Add deeparg

data_managers/data_manager_deeparg/.shed.yml

@@ -0,0 +1,13 @@
+name: data_manager_deeparg
+owner: iuc
+description: "Download deepARG database"
+homepage_url: "https://github.com/gaarangoa/deeparg"
+long_description: |
+    Data manager to download the database needed for deepARG to run (datasets, databases, models)
+remote_repository_url: "https://github.com/galaxyproject/tools-iuc/tree/master/data_managers/data_manager_deeparg"
+type: unrestricted
+categories:
+- Data Managers
+suite:
+  name: "suite_deeparg"
+  description: "DeepARG is a deep learning based approach to predict Antibiotic Resistance Genes (ARGs) from metagenomes with short or long sequences"

data_managers/data_manager_deeparg/data_manager/data_manager_deeparg.xml

@@ -0,0 +1,65 @@
+<tool id="data_manager_deeparg" name="Download data for DeepARG" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" tool_type="manage_data" profile="22.05">
+    <description></description>
+    <macros>
+        <token name="@TOOL_VERSION@">1.0.4</token>
+        <token name="@VERSION_SUFFIX@">0</token>
+    </macros>
+    <requirements>
+        <requirement type="package" version="@TOOL_VERSION@">deeparg</requirement>
+    </requirements>
+    <stdio>
+        <exit_code range=":-1" level="fatal" description="Error: Cannot open file"/>
+        <exit_code range="1:" level="fatal" description="Error"/>
+    </stdio>
+    <command><![CDATA[
+        mkdir -p '$out_file.extra_files_path' &&
+        deeparg download_data -o 'deeparg_$version' &&
+        mv 'deeparg_$version' '$out_file.extra_files_path' &&
+        cp '$dmjson' '$out_file'
+    ]]></command>
+     <configfiles>
+        <configfile name="dmjson"><![CDATA[
+#from datetime import date
+{
+  "data_tables":{
+    "deeparg_database_versioned":[
+      {
+        "value": "deeparg_$version-#echo date.today().strftime('%d%m%Y')#",
+        "name": "Files needed for running deepARG v-$version-#echo date.today().strftime('%d%m%Y')#",
+        "path": "deeparg_$version",
+        "db_version": "$version"
+      }
+    ]
+  }
+}]]>
+        </configfile>
+    </configfiles>
+    <inputs>
+        <param name="version" type="select" label="DB version">
+            <option value="1.0.4" selected="true">Data needed for running DeepARG v1.0.4</option>
+        </param>
+    </inputs>
+    <outputs>
+        <data name="out_file" format="data_manager_json" label="${tool.name}"/>
+    </outputs>
+    <tests>
+        <test expect_num_outputs="1">
+            <param name="version" value="1.0.4"/>
+            <output name="out_file">
+                <assert_contents>
+                    <has_text text='"deeparg_database_versioned":'/>
+                    <has_text text='"db_version": "1.0.4"'/>
+                    <has_text_matching expression='"value": "deeparg_1.0.4-[0-9]{8}"'/>
+                    <has_text_matching expression='"name": "Files needed for running deepARG v-1.0.4-[0-9]{8}"'/>
+                    <has_text text='"path": "deeparg_1.0.4"'/>
+                </assert_contents>
+            </output>
+        </test>
+    </tests>
+    <help><![CDATA[
+DeepARG is a tool to predict antibiotic resistance genes (ARGs) in metagenomic samples.
+    ]]></help>
+    <citations>
+        <citation type="doi">10.1186/s40168-018-0401-z</citation>
+    </citations>
+</tool>

data_managers/data_manager_deeparg/data_manager_conf.xml

@@ -0,0 +1,21 @@
+<?xml version="1.0"?>
+<data_managers>
+    <data_manager tool_file="data_manager/data_manager_deeparg.xml" id="data_manager_deeparg">
+        <data_table name="deeparg_database_versioned">  <!-- Defines a Data Table to be modified. -->
+            <output> <!-- Handle the output of the Data Manager Tool -->
+                <column name="value"/>  <!-- columns that are going to be specified by the Data Manager Tool -->
+                <column name="name"/>  <!-- columns that are going to be specified by the Data Manager Tool -->
+                <column name="path" output_ref="out_file">
+                    <move type="directory">
+                        <source>${path}</source>
+                        <target base="${GALAXY_DATA_MANAGER_DATA_PATH}">deeparg_db/${path}</target>
+                    </move>
+                    <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/deeparg_db/${path}</value_translation>
+                    <value_translation type="function">abspath</value_translation>
+                </column>
+                <column name="db_version"/> <!-- columns that are going to be specified by the Data Manager Tool -->
+            </output>
+        </data_table>
+    </data_manager>
+</data_managers>
+

data_managers/data_manager_deeparg/test-data/deeparg_database_versioned.loc.test

@@ -0,0 +1,5 @@
+#This is a sample file distributed with Galaxy that enables tools
+#to use a directory of metagenomics files.  
+#file has this format (white space characters are TAB characters)
+#deeparg_1.0.4	Files needed for running deepARG (1.0.4)	deeparg_1.0.4-20241010	/path/to/data	1.0.4
+deeparg_1.0.4-19122024	Files needed for running deepARG v-1.0.4-19122024	/tmp/tmpizmxs2l_/galaxy-dev/tool-data/deeparg_db/deeparg_1.0.4	1.0.4

data_managers/data_manager_deeparg/tool-data/deeparg_database_versioned.loc.sample

