rcsb.exdb 1.24__tar.gz → 1.26__tar.gz

{rcsb_exdb-1.24 → rcsb_exdb-1.26}/HISTORY.txt

@@ -104,3 +104,7 @@
 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
+22-Oct-2024 V1.25 Add CLI for CCD image and file generation;
+                  Update CI/CD to python 3.10
+10-Dec-2024 V1.26 Update PolymerEntityExtractor to sort extracted sequence data;
+                  Update Azure pipelines to run on latest macOS and ubuntu version

{rcsb_exdb-1.24/rcsb.exdb.egg-info → rcsb_exdb-1.26}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: rcsb.exdb
-Version: 1.24
+Version: 1.26
 Summary: RCSB Python ExDB data extraction and loading workflows
 Home-page: https://github.com/rcsb/py-rcsb_exdb
 Author: John Westbrook
@@ -13,13 +13,14 @@ Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Programming Language :: Python
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: OpenEye-toolkits>=2020.2.2
+Requires-Dist: OpenEye-toolkits>=2024.1.1
 Requires-Dist: numpy
 Requires-Dist: jsonschema>=2.6.0
 Requires-Dist: rcsb.utils.io>=1.48
-Requires-Dist: rcsb.db>=1.723
+Requires-Dist: rcsb.db>=1.725
 Requires-Dist: rcsb.utils.chem>=0.79
 Requires-Dist: rcsb.utils.chemref>=0.91
 Requires-Dist: rcsb.utils.citation>=0.22
@@ -27,12 +28,12 @@ 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>=0.82
-Requires-Dist: rcsb.utils.seqalign>=0.29
+Requires-Dist: rcsb.utils.seqalign>=0.31
 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>=1.27
-Requires-Dist: rcsb.workflow>=0.45
+Requires-Dist: rcsb.workflow>=0.46
 Requires-Dist: statistics; python_version < "3.0"
 Provides-Extra: dev
 Requires-Dist: check-manifest; extra == "dev"

{rcsb_exdb-1.24 → rcsb_exdb-1.26}/rcsb/exdb/cli/ExDbExec.py

@@ -11,6 +11,8 @@
 #  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
+#  22-Oct-2024 dwp Add ccd_img_gen and ccd_file_gen operations
+#                  (latter will only be used briefly, as will stop generating SDF and Mol2 files in Dec 2024)
 ##
 __docformat__ = "google en"
 __author__ = "John Westbrook"
@@ -53,6 +55,8 @@ def main():
             "upd_entry_info",
             "upd_glycan_idx",
             "upd_resource_stash",
+            "ccd_img_gen",
+            "ccd_file_gen",
         ]
     )
     parser.add_argument(
@@ -86,6 +90,11 @@ def main():
     parser.add_argument("--min_match_primary_percent", default=None, help="Minimum reference sequence match percentage (for op 'upd_ref_seq')")
     parser.add_argument("--test_mode", default=False, action="store_true", help="Test mode for reference sequence updates (for op 'upd_ref_seq')")
     #
+    # Arguments specific for op == 'ccd_img_gen' or 'ccd_file_gen'
+    parser.add_argument("--cc_output_path", default=None, help="The base local directory path where chemical component files (image, coordinates) are written (for op 'ccd_img_gen')")
+    parser.add_argument("--cc_cache_path", default=None, help="The base local directory path where chemical component cache data are written (for op 'ccd_img_gen')")
+    parser.add_argument("--oe_license_path", default=None, help="Path to OpenEye license file")
+    #
     # Arguments buildExdbResources
     parser.add_argument("--rebuild_all_neighbor_interactions", default=False, action="store_true", help="Rebuild all neighbor interactions from scratch (default is incrementally)")
     parser.add_argument("--cc_file_prefix", default="cc-full", help="File name discriminator for index sets")
@@ -121,6 +130,11 @@ def main():
         "upd_resource_stash",
     ]:
         okR = exWf.buildExdbResource(op, **loadD)
+    elif op in [
+        "ccd_img_gen",
+        "ccd_file_gen",
+    ]:
+        okR = exWf.generateCcdFiles(op, **loadD)
     else:
         logger.error("Unsupported op %r", op)
     #
@@ -209,6 +223,9 @@ def processArguments(args):
         "ccFileNamePrefix": args.cc_file_prefix,
         "ccUrlTarget": args.cc_url_target,
         "birdUrlTarget": args.bird_url_target,
+        "ccOutputPath": args.cc_output_path,
+        "ccCachePath": args.cc_cache_path,
+        "licenseFilePath": args.oe_license_path,
     }
 
