Add beacon2 tools (vcf2bff.pl, pxf2bff, csv2xlsx and bff-validator) into galaxy

tools/beacon2/.shed.yml

@@ -0,0 +1,16 @@
+categories: 
+- Variant Analysis
+description: beacon2-ri-tools are part of the ELIXIR-CRG Beacon v2 Reference Implementation (B2RI).
+long_description: beacon2-ri-tools are a collection of Perl programmes with the aim of 
+    transforming genomic variations data (VCF) to queryable data (MongoDB). 
+homepage_url: https://github.com/EGA-archive/beacon2-ri-tools/tree/main
+name: beacon2
+owner: iuc
+remote_repository_url: https://github.com/galaxyproject/tools-iuc/tree/master/tools/beacon2
+auto_tool_repositories:
+  name_template: "{{ tool_id }}"
+  description_template: "Wrapper for {{ tool_name }}."
+suite:
+  name: "suite_beacon2"
+  description: "A suite of Galaxy tools designed to work with the beacon2-ri-tools collection."
+  type: repository_suite_definition

tools/beacon2/csv2xlsx.xml

@@ -0,0 +1,47 @@
+<tool id="beacon2_csv2xlsx" name="Beacon2 CSV2XLSX" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="21.05">
+    <description>v2 CSV Models to XLSX</description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="xrefs"/>
+    <expand macro="requirements"/>
+    <expand macro="creators"/>
+    <command detect_errors="exit_code"><![CDATA[   
+        #import re
+        #set $names = []
+        #set $x=1
+        #for $x, $csv in enumerate($csvs):
+            #set $name_base = re.sub('[^\w\-_\.]', '_', $csv.element_identifier)
+            #set $name = $name_base
+            #silent $names.append( $name )
+            ln -s '$csv' ${name}  &&
+        #end for
+        csv2xlsx
+            #for $name in $names:
+                ${name}
+            #end for
+            -o Beacon-v2-Models_template.xlsx
+    ]]></command>
+    <inputs>
+        <param name="csvs" type="data" multiple="true" format="csv" label="CSV files" help="" />
+    </inputs>
+    <outputs>
+        <data name="Beacon_v2_Models_template" format="xlsx" label="${tool.name} on ${on_string}: Beacon-v2-Models_template file" from_work_dir="Beacon-v2-Models_template.xlsx" />
+    </outputs>
+    <tests>
+        <test expect_num_outputs="1">
+            <param name="csvs" ftype="csv" value="analyses.csv,genomicVariations.csv,runs.csv,datasets.csv,biosamples.csv,individuals.csv,cohorts.csv" />
+            <output name="Beacon_v2_Models_template" file="Beacon-v2-Models_template.xlsx" compare="sim_size">
+                <assert_contents><has_size value="12000" delta="1000" /></assert_contents>
+            </output>
+        </test>
+    </tests>
+    <help><![CDATA[
+         The Tool converts the data from multiple CSV files to the hierarchical structure of the Beacon v2 Models and creates an Excel file with seven entities.
+         The Models entities are (analyses, biosamples, cohorts, datasets, genomicVariations, individuals and runs). The Excel consisting of all Models properties ‘flattened-out’
+         The Excel file is separated into seven sheets (one per entry type). The user is responsible for filling out the Excel according to the entities and terms they want to share.
+         Once the sheets are filled out, the Beacon v2 Reference Implementation comes with a utility that validates the Excel file against the Models JSON Schemas, and, if successful, it creates a set of JSON text
+         files (JSON arrays) as an output that will be later loaded into the database.
+    ]]></help>
+    <expand macro="citations" />
+</tool>

tools/beacon2/macros.xml

@@ -0,0 +1,29 @@
+<macros>
+    <token name="@VERSION_SUFFIX@">0</token>
+    <token name="@TOOL_VERSION@">2.0.0</token>
+    <xml name="requirements">
+        <requirements>
+            <requirement type="package" version="@TOOL_VERSION@">beacon2-ri-tools</requirement>
+            <requirement type="package" version="1.12">gzip</requirement>
+        </requirements>
+    </xml>
+    <xml name="xrefs">
+        <xrefs>
+            <xref type="bio.tools">GA4GH Beacon</xref>
+        </xrefs>
+    </xml>
+    <xml name="creators">
+        <creator>
+            <person givenName="Khaled" familyName="Jum'ah" url="https://github.com/khaled196" />
+            <person givenName="Björn" familyName="Grüning" url="https://github.com/bgruening" />
+            <person givenName="Katarzyna" familyName="Kamieniecka" url="https://github.com/kkamieniecka" />
+            <person givenName="Krzysztof" familyName="Poterlowicz" url="https://github.com/poterlowicz-lab" />
+            <organization name="poterlowicz-lab" url="https://github.com/poterlowicz-lab" />
+        </creator>
+    </xml>
+    <xml name="citations">
+        <citations>
+            <citation type="doi">10.1093/bioinformatics/btac568</citation>
+        </citations>
+    </xml>
+</macros>

