rcsb.exdb 1.25__tar.gz → 1.27__tar.gz

{rcsb_exdb-1.25 → rcsb_exdb-1.27}/HISTORY.txt

@@ -106,3 +106,6 @@
 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
+23-Jan-2025 V1.27 Update TreeNodeListWorker to index 'id' field

{rcsb_exdb-1.25/rcsb.exdb.egg-info → rcsb_exdb-1.27}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.2
 Name: rcsb.exdb
-Version: 1.25
+Version: 1.27
 Summary: RCSB Python ExDB data extraction and loading workflows
 Home-page: https://github.com/rcsb/py-rcsb_exdb
 Author: John Westbrook
@@ -28,7 +28,7 @@ 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
@@ -39,6 +39,16 @@ Provides-Extra: dev
 Requires-Dist: check-manifest; extra == "dev"
 Provides-Extra: test
 Requires-Dist: coverage; extra == "test"
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: license
+Dynamic: provides-extra
+Dynamic: requires-dist
+Dynamic: summary
 
 # py-rcsb_exdb
 

{rcsb_exdb-1.25 → rcsb_exdb-1.27}/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__ = "1.25"
+__version__ = "1.27"

{rcsb_exdb-1.25 → rcsb_exdb-1.27}/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-1.25 → rcsb_exdb-1.27}/rcsb/exdb/tree/TreeNodeListWorker.py

