Mercurial > repos > florianbegusch > qiime2_suite
diff qiime2/qiime_feature-classifier_classify-consensus-vsearch.xml @ 14:a0a8d77a991c draft
Uploaded
| author | florianbegusch |
|---|---|
| date | Thu, 03 Sep 2020 09:51:29 +0000 |
| parents | f190567fe3f6 |
| children |
line wrap: on
line diff
--- a/qiime2/qiime_feature-classifier_classify-consensus-vsearch.xml Thu Sep 03 09:46:00 2020 +0000 +++ b/qiime2/qiime_feature-classifier_classify-consensus-vsearch.xml Thu Sep 03 09:51:29 2020 +0000 @@ -1,122 +1,114 @@ <?xml version="1.0" ?> -<tool id="qiime_feature-classifier_classify-consensus-vsearch" name="qiime feature-classifier classify-consensus-vsearch" version="2019.7"> - <description> - VSEARCH consensus taxonomy classifier</description> - <requirements> - <requirement type="package" version="2019.7">qiime2</requirement> - </requirements> - <command><![CDATA[ +<tool id="qiime_feature-classifier_classify-consensus-vsearch" name="qiime feature-classifier classify-consensus-vsearch" + version="2020.8"> + <description>VSEARCH-based consensus taxonomy classifier</description> + <requirements> + <requirement type="package" version="2020.8">qiime2</requirement> + </requirements> + <command><![CDATA[ qiime feature-classifier classify-consensus-vsearch --i-query=$iquery + --i-reference-reads=$ireferencereads +--i-reference-taxonomy=$ireferencetaxonomy -#if str( $id_to_taxonomy_fp.selector ) == 'history' -#set $tax = $id_to_taxonomy_fp.taxonomy_fp ---i-reference-taxonomy '$tax' -#else: -#set $tax = $id_to_taxonomy_fp.taxonomy_fp.fields.path ---i-reference-taxonomy '$tax' +#if str($pmaxaccepts) != 'None': +--p-maxaccepts=$pmaxaccepts #end if - -#if $psearchexact: - --p-search-exact -#end if - +--p-perc-identity=$ppercidentity -#if $ptophitsonly: - --p-top-hits-only -#end if - - +--p-query-cov=$pquerycov -#if str($pmaxaccepts): - --p-maxaccepts=$pmaxaccepts -#end if - -#if str($ppercidentity): - --p-perc-identity=$ppercidentity +#if str($pstrand) != 'None': +--p-strand=$pstrand #end if -#if str($pquerycov): - --p-query-cov=$pquerycov +--p-min-consensus=$pminconsensus + +#if str($punassignablelabel): + --p-unassignable-label=$punassignablelabel +#end if +#if $psearchexact: + --p-search-exact #end if -#if str($pstrand) != 'None': - --p-strand=$pstrand -#end if - -#if str($pminconsensus): - --p-min-consensus=$pminconsensus +#if $ptophitsonly: + --p-top-hits-only #end if - - - +#if str($pmaxhits) != 'None': +--p-maxhits=$pmaxhits +#end if -#if '__sq__' in str($punassignablelabel): - #set $punassignablelabel_temp = $punassignablelabel.replace('__sq__', "'") - #set $punassignablelabel = $punassignablelabel_temp +#if str($pmaxrejects) != 'None': +--p-maxrejects=$pmaxrejects #end if -#if str($punassignablelabel): - --p-unassignable-label="$punassignablelabel" +#if $pnooutputnohits: + --p-no-output-no-hits #end if - - +--p-weak-id=$pweakid -#set $pthreads = '${GALAXY_SLOTS:-4}' -#if str($pthreads): - --p-threads="$pthreads" -#end if +--p-threads=$pthreads --o-classification=oclassification +#if str($examples) != 'None': +--examples=$examples +#end if + ; cp oclassification.qza $oclassification - ]]></command> - <inputs> - <param format="qza,no_unzip.zip" label="--i-query: ARTIFACT FeatureData[Sequence] Sequences to classify taxonomically. [required]" name="iquery" optional="False" type="data"/> - <param format="qza,no_unzip.zip" label="--i-reference-reads: ARTIFACT FeatureData[Sequence] reference sequences. [required]" name="ireferencereads" optional="False" type="data"/> - - <conditional name="id_to_taxonomy_fp" optional="True"> - <param name="selector" type="select" label="Reference taxonomy to query"> - <option value="cached">Public databases</option> - <option value="history">Databases from your history</option> - </param> - <when value="cached"> - <param argument="--taxonomy_fp" label="Reference taxonomy" type="select" optional="True"> - <options from_data_table="qiime_taxonomy" /> - </param> - </when> - <when value="history"> - <param argument="--taxonomy_fp" type="data" format="qza,no_unzip.zip" label="Reference databases" optional="True" /> - </when> - </conditional> - <param label="--p-maxaccepts: INTEGER Maximum number of hits to keep for each query. Set Range(0, None) to 0 to keep all hits > perc-identity similarity. Must be in range [0, infinity]. [default: 10]" name="pmaxaccepts" optional="True" type="integer" min="0" value="10"/> - <param label="--p-perc-identity: PROPORTION Range(0.0, 1.0, inclusive_end=True) Reject match if percent identity to query is lower. Must be in range [0.0, 1.0]. [default: 0.8]" name="ppercidentity" optional="True" type="float" min="0" max="1" exclude_max="False" value="0.8"/> - <param label="--p-query-cov: PROPORTION Range(0.0, 1.0, inclusive_end=True) Reject match if query alignment coverage per high-scoring pair is lower. Must be in range [0.0, 1.0]. [default: 0.8]" name="pquerycov" optional="True" type="float" min="0" max="1" exclude_max="False" value="0.8"/> - <param label="--p-strand: Align against reference sequences in forward ('plus') or both directions ('both'). [default: 'both']" name="pstrand" optional="True" type="select"> - <option value="None">Selection is Optional</option> - <option selected="True" value="both">both</option> - <option value="plus">plus</option> - </param> - <param label="--p-min-consensus: NUMBER Range(0.5, 1.0, inclusive_start=False, inclusive_end=True) Minimum fraction of assignments must match top hit to be accepted as consensus assignment. Must be in range (0.5, 1.0]. [default: 0.51]" name="pminconsensus" optional="True" type="float" min="0.5" max="1" exclude_min="True" exclude_max="False" value="0.51"/> - <param label="--p-unassignable-label: TEXT [default: 'Unassigned']" name="punassignablelabel" optional="True" type="text" value="Unassigned"/> + ]]></command> + <inputs> + <param format="qza,no_unzip.zip" label="--i-query: ARTIFACT FeatureData[Sequence] Sequences to classify taxonomically. [required]" name="iquery" optional="False" type="data" /> + <param format="qza,no_unzip.zip" label="--i-reference-reads: ARTIFACT FeatureData[Sequence] reference sequences. [required]" name="ireferencereads" optional="False" type="data" /> + <param format="qza,no_unzip.zip" label="--i-reference-taxonomy: ARTIFACT FeatureData[Taxonomy] reference taxonomy labels. [required]" name="ireferencetaxonomy" optional="False" type="data" /> + <param label="--p-maxaccepts: " name="pmaxaccepts" optional="True" type="select"> + <option selected="True" value="None">Selection is Optional</option> + <option value="Int % Range(1">Int % Range(1</option> + <option value="None">None</option> + </param> + <param exclude_max="False" label="--p-perc-identity: PROPORTION Range(0.0, 1.0, inclusive_end=True) Reject match if percent identity to query is lower. [default: 0.8]" max="1.0" min="0.0" name="ppercidentity" optional="True" type="float" value="0.8" /> + <param exclude_max="False" label="--p-query-cov: PROPORTION Range(0.0, 1.0, inclusive_end=True) Reject match if query alignment coverage per high-scoring pair is lower. [default: 0.8]" max="1.0" min="0.0" name="pquerycov" optional="True" type="float" value="0.8" /> + <param label="--p-strand: " name="pstrand" optional="True" type="select"> + <option selected="True" value="None">Selection is Optional</option> + <option value="both">both</option> + <option value="plus">plus</option> + </param> + <param exclude_max="False" exclude_min="True" label="--p-min-consensus: NUMBER Range(0.5, 1.0, inclusive_start=False, inclusive_end=True) Minimum fraction of assignments must match top hit to be accepted as consensus assignment. [default: 0.51]" max="1.0" min="0.5" name="pminconsensus" optional="True" type="float" value="0.51" /> + <param label="--p-unassignable-label: TEXT [default: \'Unassigned\']" name="punassignablelabel" optional="False" type="text" value="\'Unassigned\'" /> + <param label="--p-search-exact: --p-search-exact: / --p-no-search-exact Search for exact full-length matches to the query sequences. Only 100% exact matches are reported and this command is much faster than the default. If True, the perc-identity and query-cov settings are ignored. Note: query and reference reads must be trimmed to the exact same DNA locus (e.g., primer site) because only exact matches will be reported. [default: False]" name="psearchexact" selected="False" type="boolean" /> + <param label="--p-top-hits-only: --p-top-hits-only: / --p-no-top-hits-only Only the top hits between the query and reference sequence sets are reported. For each query, the top hit is the one presenting the highest percentage of identity. Multiple equally scored top hits will be used for consensus taxonomic assignment if maxaccepts is greater than 1. [default: False]" name="ptophitsonly" selected="False" type="boolean" /> + <param label="--p-maxhits: " name="pmaxhits" optional="True" type="select"> + <option selected="True" value="None">Selection is Optional</option> + <option value="Int % Range(1">Int % Range(1</option> + <option value="None">None</option> + </param> + <param label="--p-maxrejects: " name="pmaxrejects" optional="True" type="select"> + <option selected="True" value="None">Selection is Optional</option> + <option value="Int % Range(1">Int % Range(1</option> + <option value="None">None</option> + </param> + <param label="--p-no-output-no-hits: Do not report both matching and non-matching queries. WARNING: always use the default setting for this option unless if you know what you are doing! If you set this option to False, your sequences and feature table will need to be filtered to exclude unclassified sequences, otherwise you may run into errors downstream from missing feature IDs. [default: True]" name="pnooutputnohits" selected="False" type="boolean" /> + <param exclude_max="False" label="--p-weak-id: PROPORTION Range(0.0, 1.0, inclusive_end=True) Show hits with percentage of identity of at least N, without terminating the search. A normal search stops as soon as enough hits are found (as defined by maxaccepts, maxrejects, and perc-identity). As weak-id reports weak