integer" min="0" value="2147483647" label="Maximum number of results to return in realignment" help=""/>
<param argument="--corr-score-weight" type="float" value="0" label="Weight of backtrace correlation score that is added to the alignment score" help=""/>
</section>
<section name="cluster" title="Clustering">
<param argument="--cluster-mode" type="select" label="Cluster mode" help="" >
Expand Down Expand Up @@ -189,9 +220,15 @@ mmseqs easy-linclust
</param>
<param argument="--id-offset" type="integer" min="0" value="0" label="Numeric ids in index file are offset by this value" help=""/>
</section>
<expand macro="common_section"/>
<section name="common" title="Common">
<param argument="--max-seq-len" type="integer" min="0" value="65535" optional="true" label="Maximum sequence length" help=""/>
</section>
<section name="expert" title="Expert">
<expand macro="expert_common_parameters" />
<param argument="--filter-hits" type="boolean" checked="false" truevalue="1" falsevalue="0" label="Filter hits by seq.id. and coverage" help=""/>
<param argument="--sort-results" type="select" label="Sort results" help="">
<option value="0" selected="true">No sorting</option>
<option value="1">Sort by E-value (Alignment) or seq.id. (Hamming)</option>
</param>
</section>
<section name="output_files" title="Selection of the output files">
<param name="output_selection" type="select" min="1" display="checkboxes" multiple="true" label="Output files selection">
Expand Down
55 changes: 46 additions & 9 deletions tools/mmseqs2/mmseqs2_taxonomy_assignment.xml
Original file line number Diff line number Diff line change
Expand Up @@ -287,13 +287,9 @@ mmseqs createtsv
</when>
</conditional>
<section name="prefilter" title="Pre-filter">
<expand macro="prefilter_common_parameters" />
<param argument="--spaced-kmer-mode" type="select" label="Spaced k-mer mode" help="">
<option value="0">Use consecutive positions in k-mers</option>
<option value="1" selected="true">Use spaced k-mers</option>
</param>
<param argument="--min-ungapped-score" type="integer" min="0" value="15" label="Accept only matches with ungapped alignment score above threshold" help=""/>
<param argument="--add-self-matches" type="boolean" checked="false" truevalue="1" falsevalue="0" label="Artificially add entries of queries with themselves (for clustering)" help=""/>
<param argument="-s" name="sensitivity" type="float" min="0" max="7.5" value="2" label="Sensitivity" help="1.0 faster; 4.0 fast; 7.5 sensitive"/>
<param argument="-k" name="kmer_length" type="integer" min="0" value="0" label="k-mer length" help="(0: automatically set to optimum)"/>
<param argument="--target-search-mode" type="select" label="Target search mode" help="" >
<option value="0" selected="true">Regular k-mer</option>
<option value="1">Similar k-mer</option>
Expand All @@ -307,18 +303,48 @@ mmseqs createtsv
</param>
<param argument="--diag-score" type="boolean" checked="true" truevalue="1" falsevalue="0" label="Use ungapped diagonal scoring during prefilter" help=""/>
<param argument="--exact-kmer-matching" type="integer" min="0" max="1" value="0" label="Extract only exact k-mers for matching" help=""/>
<param argument="--mask" type="select" label="Mask sequences in k-mer stage" help="">
<option value="0">Without low complexity masking</option>
<option value="1" selected="true">With low complexity masking</option>
</param>
<param argument="--mask-prob" type="float" min="0" value="0.9" label="Mask sequences if probablity is above threshold" help=""/>
<param argument="--mask-lower-case" type="select" label="Mask lower case letters" help="">
<option value="0" selected="true">Include region</option>
<option value="1">Exclude region</option>
</param>
<param argument="--min-ungapped-score" type="integer" min="0" value="15" label="Accept only matches with ungapped alignment score above threshold" help=""/>
<param argument="--spaced-kmer-mode" type="select" label="Spaced k-mer mode" help="">
<option value="0">Use consecutive positions in k-mers</option>
<option value="1" selected="true">Use spaced k-mers</option>
</param>
</section>
<section name="align" title="Align">
<expand macro="align_common_parameters" />
<param argument="-a" name="convertalis" type="boolean" checked="false" truevalue="1" falsevalue="0" label="Add backtrace string" help="Convert to alignments with mmseqs convertalis module (-a)"/>