     return op, commonD, loadD

{rcsb_exdb-1.24 → rcsb_exdb-1.26}/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__ = "1.24"
+__version__ = "1.26"

{rcsb_exdb-1.24 → rcsb_exdb-1.26}/rcsb/exdb/seq/PolymerEntityExtractor.py

@@ -7,6 +7,8 @@
 #
 # Updates:
 #  9-Jan-2024 dwp Turn off use of uniprot_exdb DB for enriching protein entity details file (data not used)
+# 10-Dec-2024 dwp Sort extracted polymer entity sequence data by entity ID (alphabetically), to ensure consistent
+#                 ordering between coasts (order of sequence data influences results of mmseqs2 sequence searching)
 #
 ##
 __docformat__ = "google en"
@@ -16,6 +18,7 @@ __license__ = "Apache 2.0"
 
 import logging
 import os
+from collections import OrderedDict
 
 from rcsb.exdb.utils.ObjectExtractor import ObjectExtractor
 from rcsb.utils.io.MarshalUtil import MarshalUtil
@@ -175,9 +178,12 @@ class PolymerEntityExtractor(object):
                     pass
                 rD[rId] = {"alignmentL": uDL, "sourceOrgL": sL, "partCount": partCount, "taxCount": taxCount, "sequence": seqS, "seqLen": seqLen}
 
+            # Sort the dict in alphabetical order (by entity ID key) to ensure consistent/reproducible treatment by mmseqs2
+            sortedD = OrderedDict((k, rD.pop(k)) for k in sorted(rD))
+
         except Exception as e:
             logger.exception("Failing with %s", str(e))
-        return rD, missingSrcD
+        return sortedD, missingSrcD
 
     def __getSourcePart(self, entityId, sourceOrgL, entityBeg, seqLen):
         """Return the source part containing the input entity range -

{rcsb_exdb-1.24 → rcsb_exdb-1.26}/rcsb/exdb/wf/ExDbWorkflow.py

@@ -25,6 +25,8 @@ from rcsb.utils.dictionary.DictMethodResourceProvider import DictMethodResourceP
 from rcsb.utils.dictionary.DictMethodResourceCacheWorkflow import DictMethodResourceCacheWorkflow
 from rcsb.utils.dictionary.NeighborInteractionWorkflow import NeighborInteractionWorkflow
 from rcsb.workflow.targets.ProteinTargetSequenceExecutionWorkflow import ProteinTargetSequenceExecutionWorkflow
+from rcsb.workflow.chem.ChemCompImageWorkflow import ChemCompImageWorkflow
+from rcsb.workflow.chem.ChemCompFileWorkflow import ChemCompFileWorkflow
 from rcsb.exdb.chemref.ChemRefEtlWorker import ChemRefEtlWorker
 from rcsb.exdb.seq.ReferenceSequenceAnnotationAdapter import ReferenceSequenceAnnotationAdapter
 from rcsb.exdb.seq.ReferenceSequenceAnnotationProvider import ReferenceSequenceAnnotationProvider
@@ -271,6 +273,88 @@ class ExDbWorkflow(object):
             logger.exception("Failing with %s", str(e))
         return False
 