tools/beacon2/pxf2bff.xml

@@ -0,0 +1,42 @@
+<tool id="beacon2_pxf2bff" name="Beacon2 PXF2BFF" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="21.05">
+    <description>converts Phenopacket PXF (JSON) to BFF (JSON)</description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="xrefs"/>
+    <expand macro="requirements"/>
+    <expand macro="creators"/>
+    <command detect_errors="exit_code"><![CDATA[   
+        #import re
+        #set $names = []
+        #set $x=1
+        #for $x, $i in enumerate($input):
+            #set $name_base = re.sub('[^\w\-_\.]', '_', $i.element_identifier)
+            #set $name = $name_base
+            #silent $names.append( $name )
+            ln -s '$i' ${name}  &&
+        #end for
+        pxf2bff
+            #for $name in $names:
+                -i ${name}
+            #end for
+            -o ./
+    ]]></command>
+    <inputs>
+        <param argument="--input" type="data" multiple="true" format="json" label="Phenopacket JSON files" help="" />
+    </inputs>
+    <outputs>
+        <data name="BFF_JSON_File" format="json" label="${tool.name} on ${on_string}: BFF_JSON_File" from_work_dir="individuals.json" />
+    </outputs>
+    <tests>
+        <test expect_num_outputs="1">
+            <param name="input" ftype="json" value="EGAF00005572750.json,EGAF00005572753.json,EGAF00005572884.json,EGAF00005572893.json,EGAF00005572727.json,EGAF00005572756.json,EGAF00005572721.json,EGAF00005572902.json,EGAF00005572759.json,EGAF00005572881.json,EGAF00005572896.json,EGAF00005572890.json,EGAF00005572861.json,EGAF00005572899.json,EGAF00005572762.json,EGAF00005572887.json,EGAF00005572724.json,EGAF00005572747.json" />
+            <output name="BFF_JSON_File" file="individuals.json" />
+        </test>
+    </tests>
+    <help><![CDATA[
+      The tool combines different Phenopacket JSON files into one JSON file. The Phenopacket Schema represents an open standard for sharing disease and phenotype information to
+      improve our ability to understand, diagnose, and treat both rare and common diseases. The generated file will be ready to be stored on the MongoDB instance as MongoDB works directly with JSON files.
+    ]]></help>
+    <expand macro="citations" />
+</tool>

tools/beacon2/test-data/EGAF00005572721.json

@@ -0,0 +1,106 @@
+{
+  "phenopacket": {
+    "id": "P0007500",
+    "subject": {
+      "id": "P0007500",
+      "dateOfBirth": "unknown-01-01T00:00:00Z",
+      "sex": "FEMALE"
+    },
+    "phenotypicFeatures": [],
+    "diseases": [],
+    "genes": [],
+    "variants": [],
+    "meta_data": {
+      "created": "2021-04-21T09:37:19.994Z",
+      "resources": [
+        {
+          "id": "hp",
+          "name": "Human Phenotype Ontology",
+          "url": "http://purl.obolibrary.org/obo/hp.owl",
+          "version": "2020-12-07",
+          "namespacePrefix": "HP",
+          "iriPrefix": "http://purl.obolibrary.org/obo/HP_"
+        },
+        {
+          "id": "orphanet",
+          "name": "Orphanet Rare Disease Ontology",
+          "url": "http://orpha.net/ontology/ORDO_en_3.1.owl",
+          "version": "3.1",
+          "namespacePrefix": "Orphanet",
+          "iriPrefix": "http://www.orpha.net/ORDO/Orphanet_"
+        },
+        {
+          "id": "hgnc",
+          "name": "HUGO Gene Nomenclature Committee",
+          "url": "https://www.genenames.org",
+          "version": "2021-01-13",
+          "namespacePrefix": "HGNC",
+          "iriPrefix": "https://www.genenames.org/data/gene-symbol-report/#!/hgnc_id/"
+        },
+        {
+          "id": "mim",
+          "name": "Online Mendelian Inheritance in Man",
+          "url": "https://omim.org/",
+          "version": "2021-01-21",
+          "namespacePrefix": "OMIM",
+          "iriPrefix": "https://omim.org/entry/"
+        }
+      ]
+    }
+  },
+  "interpretation": {
+    "id": "P0007500",
+    "resolutionStatus": "UNSOLVED",
+    "phenopacket": {
+      "id": "P0007500",
+      "subject": {
+        "id": "P0007500",
+        "dateOfBirth": "unknown-01-01T00:00:00Z",
+        "sex": "FEMALE"
+      },
+      "phenotypicFeatures": [],
+      "diseases": [],
+      "genes": [],
+      "variants": [],
+      "meta_data": {
+        "created": "2021-04-21T09:37:19.994Z",
+        "resources": [
+          {
+            "id": "hp",
+            "name": "Human Phenotype Ontology",
+            "url": "http://purl.obolibrary.org/obo/hp.owl",
+            "version": "2020-12-07",
+            "namespacePrefix": "HP",
+            "iriPrefix": "http://purl.obolibrary.org/obo/HP_"
+          },
+          {
+            "id": "orphanet",
+            "name": "Orphanet Rare Disease Ontology",
+            "url": "http://orpha.net/ontology/ORDO_en_3.1.owl",
+            "version": "3.1",
+            "namespacePrefix": "Orphanet",
+            "iriPrefix": "http://www.orpha.net/ORDO/Orphanet_"
+          },
+          {
+            "id": "hgnc",
+            "name": "HUGO Gene Nomenclature Committee",
+            "url": "https://www.genenames.org",
+            "version": "2021-01-13",
+            "namespacePrefix": "HGNC",
+            "iriPrefix": "https://www.genenames.org/data/gene-symbol-report/#!/hgnc_id/"
+          },
+          {
+            "id": "mim",
+            "name": "Online Mendelian Inheritance in Man",
+            "url": "https://omim.org/",
+            "version": "2021-01-21",
+            "namespacePrefix": "OMIM",
+            "iriPrefix": "https://omim.org/entry/"
+          }
+        ]
+      }
+    },
+    "diagnosis": [],
+    "meta_data": {}
+  }
+}

