rcsb.workflow 0.43__tar.gz → 0.45__tar.gz

{rcsb_workflow-0.43 → rcsb_workflow-0.45}/HISTORY.txt

@@ -35,3 +35,5 @@
                     Reduce resource footprint for Azure tests;
                     Make CARDTargetOntologyProvider stashable on Buildlocker
 21-May-2024 - V0.43 Fix pylinting
+20-Aug-2024 - V0.44 Add step for loading target cofactor data to MongoDB
+27-Aug-2024 - V0.45 Update usage of CARDTargetOntologyProvider

{rcsb_workflow-0.43/rcsb.workflow.egg-info → rcsb_workflow-0.45}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: rcsb.workflow
-Version: 0.43
+Version: 0.45
 Summary: RCSB Python data processing and ETL/ELT workflow entry points
 Home-page: https://github.com/rcsb/py-rcsb_workflow
 Author: John Westbrook
@@ -16,12 +16,12 @@ Classifier: Programming Language :: Python :: 3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: OpenEye-toolkits>=2020.2.2
-Requires-Dist: rcsb.utils.chem>=0.75
-Requires-Dist: rcsb.utils.seq>=0.63
-Requires-Dist: rcsb.utils.targets>=0.57
-Requires-Dist: rcsb.utils.seqalign>=0.24
-Requires-Dist: rcsb.exdb>=0.87
-Requires-Dist: rcsb.utils.io>=1.20
+Requires-Dist: rcsb.utils.chem>=0.79
+Requires-Dist: rcsb.utils.seq>=0.82
+Requires-Dist: rcsb.utils.targets>=0.82
+Requires-Dist: rcsb.utils.seqalign>=0.29
+Requires-Dist: rcsb.exdb>=1.23
+Requires-Dist: rcsb.utils.io>=1.48
 Provides-Extra: dev
 Requires-Dist: check-manifest; extra == "dev"
 Provides-Extra: test

{rcsb_workflow-0.43 → rcsb_workflow-0.45}/rcsb/workflow/chem/__init__.py

@@ -2,4 +2,4 @@ __docformat__ = "google en"
 __author__ = "John Westbrook"
 __email__ = "john.westbrook@rcsb.org"
 __license__ = "Apache 2.0"
-__version__ = "0.43"
+__version__ = "0.45"

{rcsb_workflow-0.43 → rcsb_workflow-0.45}/rcsb/workflow/targets/ProteinTargetSequenceExecutionWorkflow.py

@@ -219,6 +219,17 @@ class ProteinTargetSequenceExecutionWorkflow(object):
             logger.exception("Failing with %s", str(e))
         return ok
 
+    def loadTargetCofactorData(self):
+        """Load target cofactor data from search results"""
+        logger.info("Running loadTargetCofactorData...")
+        ok = False
+        try:
+            ptsW = ProteinTargetSequenceWorkflow(self.__cfgOb, self.__cachePath)
+            ok = ptsW.loadTargetCofactorData(resourceNameList=["chembl", "pharos", "drugbank"])
+        except Exception as e:
+            logger.exception("Failing with %s", str(e))
+        return ok
+
     #
     # --- --- --- ---
 

{rcsb_workflow-0.43 → rcsb_workflow-0.45}/rcsb/workflow/targets/ProteinTargetSequenceWorkflow.py

@@ -15,6 +15,8 @@
 #   1-Jun-2023 aae Don't back up resources to GitHub during cache update workflows
 #  12-Jun-2023 dwp Set useTaxonomy filter to False for CARD annotations
 #   6-Jul-2023 aae Don't overwrite Buildlocker files if there is no data
+#  20-Aug-2024 dwp Add step for loading target cofactor data to MongoDB
+#  27-Aug-2024 dwp Update usage of CARDTargetOntologyProvider
 ##
 __docformat__ = "google en"
 __author__ = "John Westbrook"
@@ -304,7 +306,7 @@ class ProteinTargetSequenceWorkflow(object):
             )
             #
             if taxonPath and mU.exists(taxonPath):
-                mL = mmS.getMatchResults(rawPath, taxonPath, useTaxonomy=True, misMatchCutoff=-1, sequenceIdentityCutoff=identityCutoff, useBitScore=useBitScore)
+                mL = mmS.getMatchResults(rawPath, taxonPath, useTaxonomy=True, useTaxonomyCache=True, misMatchCutoff=-1, sequenceIdentityCutoff=identityCutoff, useBitScore=useBitScore)
             else:
                 mL = mmS.getMatchResults(rawPath, None, useTaxonomy=False, misMatchCutoff=-1, sequenceIdentityCutoff=identityCutoff, useBitScore=useBitScore)
             logger.info("Query sequences with matches %r (%d) bitScore filter (%r)", resourceName, len(mL), useBitScore)
@@ -320,7 +322,7 @@ class ProteinTargetSequenceWorkflow(object):
 
