From 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B6rn=20Gr=C3=BCning?= <bjoern@gruenings.eu>
Date: Sun, 11 Aug 2024 22:59:30 +0200
Subject: [PATCH] add new reference genomes (#6221)

---
 tools/basil/all_fasta.loc.sample            | 18 +++++++
 tools/basil/basil.xml                       | 54 ++++++++++++++++++---
 tools/basil/test-data/all_fasta.loc.test    |  1 +
 tools/basil/tool_data_table_conf.xml.sample |  9 ++++
 tools/basil/tool_data_table_conf.xml.test   |  7 +++
 5 files changed, 81 insertions(+), 8 deletions(-)
 create mode 100644 tools/basil/all_fasta.loc.sample
 create mode 100644 tools/basil/test-data/all_fasta.loc.test
 create mode 100644 tools/basil/tool_data_table_conf.xml.sample
 create mode 100755 tools/basil/tool_data_table_conf.xml.test

diff --git a/tools/basil/all_fasta.loc.sample b/tools/basil/all_fasta.loc.sample
new file mode 100644
index 00000000000..1a5a28d5e3f
--- /dev/null
+++ b/tools/basil/all_fasta.loc.sample
@@ -0,0 +1,18 @@
+#This file lists the locations and dbkeys of all the fasta files
+#under the "genome" directory (a directory that contains a directory
+#for each build). The script extract_fasta.py will generate the file
+#all_fasta.loc. This file has the format (white space characters are
+#TAB characters):
+#
+#<unique_build_id>	<dbkey>	<display_name>	<file_path>
+#
+#So, all_fasta.loc could look something like this:
+#
+#apiMel3	apiMel3	Honeybee (Apis mellifera): apiMel3	/path/to/genome/apiMel3/apiMel3.fa
+#hg19canon	hg19	Human (Homo sapiens): hg19 Canonical	/path/to/genome/hg19/hg19canon.fa
+#hg19full	hg19	Human (Homo sapiens): hg19 Full	/path/to/genome/hg19/hg19full.fa
+#
+#Your all_fasta.loc file should contain an entry for each individual
+#fasta file. So there will be multiple fasta files for each build,
+#such as with hg19 above.
+#
diff --git a/tools/basil/basil.xml b/tools/basil/basil.xml
index 5d22e1560f5..39cd204a4c5 100644
--- a/tools/basil/basil.xml
+++ b/tools/basil/basil.xml
@@ -1,11 +1,19 @@
-<tool id="basil" name="basil" version="1.2.0">
+<tool id="basil" name="basil" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="23.0">
     <description>Breakpoint detection, including large insertions</description>
+    <macros>
+        <token name="@TOOL_VERSION@">1.2.0</token>
+        <token name="@VERSION_SUFFIX@">1</token>
+    </macros>
     <requirements>
-        <requirement type="package" version="1.2.0">anise_basil</requirement>
+        <requirement type="package" version="@TOOL_VERSION@">anise_basil</requirement>
     </requirements>
-    <version_command>basil --version 2>&amp;1 | grep 'basil version' | cut -f 3 -d ' '</version_command>
+    <version_command>basil --version 2&gt;&amp;1 | grep 'basil version' | cut -f 3 -d ' '</version_command>
     <command detect_errors="aggressive"><![CDATA[
-        ln -s '$ref' 'ref.fa' &&
+        #if $reference_source.reference_source_selector == 'history':
+            ln -f -s '$reference_source.ref' ref.fa &&
+        #else:
+            ln -f -s '$reference_source.ref.fields.path' ref.fa &&
+        #end if
         ln -s '$bam' 'in.bam' &&
         ln -s '$vcf' 'out.vcf' &&
         basil
@@ -15,18 +23,48 @@
         --oea-min-support-each-side '$min_oea_each_side'
     ]]></command>
     <inputs>
-        <param name="ref" argument="--input-reference" type="data" format="Fasta" label="Reference Sequence File" help="FASTA file with the reference."/>
+        <conditional name="reference_source">
+            <param name="reference_source_selector" type="select" label="Select a reference genome from your history or use a built-in index?" help="Built-ins were indexed using default options. See `Indexes` section of help below. If you would like to perform self-mapping select `history` here, then choose your input file as reference.">
+                <option value="cached">Use a built-in genome index</option>
+                <option value="history">Use a genome from history and build index</option>
+            </param>
+            <when value="cached">
+                <param name="ref" type="select" label="Using reference genome" help="Select genome from the list">
