Update Beacon2-RI-tools to V2

tools/beacon2/README.md

@@ -0,0 +1,22 @@
+# Beacon2 Galaxy wrapper drafts
+
+Files included:
+- `macros.xml`
+- `csv_to_bff.xml`
+- `genomicVariations_vcf.xml`
+- `genomicVariations_postprocessing.xml`
+- `individuals_to_cohorts_csv.xml`
+
+## Design notes
+
+These wrappers are designed around the current Python CLI exposed by Beacon2 RI Tools v2:
+- `csv_to_bff.py --output --datasetId --input --entry_type`
+- `genomicVariations_vcf.py --output --datasetId --refGen --caseLevelData --numRows --verbosity --json --input --alleleCounts --alleleFrequency`
+- `genomicVariations_postprocessing.py --input --datasetId`
+- `individuals_to_cohorts_csv.py --input --output --datasetId --cohortId --cohortName --cohortType`
+
+The wrappers generate a temporary `conf/conf.py` at runtime and copy the installed package tree into the job directory before execution. This is meant to cope with the upstream scripts relying on package-relative resources such as `files/headers/*.txt`, `files/deref_schemas/*.json`, and `conf/conf.py`.
+
+## Important caveat
+
+I could validate that the XML files are well-formed, but I did **not** run `planemo test` here. You will still want to adapt test-data paths and, if needed, the exact conda package name/version used by your Bioconda recipe.

