Merge pull request #18919 from jmchilton/biotools

Fix commas that shouldn't be in biotools_mappings.tsv

lib/galaxy/tool_util/ontologies/biotools_mappings.tsv

@@ -44,6 +44,7 @@ gffcompare	gffcompare
 sample_seqs	biopython
 seq_filter_by_id	biopython
 rxlr_motifs	signalp
+rxlr_motifs	hmmer2
 crossmap_bam	crossmap
 samtools_bam_to_cram	samtools
 crossmap_region	crossmap
@@ -132,7 +133,6 @@ samtools_fixmate	samtools
 samtool_filter2	samtools
 ngsutils_bam_filter	ngsutils
 samtools_rmdup	samtools
-sam_merge2	Broken link in tool shed
 bamhash	bamhash
 bedtools_annotatebed	bedtools
 bedtools_bed12tobed6	bedtools
@@ -260,7 +260,6 @@ fraggenescan	fraggenescan
 repeatmodeler	repeatmodeler
 promoter2	promoter
 Psortb	psortb
-rxlr_motifs	signalp hmmer2
 signalp3	signalp
 tmhmm2	tmhmm
 wolf_psort	wolf_psort
@@ -965,23 +964,23 @@ stacks2_tsv2bam	stacks
 stacks2_sstacks	stacks
 BayeScan	bayescan
 stacks2_cstacks	stacks
-NSPDK_candidateClust	graphclust, GraphClust2
-structure_to_gspan	graphclust, GraphClust2
-preproc	graphclust, GraphClust3
-preMloc	graphclust, GraphClust4
-nspdk_sparse	graphclust, GraphClust5
-locarna_best_subtree	graphclust, GraphClust6
-gspan	graphclust, GraphClust7
-glob_report	graphclust, GraphClust8
-cmFinder	graphclust, GraphClust9
-graphclust_align_cluster	graphclust, GraphClust10
-graphclust_aggregate_alignments	graphclust, GraphClust11
-graphclust_glob_report_no_align	graphclust, GraphClust12
-motifFinderPlot	graphclust, GraphClust13
+NSPDK_candidateClust	graphclust
+structure_to_gspan	graphclust
+preproc	graphclust
+preMloc	graphclust
+nspdk_sparse	graphclust
+locarna_best_subtree	graphclust
+gspan	graphclust
+glob_report	graphclust
+cmFinder	graphclust
+graphclust_align_cluster	graphclust
+graphclust_aggregate_alignments	graphclust
+graphclust_glob_report_no_align	graphclust
+motifFinderPlot	graphclust
 infernal_cmbuild	infernal
 infernal_cmsearch	infernal
 infernal_cmstat	infernal
-customize_metaphlan_database	metaphlan, seqtk
+customize_metaphlan_database	metaphlan
 merge_metaphlan_tables	metaphlan
 metabat2_jgi_summarize_bam_contig_depths	MetaBAT_2
 est_abundance	bracken
@@ -1898,10 +1897,10 @@ gatk_count_covariates	gatk
 spring_model	spring
 spring_minz	spring
 spring_cross	spring
-pubmed_by_queries	pubmed, simtext
-text_to_wordmatrix	pubmed, simtext
-abstracts_by_pmids	pubmed, simtext
-pmids_to_pubtator_matrix	pubmed, simtext
+pubmed_by_queries	pubmed
+text_to_wordmatrix	pubmed
+abstracts_by_pmids	pubmed
+pmids_to_pubtator_matrix	pubmed
 spring_model_all	spring
 spring_map	spring
 spring_mcc	spring

lib/galaxy/tool_util/ontologies/ontology_data.py

@@ -1,3 +1,4 @@
+from collections import defaultdict
 from typing import (
     cast,
     Dict,
@@ -34,13 +35,11 @@ def _read_ontology_data_text(filename: str) -> str:
 EDAM_TOPIC_MAPPING_FILENAME = "edam_topic_mappings.tsv"
 
