rcsb.workflow 0.67__tar.gz → 0.69__tar.gz

{rcsb_workflow-0.67 → rcsb_workflow-0.69}/HISTORY.txt

@@ -62,3 +62,5 @@
  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
+17-Jul-2026 - V0.69 Add shortlink support for bcif generation

{rcsb_workflow-0.67 → rcsb_workflow-0.69}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rcsb.workflow
-Version: 0.67
+Version: 0.69
 Summary: RCSB Python data processing and ETL/ELT workflow entry points
 Project-URL: Homepage, https://github.com/rcsb/py-rcsb_workflow
 Author-email: John Westbrook <john.westbrook@rcsb.org>

{rcsb_workflow-0.67 → rcsb_workflow-0.69}/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 = "0.69"
 readme = "README.md"
 authors = [
     { name="John Westbrook", email="john.westbrook@rcsb.org" }

{rcsb_workflow-0.67 → rcsb_workflow-0.69}/rcsb/workflow/bcif/task_functions.py

@@ -50,6 +50,7 @@ def convertCifFilesToBcif(
     rcsbDict: str,
     ihmDict: str,
     flrDict: str,
+    shortlink: bool,
 ):
     """
     Converts CIF files to BCIF format based on a given list file.
@@ -107,6 +108,7 @@ def convertCifFilesToBcif(
                 contentType,
                 dictionaryApi,
                 temppath,
+                shortlink,
             )
             singleTask(*args)
     elif batchSize > 1:
@@ -125,6 +127,7 @@ def convertCifFilesToBcif(
                 contentType,
                 dictionaryApi,
                 temppath,
+                shortlink,
             )
             results.append(pool.apply_async(singleTask, args))
         for r in results:
@@ -167,6 +170,7 @@ def singleTask(
     contentType: str,
     dictionaryApi: DictionaryApi,
     temppath: str,
+    shortlink: bool,
 ) -> None:
     remoteFileName = "%s%s" % (
         getInputPdbId(pdbId, contentType),
@@ -174,7 +178,10 @@ def singleTask(
     )
 
     # form input cifFilePath
-    if not remotePath.startswith("http"):
+    if shortlink:
+        # Use remote path without hash
+        cifFilePath = os.path.join(remotePath, remoteFileName)
+    elif not remotePath.startswith("http"):
         # local file
         cifFilePath = os.path.join(remotePath, remoteFileName)
         if inputHash:

{rcsb_workflow-0.67 → rcsb_workflow-0.69}/rcsb/workflow/cli/BcifExec.py

@@ -126,6 +126,14 @@ def main():
         default="https://raw.githubusercontent.com/ihmwg/flrCIF/refs/heads/master/dist/mmcif_ihm_flr_ext.dic",
         required=False,
     )
+    parser.add_argument(
+        "--shortlink",
+        action="store_true",
+        default=False,
+        required=False,
+        help="Build remote file path without a hash",
+    )
+    
     # logging
     parser.add_argument("--log_file_path", required=False)
     parser.add_argument("--debug", action="store_true", default=False, required=False)

{rcsb_workflow-0.67 → rcsb_workflow-0.69}/rcsb/workflow/targets/ProteinTargetSequenceExecutionWorkflow.py

@@ -176,7 +176,8 @@ class ProteinTargetSequenceExecutionWorkflow(object):
                 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 @@ class ProteinTargetSequenceExecutionWorkflow(object):
         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 @@ class ProteinTargetSequenceExecutionWorkflow(object):
             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 @@ class ProteinTargetSequenceExecutionWorkflow(object):
         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 @@ class ProteinTargetSequenceExecutionWorkflow(object):
         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

{rcsb_workflow-0.67 → rcsb_workflow-0.69}/rcsb/workflow/targets/ProteinTargetSequenceWorkflow.py

@@ -64,7 +64,8 @@ class ProteinTargetSequenceWorkflow(object):
         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

{rcsb_workflow-0.67 → rcsb_workflow-0.69}/rcsb/workflow/wuw/BcifWorkflow.py

@@ -37,6 +37,7 @@ class BcifWorkflow:
         self.outputHash = bool(args.outputHash)
         self.inputHash = bool(args.inputHash)
         self.batchSize = int(args.batchSize)
+        self.shortlink = bool(args.shortlink)
         # config
         self.pdbxDict = args.pdbxDict
         self.maDict = args.maDict
@@ -83,5 +84,6 @@ class BcifWorkflow:
             self.maDict,
             self.rcsbDict,
             self.ihmDict,
-            self.flrDict
+            self.flrDict,
+            self.shortlink,
         )