pidibble 1.1.2__tar.gz → 1.1.4__tar.gz

{pidibble-1.1.2 → pidibble-1.1.4}/.readthedocs.yaml

@@ -27,6 +27,6 @@ sphinx:
 # Optional but recommended, declare the Python requirements required
 # to build your documentation
 # See https://docs.readthedocs.io/en/stable/guides/reproducible-builds.html
-# python:
-#    install:
-#    - requirements: docs/requirements.txt
+python:
+   install:
+   - requirements: docs/requirements.txt

{pidibble-1.1.2 → pidibble-1.1.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pidibble
-Version: 1.1.2
+Version: 1.1.4
 Summary: A complete Protein Data Bank (PDB) file parser
 Project-URL: Source, https://github.com/cameronabrams/pidibble
 Project-URL: Documentation, https://pidibble.readthedocs.io/en/latest/
@@ -88,6 +88,10 @@ ATOM
 ```
 
 ## Release History
+* 1.1.4
+   * Added ability to read hexadecimal atom indices for files with > 99999 atoms
+* 1.1.3
+   * Added ability to group into models for multiple-model entries
 * 1.1.2
    * Added ability to retrieve pdbs from AlphaFold database
 * 1.1.1

{pidibble-1.1.2 → pidibble-1.1.4}/README.md

@@ -70,6 +70,10 @@ ATOM
 ```
 
 ## Release History
+* 1.1.4
+   * Added ability to read hexadecimal atom indices for files with > 99999 atoms
+* 1.1.3
+   * Added ability to group into models for multiple-model entries
 * 1.1.2
    * Added ability to retrieve pdbs from AlphaFold database
 * 1.1.1

pidibble-1.1.4/docs/requirements.txt

@@ -0,0 +1,8 @@
+pillow 
+mock==1.0.1
+alabaster>=0.7,<0.8,!=0.7.5 
+commonmark==0.9.1
+recommonmark==0.5.0
+sphinx 
+sphinx-rtd-theme 
+readthedocs-sphinx-ext<2.3

{pidibble-1.1.2 → pidibble-1.1.4}/docs/source/conf.py

@@ -3,11 +3,11 @@
 # -- Project information
 
 project = 'Pidibble'
-copyright = '2023, Cameron F. Abrams'
+copyright = '2023-2024, Cameron F. Abrams'
 author = 'cfa22@drexel.edu'
 
 release = '1.1'
-version = '1.1.1'
+version = '1.1.4'
 
 # -- General configuration
 

{pidibble-1.1.2 → pidibble-1.1.4}/docs/source/index.rst

@@ -1,7 +1,7 @@
 Welcome to Pidibble's documentation!
 ====================================
 
-**Pidibble** is a Python package for parsing standard Protein Data Bank (PDB) files.  It conforms to the `most recent standard <https://www.wwpdb.org/documentation/file-format-content/format33/v3.3.html>`_ (v.3.3 Atomic Coordinate Entry Format, ca. 2011).
+**Pidibble** is a Python package for parsing Protein Data Bank (PDB) files.  It conforms to the `most recent standard <https://www.wwpdb.org/documentation/file-format-content/format33/v3.3.html>`_ (v.3.3 Atomic Coordinate Entry Format, ca. 2011).
 
 Unlike parsers like that found in packages like `BioPython <https://biopython.org/wiki/PDBParser>`_, ``pidibble`` provides meaningfully parsed objects from *all* standard PDB record types, not just ATOMs and CONECTs.
 
@@ -9,8 +9,9 @@ Once installed, the user has access to the ``PDBParser`` class in the ``pidibble
 
 Pidibble can fetch coordinate files from the RSCB PDB and from the AlphaFold model database.
 
-Check out the :doc:`usage` section for further information, including
-on :ref:`installation` of the package.
+Pidibble can handle hexadecimal serial numbers in all record types.
+
+Check out the :doc:`usage` section for further information, including on :ref:`installation` of the package.
 
 .. note::
 

pidibble-1.1.4/pidibble/hex.py

@@ -0,0 +1,7 @@
+def int_or_hex(arg,force=False):
+    if type(arg)==int and not force: return arg
+    assert type(arg)==str
+    if force or any([(x in arg) for x in 'abcdef']):
+        return int(arg,16)
+    else:
+        return int(arg)

{pidibble-1.1.2 → pidibble-1.1.4}/pidibble/pdbparse.py

@@ -21,11 +21,13 @@ from pidibble import resources
 logger=logging.getLogger(__name__)
 import importlib.metadata
 import json
+from .hex import int_or_hex
 