         Args:
             referenceResourceName (str): reference resource name (e.g., pdbprent)
-            resourceNameList (list, optional): list of data resources. Defaults to ["sabdab", "card"].
+            resourceNameList (list, optional): list of data resources. Defaults to ["sabdab", "card", "imgt"].
             useTaxonomy (bool, optional): use taxonomy in filtering selections where implemented  (e.g., card). Defaults to True.
             backup (bool, optional): backup results to stash storage. Defaults to False.
             remotePrefix (str, optional): channel prefix for stash storage. Defaults to None.
@@ -328,7 +330,7 @@ class ProteinTargetSequenceWorkflow(object):
         Returns:
             bool: True for success or False otherwise
         """
-        resourceNameList = resourceNameList if resourceNameList else ["sabdab", "card"]
+        resourceNameList = resourceNameList if resourceNameList else ["sabdab", "card", "imgt"]
         retOk = True
         for resourceName in resourceNameList:
             startTime = time.time()
@@ -358,17 +360,18 @@ class ProteinTargetSequenceWorkflow(object):
                     okB = fP.backup(self.__cfgOb, self.__configName, remotePrefix=remotePrefix, useStash=True, useGit=False)
                     logger.info("%r features backup status (%r)", resourceName, okB)
             elif resourceName == "card":
+                fP = CARDTargetOntologyProvider(cachePath=self.__cachePath, useCache=True)
+                ok = fP.buildOntologyData()
+                fP.reload()
+                if ok and backup and fP.testCache():
+                    okB = fP.backup(self.__cfgOb, self.__configName, remotePrefix=remotePrefix, useStash=True, useGit=False)
+                    logger.info("%r ontology backup status (%r)", resourceName, okB)
                 fP = CARDTargetAnnotationProvider(cachePath=self.__cachePath, useCache=True)
                 ok = fP.buildAnnotationList(resultPath, useTaxonomy=useTaxonomy)
                 fP.reload()
                 if ok and backup and fP.testCache():
                     okB = fP.backup(self.__cfgOb, self.__configName, remotePrefix=remotePrefix, useStash=True, useGit=False)
                     logger.info("%r annotations backup status (%r)", resourceName, okB)
-                fP = CARDTargetOntologyProvider(cachePath=self.__cachePath, useCache=False)
-                ok = fP.reload()
-                if ok and backup and fP.testCache():
-                    okB = fP.backup(self.__cfgOb, self.__configName, remotePrefix=remotePrefix, useStash=True, useGit=False)
-                    logger.info("%r ontology backup status (%r)", resourceName, okB)
             elif resourceName == "imgt":
                 fP = IMGTTargetFeatureProvider(cachePath=self.__cachePath, useCache=True)
                 ok = fP.buildFeatureList(useCache=True)
@@ -490,7 +493,7 @@ class ProteinTargetSequenceWorkflow(object):
             crmpObj = ChemRefMappingProvider(cachePath=self.__cachePath, useCache=True)
             lnmpObj = LigandNeighborMappingProvider(cachePath=self.__cachePath, useCache=True)
 
-            okB = True
+            ok = okB = True
             resultPath = self.__getFilteredSearchResultPath(resourceName, referenceResourceName)
             #
             if resourceName == "chembl":
@@ -528,6 +531,55 @@ class ProteinTargetSequenceWorkflow(object):
             logger.exception("Failing with %s", str(e))
         return False
 
