Merge pull request #25 from rcsb/dev-dwp

V1.23 Add support for target cofactor data loading to Mongo
rcsb · Aug 21, 2024 · 4ce0f46 · 4ce0f46
2 parents f79d637 + fcba4dd
commit 4ce0f46
Show file tree

Hide file tree

Showing 5 changed files with 47 additions and 11 deletions.
diff --git a/HISTORY.txt b/HISTORY.txt
@@ -102,3 +102,4 @@
  9-May-2024 V1.2  Adjust provider type exclusion input to accept a list of types
 13-May-2024 V1.21 Update requirements; fix linting
 17-Jul-2024 V1.22 Adjust LigandNeighborMappingExtractor
+20-Aug-2024 V1.23 Add support for target cofactor data loading
diff --git a/rcsb/exdb/cli/ExDbExec.py b/rcsb/exdb/cli/ExDbExec.py
@@ -10,6 +10,7 @@
 #   9-Mar-2023 dwp Lower refChunkSize to 10 (UniProt API having trouble streaming XML responses)
 #  25-Apr-2024 dwp Add arguments and logic to support CLI usage from weekly-update workflow;
 #                  Add support for logging output to a specific file
+#  20-Aug-2024 dwp Add load_target_cofactors operation; change name of upd_targets_cofactors to upd_targets
 ##
 __docformat__ = "google en"
 __author__ = "John Westbrook"
@@ -46,7 +47,8 @@ def main():
             "upd_ref_seq",  # Update reference sequence assignments
             "upd_neighbor_interactions",
             "upd_uniprot_taxonomy",
-            "upd_targets_cofactors",
+            "upd_targets",
+            "load_target_cofactors",
             "upd_pubchem",
             "upd_entry_info",
             "upd_glycan_idx",
@@ -108,7 +110,16 @@ def main():
     exWf = ExDbWorkflow(**commonD)
     if op in ["etl_chemref", "etl_uniprot_core", "etl_tree_node_lists", "upd_ref_seq"]:
         okR = exWf.load(op, **loadD)
-    elif op in ["upd_neighbor_interactions", "upd_uniprot_taxonomy", "upd_targets_cofactors", "upd_pubchem", "upd_entry_info", "upd_glycan_idx", "upd_resource_stash"]:
+    elif op in [
+        "upd_neighbor_interactions",
+        "upd_uniprot_taxonomy",
+        "upd_targets",
+        "load_target_cofactors",
+        "upd_pubchem",
+        "upd_entry_info",
+        "upd_glycan_idx",
+        "upd_resource_stash",
+    ]:
         okR = exWf.buildExdbResource(op, **loadD)
     else:
         logger.error("Unsupported op %r", op)

diff --git a/rcsb/exdb/cli/__init__.py b/rcsb/exdb/cli/__init__.py
@@ -2,4 +2,4 @@
 __author__ = "John Westbrook"
 __email__ = "[email protected]"
 __license__ = "Apache 2.0"
-__version__ = "1.22"
+__version__ = "1.23"
diff --git a/rcsb/exdb/wf/ExDbWorkflow.py b/rcsb/exdb/wf/ExDbWorkflow.py
@@ -8,6 +8,7 @@
 #   2-Mar-2023 dwp Add "numProc" parameter to 'upd_ref_seq' operation methods
 #   9-Mar-2023 dwp Lower refChunkSize to 10 (UniProt API having trouble streaming XML responses)
 #  25-Apr-2024 dwp Add arguments and methods to support CLI usage from weekly-update workflow
+#  20-Aug-2024 dwp Add LoadTargetCofactors step; change name of UpdateTargetsCofactors step to UpdateTargetsData
 ##
 __docformat__ = "google en"
 __author__ = "John Westbrook"
@@ -274,7 +275,16 @@ def buildExdbResource(self, op, **kwargs):
         logger.info("Starting operation %r\n", op)
         #
         # argument processing
-        if op not in ["upd_neighbor_interactions", "upd_uniprot_taxonomy", "upd_targets_cofactors", "upd_pubchem", "upd_entry_info", "upd_glycan_idx", "upd_resource_stash"]:
+        if op not in [
+            "upd_neighbor_interactions",
+            "upd_uniprot_taxonomy",
+            "upd_targets",
+            "load_target_cofactors",
+            "upd_pubchem",
+            "upd_entry_info",
+            "upd_glycan_idx",
+            "upd_resource_stash",
+        ]:
             logger.error("Unsupported operation %r - exiting", op)
             return False
         try:
@@ -324,8 +334,8 @@ def buildExdbResource(self, op, **kwargs):
                 ok = ptsWf.updateUniProtTaxonomy() and ok
                 logger.info("updateUniProtTaxonomy status %r", ok)
             #
-            elif op == "upd_targets_cofactors":
-                logger.info("Starting UpdateTargetsCofactors")
+            elif op == "upd_targets":
+                logger.info("Starting UpdateTargetsData")
                 ptsWf = ProteinTargetSequenceExecutionWorkflow(
                     configPath=self.__configPath,
                     mockTopPath=self.__mockTopPath,
@@ -352,6 +362,18 @@ def buildExdbResource(self, op, **kwargs):
                 logger.info("buildCofactorData status %r", ok)
                 ptsWf.resourceCheck()
             #
+            elif op == "load_target_cofactors":
+                logger.info("Starting LoadTargetCofactors")
+                ptsWf = ProteinTargetSequenceExecutionWorkflow(
+                    configPath=self.__configPath,
+                    mockTopPath=self.__mockTopPath,
+                    configName=self.__configName,
+                    cachePath=self.__cachePath,
+                )
+                ok = ptsWf.loadTargetCofactorData()
+                logger.info("loadTargetCofactorData status %r", ok)
+                ptsWf.resourceCheck()
+            #
             elif op == "upd_pubchem":
                 #  -- Update local chemical indices and  create PubChem mapping index ---
                 logger.info("Starting workflow PubChemEtlWorkflow")

diff --git a/requirements.txt b/requirements.txt
@@ -2,17 +2,19 @@
 OpenEye-toolkits >= 2020.2.2
 numpy
 jsonschema >= 2.6.0
-rcsb.utils.io >= 1.46
-rcsb.db >= 1.721
+rcsb.utils.io >= 1.48
+rcsb.db >= 1.723
 rcsb.utils.chem >= 0.79
 rcsb.utils.chemref >= 0.91
 rcsb.utils.citation >= 0.22
 rcsb.utils.config >= 0.40
 rcsb.utils.ec >= 0.25
 rcsb.utils.go >= 0.18
-rcsb.utils.seq >= 0.79
+rcsb.utils.seq >= 0.82
+rcsb.utils.seqalign >= 0.29
+rcsb.utils.targets >= 0.80
 rcsb.utils.struct >= 0.47
 rcsb.utils.taxonomy >= 0.43
-rcsb.utils.dictionary >= 1.24
-rcsb.workflow >= 0.42
+rcsb.utils.dictionary >= 1.26
+rcsb.workflow >= 0.44
 statistics; python_version < "3.0"