tools/beacon2/csv_to_bff.xml

@@ -0,0 +1,195 @@
+<tool id="beacon2_csv_to_bff" name="Beacon2 CSV to BFF" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
+    <description>convert Beacon CSV sheets to Beacon Friendly Format JSON</description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="xrefs"/>
+    <expand macro="requirements"/>
+    <expand macro="creators"/>
+    <expand macro="stdio"/>
+    <expand macro="version_command"/>
+    <command detect_errors="exit_code"><![CDATA[
+@BEACON2_RUNTIME_SETUP@ &&
+
+cp '$conf_py' 'conf/conf.py' &&
+
+ln -s  '$input_csv' '${advanced.entry_type}.csv' &&
+
+csv_to_bff.py 
+    -i . 
+    -o . 
+    -d '$dataset_id' 
+    -e '$advanced.entry_type' 
+    > output.log 2>&1 &&
+
+cp '${advanced.entry_type}.json' output.json
+]]></command>
+    <environment_variables>
+        <environment_variable name="PYTHONPATH">.:\$PYTHONPATH</environment_variable>
+    </environment_variables>
+    <configfiles>
+        <configfile name="conf_py"><![CDATA[
+# Auto-generated by the Galaxy wrapper for Beacon2 CSV to BFF
+
+csv_folder='.'
+output_docs_folder='.'
+entry_type='${advanced.entry_type}'
+only_process_reads_with_allele_frequency=${advanced.only_process_reads_with_allele_frequency}
+populations_by_allele_counts = ${advanced.populations_by_allele_counts}
+reference_genome='${advanced.reference_genome}'
+datasetId='${dataset_id}'
+case_level_data=${advanced.case_level_data}
+exact_heterozygosity=${advanced.exact_heterozygosity}
+num_rows=${advanced.num_rows}
+verbosity=${advanced.verbosity}
+
+# Database connection
+database_host='${advanced.database.database_host}'
+database_port=${advanced.database.database_port}
+database_name='${advanced.database.database_name}'
+
+# Credentials (exact same logic as your beacon2-import tool)
+#set $db_auth_source = $__user__.extra_preferences.get('beacon2_account|db_auth_source', "")
+#set $db_user = $__user__.extra_preferences.get('beacon2_account|db_user', "")
+#set $db_password = $__user__.extra_preferences.get('beacon2_account|db_password', "")
+#if $db_user == "" or $db_password == "" or $db_auth_source == "":
+    #set $db_auth_source = "admin"
+    #set $db_user = "root"
+    #set $db_password = "example"
+#end if
+
+database_user = '$db_user'
+database_password = '$db_password'
+database_auth_source = '$db_auth_source'
+        ]]></configfile>
+    </configfiles>
+
+    <inputs>
+        <param name="input_csv" type="data" format="csv" label="Input CSV file"/>
+        <expand macro="dataset_id"/>
+        <expand macro="advanced_section"/>
+    </inputs>
+
+    <outputs>
+        <data name="out_json" format="json" from_work_dir="output.json" label="${tool.name} on ${on_string}: ${advanced.entry_type}.json"/>
+        <data name="log" format="txt" from_work_dir="output.log" label="${tool.name} on ${on_string}: execution log"/>
+    </outputs>
+
+    <tests>
+        <test expect_num_outputs="2">
+            <!-- test1: individuals.csv -->
+            <param name="input_csv" value="individuals.csv" />
+            <param name="advanced|entry_type" value="individuals" />
+            <param name="dataset_id" value="test_dataset" />
+            <output name="out_json" file="individuals.json" ftype="json"/>
+            <output name="log" compare="contains">
+                <assert_contents>
+                    <has_text text="Successfully converted" />
+                </assert_contents>
+            </output>
+        </test>
+        <test expect_num_outputs="2">
+            <!-- test2: genomicVariations.csv -->
+            <param name="input_csv" value="genomicVariations.csv" />
+            <param name="advanced|entry_type" value="genomicVariations" />
+            <param name="dataset_id" value="test_dataset" />
+            <output name="out_json" file="genomicVariations.json" ftype="json"/>
+            <output name="log" compare="contains">
+                <assert_contents>
+                    <has_text text="Successfully converted" />
+                </assert_contents>
+            </output>
+        </test>
+        <test expect_num_outputs="2">
+            <!-- test3: cohorts.csv -->
+            <param name="input_csv" value="cohorts.csv" />
+            <param name="advanced|entry_type" value="cohorts" />
+            <param name="dataset_id" value="test_dataset" />
+            <output name="out_json" file="cohorts.json" ftype="json"/>
+            <output name="log" compare="contains">
+                <assert_contents>
+                    <has_text text="Successfully converted" />
+                </assert_contents>
+            </output>
+        </test>
+        <test expect_num_outputs="2">
+            <!-- test4: analyses.csv -->
+            <param name="input_csv" value="analyses.csv" />
+            <param name="advanced|entry_type" value="analyses" />
+            <param name="dataset_id" value="test_dataset" />
+            <output name="out_json" file="analyses.json" ftype="json"/>
+            <output name="log" compare="contains">
+                <assert_contents>
+                    <has_text text="Successfully converted" />
+                </assert_contents>
+            </output>
+        </test>
+        <test expect_num_outputs="2">
+            <!-- test5: biosamples.csv -->
+            <param name="input_csv" value="biosamples.csv" />
+            <param name="advanced|entry_type" value="biosamples" />
+            <param name="dataset_id" value="test_dataset" />
+            <output name="out_json" file="biosamples.json" ftype="json"/>
+            <output name="log" compare="contains">
+                <assert_contents>
+                    <has_text text="Successfully converted" />
+                </assert_contents>
+            </output>
+        </test>
+        <test expect_num_outputs="2">
+            <!-- test6: collections.csv -->
+            <param name="input_csv" value="collections.csv" />
+            <param name="advanced|entry_type" value="collections" />
+            <param name="dataset_id" value="test_dataset" />
+            <output name="out_json" file="collections.json" ftype="json"/>
+            <output name="log" compare="contains">
+                <assert_contents>
+                    <has_text text="Successfully converted" />
+                </assert_contents>
+            </output>
+        </test>
+        <test expect_num_outputs="2">
+            <!-- test7: datasets.csv -->
+            <param name="input_csv" value="datasets.csv" />
+            <param name="advanced|entry_type" value="datasets" />
+            <param name="dataset_id" value="test_dataset" />
+            <output name="out_json" file="datasets.json" ftype="json"/>
+            <output name="log" compare="contains">
+                <assert_contents>
+                    <has_text text="Successfully converted" />
+                </assert_contents>
+            </output>
+        </test>
+        <test expect_num_outputs="2">
+            <!-- test8: patients.csv -->
+            <param name="input_csv" value="patients.csv" />
+            <param name="advanced|entry_type" value="patients" />
+            <param name="dataset_id" value="test_dataset" />
+            <output name="out_json" file="patients.json" ftype="json"/>
+            <output name="log" compare="contains">
+                <assert_contents>
+                    <has_text text="Successfully converted" />
+                </assert_contents>
+            </output>
+        </test>
+        <test expect_num_outputs="2">
+            <!-- test9: runs.csv -->
+            <param name="input_csv" value="runs.csv" />
+            <param name="advanced|entry_type" value="runs" />
+            <output name="out_json" file="runs.json" ftype="json"/>
+            <param name="dataset_id" value="test_dataset" />
+            <output name="log" compare="contains">
+                <assert_contents>
+                    <has_text text="Successfully converted" />
+                </assert_contents>
+            </output>
+        </test>
+    </tests>
+
+    <help><![CDATA[
+**Beacon2 CSV to BFF**
+
+Converts Beacon CSV files to Beacon Friendly Format (BFF) JSON.
+    ]]></help>
+    <expand macro="citations"/>
+</tool>

