diff qiime2/qiime_quality-control_exclude-seqs.xml @ 0:370e0b6e9826 draft

Uploaded
author florianbegusch
date Wed, 17 Jul 2019 03:05:17 -0400
parents
children a025a4a89e07
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/qiime2/qiime_quality-control_exclude-seqs.xml	Wed Jul 17 03:05:17 2019 -0400
@@ -0,0 +1,103 @@
+<?xml version="1.0" ?>
+<tool id="qiime_quality-control_exclude-seqs" name="qiime quality-control exclude-seqs" version="2019.4">
+	<description> - Exclude sequences by alignment</description>
+	<requirements>
+		<requirement type="package" version="2019.4">qiime2</requirement>
+	</requirements>
+	<command><![CDATA[
+qiime quality-control exclude-seqs
+
+--i-query-sequences=$iquerysequences
+--i-reference-sequences=$ireferencesequences
+
+#if str($pmethod) != 'None':
+ --p-method=$pmethod
+#end if
+
+#if $ppercidentity:
+ --p-perc-identity=$ppercidentity
+#end if
+
+#if str($pevalue):
+ --p-evalue="$pevalue"
+#end if
+
+#if $ppercqueryaligned:
+ --p-perc-query-aligned=$ppercqueryaligned
+#end if
+
+#set $pthreads = '${GALAXY_SLOTS:-4}'
+#if str($pthreads):
+ --p-threads="$pthreads"
+#end if
+
+--o-sequence-hits=osequencehits
+--o-sequence-misses=osequencemisses
+;
+cp osequencehits.qza $osequencehits;
+cp osequencemisses.qza $osequencemisses
+	]]></command>
+	<inputs>
+		<param format="qza,no_unzip.zip" label="--i-query-sequences: ARTIFACT FeatureData[Sequence] Sequences to test for exclusion              [required]" name="iquerysequences" optional="False" type="data"/>
+		<param format="qza,no_unzip.zip" label="--i-reference-sequences: ARTIFACT FeatureData[Sequence] Reference sequences to align against feature sequences [required]" name="ireferencesequences" optional="False" type="data"/>
+		<param label="--p-method: " name="pmethod" optional="True" type="select">
+			<option selected="True" value="None">Selection is Optional</option>
+			<option value="blast">blast</option>
+			<option value="vsearch">vsearch</option>
+			<option value="blastn-short">blastn-short</option>
+		</param>
+		<param label="--p-perc-identity: PROPORTION Range(0.0, 1.0, inclusive_end=True) Reject match if percent identity to reference is lower. Must be in range [0.0, 1.0]      [default: 0.97]" name="ppercidentity" optional="True" type="float" value="0.97" min="0" max="1" exclusive_end="False"/>
+		<param label="--p-evalue: NUMBER    BLAST expectation (E) value threshold for saving hits. Reject if E value is higher than threshold. This threshold is disabled by default.            [optional]" name="pevalue" optional="True" type="text"/>
+		<param label="--p-perc-query-aligned: NUMBER Percent of query sequence that must align to reference in order to be accepted as a hit.       [default: 0.97]" name="ppercqueryaligned" optional="True" type="float" value="0.97"/>
+	</inputs>
+	<outputs>
+		<data format="qza" label="${tool.name} on ${on_string}: sequencehits.qza" name="osequencehits"/>
+		<data format="qza" label="${tool.name} on ${on_string}: sequencemisses.qza" name="osequencemisses"/>
+	</outputs>
+	<help><![CDATA[
+Exclude sequences by alignment
+##############################
+
+This method aligns feature sequences to a set of reference sequences to
+identify sequences that hit/miss the reference within a specified
+perc_identity, evalue, and perc_query_aligned. This method could be used to
+define a positive filter, e.g., extract only feature sequences that align
+to a certain clade of bacteria; or to define a negative filter, e.g.,
+identify sequences that align to contaminant or human DNA sequences that
+should be excluded from subsequent analyses. Note that filtering is
+performed based on the perc_identity, perc_query_aligned, and evalue
+thresholds (the latter only if method==BLAST and an evalue is set). Set
+perc_identity==0 and/or perc_query_aligned==0 to disable these filtering
+thresholds as necessary.
+
+Parameters
+----------
+query_sequences : FeatureData[Sequence]
+    Sequences to test for exclusion
+reference_sequences : FeatureData[Sequence]
+    Reference sequences to align against feature sequences
+method : Str % Choices('blast', 'vsearch', 'blastn-short'), optional
+    Alignment method to use for matching feature sequences against
+    reference sequences
+perc_identity : Float % Range(0.0, 1.0, inclusive_end=True), optional
+    Reject match if percent identity to reference is lower. Must be in
+    range [0.0, 1.0]
+evalue : Float, optional
+    BLAST expectation (E) value threshold for saving hits. Reject if E
+    value is higher than threshold. This threshold is disabled by default.
+perc_query_aligned : Float, optional
+    Percent of query sequence that must align to reference in order to be
+    accepted as a hit.
+
+Returns
+-------
+sequence_hits : FeatureData[Sequence]
+    Subset of feature sequences that align to reference sequences
+sequence_misses : FeatureData[Sequence]
+    Subset of feature sequences that do not align to reference sequences
+	]]></help>
+<macros>
+    <import>qiime_citation.xml</import>
+</macros>
+<expand macro="qiime_citation"/>
+</tool>