@@ -0,0 +1,4 @@
+#This is a sample file distributed with Galaxy that enables tools
+#to use a directory of metagenomics files.  
+#file has this format (white space characters are TAB characters)
+#deeparg_1.0.4	Files needed for running deepARG (1.0.4)	deeparg_1.0.4-20241010	/path/to/data	1.0.4

data_managers/data_manager_deeparg/tool_data_table_conf.xml.sample

@@ -0,0 +1,6 @@
+<tables>
+    <table name="deeparg_database_versioned" comment_char="#">
+        <columns>value, name, path, db_version</columns>
+        <file path="tool-data/deeparg_database_versioned.loc.sample"/>
+    </table>
+</tables>

data_managers/data_manager_deeparg/tool_data_table_conf.xml.test

@@ -0,0 +1,6 @@
+<tables>
+    <table name="deeparg_database_versioned" comment_char="#">
+        <columns>value, name, path, db_version</columns>
+        <file path="${__HERE__}/test-data/deeparg_database_versioned.loc.test"/>
+    </table>
+</tables>

tools/deeparg/.shed.yml

@@ -0,0 +1,15 @@
+name: deeparg
+owner: iuc
+long_description: |
+  A deep learning based approach to predict Antibiotic Resistance Genes (ARGs) from metagenomes
+categories:
+- Sequence Analysis
+remote_repository_url: https://github.com/galaxyproject/tools-iuc/tree/master/tools/deeparg
+homepage_url: https://github.com/gaarangoa/deeparg
+type: unrestricted
+auto_tool_repositories:
+  name_template: "{{ tool_id }}"
+  description_template: "Wrapper for the DeepARG tool suite: {{ tool_name }}"
+suite:
+  name: "suite_deeparg"
+  description: "DeepARG is a deep learning based approach to predict Antibiotic Resistance Genes (ARGs) from metagenomes with short or long sequences"

