Merge pull request #295 from microbiomedata/293-skip-metagenome-seque…

…ncing

293 skip metagenome sequencing

nmdc_automation/workflow_automation/workflow_process.py

@@ -100,6 +100,7 @@ def get_current_workflow_process_nodes(
 
     data_generation_ids = set()
     data_generation_workflows = [wf for wf in workflows if wf.collection == "data_generation_set"]
+
     workflow_execution_workflows = [wf for wf in workflows if wf.collection == "workflow_execution_set"]
 
     # default query for data_generation_set records filtered by analyte category
@@ -129,6 +130,9 @@ def get_current_workflow_process_nodes(
 
         records = db[wf.collection].find(q)
         for rec in records:
+            # legacy JGI sequencing records
+            if rec.get("type") == "nmdc:MetagenomeSequencing" or rec["name"].startswith("Metagenome Sequencing"):
+                continue
             if wf.version and not _within_range(rec["version"], wf.version):
                 continue
             if _is_missing_required_input_output(wf, rec, data_objects_by_id):

tests/fixtures/nmdc_db/legacy_data_generation.json

@@ -0,0 +1,27 @@
+[
+  {
+    "id" : "nmdc:omprc-11-cegmwy02",
+    "name" : "Terrestrial soil microbial communities - BONA_004-O-20210707-COMP",
+    "has_input" : [
+        "nmdc:procsm-11-d8hkca85"
+    ],
+    "gold_sequencing_project_identifiers" : [
+        "gold:Gp0704890"
+    ],
+    "processing_institution" : "JGI",
+    "type" : "nmdc:NucleotideSequencing",
+    "insdc_bioproject_identifiers" : [
+        "bioproject:PRJNA1029072"
+    ],
+    "analyte_category" : "metagenome",
+    "associated_studies" : [
+        "nmdc:sty-11-34xj1150"
+    ],
+    "instrument_used" : [
+        "nmdc:inst-14-mr4r2w09"
+    ],
+    "has_output" : [
+        "nmdc:dobj-11-hnw52332"
+    ]
+}
+]

tests/fixtures/nmdc_db/legacy_data_obj.json

@@ -0,0 +1,15 @@
+[
+  {
+    "id" : "nmdc:dobj-11-hnw52332",
+    "name" : "52832.3.464616.CTATCGCA-CTATCGCA.fastq.gz",
+    "description" : "Metagenome Raw Reads for nmdc:omprc-11-cegmwy02",
+    "alternative_identifiers" : [
+
+    ],
+    "file_size_bytes" : 31068664547,
+    "md5_checksum" : "12f380b91ff3364cd3d228505d3402b5",
+    "data_object_type" : "Metagenome Raw Reads",
+    "url" : "https://data.microbiomedata.org/data/nmdc:omprc-11-cegmwy02/nmdc:wfmsa-11-jc5cmf37.1/52832.3.464616.CTATCGCA-CTATCGCA.fastq.gz",
+    "type" : "nmdc:DataObject"
+}
+]

tests/fixtures/nmdc_db/metagenome_sequencing.json

@@ -0,0 +1,19 @@
+[
+  {
+    "id" : "nmdc:wfmsa-11-jc5cmf37.1",
+    "name" : "Metagenome Sequencing Activity for nmdc:wfmsa-11-jc5cmf37.1",
+    "started_at_time" : "2023-09-13T19:57:49.595727+00:00",
+    "ended_at_time" : "2023-09-13T19:57:49.595743+00:00",
+    "was_informed_by" : "nmdc:omprc-11-cegmwy02",
+    "execution_resource" : "JGI",
+    "git_url" : "https://github.com/microbiomedata/RawSequencingData",
+    "has_input" : [
+        "nmdc:procsm-11-d8hkca85"
+    ],
+    "has_output" : [
+        "nmdc:dobj-11-hnw52332"
+    ],
+    "type" : "nmdc:MetagenomeSequencing",
+    "version" : "v1.0.0"
+}
+]

tests/test_workflow_process.py

@@ -45,6 +45,28 @@ def test_load_workflow_process_nodes(test_db, workflow_file, workflows_config_di
     assert data_gen.children[0].type == "nmdc:ReadQcAnalysis"
 
 
+def test_load_workflow_process_nodes_does_not_load_metagenome_sequencing(test_db, workflows_config_dir):
+    """
+    Test that legacy nmdc:MetagenomeSequencing instances are not loaded
+    """
+    exp_omprc = "nmdc:omprc-11-cegmwy02"
+    reset_db(test_db)
+    load_fixture(test_db, "legacy_data_obj.json", "data_object_set")
+    load_fixture(test_db, "legacy_data_generation.json", "data_generation_set")
+    load_fixture(test_db, "metagenome_sequencing.json", "workflow_execution_set")
+
+    wfs = load_workflow_configs(workflows_config_dir / "workflows.yaml")
+    data_objs_by_id = get_required_data_objects_map(test_db, wfs)
+    wf_execs = get_current_workflow_process_nodes(test_db, wfs, data_objs_by_id, allowlist=[exp_omprc,])
+    # We only expect the data generation to be loaded
+    assert wf_execs
+    assert len(wf_execs) == 1
+    wf = wf_execs[0]
+    assert wf.type == "nmdc:NucleotideSequencing"
+    assert wf.id == exp_omprc
+    assert wf.was_informed_by == exp_omprc
+
+
 @mark.parametrize(
     "workflow_file", ["workflows.yaml", "workflows-mt.yaml"]
 )