hits that are not deduced from maxaccepts, high perc-identity values can be used, hence preserving both speed and sensitivity. Logically, weak-id must be smaller than the value indicated by perc-identity, otherwise this option will be ignored. [default: 0.0]" max="1.0" min="0.0" name="pweakid" optional="True" type="float" value="0.0" /> + <param label="--examples: Show usage examples and exit." name="examples" optional="False" type="data" /> + + </inputs> - - <param label="--p-search-exact: Search for exact full-length matches to the query sequences. Only 100% exact matches are reported and this command is much faster than the default. If True, the perc-identity and query-cov settings are ignored. Note: query and reference reads must be trimmed to the exact same DNA locus (e.g., primer site) because only exact matches will be reported. [default: False]" name="psearchexact" selected="False" type="boolean"/> - <param label="--p-top-hits-only: Only the top hits between the query and reference sequence sets are reported. For each query, the top hit is the one presenting the highest percentage of identity. Multiple equally scored top hits will be used for consensus taxonomic assignment if maxaccepts is greater than 1. [default: False]" name="ptophitsonly" selected="False" type="boolean"/> + <outputs> + <data format="qza" label="${tool.name} on ${on_string}: classification.qza" name="oclassification" /> + + </outputs> - </inputs> - <outputs> - <data format="qza" label="${tool.name} on ${on_string}: classification.qza" name="oclassification"/> - </outputs> - <help><![CDATA[ + <help><![CDATA[ VSEARCH-based consensus taxonomy classifier +############################################################### Assign taxonomy to query sequences using VSEARCH. Performs VSEARCH global alignment between query and reference_reads, then assigns consensus @@ -135,7 +127,18 @@ reference taxonomy labels. maxaccepts : Int % Range(1, None) | Str % Choices('all'), optional Maximum number of hits to keep for each query. Set to "all" to keep all - hits > perc_identity similarity. + hits > perc_identity similarity. Note that if strand=both, maxaccepts + will keep N hits for each direction (if searches in the opposite + direction yield results that exceed the minimum perc_identity). In + those cases use maxhits to control the total number of hits returned. + This option works in pair with maxrejects. The search process sorts + target sequences by decreasing number of k-mers they have in common + with the query sequence, using that information as a proxy for sequence + similarity. After pairwise alignments, if the first target sequence + passes the acceptation criteria, it is accepted as best hit and the + search process stops for that query. If maxaccepts is set to a higher + value, more hits are accepted. If maxaccepts and maxrejects are both + set to "all", the complete database is searched. perc_identity : Float % Range(0.0, 1.0, inclusive_end=True), optional Reject match if percent identity to query is lower. query_cov : Float % Range(0.0, 1.0, inclusive_end=True), optional @@ -159,6 +162,26 @@ reported. For each query, the top hit is the one presenting the highest percentage of identity. Multiple equally scored top hits will be used for consensus taxonomic assignment if maxaccepts is greater than 1. +maxhits : Int % Range(1, None) | Str % Choices('all'), optional + Maximum number of hits to show once the search is terminated. +maxrejects : Int % Range(1, None) | Str % Choices('all'), optional + Maximum number of non-matching target sequences to consider before + stopping the search. This option works in pair with maxaccepts (see + maxaccepts description for details). +output_no_hits : Bool, optional + Report both matching and non-matching queries. WARNING: always use the + default setting for this option unless if you know what you are doing! + If you set this option to False, your sequences and feature table will + need to be filtered to exclude unclassified sequences, otherwise you + may run into errors downstream from missing feature IDs. +weak_id : Float % Range(0.0, 1.0, inclusive_end=True), optional + Show hits with percentage of identity of at least N, without + terminating the search. A normal search stops as soon as enough hits + are found (as defined by maxaccepts, maxrejects, and perc_identity). As + weak_id reports weak hits that are not deduced from maxaccepts, high + perc_identity values can be used, hence preserving both speed and + sensitivity. Logically, weak_id must be smaller than the value + indicated by perc_identity, otherwise this option will be ignored. threads : Int % Range(1, None), optional Number of threads to use for job parallelization. @@ -166,9 +189,9 @@ ------- classification : FeatureData[Taxonomy] The resulting taxonomy classifications. - ]]></help> -<macros> + ]]></help> + <macros> <import>qiime_citation.xml</import> -</macros> -<expand macro="qiime_citation"/> -</tool> + </macros> + <expand macro="qiime_citation"/> +</tool> \ No newline at end of file