+    def loadTargetCofactorData(self, resourceNameList=None):
+        """Load target cofactor data to MongoDB.
+
+        Args:
+            resourceNameList (list, optional): list of data resources. Defaults to ["pharos", "chembl"].
+
+        Returns:
+            bool: True for success or False otherwise
+        """
+        resourceNameList = resourceNameList if resourceNameList else ["chembl", "pharos", "drugbank"]
+        retOk = True
+        for resourceName in resourceNameList:
+            startTime = time.time()
+            ok = self.__loadTargetCofactorData(resourceName)
+            logger.info(
+                "Completed loading target cofactor data for %s (status %r)  at %s (%.4f seconds)",
+                resourceName,
+                ok,
+                time.strftime("%Y %m %d %H:%M:%S", time.localtime()),
+                time.time() - startTime,
+            )
+            retOk = retOk and ok
+        #
+        return retOk
+
+    def __loadTargetCofactorData(self, resourceName):
+        """Load cofactor data inferred from sequence comparison results to MongoDB."""
+        try:
+            ok = okLoad = False
+            aP = None
+            #
+            if resourceName == "chembl":
+                aP = ChEMBLTargetCofactorProvider(cachePath=self.__cachePath, useCache=True)
+            elif resourceName == "pharos":
+                aP = PharosTargetCofactorProvider(cachePath=self.__cachePath, useCache=True, useStash=True, useGit=True)
+            elif resourceName == "drugbank":
+                aP = DrugBankTargetCofactorProvider(cachePath=self.__cachePath, useCache=True)
+            #
+            ok = aP.reload()
+            logger.info("%r cofactor data reload status (%r)", resourceName, ok)
+            #
+            if ok and aP.testCache():
+                okLoad = aP.loadCofactorData(cfgOb=self.__cfgOb)
+
+            return ok and okLoad
+        except Exception as e:
+            logger.exception("Failing with %s", str(e))
+        return False
+
     def __getDatabasePath(self):
         return os.path.join(self.__cachePath, "sequence-databases")
 

{rcsb_workflow-0.43 → rcsb_workflow-0.45/rcsb.workflow.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: rcsb.workflow
-Version: 0.43
+Version: 0.45
 Summary: RCSB Python data processing and ETL/ELT workflow entry points
 Home-page: https://github.com/rcsb/py-rcsb_workflow
 Author: John Westbrook
@@ -16,12 +16,12 @@ Classifier: Programming Language :: Python :: 3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: OpenEye-toolkits>=2020.2.2
-Requires-Dist: rcsb.utils.chem>=0.75
-Requires-Dist: rcsb.utils.seq>=0.63
-Requires-Dist: rcsb.utils.targets>=0.57
-Requires-Dist: rcsb.utils.seqalign>=0.24
-Requires-Dist: rcsb.exdb>=0.87
-Requires-Dist: rcsb.utils.io>=1.20
+Requires-Dist: rcsb.utils.chem>=0.79
+Requires-Dist: rcsb.utils.seq>=0.82
+Requires-Dist: rcsb.utils.targets>=0.82
+Requires-Dist: rcsb.utils.seqalign>=0.29
+Requires-Dist: rcsb.exdb>=1.23
+Requires-Dist: rcsb.utils.io>=1.48
 Provides-Extra: dev
 Requires-Dist: check-manifest; extra == "dev"
 Provides-Extra: test

rcsb_workflow-0.45/rcsb.workflow.egg-info/requires.txt

@@ -0,0 +1,13 @@
+OpenEye-toolkits>=2020.2.2
+rcsb.utils.chem>=0.79
+rcsb.utils.seq>=0.82
+rcsb.utils.targets>=0.82
+rcsb.utils.seqalign>=0.29
+rcsb.exdb>=1.23
+rcsb.utils.io>=1.48
+
+[dev]
+check-manifest
+
+[test]
+coverage

rcsb_workflow-0.45/requirements.txt

@@ -0,0 +1,8 @@
+--extra-index-url https://pypi.anaconda.org/OpenEye/simple
+OpenEye-toolkits >= 2020.2.2
+rcsb.utils.chem >= 0.79
+rcsb.utils.seq >= 0.82
+rcsb.utils.targets >= 0.82
+rcsb.utils.seqalign >= 0.29
+rcsb.exdb >= 1.23
+rcsb.utils.io >= 1.48

rcsb_workflow-0.43/rcsb.workflow.egg-info/requires.txt

@@ -1,13 +0,0 @@
-OpenEye-toolkits>=2020.2.2
-rcsb.utils.chem>=0.75
-rcsb.utils.seq>=0.63
-rcsb.utils.targets>=0.57
-rcsb.utils.seqalign>=0.24
-rcsb.exdb>=0.87
-rcsb.utils.io>=1.20
-
-[dev]
-check-manifest
-
-[test]
-coverage

rcsb_workflow-0.43/requirements.txt

@@ -1,8 +0,0 @@
---extra-index-url https://pypi.anaconda.org/OpenEye/simple
-OpenEye-toolkits >= 2020.2.2
-rcsb.utils.chem >= 0.75
-rcsb.utils.seq >= 0.63
-rcsb.utils.targets >= 0.57
-rcsb.utils.seqalign >= 0.24
-rcsb.exdb >= 0.87
-rcsb.utils.io >= 1.20