rcsb.exdb 1.22__tar.gz → 1.24__tar.gz

{rcsb_exdb-1.22 → rcsb_exdb-1.24}/HISTORY.txt

@@ -102,3 +102,5 @@
  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
+27-Aug-2024 V1.24 Update tree loading for CARD ontology data

{rcsb_exdb-1.22/rcsb.exdb.egg-info → rcsb_exdb-1.24}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: rcsb.exdb
-Version: 1.22
+Version: 1.24
 Summary: RCSB Python ExDB data extraction and loading workflows
 Home-page: https://github.com/rcsb/py-rcsb_exdb
 Author: John Westbrook
@@ -18,19 +18,21 @@ License-File: LICENSE
 Requires-Dist: OpenEye-toolkits>=2020.2.2
 Requires-Dist: numpy
 Requires-Dist: jsonschema>=2.6.0
-Requires-Dist: rcsb.utils.io>=1.46
-Requires-Dist: rcsb.db>=1.721
+Requires-Dist: rcsb.utils.io>=1.48
+Requires-Dist: rcsb.db>=1.723
 Requires-Dist: rcsb.utils.chem>=0.79
 Requires-Dist: rcsb.utils.chemref>=0.91
 Requires-Dist: rcsb.utils.citation>=0.22
 Requires-Dist: rcsb.utils.config>=0.40
 Requires-Dist: rcsb.utils.ec>=0.25
 Requires-Dist: rcsb.utils.go>=0.18
-Requires-Dist: rcsb.utils.seq>=0.79
+Requires-Dist: rcsb.utils.seq>=0.82
+Requires-Dist: rcsb.utils.seqalign>=0.29
+Requires-Dist: rcsb.utils.targets>=0.82
 Requires-Dist: rcsb.utils.struct>=0.47
 Requires-Dist: rcsb.utils.taxonomy>=0.43
-Requires-Dist: rcsb.utils.dictionary>=1.24
-Requires-Dist: rcsb.workflow>=0.42
+Requires-Dist: rcsb.utils.dictionary>=1.27
+Requires-Dist: rcsb.workflow>=0.45
 Requires-Dist: statistics; python_version < "3.0"
 Provides-Extra: dev
 Requires-Dist: check-manifest; extra == "dev"

{rcsb_exdb-1.22 → rcsb_exdb-1.24}/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)

{rcsb_exdb-1.22 → rcsb_exdb-1.24}/rcsb/exdb/cli/__init__.py

@@ -2,4 +2,4 @@ __docformat__ = "google en"
 __author__ = "John Westbrook"
 __email__ = "john.westbrook@rcsb.org"
 __license__ = "Apache 2.0"
-__version__ = "1.22"
+__version__ = "1.24"

{rcsb_exdb-1.22 → rcsb_exdb-1.24}/rcsb/exdb/tree/TreeNodeListWorker.py

@@ -8,6 +8,7 @@
 #  9-Sep-2019 jdw add AtcProvider() and ChemrefExtractor() for ATC tree.
 # 12-Apr-2023 dwp add CARD ontology tree
 #  8-Aug-2023 dwp Load full (unfiltered) taxonomy tree node list, and stop loading GO tree (will be loaded in DW instead)
+# 27-Aug-2024 dwp Update CARD ontology tree loading
 #
 ##
 __docformat__ = "google en"
@@ -181,13 +182,30 @@ class TreeNodeListWorker(object):
                 ok = dl.load(databaseName, collectionName, loadType=loadType, documentList=nL, indexAttributeList=["update_id"], keyNames=None, addValues=addValues, schemaLevel=None)
                 self.__updateStatus(updateId, databaseName, collectionName, ok, statusStartTimestamp)
             # ---- CARD
-            cou = CARDTargetOntologyProvider(cachePath=self.__cachePath, useCache=False)
-            nL = cou.getTreeNodeList()
-            logger.info("Starting load of EC node tree length %d", len(nL))
-            if doLoad:
-                collectionName = "tree_card_node_list"
-                ok = dl.load(databaseName, collectionName, loadType=loadType, documentList=nL, indexAttributeList=["update_id"], keyNames=None, addValues=addValues, schemaLevel=None)
-                self.__updateStatus(updateId, databaseName, collectionName, ok, statusStartTimestamp)
+            okCou = True
+            cou = CARDTargetOntologyProvider(cachePath=self.__cachePath, useCache=useCache)
+            if not cou.testCache():
+                ok = cou.buildOntologyData()
+                cou.reload()
+                if not (ok and cou.testCache()):
+                    logger.error("Skipping load of CARD Target Ontology tree data because it is missing.")
+                    okCou = False
+            if okCou:
+                nL = cou.getTreeNodeList()
+                logger.info("Starting load of CARD ontology node tree length %d", len(nL))
+                if doLoad:
+                    collectionName = "tree_card_node_list"
+                    ok = dl.load(
+                        databaseName,
+                        collectionName,
+                        loadType=loadType,
+                        documentList=nL,
+                        indexAttributeList=["update_id"],
+                        keyNames=None,
+                        addValues=addValues,
+                        schemaLevel=None
+                    )
+                    self.__updateStatus(updateId, databaseName, collectionName, ok, statusStartTimestamp)
             # ---- Taxonomy
             tU = TaxonomyProvider(cachePath=self.__cachePath, useCache=useCache)
             if self.__useFilteredLists:

{rcsb_exdb-1.22 → rcsb_exdb-1.24}/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 @@ class ExDbWorkflow(object):
         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 @@ class ExDbWorkflow(object):
                 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 @@ class ExDbWorkflow(object):
                 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")

{rcsb_exdb-1.22 → rcsb_exdb-1.24/rcsb.exdb.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: rcsb.exdb
-Version: 1.22
+Version: 1.24
 Summary: RCSB Python ExDB data extraction and loading workflows
 Home-page: https://github.com/rcsb/py-rcsb_exdb
 Author: John Westbrook
@@ -18,19 +18,21 @@ License-File: LICENSE
 Requires-Dist: OpenEye-toolkits>=2020.2.2
 Requires-Dist: numpy
 Requires-Dist: jsonschema>=2.6.0
-Requires-Dist: rcsb.utils.io>=1.46
-Requires-Dist: rcsb.db>=1.721
+Requires-Dist: rcsb.utils.io>=1.48
+Requires-Dist: rcsb.db>=1.723
 Requires-Dist: rcsb.utils.chem>=0.79
 Requires-Dist: rcsb.utils.chemref>=0.91
 Requires-Dist: rcsb.utils.citation>=0.22
 Requires-Dist: rcsb.utils.config>=0.40
 Requires-Dist: rcsb.utils.ec>=0.25
 Requires-Dist: rcsb.utils.go>=0.18
-Requires-Dist: rcsb.utils.seq>=0.79
+Requires-Dist: rcsb.utils.seq>=0.82
+Requires-Dist: rcsb.utils.seqalign>=0.29
+Requires-Dist: rcsb.utils.targets>=0.82
 Requires-Dist: rcsb.utils.struct>=0.47
 Requires-Dist: rcsb.utils.taxonomy>=0.43
-Requires-Dist: rcsb.utils.dictionary>=1.24
-Requires-Dist: rcsb.workflow>=0.42
+Requires-Dist: rcsb.utils.dictionary>=1.27
+Requires-Dist: rcsb.workflow>=0.45
 Requires-Dist: statistics; python_version < "3.0"
 Provides-Extra: dev
 Requires-Dist: check-manifest; extra == "dev"

{rcsb_exdb-1.22 → rcsb_exdb-1.24}/rcsb.exdb.egg-info/requires.txt

@@ -1,19 +1,21 @@
 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>=0.82
 rcsb.utils.struct>=0.47
 rcsb.utils.taxonomy>=0.43
-rcsb.utils.dictionary>=1.24
-rcsb.workflow>=0.42
+rcsb.utils.dictionary>=1.27
+rcsb.workflow>=0.45
 
 [:python_version < "3.0"]
 statistics

{rcsb_exdb-1.22 → rcsb_exdb-1.24}/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 >= 0.82
 rcsb.utils.struct >= 0.47
 rcsb.utils.taxonomy >= 0.43
-rcsb.utils.dictionary >= 1.24
-rcsb.workflow >= 0.42
+rcsb.utils.dictionary >= 1.27
+rcsb.workflow >= 0.45
 statistics; python_version < "3.0"