diff freyja_demix.xml @ 0:fc6252e78d5b draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/freyja commit 2036e233d159a5c4b3b06ce6a681531259098f73
author iuc
date Thu, 28 Jul 2022 09:26:02 +0000
parents
children c0a0e79d7196
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/freyja_demix.xml	Thu Jul 28 09:26:02 2022 +0000
@@ -0,0 +1,146 @@
+<tool id="freyja_demix" name="Freyja: Demix" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@"
+      profile="@PROFILE@">
+    <description>
+        lineage abundances
+    </description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="biotools"/>
+    <expand macro="requirements">
+        <requirement type="package" version="4.7">sed</requirement>
+    </expand>
+    <expand macro="version"/>
+    <command detect_errors="exit_code"><![CDATA[
+@RUN_FREYJA_UPDATE_COMMAND@
+#if str($sample_name.source) == 'auto':
+    #set $sn = $variants_in.element_identifier
+#else:
+    #set $sn = str($sample_name.name)
+#end if
+#set $in_file = $sn.replace(' ', '_') + '.' + $variants_in.ext
+ln -s '$variants_in' $in_file &&
+freyja demix
+    '$in_file'
+    '$depth_file'
+    #if $eps
+        --eps $eps
+    #end if
+    #if $meta
+        --meta '$meta'
+    #end if
+    $confirmedonly
+    @CUSTOM_BARCODES_COMMAND@
+    --covcut $depth_cutoff
+    --output abundances_raw.tsv &&
+sed 's/$in_file/$sn/' abundances_raw.tsv > abundances.tsv
+    ]]></command>
+    <inputs>
+        <param name="variants_in" type="data" format="tabular"
+               label="Dataset with input variant calls"
+               help="This can be a VCF dataset, or the tabular calls output of freayja call or ivar variants."/>
+        <conditional name="sample_name">
+            <param name="source" type="select" label="Set sample name"
+                   help="Select autodetect to have the dataset or collection element name used as the sample name, or, for a single input dataset, provide an explicit sample name.">
+                <option value="auto">Autodetect sample name</option>
+                <option value="manual">Specify sample name explicitly</option>
+            </param>
+            <when value="auto"/>
+            <when value="manual">
+                <param name="name" type="text" label="Name of the sample"/>
+            </when>
+        </conditional>
+        <expand macro="demixing_common_options"/>
+        <param name="depth_cutoff" argument="--covcut" type="integer" min="0" value="10"
+               multiple="true"
+               label="Depth cutoff for coverage estimate"
+               help="In the result file the coverage value will provide the 10x coverage estimate (percent of sites with 10 or greater reads- 10 is the default but can be modfied in this field. "/>
+    </inputs>
+    <outputs>
+        <data name="abundances" format="tabular"
+              label="${tool.name} on ${on_string}: Lineages abundances summary"
+              from_work_dir="abundances.tsv"/>
+    </outputs>
+    <tests>
+        <!-- Test 01: manual name sample -->
+        <test expect_num_outputs="1">
+            <param name="variants_in" value="variants.tsv"/>
+            <param name="depth_file" value="depths.tsv"/>
+            <conditional name="usher_update_option">
+                <param name="choice" value="repo"/>
+            </conditional>
+            <conditional name="sample_name">
+                <param name="source" value="manual"/>
+                <param name="name" value="samplename"/>
+            </conditional>
+            <output name="abundances" ftype="tabular">
+                <assert_contents>
+                    <has_text text="samplename"/>
+                </assert_contents>
+            </output>
+        </test>
+        <!-- Test 02: autoname sample -->
+        <test expect_num_outputs="1">
+            <param name="variants_in" value="variants.tsv"/>
+            <param name="depth_file" value="depths.tsv"/>
+            <conditional name="usher_update_option">
+                <param name="choice" value="repo"/>
+            </conditional>
+            <conditional name="sample_name">
+                <param name="source" value="auto"/>
+            </conditional>
+            <output name="abundances" ftype="tabular">
+                <assert_contents>
+                    <has_text text="summarized"/>
+                </assert_contents>
+            </output>
+        </test>
+    </tests>
+    <help><![CDATA[
+@HELP_HEADER@
+
+**Freyja demix** estimates lineage abundances in a potentially multi-lineage input sample.
+
+Inputs
+======
+
+The tool requires as input a dataset with called variants and a dataset with genome-wide sequencing depth information.
+Both types of data can be produced with *Freyja call*, but the tool accepts variant calls also in VCF format.
+
+Note
+----
+
+For single samples it is recommended to select "Specify sample name explicitly"
+under "Set sample name".
+
+To use this tool on multiple samples in parallel, please provide two
+collections in the same sample sort order - one with the variant calls, the
+other one with the sequencing depths - and select "Autodetect sample name",
+which will use collection element identifiers as the names of the samples.
+This will produce a new collection of demixing reports that can be passed to
+*Freyja: Aggregate and visualize* with sample names preserved.
+
+Selection of multiple regular called variants and depth datasets is discouraged
+since proper dataset pairing cannot be guaranteed!
+
+Outputs
+=======
+
+The tool produces tabular output that includes the lineages detected in the sample, their corresponding abundances, and a lineage summary by constellation.
+
+Example output:
+
+========== ===================================================
+           filename
+summarized [('Delta', 0.65), ('Other', 0.25), ('Alpha', 0.1')] 
+lineages   ['B.1.617.2' 'B.1.2' 'AY.6' 'Q.3']
+abundances "[0.5 0.25 0.15 0.1]"
+resid      3.14159
+coverage   95.8
+========== ===================================================
+
+
+Where *summarized* denotes a sum of all lineage abundances in a particular WHO designation (i.e. B.1.617.2 and AY.6 abundances are summed in the above example), otherwise they are grouped into "Other". The *lineage* array lists the identified lineages in descending order, and *abundances* contains the corresponding abundances estimates. The value of *resid* corresponds to the residual of the weighted least absolute devation problem used to estimate lineage abundances. The *coverage* value provides the 10x coverage estimate (percent of sites with 10 or greater reads- 10 is the default but can be modfied using the *--covcut* option).
+    ]]></help>
+    <expand macro="citations"/>
+</tool>