tools/beacon2/genomicVariations_postprocessing.xml

@@ -0,0 +1,103 @@
+<tool id="beacon2_genomic_variations_postprocessing" name="Beacon2 genomicVariations postprocessing" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
+    <description>add caseLevelData or variantLevelData to existing Beacon genomic variations</description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="xrefs"/>
+    <expand macro="requirements"/>
+    <expand macro="creators"/>
+    <expand macro="stdio"/>
+    <expand macro="version_command"/>
+
+    <command detect_errors="exit_code"><![CDATA[
+@BEACON2_RUNTIME_SETUP@ &&
+touch conf/__init__.py &&
+cp '$conf_py' 'conf/conf.py' &&
+ln -s '$input_csv' 'input.csv' &&
+genomicVariations_postprocessing.py
+    --input 'input.csv'
+    --datasetId '${dataset_id}'
+    > output.log 2>&1
+    ]]></command>
+    <environment_variables>
+        <environment_variable name="PYTHONPATH">.:\$PYTHONPATH</environment_variable>
+    </environment_variables>
+    <!-- SINGLE <configfiles> SECTION -->
+    <configfiles>
+        <configfile name="conf_py"><![CDATA[
+# Auto-generated by the Galaxy wrapper for Beacon2 CSV to BFF
+
+csv_folder = '.'
+output_docs_folder = '.'
+entry_type = '${advanced.entry_type}'
+only_process_reads_with_allele_frequency = ${advanced.only_process_reads_with_allele_frequency}
+populations_by_allele_counts = ${advanced.populations_by_allele_counts}
+reference_genome = '${advanced.reference_genome}'
+datasetId = '${dataset_id}'
+case_level_data = ${advanced.case_level_data}
+exact_heterozygosity = ${advanced.exact_heterozygosity}
+num_rows = ${advanced.num_rows}
+verbosity = ${advanced.verbosity}
+
+# Database connection
+database_host = '${advanced.database.database_host}'
+database_port = ${advanced.database.database_port}
+database_name = '${advanced.database.database_name}'
+
+# Credentials (exact same logic as your beacon2-import tool)
+#set $db_auth_source = $__user__.extra_preferences.get('beacon2_account|db_auth_source', "")
+#set $db_user = $__user__.extra_preferences.get('beacon2_account|db_user', "")
+#set $db_password = $__user__.extra_preferences.get('beacon2_account|db_password', "")
+#if $db_user == "" or $db_password == "" or $db_auth_source == "":
+    #set $db_auth_source = "admin"
+    #set $db_user = "root"
+    #set $db_password = "example"
+#end if
+
+database_user = '$db_user'
+database_password = '$db_password'
+database_auth_source = '$db_auth_source'
+        ]]></configfile>
+    </configfiles>
+
+    <inputs>
+        <param name="input_csv" type="data" format="csv" label="genomicVariations CSV for postprocessing"/>
+        <expand macro="dataset_id"/>
+        <!-- Full advanced options (single source of truth, includes custom conf.py) -->
+        <!-- entry_type is hard-coded above because this tool is single-purpose -->
+        <expand macro="advanced_section"/>
+    </inputs>
+
+    <outputs>
+        <expand macro="log_output"/>
+    </outputs>
+
+    <tests>
+        <test>
+            <param name="input_csv" value="genomicVariations.csv" />
+            <param name="dataset_id" value="test_dataset" />
+            <output name="log" compare="contains">
+                <assert_contents>
+                    <has_text text="Successfully updated" />
+                </assert_contents>
+            </output>
+        </test>
+    </tests>
+
+    <help><![CDATA[
+**Beacon2 genomicVariations Post-processing**
+
+Adds `caseLevelData` or `variantLevelData` to genomic variations that have already been loaded into the Beacon MongoDB.
+
+**New flexible options (Advanced section):**
+- Reference genome
+- Case-level data generation
+- Maximum rows to process (0 = unlimited)
+- Allele frequency & population settings
+- Verbose logging
+- **Custom conf.py** (upload your own optimized config file for full control)
+
+MongoDB credentials are read automatically from your Galaxy user preferences.
+    ]]></help>
+    <expand macro="citations"/>
+</tool>