tools/beacon2/test-data/EGAF00005572724.json

@@ -0,0 +1,106 @@
+{
+  "phenopacket": {
+    "id": "P0007499",
+    "subject": {
+      "id": "P0007499",
+      "dateOfBirth": "unknown-01-01T00:00:00Z",
+      "sex": "MALE"
+    },
+    "phenotypicFeatures": [],
+    "diseases": [],
+    "genes": [],
+    "variants": [],
+    "meta_data": {
+      "created": "2021-04-21T09:33:50.417Z",
+      "resources": [
+        {
+          "id": "hp",
+          "name": "Human Phenotype Ontology",
+          "url": "http://purl.obolibrary.org/obo/hp.owl",
+          "version": "2020-12-07",
+          "namespacePrefix": "HP",
+          "iriPrefix": "http://purl.obolibrary.org/obo/HP_"
+        },
+        {
+          "id": "orphanet",
+          "name": "Orphanet Rare Disease Ontology",
+          "url": "http://orpha.net/ontology/ORDO_en_3.1.owl",
+          "version": "3.1",
+          "namespacePrefix": "Orphanet",
+          "iriPrefix": "http://www.orpha.net/ORDO/Orphanet_"
+        },
+        {
+          "id": "hgnc",
+          "name": "HUGO Gene Nomenclature Committee",
+          "url": "https://www.genenames.org",
+          "version": "2021-01-13",
+          "namespacePrefix": "HGNC",
+          "iriPrefix": "https://www.genenames.org/data/gene-symbol-report/#!/hgnc_id/"
+        },
+        {
+          "id": "mim",
+          "name": "Online Mendelian Inheritance in Man",
+          "url": "https://omim.org/",
+          "version": "2021-01-21",
+          "namespacePrefix": "OMIM",
+          "iriPrefix": "https://omim.org/entry/"
+        }
+      ]
+    }
+  },
+  "interpretation": {
+    "id": "P0007499",
+    "resolutionStatus": "UNSOLVED",
+    "phenopacket": {
+      "id": "P0007499",
+      "subject": {
+        "id": "P0007499",
+        "dateOfBirth": "unknown-01-01T00:00:00Z",
+        "sex": "MALE"
+      },
+      "phenotypicFeatures": [],
+      "diseases": [],
+      "genes": [],
+      "variants": [],
+      "meta_data": {
+        "created": "2021-04-21T09:33:50.417Z",
+        "resources": [
+          {
+            "id": "hp",
+            "name": "Human Phenotype Ontology",
+            "url": "http://purl.obolibrary.org/obo/hp.owl",
+            "version": "2020-12-07",
+            "namespacePrefix": "HP",
+            "iriPrefix": "http://purl.obolibrary.org/obo/HP_"
+          },
+          {
+            "id": "orphanet",
+            "name": "Orphanet Rare Disease Ontology",
+            "url": "http://orpha.net/ontology/ORDO_en_3.1.owl",
+            "version": "3.1",
+            "namespacePrefix": "Orphanet",
+            "iriPrefix": "http://www.orpha.net/ORDO/Orphanet_"
+          },
+          {
+            "id": "hgnc",
+            "name": "HUGO Gene Nomenclature Committee",
+            "url": "https://www.genenames.org",
+            "version": "2021-01-13",
+            "namespacePrefix": "HGNC",
+            "iriPrefix": "https://www.genenames.org/data/gene-symbol-report/#!/hgnc_id/"
+          },
+          {
+            "id": "mim",
+            "name": "Online Mendelian Inheritance in Man",
+            "url": "https://omim.org/",
+            "version": "2021-01-21",
+            "namespacePrefix": "OMIM",
+            "iriPrefix": "https://omim.org/entry/"
+          }
+        ]
+      }
+    },
+    "diagnosis": [],
+    "meta_data": {}
+  }
+}