+    def generateCcdFiles(self, op, **kwargs):
+        logger.info("Starting operation %r\n", op)
+        #
+        # argument processing
+        if op not in [
+            "ccd_img_gen",
+            "ccd_file_gen",
+        ]:
+            logger.error("Unsupported operation %r - exiting", op)
+            return False
+        try:
+            ccOutputPath = kwargs.get("ccOutputPath", None)
+            ccCachePath = kwargs.get("ccCachePath", None)
+            licenseFilePath = kwargs.get("licenseFilePath", None)
+            ccUrlTarget = kwargs.get("ccUrlTarget", None)
+            birdUrlTarget = kwargs.get("birdUrlTarget", None)
+            #
+        except Exception as e:
+            logger.exception("Argument or configuration processing failing with %s", str(e))
+            return False
+        #
+        ok = False
+        if op == "ccd_img_gen":
+            logger.info("Generating CCD 2D images ...")
+            cciWf = ChemCompImageWorkflow(
+                imagePath=ccOutputPath,
+                cachePath=ccCachePath,
+                licenseFilePath=licenseFilePath,
+                ccUrlTarget=ccUrlTarget,
+                birdUrlTarget=birdUrlTarget,
+            )
+            ok = cciWf.testCache()
+            logger.info("CCD image generation setup status %r", ok)
+            #
+            ok = cciWf.makeImages() and ok
+            logger.info("CCD image generation status %r", ok)
+        #
+        elif op == "ccd_file_gen":
+            logger.info("Generating SDF and Mol2 files from CCD...")
+            # CCD ideal coordinates
+            ccfWf = ChemCompFileWorkflow(
+                fileDirPath=ccOutputPath,
+                cachePath=ccCachePath,
+                licenseFilePath=licenseFilePath,
+                ccUrlTarget=ccUrlTarget,
+                birdUrlTarget=birdUrlTarget,
+                molBuildType="ideal-xyz"
+            )
+            ok1 = ccfWf.testCache()
+            logger.info("CCD ideal coordinates generation setup status %r", ok1)
+            #
+            ok1 = ccfWf.makeFiles(fmt="sdf") and ok1
+            logger.info("CCD ideal file sdf generation status %r", ok1)
+            ok1 = ccfWf.makeFiles(fmt="mol2") and ok1
+            logger.info("CCD ideal file mol2 generation status %r", ok1)
+
+            # CCD model coordinates
+            ccfWf = ChemCompFileWorkflow(
+                fileDirPath=ccOutputPath,
+                cachePath=ccCachePath,
+                licenseFilePath=licenseFilePath,
+                ccUrlTarget=ccUrlTarget,
+                birdUrlTarget=birdUrlTarget,
+                molBuildType="model-xyz"
+            )
+            ok2 = ccfWf.testCache()
+            logger.info("CCD model coordinates generation setup status %r", ok2)
+            #
+            ok2 = ccfWf.makeFiles(fmt="sdf") and ok2
+            logger.info("CCD model file sdf generation status %r", ok2)
+            ok2 = ccfWf.makeFiles(fmt="mol2") and ok2
+            logger.info("CCD model file mol2 generation status %r", ok2)
+            #
+            ok = ok1 and ok2
+        #
+        logger.info("Completed operation %r with status %r\n", op, ok)
+        if not ok:
+            logger.error("%r FAILED with status %s", op, ok)
+            raise ValueError("%r FAILED. Check the loader log for details." % op)
+
+        return ok
+
     def buildExdbResource(self, op, **kwargs):
         logger.info("Starting operation %r\n", op)
         #

