pidibble 1.5.0__tar.gz → 1.5.2__tar.gz

{pidibble-1.5.0 → pidibble-1.5.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pidibble
-Version: 1.5.0
+Version: 1.5.2
 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/
@@ -91,6 +91,8 @@ ATOM
 ```
 
 ## Release History
+* 1.5.2
+   * added capability to download from OPM and split out DUM resi's into a "dum" pdb
 * 1.4.2
    * updated alphafold interface
 * 1.4.1

{pidibble-1.5.0 → pidibble-1.5.2}/README.md

@@ -73,6 +73,8 @@ ATOM
 ```
 
 ## Release History
+* 1.5.2
+   * added capability to download from OPM and split out DUM resi's into a "dum" pdb
 * 1.4.2
    * updated alphafold interface
 * 1.4.1

{pidibble-1.5.0 → pidibble-1.5.2}/pidibble/baseparsers.py

@@ -87,7 +87,7 @@ class StringParser:
         self.fields={k:v for k,v in fmtdict.items()}
         self.allowed=allowed
 
-    def parse(self,record):
+    def parse(self, record):
         """
         Parse a fixed-width string record into a dictionary of fields.
         
@@ -104,7 +104,10 @@ class StringParser:
         if len(record)>80:
             logger.warning('The following record exceeds 80 bytes in length:')
             self.report_record_error(record)
-        assert len(record)<=80,f'Record is too long; something wrong with your PDB file?'
+            logger.warning('Stripping...')
+            record = record.strip()
+            if len(record)>80:
+               raise ValueError(f'Record is too long; something wrong with your PDB file?')
         input_dict={}
         record+=' '*(80-len(record)) # pad
         for k,v in self.fields.items():
@@ -141,7 +144,7 @@ class StringParser:
         """
         if byte_range:
             record=record[:byte_range[0]-1]+'\033[91m'+record[byte_range[0]:byte_range[1]+1]+'\033[0m'+record[byte_range[1]+1:]
-        repstr=_cols+'\n'+record
+        repstr=_cols+'\n'+record+'|'
         logger.warning(repstr)
         
     def report_field_error(self,record,k):

{pidibble-1.5.0 → pidibble-1.5.2}/pidibble/pdbparse.py

@@ -120,7 +120,7 @@ class PDBParser:
         bool
             True if the file was successfully fetched, False otherwise.
         """
-        assert self.source_db is not None or self.filepath is not None, f'source_db or filepath must be specified for fetch()'
+        assert self.source_db is not None or self.filepath is not None, f'source_db {self.source_db} or filepath {self.filepath} must be specified for fetch()'
         if self.source_db is not None and self.source_id is None:
             raise ValueError(f'You must specify a source ID code for source_db {self.source_db}')
         if self.source_db is not None and self.source_db not in ['rcsb', 'alphafold', 'opm']:
@@ -176,6 +176,19 @@ class PDBParser:
                     except:
                         logger.warning(f'Could not fetch {self.filepath.name} from {self.source_db}')
                         return False
+                    logger.warning(f'Stripping blanks and END lines from OPM pdb')
+                    badlines = self.filepath.read_text().split('\n')
+                    with open(self.filepath.name, 'w') as f_base:
+                        with open(f'{self.filepath.stem}-dum.pdb', 'w') as f_dum:
+                            f = f_base
+                            for line in badlines:
+                                sline = line.strip()
+                                if not sline.startswith('END') and len(sline) > 0:
+                                    f.write(sline+'\n')
+                                if sline.startswith('END') and f is f_base:
+                                    f = f_dum
+                    logger.debug(f'Generated {self.filepath.name} and {self.filepath.stem}-dum.pdb')
+                                
                 return True
             case '_':
                 logger.debug(f'Source db {self.source_db} is not recognized.')
@@ -187,10 +200,10 @@ class PDBParser:
         This method opens the PDB file, reads its contents, and splits it into lines.
         If the last line is empty, it removes it from the list of lines.
         """
-        with open(self.filepath,'r') as f:
-            self.pdb_lines=f.read().split('\n')
-            if self.pdb_lines[-1]=='':
-                self.pdb_lines=self.pdb_lines[:-1]
+        with open(self.filepath, 'r') as f:
+            self.pdb_lines = f.read().split('\n')
+            if self.pdb_lines[-1] == '':
+                self.pdb_lines = self.pdb_lines[:-1]
 
     def read_mmCIF(self):
         """
@@ -198,16 +211,16 @@ class PDBParser:
         This method uses the :class:`mmcif.io.IoAdapterCore.IoAdapterCore` to read the
         mmCIF file and store the data in :attr:`PDBParser.cif_data`.
         """
-        io=IoAdapterCore()
-        l_dc=io.readFile(self.filepath)
-        self.cif_data=l_dc[0]
+        io = IoAdapterCore()
+        l_dc = io.readFile(self.filepath)
+        self.cif_data = l_dc[0]
 
     def read(self):
         """
         Read the PDB or mmCIF file based on the input format.
         This method checks the input format and calls the appropriate read method.
         """
-        if self.input_format=='mmCIF':
+        if self.input_format == 'mmCIF':
             self.read_mmCIF()
         else:
             self.read_PDB()
@@ -219,7 +232,7 @@ class PDBParser:
         If the input format is mmCIF, it uses the :class:`.mmcif_parse.MMCIF_Parser` to parse the mmCIF data.
         If the input format is PDB, it uses the :class:`.pdbrecord.PDBRecord` class to parse the PDB lines.
         """
-        if self.input_format=='mmCIF':
+        if self.input_format == 'mmCIF':
             self.parse_mmCIF()
         else:
             self.parse_PDB()
@@ -230,8 +243,8 @@ class PDBParser:
         This method uses the :class:`.mmcif_parse.MMCIF_Parser` to parse the mmCIF data and store the parsed records
         in :attr:`PDBParser.parsed`.
         """
-        mmcif_parser=MMCIF_Parser(self.mmcif_format_dict,self.pdb_format_dict['record_formats'],self.cif_data)
-        self.parsed=mmcif_parser.parse()
+        mmcif_parser = MMCIF_Parser(self.mmcif_format_dict,self.pdb_format_dict['record_formats'],self.cif_data)
+        self.parsed = mmcif_parser.parse()
 
     def parse_PDB(self):
         """

{pidibble-1.5.0 → pidibble-1.5.2}/pyproject.toml

@@ -3,7 +3,7 @@ requires = ["hatchling"]
 build-backend = "hatchling.build"
 [project]
 name = "pidibble"
-version = "1.5.0"
+version = "1.5.2"
 authors = [
   { name="Cameron F Abrams", email="cfa22@drexel.edu" },
 ]