 __version__ = importlib.metadata.version("pidibble")
 
 class PDBParser:
-    mappers={'Integer':int,'String':str,'Float':float}
+    # mappers={'Integer':int,'String':str,'Float':float}
+    mappers={'Integer':int_or_hex,'String':str,'Float':float}
     mappers.update(ListParsers)
     comment_lines=[]
     comment_chars=['#']
@@ -144,6 +146,7 @@ class PDBParser:
         record_formats=self.pdb_format_dict['record_formats']
         key=''
         record_format={}
+        group_open_record=None
         for i,pdbrecord_line in enumerate(self.pdb_lines):
             tc=pdbrecord_line[0]
             if tc in PDBParser.comment_chars:
@@ -167,6 +170,18 @@ class PDBParser:
             elif record_type in [3,4,5]:
                 if not key in self.parsed:
                     # this is necessarily the first occurance of a record with this key, but since there can be multiple instances this must be a list of records
+                    if 'groupuntil' in record_format:
+                        group_open_record=new_record
+                        logger.debug(f'opening group {group_open_record.serial} until {group_open_record.format["groupuntil"]}')
+                    if group_open_record!=None and key==group_open_record.format['groupuntil']:
+                        logger.debug(f'closing group {group_open_record.serial}')
+                        group_open_record=None
+                    if 'groupby' in record_format:
+                        tok=new_record.format['groupby'].split('.')
+                        if group_open_record!=None:
+                            if tok[0]==group_open_record.key:
+                                groupid=getattr(group_open_record,tok[1])
+                                setattr(new_record,group_open_record.key.lower(),groupid)
                     self.parsed[key]=[new_record]
                 else:
                     # this is either
@@ -189,15 +204,32 @@ class PDBParser:
                         root_record.continue_record(new_record,record_format)
                     else:
                         # case (b)
+                        if 'groupuntil' in record_format:
+                            group_open_record=new_record
+                            logger.debug(f'opening group {group_open_record.serial} until {group_open_record.format["groupuntil"]}')
+                        if group_open_record!=None and key==group_open_record.format['groupuntil']:
+                            logger.debug(f'closing group {group_open_record.serial}')
+                            group_open_record=None
+                        if 'groupby' in record_format:
+                            tok=new_record.format['groupby'].split('.')
+                            if group_open_record!=None:
+                                if tok[0]==group_open_record.key:
+                                    groupid=getattr(group_open_record,tok[1])
+                                    setattr(new_record,group_open_record.key.lower(),groupid)
                         self.parsed[key].append(new_record)
 
-
     def post_process(self):
         if self.input_format!='mmCIF':
             self.parse_embedded_records()
             self.parse_tokens()
             self.parse_tables()
 
+    # def parse_models(self):
+    #     n_models=self.parsed.get('NUMMDL',1)
+    #     for i in range(n_models):
+    #         self.parsed['MODEL'][i+1]={}
+    #         # in progress
+        
     def parse_embedded_records(self):
         new_parsed_records={}
         for key,p in self.parsed.items():

{pidibble-1.1.2 → pidibble-1.1.4}/pidibble/resources/pdb_format.yaml

@@ -303,6 +303,7 @@ record_formats:
       - sidCodes
   ANISOU:
     type: 3
+    groupby: MODEL.serial
     fields:
       serial: [Integer,[7,11]]
       name: [String,[13,16]]
@@ -318,6 +319,7 @@ record_formats:
       charge: [Float,[79,80]] # String?      
   ATOM:
     type: 3
+    groupby: MODEL.serial
     fields:
       serial: [Integer,[7,11]]
       name: [String,[13,16]]
@@ -332,6 +334,7 @@ record_formats:
       charge: [Float,[79,80]] # String?
   HETATM:
     type: 3
+    groupby: MODEL.serial
     fields:
       serial: [Integer,[7,11]]
       name: [String,[13,16]]
@@ -593,9 +596,11 @@ record_formats:
     type: 5
   MODEL:
     type: 5
+    groupuntil: ENDMDL
     fields:
       serial: [Integer,[11,14]]
   TER:
+    groupby: MODEL.serial
     type: 5
     fields:
       serial: [Integer,[7,11]]

{pidibble-1.1.2 → pidibble-1.1.4}/pyproject.toml

@@ -3,7 +3,7 @@ requires = ["hatchling"]
 build-backend = "hatchling.build"
 [project]
 name = "pidibble"
-version = "1.1.2"
+version = "1.1.4"
 authors = [
   { name="Cameron F Abrams", email="cfa22@drexel.edu" },
 ]

pidibble-1.1.4/tests/unit/test_hex/my_system.pdb

@@ -0,0 +1,6 @@
+ATOM  10000  H1  TIP3U 603      61.189  74.991  53.726  0.00  0.00      U81   
+ATOM  99999  H2  TIP3U 603      60.935  75.727  52.428  0.00  0.00      U81   
+ATOM  6b973  OH2 TIP3U 604      67.398   7.302  34.043  0.00  0.00      U81   
+ATOM  6b974  H1  TIP3U 604      68.253   6.886  34.152  0.00  0.00      U81   
+ATOM  6b975  H2  TIP3U 604      67.326   7.902  34.786  0.00  0.00      U81   
+ATOM  6b976  OH2 TIP3U 605      74.371 -45.062 -65.565  0.00  0.00      U81   

pidibble-1.1.4/tests/unit/test_hex.py

@@ -0,0 +1,20 @@
+import numpy as np
+from pidibble.pdbparse import PDBParser, PDBRecord, get_symm_ops
+from pidibble.hex import int_or_hex
+import unittest
+import logging
+
+def test_hex():
+    a=int_or_hex('186a0')
+    assert a==100000
+
+def test_hex_in_pdb():
+    p=PDBParser(PDBcode='my_system').parse()
+    atoms=p.parsed['ATOM']
+    assert len(atoms)==6
+    a1=atoms[0]
+    assert a1.serial==10000
+    a1=atoms[1]
+    assert a1.serial==99999
+    a1=atoms[2]
+    assert a1.serial==440691

{pidibble-1.1.2 → pidibble-1.1.4}/tests/unit/test_rcsb.py

@@ -1,7 +1,6 @@
 import numpy as np
 from pidibble.pdbparse import PDBParser, PDBRecord, get_symm_ops
 import unittest
-import pytest
 import logging
 logger=logging.getLogger(__name__)
 def test_pdbformat():