rcsb.exdb 1.25__tar.gz → 1.26__tar.gz

{rcsb_exdb-1.25 → rcsb_exdb-1.26}/HISTORY.txt

@@ -106,3 +106,5 @@
 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-1.25/rcsb.exdb.egg-info → rcsb_exdb-1.26}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: rcsb.exdb
-Version: 1.25
+Version: 1.26
 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

{rcsb_exdb-1.25 → 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__ = "1.25"
+__version__ = "1.26"

{rcsb_exdb-1.25 → 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-1.25 → rcsb_exdb-1.26/rcsb.exdb.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: rcsb.exdb
-Version: 1.25
+Version: 1.26
 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

{rcsb_exdb-1.25 → rcsb_exdb-1.26}/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-1.26}/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