<param argument="--alignment-mode" type="select" label="Alignment mode : How to compute the alignment" help="" >
<option value="0">Automatic</option>
<option value="1" selected="true">Only score and end_pos</option>
<option value="2">Also start_pos and cov</option>
<option value="3">Also seq.id</option>
<option value="4">Only ungapped alignment</option>
</param>
<param argument="--alignment-output-mode" type="select" label="Alignment mode : How to compute the alignment" help="" >
<option value="0" selected="true">Automatic</option>
<option value="1">Only score and end_pos</option>
<option value="2">Also start_pos and cov</option>
<option value="3">Also seq.id</option>
<option value="4">Only ungapped alignment</option>
<option value="5">score only (output) cluster format</option>
</param>
<param argument="--wrapped-scoring" type="boolean" checked="false" truevalue="1" falsevalue="0" label="Double the (nucleotide) query sequence during the scoring process" help="Allow wrapped diagonal scoring around end and start"/>
<param argument="-e" name="evalue" type="float" min="0" value="1" label="E-value threshold" help="List matches below this E-value"/>
<param argument="--min-seq-id" type="float" min="0" max="1" value="0" label="Minimum sequence identity" help="List matches above this sequence identity for clustering"/>
<param argument="--min-aln-len" type="integer" min="0" value="0" label="Minimum alignment length" help=""/>
<param argument="--seq-id-mode" type="select" label="Sequence identity mode" help="" >
<option value="0" selected="true">Alignment length</option>
<option value="1">Shorter</option>
<option value="2">Longer sequence</option>
</param>
<param argument="--alt-ali" type="integer" min="0" value="0" label="Show up to this many alternative alignments" help=""/>
<param argument="-c" name="cov" type="float" min="0" value="0" label="List matches above this fraction of aligned (covered) residues" help=""/>
<param argument="--cov-mode" type="select" label="Coverage mode" help="" >
<option value="0" selected="true">Coverage of query and target</option>
Expand All @@ -330,6 +356,11 @@ mmseqs createtsv
</param>
<param argument="--max-rejected" type="integer" min="0" value="5" label="Maximum rejected alignments before alignment calculation for a query is stopped" help=""/>
<param argument="--max-accept" type="integer" min="0" value="30" label="Maximum accepted alignments before alignment calculation for a query is stopped" help=""/>
<param argument="--score-bias" type="float" value="0" label="Score bias when computing Smith-Waterman alignment" help=""/>
<param argument="--realign" type="boolean" checked="false" truevalue="1" falsevalue="0" label="Compute more conservative, shorter alignments" help="Scores and E-values not changed"/>
<param argument="--realign-score-bias" type="float" value="-0.200" label="Additional bias when computing realignment" help=""/>
<param argument="--realign-max-seqs" type="integer" min="0" value="2147483647" label="Maximum number of results to return in realignment" help=""/>
<param argument="--corr-score-weight" type="float" value="0" label="Weight of backtrace correlation score that is added to the alignment score" help=""/>
<param argument="--exhaustive-search-filter" type="boolean" checked="false" truevalue="1" falsevalue="0" label="Filter result during search ?" help=""/>
</section>
<section name="profile" title="Profile">
Expand Down Expand Up @@ -451,9 +482,15 @@ mmseqs createtsv
<option value="2">No filter</option>
</param>
</section>
<expand macro="common_section"/>
<section name="common" title="Common">
<param argument="--max-seq-len" type="integer" min="0" value="65535" label="Maximum sequence length" help=""/>
</section>
<section name="expert" title="Expert">
<expand macro="expert_common_parameters" />
<param argument="--filter-hits" type="boolean" checked="false" truevalue="1" falsevalue="0" label="Filter hits by seq.id. and coverage" help=""/>
<param argument="--sort-results" type="select" label="Sort results" help="">
<option value="0" selected="true">No sorting</option>
<option value="1">Sort by E-value (Alignment) or seq.id. (Hamming)</option>
</param>
<param argument="--chain-alignments" type="integer" min="0" value="0" label="Chain alignments" help=""/>
<param argument="--merge-query" type="integer" min="0" value="1" label="Combine ORFs/split sequences to a single entry" help=""/>
</section>
Expand Down

0 comments on commit 09e0d94

Please sign in to comment.