Cmsearch: added missing args to command

tools/rna_tools/infernal/cmalign.xml

@@ -3,9 +3,9 @@
     <macros>
         <import>macros.xml</import>
     </macros>
+    <expand macro="xrefs"/>
     <expand macro="requirements" />
     <expand macro="stdio" />
-    <expand macro="xrefs"/>
     <command>
 <![CDATA[
 
@@ -76,7 +76,7 @@
             </param>
             <when value="db">
                 <param name="database" type="select" label="Covariance models">
-                    <options from_file="infernal.loc">
+                    <options from_data_table="infernal.loc">
                       <column name="value" index="0"/>
                       <column name="name" index="1"/>
                       <column name="path" index="2"/>
@@ -105,8 +105,11 @@
                 </when>
             </conditional>
             <conditional name="notrunc_opt">
-                <param argument="--notrunc" truevalue="" falsevalue="--notrunc" checked="true" type="boolean"
-                label="Use truncated alignment algorithm" help=""/>
+                <param argument="--notrunc" truevalue="" falsevalue="--notrunc" type="select"
+                label="Use truncated alignment algorithm">
+                    <option value="">Yes</option>
+                    <option value="--notrunc">No</option>
+                </param>
                 <when value=""></when>
                 <when value="--notrunc">
                     <param argument="--sub" type="boolean" truevalue="--sub" falsevalue="" checked="false"
@@ -143,8 +146,11 @@
 
         <section name="other_opts" title="Other options">
             <conditional name="mapali_opt">
-                <param name="mapali_cond" type="boolean" checked="false"
-                    label="Read the aligment file that used to build the CM" help="The alignment from the file is held fixed. This allows you to align sequences to a model with cmalign and view them in the context of an existing trusted multiple alignment."/>
+                <param name="mapali_cond" type="select"
+                    label="Read the aligment file that used to build the CM" help="The alignment from the file is held fixed. This allows you to align sequences to a model with cmalign and view them in the context of an existing trusted multiple alignment.">
+                    <option value="false">No</option>
+                    <option value="true">Yes</option>
+                </param>
                 <when value="true">
                     <param argument="--mapali" type="data" format="fasta"
                         label="The aligment file that used to build the CM" help=""/>

tools/rna_tools/infernal/cmbuild.xml

@@ -4,9 +4,9 @@
         <import>macros.xml</import>
     </macros>
     <!--parallelism method="multi" split_inputs="alignment_infile" split_mode="to_size" split_size="10" merge_outputs="cmfile_outfile"></parallelism-->
+    <expand macro="xrefs"/>
     <expand macro="requirements" />
     <expand macro="stdio" />
-    <expand macro="xrefs"/>
     <command>
 <![CDATA[
     cmbuild
@@ -196,19 +196,22 @@
                         <option value="--cyk">align with the CYK algorithm</option>
                     </param>
 
-                    <param name="refine_output" truevalue="" falsevalue="" checked="False" type="boolean"
+                    <param name="refine_output" truevalue="--refine" falsevalue="" checked="False" type="boolean"
                         label="Output the refined alignment file as it is used to build the covariance model" help=""/>
 
                 </when>
             </conditional>
 
-            <param name="is_summery_output" truevalue="" falsevalue="" checked="False" type="boolean"
+            <param name="is_summery_output" truevalue="-o" falsevalue="" checked="False" type="boolean"
                 label="Output a summery file?" help=""/>
 
             <!-- calibrate options -->
             <conditional name="Calibrate">
-                <param name="selector" type="boolean" checked="true" label="Calibrate the covariance model"
-                    help="A CM file must be calibrated with cmcalibrate before it can be used in cmsearch or cmscan. cmcalibrate is very slow. It takes a couple of hours to calibrate a single average sized CM on a single CPU"/>
+                <param name="selector" type="select" label="Calibrate the covariance model"
+                    help="A CM file must be calibrated with cmcalibrate before it can be used in cmsearch or cmscan. cmcalibrate is very slow. It takes a couple of hours to calibrate a single average sized CM on a single CPU">
+                    <option value="true">Yes</option>
+                    <option value="false">No</option>
+                </param>
                 <when value="false"/>
                 <when value="true">
                     <param argument="-L" type="float" value="1.6" min="0.01" max="160" label="Total length of random sequences to search" help="Set random seq length to search in Mb (megabases)"/>
@@ -325,7 +328,7 @@
     </outputs>
 
     <tests>
-        <test>
+        <test expect_num_outputs="1">
             <param name="alignment_infile" value="cmbuild_input_tRNA5.sto"/>
             <conditional name="Calibrate">
                 <param name="selector" value="true"/>
@@ -338,7 +341,7 @@
             </output>
         </test>
         <!-- Test emax seq parameter -->
-        <test>
+        <test expect_num_outputs="1">
             <param name="alignment_infile" value="cmbuild_input_tRNA5.sto"/>
             <conditional name="Calibrate">
                 <param name="selector" value="true"/>
@@ -422,8 +425,7 @@ These options control how consensus columns are defined in an alignment.
 
 cmbuild uses an ad hoc sequence weighting algorithm to downweight closely related sequences and upweight distantly related ones. This has the effect of making models less biased by uneven phylogenetic representation. For example, two identical sequences would typically each receive half the weight that one sequence would. These options control which algorithm gets used.
 