@@ -9,6 +9,7 @@
 # 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
+# 23-Jan-2025 dwp Change indexed field from 'update_id' to 'id'
 #
 ##
 __docformat__ = "google en"
@@ -138,7 +139,7 @@ class TreeNodeListWorker(object):
             # logger.info("GO tree node list length %d", len(nL))
             # if doLoad:
             #     collectionName = "tree_go_node_list"
-            #     ok = dl.load(databaseName, collectionName, loadType=loadType, documentList=nL, indexAttributeList=["update_id"], keyNames=None, addValues=addValues, schemaLevel=None)
+            #     ok = dl.load(databaseName, collectionName, loadType=loadType, documentList=nL, indexAttributeList=["id"], keyNames=None, addValues=addValues, schemaLevel=None)
             #     self.__updateStatus(updateId, databaseName, collectionName, ok, statusStartTimestamp)
             #
             # ---- CATH
@@ -147,7 +148,7 @@ class TreeNodeListWorker(object):
             logger.info("Starting load SCOP node tree length %d", len(nL))
             if doLoad:
                 collectionName = "tree_cath_node_list"
-                ok = dl.load(databaseName, collectionName, loadType=loadType, documentList=nL, indexAttributeList=["update_id"], keyNames=None, addValues=addValues, schemaLevel=None)
+                ok = dl.load(databaseName, collectionName, loadType=loadType, documentList=nL, indexAttributeList=["id"], keyNames=None, addValues=addValues, schemaLevel=None)
                 self.__updateStatus(updateId, databaseName, collectionName, ok, statusStartTimestamp)
             # ---- SCOP
             scu = ScopClassificationProvider(cachePath=self.__cachePath, useCache=useCache)
@@ -155,7 +156,7 @@ class TreeNodeListWorker(object):
             logger.info("Starting load SCOP node tree length %d", len(nL))
             if doLoad:
                 collectionName = "tree_scop_node_list"
-                ok = dl.load(databaseName, collectionName, loadType=loadType, documentList=nL, indexAttributeList=["update_id"], keyNames=None, addValues=addValues, schemaLevel=None)
+                ok = dl.load(databaseName, collectionName, loadType=loadType, documentList=nL, indexAttributeList=["id"], keyNames=None, addValues=addValues, schemaLevel=None)
                 self.__updateStatus(updateId, databaseName, collectionName, ok, statusStartTimestamp)
             # --- SCOP2
             scu = Scop2ClassificationProvider(cachePath=self.__cachePath, useCache=useCache)
@@ -163,7 +164,7 @@ class TreeNodeListWorker(object):
             logger.info("Starting load SCOP2 node tree length %d", len(nL))
             if doLoad:
                 collectionName = "tree_scop2_node_list"
-                ok = dl.load(databaseName, collectionName, loadType=loadType, documentList=nL, indexAttributeList=["update_id"], keyNames=None, addValues=addValues, schemaLevel=None)
+                ok = dl.load(databaseName, collectionName, loadType=loadType, documentList=nL, indexAttributeList=["id"], keyNames=None, addValues=addValues, schemaLevel=None)
                 self.__updateStatus(updateId, databaseName, collectionName, ok, statusStartTimestamp)
             # ---- Ecod
             ecu = EcodClassificationProvider(cachePath=self.__cachePath, useCache=useCache)
@@ -171,7 +172,7 @@ class TreeNodeListWorker(object):
             logger.info("Starting load ECOD node tree length %d", len(nL))
             if doLoad:
                 collectionName = "tree_ecod_node_list"
-                ok = dl.load(databaseName, collectionName, loadType=loadType, documentList=nL, indexAttributeList=["update_id"], keyNames=None, addValues=addValues, schemaLevel=None)
+                ok = dl.load(databaseName, collectionName, loadType=loadType, documentList=nL, indexAttributeList=["id"], keyNames=None, addValues=addValues, schemaLevel=None)
                 self.__updateStatus(updateId, databaseName, collectionName, ok, statusStartTimestamp)
             # ---- EC
             edbu = EnzymeDatabaseProvider(cachePath=self.__cachePath, useCache=useCache)
@@ -179,7 +180,7 @@ class TreeNodeListWorker(object):
             logger.info("Starting load of EC node tree length %d", len(nL))
             if doLoad:
                 collectionName = "tree_ec_node_list"
-                ok = dl.load(databaseName, collectionName, loadType=loadType, documentList=nL, indexAttributeList=["update_id"], keyNames=None, addValues=addValues, schemaLevel=None)
+                ok = dl.load(databaseName, collectionName, loadType=loadType, documentList=nL, indexAttributeList=["id"], keyNames=None, addValues=addValues, schemaLevel=None)
                 self.__updateStatus(updateId, databaseName, collectionName, ok, statusStartTimestamp)
             # ---- CARD
             okCou = True
@@ -200,7 +201,7 @@ class TreeNodeListWorker(object):
                         collectionName,
                         loadType=loadType,
                         documentList=nL,
-                        indexAttributeList=["update_id"],
+                        indexAttributeList=["id"],
                         keyNames=None,
                         addValues=addValues,
                         schemaLevel=None
@@ -229,7 +230,7 @@ class TreeNodeListWorker(object):
             if doLoad:
                 collectionName = "tree_taxonomy_node_list"
                 logger.debug("Taxonomy nodes (%d) %r", len(nL), nL[:5])
-                ok = dl.load(databaseName, collectionName, loadType=loadType, documentList=nL, indexAttributeList=["update_id"], keyNames=None, addValues=addValues, schemaLevel=None)
+                ok = dl.load(databaseName, collectionName, loadType=loadType, documentList=nL, indexAttributeList=["id"], keyNames=None, addValues=addValues, schemaLevel=None)
                 self.__updateStatus(updateId, databaseName, collectionName, ok, statusStartTimestamp)
             logger.info("Tree loading operations completed.")
             #
@@ -241,7 +242,7 @@ class TreeNodeListWorker(object):
             nL = atcP.getTreeNodeList(filterD=atcFilterD)
             collectionName = "tree_atc_node_list"
             logger.debug("ATC node list length %d %r", len(nL), nL[:5])
-            ok = dl.load(databaseName, collectionName, loadType=loadType, documentList=nL, indexAttributeList=["update_id"], keyNames=None, addValues=addValues, schemaLevel=None)
+            ok = dl.load(databaseName, collectionName, loadType=loadType, documentList=nL, indexAttributeList=["id"], keyNames=None, addValues=addValues, schemaLevel=None)
             self.__updateStatus(updateId, databaseName, collectionName, ok, statusStartTimestamp)
             #
             # ---

{rcsb_exdb-1.25 → rcsb_exdb-1.27/rcsb.exdb.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.2
 Name: rcsb.exdb
-Version: 1.25
+Version: 1.27
 Summary: RCSB Python ExDB data extraction and loading workflows
 Home-page: https://github.com/rcsb/py-rcsb_exdb
 Author: John Westbrook
@@ -28,7 +28,7 @@ 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
@@ -39,6 +39,16 @@ Provides-Extra: dev
 Requires-Dist: check-manifest; extra == "dev"
 Provides-Extra: test
 Requires-Dist: coverage; extra == "test"
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: license
+Dynamic: provides-extra
+Dynamic: requires-dist
+Dynamic: summary
 
 # py-rcsb_exdb
 

{rcsb_exdb-1.25 → rcsb_exdb-1.27}/rcsb.exdb.egg-info/requires.txt

@@ -10,7 +10,7 @@ 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_exdb-1.25 → rcsb_exdb-1.27}/requirements.txt

@@ -11,7 +11,7 @@ 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