From 45620e08221689a26b2133b6725212e6b0ef49ed Mon Sep 17 00:00:00 2001 From: Dennis Piehl Date: Mon, 11 May 2026 12:32:13 -0400 Subject: [PATCH] V0.68 Temporarily skip DrugBank data processing until dataset becomes available --- HISTORY.txt | 1 + pyproject.toml | 2 +- .../ProteinTargetSequenceExecutionWorkflow.py | 15 ++++++++++----- .../targets/ProteinTargetSequenceWorkflow.py | 3 ++- 4 files changed, 14 insertions(+), 7 deletions(-) diff --git a/HISTORY.txt b/HISTORY.txt index 2bbdee5..b606771 100644 --- a/HISTORY.txt +++ b/HISTORY.txt @@ -62,3 +62,4 @@ 2-Mar-2026 - V0.66 Add refstats subpackage for ligand and RSCC reference generation; Update test pipelines to python 3.13 7-May-2026 - V0.67 Configure logging at start of CLI executable scripts +11-May-2026 - V0.68 Temporarily skip DrugBank data processing until dataset becomes available diff --git a/pyproject.toml b/pyproject.toml index 6bec045..9f5a8ca 100755 --- a/pyproject.toml +++ b/pyproject.toml @@ -5,7 +5,7 @@ build-backend = "hatchling.build" [project] name = "rcsb.workflow" description = "RCSB Python data processing and ETL/ELT workflow entry points" -version = "0.67" +version = "0.68" readme = "README.md" authors = [ { name="John Westbrook", email="john.westbrook@rcsb.org" } diff --git a/rcsb/workflow/targets/ProteinTargetSequenceExecutionWorkflow.py b/rcsb/workflow/targets/ProteinTargetSequenceExecutionWorkflow.py index 33d79df..7b227a0 100644 --- a/rcsb/workflow/targets/ProteinTargetSequenceExecutionWorkflow.py +++ b/rcsb/workflow/targets/ProteinTargetSequenceExecutionWorkflow.py @@ -176,7 +176,8 @@ def exportFasta(self, reloadPharos=True, fromDbPharos=True): addTaxonomy=True, reloadPharos=reloadPharos, fromDbPharos=fromDbPharos, - resourceNameList=["sabdab", "card", "drugbank", "chembl", "pharos"], + # resourceNameList=["sabdab", "card", "drugbank", "chembl", "pharos"], + resourceNameList=["sabdab", "card", "chembl", "pharos"], backupPharos=True, remotePrefix=self.__stashRemotePrefix ) @@ -199,7 +200,8 @@ def createSearchDatabases(self): ok = False try: ptsW = ProteinTargetSequenceWorkflow(self.__cfgOb, self.__cachePath) - ok = ptsW.createSearchDatabases(resourceNameList=["sabdab", "card", "drugbank", "chembl", "pharos", "pdbprent"], addTaxonomy=True, timeOutSeconds=3600, verbose=False) + # ok = ptsW.createSearchDatabases(resourceNameList=["sabdab", "card", "drugbank", "chembl", "pharos", "pdbprent"], addTaxonomy=True, timeOutSeconds=3600, verbose=False) + ok = ptsW.createSearchDatabases(resourceNameList=["sabdab", "card", "chembl", "pharos", "pdbprent"], addTaxonomy=True, timeOutSeconds=3600, verbose=False) except Exception as e: logger.exception("Failing with %s", str(e)) return ok @@ -234,7 +236,8 @@ def searchDatabases(self): ptsW = ProteinTargetSequenceWorkflow(self.__cfgOb, self.__cachePath) ok1 = ptsW.search( referenceResourceName="pdbprent", - resourceNameList=["sabdab", "drugbank", "chembl", "pharos"], + # resourceNameList=["sabdab", "drugbank", "chembl", "pharos"], + resourceNameList=["sabdab", "chembl", "pharos"], identityCutoff=0.95, sensitivity=4.5, timeOutSeconds=1000, @@ -288,7 +291,8 @@ def buildCofactorData(self): ok = False try: ptsW = ProteinTargetSequenceWorkflow(self.__cfgOb, self.__cachePath) - ok = ptsW.buildCofactorData(referenceResourceName="pdbprent", resourceNameList=["chembl", "pharos", "drugbank"], backup=True, remotePrefix=self.__stashRemotePrefix) + # ok = ptsW.buildCofactorData(referenceResourceName="pdbprent", resourceNameList=["chembl", "pharos", "drugbank"], backup=True, remotePrefix=self.__stashRemotePrefix) + ok = ptsW.buildCofactorData(referenceResourceName="pdbprent", resourceNameList=["chembl", "pharos"], backup=True, remotePrefix=self.__stashRemotePrefix) except Exception as e: logger.exception("Failing with %s", str(e)) return ok @@ -299,7 +303,8 @@ def loadTargetCofactorData(self): ok = False try: ptsW = ProteinTargetSequenceWorkflow(self.__cfgOb, self.__cachePath) - ok = ptsW.loadTargetCofactorData(resourceNameList=["chembl", "pharos", "drugbank"]) + # ok = ptsW.loadTargetCofactorData(resourceNameList=["chembl", "pharos", "drugbank"]) + ok = ptsW.loadTargetCofactorData(resourceNameList=["chembl", "pharos"]) except Exception as e: logger.exception("Failing with %s", str(e)) return ok diff --git a/rcsb/workflow/targets/ProteinTargetSequenceWorkflow.py b/rcsb/workflow/targets/ProteinTargetSequenceWorkflow.py index d579172..7c04082 100644 --- a/rcsb/workflow/targets/ProteinTargetSequenceWorkflow.py +++ b/rcsb/workflow/targets/ProteinTargetSequenceWorkflow.py @@ -64,7 +64,8 @@ def __init__(self, cfgOb, cachePath, **kwargs): self.__configName = cfgOb.getDefaultSectionName() self.__cachePath = os.path.abspath(cachePath) self.__umP = None - self.__defaultResourceNameList = ["sabdab", "card", "drugbank", "chembl", "pdbprent"] + # self.__defaultResourceNameList = ["sabdab", "card", "drugbank", "chembl", "pdbprent"] + self.__defaultResourceNameList = ["sabdab", "card", "chembl", "pdbprent"] def testCache(self): return True