-  - *--wgb*: Use the Henikoff position-based sequence weighting scheme [Henikoff
-and Henikoff, J. Mol. Biol. 243:574, 1994].  This is the default.
+  - *--wgb*: Use the Henikoff position-based sequence weighting scheme [Henikoff and Henikoff, J. Mol. Biol. 243:574, 1994].  This is the default.
   - *--wgsc*: Use the Gerstein/Sonnhammer/Chothia weighting algorithm [Gerstein et al, J. Mol. Biol. 235:1067, 1994].
   - *--wnone*: Turn sequence weighting off; e.g. explicitly set all sequence weights to 1.0.
   - *--wgiven*: Use sequence weights as given in annotation in the input alignment file. If no weights were given, assume they are all 1.0. The default is to determine new sequence weights by the Gerstein/Sonnhammer/Chothia algorithm, ignoring any annotated weights.

tools/rna_tools/infernal/cmpress.xml

@@ -1,25 +1,23 @@
-<tool id="infernal_cmpress" name="cmpress" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@">
+<tool id="infernal_cmpress" name="cmpress" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="23.0">
     <description> Prepare a covariance model database for cmscan</description>
     <macros>
         <import>macros.xml</import>
     </macros>
+    <expand macro="xrefs"/>
     <expand macro="requirements" />
     <expand macro="stdio" />
-    <expand macro="xrefs"/>
-    <command>
+    <command detect_errors="aggressive">
 <![CDATA[
-    ## CM file from the history or stored as database on disc
+    mkdir -p ./cm_model &&
     #if str($cm_opts.cm_opts_selector) == "db":
-        cmfile_path='$cm_opts.database.fields.path'
+        ln -s '$cm_opts.database.fields.path' ./cm_model/
     #else:
-        ##'$cm_opts.cmfile'
-        cmfile_path='$cmfile'
+        ln -s '$cmfile' ./cm_model/
     #end if
     &&
-    cmpress -F "\$cmfile_path" &&
-    ##cmpress creates four files in the same directory of the cm file
-    cd `dirname "\$cmfile_path"` &&
-    tar -cvf '$outfile' `basename "\$cmfile_path"`.i1*
+    cmpress -F ./cm_model/* &&
+    cd ./cm_model/ &&
+    tar -cvf '$outfile' *.i1f *.i1i *.i1m *.i1p
 ]]>
     </command>
     <inputs>
@@ -30,7 +28,7 @@
             </param>
             <when value="db">
                 <param name="database" type="select" label="Covariance models">
-                    <options from_file="infernal.loc">
+                    <options from_data_table="infernal.loc">
                         <column name="value" index="0"/>
                         <column name="name" index="1"/>
                         <column name="path" index="2"/>
@@ -86,4 +84,4 @@ For further questions please refere to the Infernal `Userguide <http://eddylab.o
     <expand macro="citations" />
 
 
-</tool>
+</tool>

tools/rna_tools/infernal/cmscan.xml

@@ -3,9 +3,9 @@
     <macros>
         <import>macros.xml</import>
     </macros>
+    <expand macro="xrefs"/>
     <expand macro="requirements"/>
     <expand macro="stdio"/>
-    <expand macro="xrefs"/>
     <command>
 <![CDATA[
     ## a temp file is needed, because the standard tabular output from infernal is not usefull in Galaxy
@@ -100,7 +100,7 @@
             </param>
             <when value="db">
                 <param name="database" type="select" label="Covariance models">
-                    <options from_file="infernal.loc">
+                    <options from_data_table="infernal.loc">
                         <column name="value" index="0"/>
                         <column name="name" index="1"/>
                         <column name="path" index="2"/>