{rcsb_exdb-1.24 → rcsb_exdb-1.26/rcsb.exdb.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: rcsb.exdb
-Version: 1.24
+Version: 1.26
 Summary: RCSB Python ExDB data extraction and loading workflows
 Home-page: https://github.com/rcsb/py-rcsb_exdb
 Author: John Westbrook
@@ -13,13 +13,14 @@ Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Programming Language :: Python
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: OpenEye-toolkits>=2020.2.2
+Requires-Dist: OpenEye-toolkits>=2024.1.1
 Requires-Dist: numpy
 Requires-Dist: jsonschema>=2.6.0
 Requires-Dist: rcsb.utils.io>=1.48
-Requires-Dist: rcsb.db>=1.723
+Requires-Dist: rcsb.db>=1.725
 Requires-Dist: rcsb.utils.chem>=0.79
 Requires-Dist: rcsb.utils.chemref>=0.91
 Requires-Dist: rcsb.utils.citation>=0.22
@@ -27,12 +28,12 @@ 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>=0.82
-Requires-Dist: rcsb.utils.seqalign>=0.29
+Requires-Dist: rcsb.utils.seqalign>=0.31
 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>=1.27
-Requires-Dist: rcsb.workflow>=0.45
+Requires-Dist: rcsb.workflow>=0.46
 Requires-Dist: statistics; python_version < "3.0"
 Provides-Extra: dev
 Requires-Dist: check-manifest; extra == "dev"

{rcsb_exdb-1.24 → rcsb_exdb-1.26}/rcsb.exdb.egg-info/requires.txt

@@ -1,8 +1,8 @@
-OpenEye-toolkits>=2020.2.2
+OpenEye-toolkits>=2024.1.1
 numpy
 jsonschema>=2.6.0
 rcsb.utils.io>=1.48
-rcsb.db>=1.723
+rcsb.db>=1.725
 rcsb.utils.chem>=0.79
 rcsb.utils.chemref>=0.91
 rcsb.utils.citation>=0.22
@@ -10,12 +10,12 @@ rcsb.utils.config>=0.40
 rcsb.utils.ec>=0.25
 rcsb.utils.go>=0.18
 rcsb.utils.seq>=0.82
-rcsb.utils.seqalign>=0.29
+rcsb.utils.seqalign>=0.31
 rcsb.utils.targets>=0.82
 rcsb.utils.struct>=0.47
 rcsb.utils.taxonomy>=0.43
 rcsb.utils.dictionary>=1.27
-rcsb.workflow>=0.45
+rcsb.workflow>=0.46
 
 [:python_version < "3.0"]
 statistics

{rcsb_exdb-1.24 → rcsb_exdb-1.26}/requirements.txt

@@ -1,9 +1,9 @@
 --extra-index-url https://pypi.anaconda.org/OpenEye/simple
-OpenEye-toolkits >= 2020.2.2
+OpenEye-toolkits >= 2024.1.1
 numpy
 jsonschema >= 2.6.0
 rcsb.utils.io >= 1.48
-rcsb.db >= 1.723
+rcsb.db >= 1.725
 rcsb.utils.chem >= 0.79
 rcsb.utils.chemref >= 0.91
 rcsb.utils.citation >= 0.22
@@ -11,10 +11,10 @@ rcsb.utils.config >= 0.40
 rcsb.utils.ec >= 0.25
 rcsb.utils.go >= 0.18
 rcsb.utils.seq >= 0.82
-rcsb.utils.seqalign >= 0.29
+rcsb.utils.seqalign >= 0.31
 rcsb.utils.targets >= 0.82
 rcsb.utils.struct >= 0.47
 rcsb.utils.taxonomy >= 0.43
 rcsb.utils.dictionary >= 1.27
-rcsb.workflow >= 0.45
+rcsb.workflow >= 0.46
 statistics; python_version < "3.0"

{rcsb_exdb-1.24 → rcsb_exdb-1.26}/setup.py

@@ -45,6 +45,7 @@ setup(
         "Programming Language :: Python",
         "Programming Language :: Python :: 3",
         "Programming Language :: Python :: 3.9",
+        "Programming Language :: Python :: 3.10",
     ],
     entry_points={"console_scripts": ["exdb_exec_cli=rcsb.exdb.cli.ExDbExec:main"]},
     #