 BIOTOOLS_MAPPING_CONTENT = _read_ontology_data_text(BIOTOOLS_MAPPING_FILENAME)
-BIOTOOLS_MAPPING: Dict[str, str] = dict(
-    [
-        cast(Tuple[str, str], tuple(x.split("\t")))
-        for x in BIOTOOLS_MAPPING_CONTENT.splitlines()
-        if not x.startswith("#")
-    ]
-)
+BIOTOOLS_MAPPING: Dict[str, List[str]] = defaultdict(list)
+for line in BIOTOOLS_MAPPING_CONTENT.splitlines():
+    if not line.startswith("#"):
+        tool_id, xref = line.split("\t")
+        BIOTOOLS_MAPPING[tool_id].append(xref)
 EDAM_OPERATION_MAPPING_CONTENT = _read_ontology_data_text(EDAM_OPERATION_MAPPING_FILENAME)
 EDAM_OPERATION_MAPPING: Dict[str, List[str]] = _multi_dict_mapping(EDAM_OPERATION_MAPPING_CONTENT)
 
@@ -61,11 +60,11 @@ def biotools_reference(xrefs):
     return None
 
 
-def legacy_biotools_external_reference(all_ids: List[str]) -> Optional[str]:
+def legacy_biotools_external_reference(all_ids: List[str]) -> List[str]:
     for tool_id in all_ids:
         if tool_id in BIOTOOLS_MAPPING:
             return BIOTOOLS_MAPPING[tool_id]
-    return None
+    return []
 
 
 def expand_ontology_data(
@@ -74,9 +73,9 @@ def expand_ontology_data(
     xrefs = tool_source.parse_xrefs()
     has_biotools_reference = any(x["reftype"] == "bio.tools" for x in xrefs)
     if not has_biotools_reference:
-        legacy_biotools_ref = legacy_biotools_external_reference(all_ids)
-        if legacy_biotools_ref is not None:
-            xrefs.append({"value": legacy_biotools_ref, "reftype": "bio.tools"})
+        for legacy_biotools_ref in legacy_biotools_external_reference(all_ids):
+            if legacy_biotools_ref is not None:
+                xrefs.append({"value": legacy_biotools_ref, "reftype": "bio.tools"})
 
     edam_operations = tool_source.parse_edam_operations()
     edam_topics = tool_source.parse_edam_topics()

test/unit/tool_util/test_ontologies.py

@@ -46,6 +46,22 @@
     type: integer
 """
 
+TOOL_YAML_NO_EXPLICIT_XREFS = """
+name: "Bowtie Mapper"
+class: GalaxyTool
+id: sort1
+version: 1.0.2
+description: "The Bowtie Mapper"
+command: "bowtie --map-the-stuff"
+outputs:
+  out1:
+    format: bam
+    from_work_dir: out1.bam
+inputs:
+  - name: input1
+    type: integer
+"""
+
 
 def test_parse_edam_empty():
     test_source = get_test_tool_source(source_file_name="testtool.yml", source_contents=TOOL_YAML_1)
@@ -66,3 +82,17 @@ def test_parse_edam_mapping_operations_legacy():
     ontology_data = expand_ontology_data(test_source, ["sort1"], None)
     assert ontology_data.edam_operations == ["operation_3802"]
     assert ontology_data.edam_topics == []
+
+
+def test_parse_biotools_default_mapping():
+    test_source = get_test_tool_source(source_file_name="testtool.yml", source_contents=TOOL_YAML_NO_EXPLICIT_XREFS)
+    ontology_data = expand_ontology_data(test_source, ["cheetah_problem_unbound_var_input"], None)
+    assert ontology_data.xrefs[0]["reftype"] == "bio.tools"
+    assert ontology_data.xrefs[0]["value"] == "bwa"
+
+    test_source = get_test_tool_source(source_file_name="testtool.yml", source_contents=TOOL_YAML_NO_EXPLICIT_XREFS)
+    ontology_data = expand_ontology_data(test_source, ["rxlr_motifs"], None)
+    assert len(ontology_data.xrefs) == 2
+    values = [x["value"] for x in ontology_data.xrefs]
+    assert "signalp" in values
+    assert "hmmer2" in values