tools/rna_tools/infernal/cmsearch.xml

@@ -4,9 +4,9 @@
         <import>macros.xml</import>
     </macros>
     <!--parallelism method="multi" split_inputs="seqdb" split_mode="to_size" split_size="500" merge_outputs="outfile,multiple_alignment_output"></parallelism-->
+    <expand macro="xrefs"/>
     <expand macro="requirements"/>
     <expand macro="stdio" />
-    <expand macro="xrefs"/>
     <command>
 <![CDATA[
         ## a temp file is needed, because the standard tabular output from infernal is not usefull in Galaxy
@@ -39,6 +39,8 @@
             #if $A:
                 $A '$multiple_alignment_output'
             #end if
+            $noali
+            $verbose
             #if str($inclusion_thresholds_opts.inclusion_thresholds_selector) == "--incE":
                 --incE $inclusion_thresholds_opts.incE
             #elif str($inclusion_thresholds_opts.inclusion_thresholds_selector) == "--incT":
@@ -87,7 +89,7 @@
             </param>
             <when value="db">
                 <param name="database" type="select" label="Covariance models">
-                    <options from_file="infernal.loc">
+                    <options from_data_table="infernal.loc">
                       <column name="value" index="0"/>
                       <column name="name" index="1"/>
                       <column name="path" index="2"/>
@@ -241,7 +243,7 @@
 
     </outputs>
     <tests>
-        <test>
+        <test expect_num_outputs="1">
             <conditional name="cm_opts">
                 <param name="cm_opts_selector" value="histdb"/>
                 <param name="cmfile" value="cmsearch_input1.cm"/>

tools/rna_tools/infernal/cmstat.xml

@@ -3,9 +3,9 @@
     <macros>
         <import>macros.xml</import>
     </macros>
+    <expand macro="xrefs"/>
     <expand macro="requirements"/>
     <expand macro="stdio" />
-    <expand macro="xrefs"/>
     <command>
 <![CDATA[
         ## a temp file is needed, because the standard tabular output from infernal is not usefull in Galaxy
@@ -32,7 +32,7 @@
                 </param>
                 <when value="db">
                     <param name="database" type="select" label="Covariance models">
-                        <options from_file="infernal.loc">
+                        <options from_data_table="infernal.loc">
                           <column name="value" index="0"/>
                           <column name="name" index="1"/>
                           <column name="path" index="2"/>

tools/rna_tools/infernal/macros.xml

@@ -1,12 +1,11 @@
 <macros>
     <xml name="requirements">
         <requirements>
-            <requirement type="package">infernal</requirement>
-            <requirement type="package" version="1.1.4">infernal</requirement>
-            <requirement type="package" version="8.32">coreutils</requirement>
+            <requirement type="package" version="@TOOL_VERSION@">infernal</requirement>
+            <requirement type="package" version="9.5">coreutils</requirement>
         </requirements>
     </xml>
-    <token name="@TOOL_VERSION@">1.1.4</token>
+    <token name="@TOOL_VERSION@">1.1.5</token>
     <token name="@VERSION_SUFFIX@">0</token>
     <xml name="xrefs">
         <xrefs>

tools/rna_tools/infernal/test-data/test_cmscan.tabular

@@ -5,11 +5,11 @@ tRNA5	-	AAGA01015927.1	-	cm	1	72	314	386	+	no	1	0.59	0.0	53.5	6e-16	!
 Cobalamin	RF00174	AAFY01022046.1	-	cm	32	191	934	832	-	5'	2	0.48	0.0	30.0	6.1e-09	!	                 Cobalamin riboswitch
 #																	                
 #	Program:	cmscan															                
-#	Version:	1.1.4	(Dec	2020)													                
+#	Version:	1.1.5	(Sep	2023)													                
 #	Pipeline	mode:	SCAN														                
-#	Query	file:	/tmp/tmp6jwp47cs/files/a/6/f/dataset_a6fe922b-72aa-4753-b4dd-cd3c716a4ae5.dat														                
+#	Query	file:	/tmp/tmpst0r7qh9/files/7/3/7/dataset_7373cb0d-0d12-49b5-96e0-e1aabaa6db38.dat														                
 #	Target	file:	cmdb.cm														                
-#	Option	settings:	cmscan	-o	/dev/null	--tblout	$temp_tabular_output	--default	--cpu	1	cmdb.cm	/tmp/tmp6jwp47cs/files/a/6/f/dataset_a6fe922b-72aa-4753-b4dd-cd3c716a4ae5.dat					                
-#	Current	dir:	/tmp/tmp6jwp47cs/job_working_directory/000/13/working														                
-#	Date:	Thu	Sep	23	15:21:39	2021											                
+#	Option	settings:	cmscan	-o	/dev/null	--tblout	$temp_tabular_output	--default	--cpu	1	cmdb.cm	/tmp/tmpst0r7qh9/files/7/3/7/dataset_7373cb0d-0d12-49b5-96e0-e1aabaa6db38.dat					                
+#	Current	dir:	/tmp/tmpst0r7qh9/job_working_directory/000/4/working														                
+#	Date:	Thu	Oct	17	11:28:32	2024											                
 #	[ok]