tools/deeparg/deeparg_predict.xml

@@ -0,0 +1,129 @@
+<tool id="deeparg_predict" name="DeepARG predict" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
+    <description>Antibiotic Resistance Genes (ARGs) from metagenomes</description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="xrefs"/>
+    <expand macro="requirements"/>
+    <command detect_errors="exit_code"><![CDATA[
+##Used only for test 
+#if str($hide_db_build) == 'true':
+    deeparg download_data -o deeparg_1.0.4 &&
+#end if
+##
+    mkdir -p deeparg_predict_output &&
+    deeparg predict
+        --model '$model'
+        -i '$input'
+        -o 'deeparg_predict_output/deeparg_predict'
+        -d '$deeparg_db.fields.path'
+        --type '$type'
+        --min-prob $min_prob
+        --arg-alignment-identity $arg_alignment_identity
+        --arg-alignment-evalue $arg_alignment_evalue
+        --arg-alignment-overlap $arg_alignment_overlap
+        --arg-num-alignments-per-entry $arg_num_alignments_per_entry 
+]]></command>
+    <inputs>
+        <!-- used only for tests, as the deeparg database contains large files that cannot be deleted or reduced. -->
+        <param name="hide_db_build" type="hidden" value=""/>
+        <!-- -->
+        <param name="input" type="data" format="fasta" label="Input file"/>
+        <param name="deeparg_db" type="select" label="DeepARG database">
+            <options from_data_table="deeparg_database_versioned">
+                <validator message="No deeparg database is available" type="no_options"/>
+            </options>
+        </param>
+        <param argument="--model" type="select" label="Select model to use">
+            <option value="SS" selected="true">SS (short sequences for reads)</option>
+            <option value="LS">LS (long sequences for genes)</option>
+        </param>
+        <param argument="--type" type="select" label="Molecular data type">
+            <option value="nucl" selected="true">Nucleotid (default)</option>
+            <option value="prot">Protein</option>
+        </param>
+        <param argument="--min-prob" type="float" min="0" max="1" value="0.8" label="Minimum probability cutoff [Default: 0.8]"/>
+        <param argument="--arg-alignment-identity" type="integer" min="0" value="50" label="Identity cutoff for sequence alignment [Default: 50]"/>
+        <param argument="--arg-alignment-evalue" type="float" min="0" value="1e-10" label="Evalue cutoff [Default: 1e-10]"/>
+        <param argument="--arg-alignment-overlap" type="float" min="0" max="1" value="0.8" label="Alignment read overlap [Default: 0.8]"/>
+        <param argument="--arg-num-alignments-per-entry" type="integer" min="0" value="1000" label="Diamond, minimum number of alignments per entry [Default: 1000]"/>
+        <section name="output_files" title="Selection of the output files">
+            <param name="output_selection" type="select" label="Output files selection" display="checkboxes" multiple="true">
+                <option value="file_ARG_tsv" selected="true">ARG detected with prob higher or equal to --prob in TSV</option>
+                <option value="file_potential_ARG_tsv" selected="true">ARG detected with prob below --prob in TSV</option>
+                <option value="file_all_hits_tsv" selected="false">All hits detected in TSV</option>
+            </param>
+        </section>
+    </inputs>
+    <outputs>
+        <data name="output_mapping_ARG" format="tabular" from_work_dir="deeparg_predict_output/deeparg_predict.mapping.ARG" label="${tool.name} on ${on_string} : ARG detected (prob higher or equal to --prob)">
+            <filter>output_files['output_selection'] and "file_ARG_tsv" in output_files['output_selection']</filter>
+        </data>
+        <data name="output_mapping_potential_ARG" format="tabular" from_work_dir="deeparg_predict_output/deeparg_predict.mapping.potential.ARG" label="${tool.name} on ${on_string} : Potential ARG (prob below --prob)">
+            <filter>output_files['output_selection'] and "file_potential_ARG_tsv" in output_files['output_selection']</filter>
+        </data>
+        <data name="output_all_hits" format="tabular" from_work_dir="deeparg_predict_output/deeparg_predict.align.daa.tsv" label="${tool.name} on ${on_string} : all hits detected">
+            <filter>output_files['output_selection'] and "file_all_hits_tsv" in output_files['output_selection']</filter>
+        </data>
+    </outputs>
+    <tests>
+        <!-- Test 1 -->
+        <test expect_num_outputs="3">
+            <param name="hide_db_build" value="true"/>
+            <param name="input" value="ORFs.fa" ftype="fasta"/>
+            <param name="deeparg_db" value="deeparg_1.0.4-19122024"/>
+            <param name="model" value="SS"/>
+            <param name="type" value="nucl"/>
+            <section name="output_files">
+                <param name="output_selection" value="file_ARG_tsv,file_potential_ARG_tsv,file_all_hits_tsv"/>
+            </section>
+            <output name="output_mapping_ARG" ftype="tabular">
+                <assert_contents>
+                    <has_text text="YP_003283625.1|FEATURES|tet(K)|tetracycline|tet(K)"/>
+                    <has_text text="RPOB2"/>
+                </assert_contents>
+            </output>
+            <output name="output_mapping_potential_ARG" ftype="tabular">
+                <assert_contents>
+                    <has_text text="gi:545254650:ref:WP_021551023.1:|FEATURES|mdtB|multidrug|mdtB"/>
+                    <has_text text="MUXB"/>
+                </assert_contents>
+            </output>
+            <output name="output_all_hits" ftype="tabular">
+                <assert_contents>
+                    <has_size value="226000" delta="10000"/>
+                    <has_text text="ADV91011.1|FEATURES|RbpA|rifamycin|RbpA"/>
+                </assert_contents>
+            </output>
+        </test>
+    </tests>
+    <help>
+DeepARG Predict is a computational tool designed to classify and annotate antibiotic resistance genes (ARGs) from nucleotide or protein sequences.
+
+It takes as input a **fasta nucleotide or protein file** containing short (SS model) or long (LS model) sequences.
+
+DeepARG output
+---------------
+
+DeepARG generates two main files: .ARG that contains the sequences with a probability sup or = --prob (0.8 default) and .potential.ARG with sequences containing a probability inf to --prob (0.8 default). The .potential.ARG file can still contain ARG-like sequences, howevere, it is necessary inspect its sequences.
+
+The output format for both files consists of the following fields:
+
+* ARG_NAME
+* QUERY_START
+* QUERY_END
+* QUERY_ID
+* PREDICTED_ARG_CLASS
+* BEST_HIT_FROM_DATABASE
+* PREDICTION_PROBABILITY
+* ALIGNMENT_BESTHIT_IDENTITY (%)
+* ALIGNMENT_BESTHIT_LENGTH
+* ALIGNMENT_BESTHIT_BITSCORE
+* ALIGNMENT_BESTHIT_EVALUE
+* COUNTS
+
+If you want to annotate paired-end short read sequencing data use the DeepARG Short Reads tool.
+
+    </help>
+    <expand macro="citations"/>
+</tool>