+                    <options from_data_table="all_fasta">
+                        <filter type="sort_by" column="2"/>
+                        <validator type="no_options" message="No reference genomes are available"/>
+                    </options>
+                    <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/>
+                </param>
+            </when>
+            <when value="history">
+                <param name="ref" argument="--input-reference" type="data" format="Fasta" label="Reference Sequence File" help="FASTA file with the reference."/>
+            </when>
+        </conditional>
         <param name="bam" argument="--input-mapping" type="data" format="sam,bam" label="Alignment File" help="SAM/BAM file to use as the input."/>
-        <param name="min_oea_each_side" argument="--oea-min-support-each-side" type="integer" value="2" label="Minimum supporting reads, each side" help="Smallest number of OEA (one-end-anchor) reads on each side to support an insertion.  In range [1..inf].  This is the minimum number of supporting reads (without mapped partners) on each side of an insertion breakpoint required to not be filtered." />
+        <param name="min_oea_each_side" argument="--oea-min-support-each-side" type="integer" value="2" label="Minimum supporting reads, each side" help="Smallest number of OEA (one-end-anchor) reads on each side to support an insertion.  In range [1..inf].  This is the minimum number of supporting reads (without mapped partners) on each side of an insertion breakpoint required to not be filtered."/>
     </inputs>
     <outputs>
-        <data name="vcf" format="vcf" />
+        <data name="vcf" format="vcf"/>
     </outputs>
     <tests>
         <test>
+            <conditional name="reference_source">
+                <param name="reference_source_selector" value="history" />
+                <param name="ref" ftype="fasta" value="ref.fa"/>
+            </conditional>
             <param name="ref" value="ref.fa"/>
             <param name="bam" value="simulated.bam"/>
-            <param name="min_oea_each_side"  value="2"/>
+            <param name="min_oea_each_side" value="2"/>
+            <output name="vcf" file="basil.vcf"/>
+        </test>
+        <test>
+            <conditional name="reference_source">
+                <param name="reference_source_selector" value="cached" />
+                <param name="ref" value="genome"/>
+            </conditional>
+            <param name="bam" value="simulated.bam"/>
+            <param name="min_oea_each_side" value="2"/>
             <output name="vcf" file="basil.vcf"/>
         </test>
     </tests>
diff --git a/tools/basil/test-data/all_fasta.loc.test b/tools/basil/test-data/all_fasta.loc.test
new file mode 100644
index 00000000000..bb76fc97735
--- /dev/null
+++ b/tools/basil/test-data/all_fasta.loc.test
@@ -0,0 +1 @@
+genome	genome-dbkey	genome-display	${__HERE__}/ref.fa
diff --git a/tools/basil/tool_data_table_conf.xml.sample b/tools/basil/tool_data_table_conf.xml.sample
new file mode 100644
index 00000000000..a0a46446a5c
--- /dev/null
+++ b/tools/basil/tool_data_table_conf.xml.sample
@@ -0,0 +1,9 @@
+<!-- Use the file tool_data_table_conf.xml.oldlocstyle if you don't want to update your loc files as changed in revision 4550:535d276c92bc-->
+<tables>
+    <!-- Locations of all fasta files under genome directory -->
+    <table name="all_fasta" comment_char="#" allow_duplicate_entries="False">
+        <columns>value, dbkey, name, path</columns>
+        <file path="tool-data/all_fasta.loc" />
+    </table>
+</tables>
+
diff --git a/tools/basil/tool_data_table_conf.xml.test b/tools/basil/tool_data_table_conf.xml.test
new file mode 100755
index 00000000000..ff6e8fbd1ed
--- /dev/null
+++ b/tools/basil/tool_data_table_conf.xml.test
@@ -0,0 +1,7 @@
+<tables>
+    <!-- Locations of all fasta files under genome directory -->
+    <table name="all_fasta" comment_char="#" allow_duplicate_entries="False">
+        <columns>value, dbkey, name, path</columns>
+        <file path="${__HERE__}/test-data/all_fasta.loc.test" />
+    </table>
+</tables>