Add XEASY PROT file lexer, parser, parserlistener, and reader

wwpdb/utils/nmr/NmrDpReport.py

@@ -88,6 +88,7 @@
 # 14-Nov-2024  M. Yokochi - add 'nm-aux-cha' file type for CHARMM extended CRD (CARD) file acting as CHARMM topology definition
 # 19-Nov-2024  M. Yokochi - add support for pH titration data (NMR restraint remediation)
 # 22-Nov-2024  M. Yokochi - add 'nm-res-noa' file type for CYANA NOA (NOE Assignment) file
+# 05-Dec-2024  M. Yokochi - add 'nm-aux-xea' file type for XEASY PROT (Assignment) file (NMR restraint remediation)
 ##
 """ Wrapper class for NMR data processing report.
     @author: Masashi Yokochi
@@ -1752,7 +1753,7 @@ def __init__(self, verbose=True, log=sys.stdout):
                       'stats_of_exptl_data')
         self.file_types = ('pdbx',
                            'nef', 'nmr-star',
-                           'nm-aux-amb', 'nm-aux-cha', 'nm-aux-gro',
+                           'nm-aux-amb', 'nm-aux-cha', 'nm-aux-gro', 'nm-aux-xea',
                            'nm-res-amb', 'nm-res-ari', 'nm-res-bio', 'nm-res-cha', 'nm-res-cns',
                            'nm-res-cya', 'nm-res-dyn', 'nm-res-gro', 'nm-res-isd', 'nm-res-mr',
                            'nm-res-noa', 'nm-res-oth', 'nm-res-ros', 'nm-res-sax', 'nm-res-syb',

wwpdb/utils/nmr/README.md

@@ -295,4 +295,12 @@ nm-res-xpl|nm-res-xpl|nmr-restraints/xplor-nih|Restraint file in XPLOR-NIH forma
 nm-res-oth|nm-res-oth|nmr-restraints/any|Restraint file in other format
 nm-res-mr|**not applicable**|nmr-restraints/pdb-mr|Restraint file in PDB-MR format
 nm-res-sax|**not applicable**|nmr-restraints/any|SAX CSV file
+nm-pea-ari|**not applicable**|nmr-peaks/any|Spectral peak list file in ARIA format
+nm-pea-pip|**not applicable**|nmr-peaks/any|Spectral peak list file in NMRPIPE format
+nm-pea-spa|**not applicable**|nmr-peaks/any|Spectral peak list file in SPARKY format
+nm-pea-top|**not applicable**|nmr-peaks/any|Spectral peak list file in TOPSPIN format
+nm-pea-vie|**not applicable**|nmr-peaks/any|Spectral peak list file in NMRVIEW format
+nm-aux-xea|**not applicable**|nmr-peaks/any|Assignment file in XEASY format
+nm-pea-xea|**not applicable**|nmr-peaks/any|Spectral peak list file in XEASY format
+nm-pea-xwi|**not applicable**|nmr-peaks/any|Spectral peak list file in XWINNMR format
 nm-pea-any|nm-pea-any|nmr-peaks/any|Any spectral peak list file

wwpdb/utils/nmr/mr/AmberPTParserListener.py

@@ -345,7 +345,7 @@ def is_metal_elem(prev_atom_name, prev_seq_id, seq_id):
                         atomName = _atomName
                         retrievedAtomNumList.append(atomNum)
 
-                if (terminus[atomNum - 1] and ancAtomName.endswith('T'))\
+                if (0 < atomNum < len(terminus) + 1 and terminus[atomNum - 1] and ancAtomName.endswith('T'))\
                    or is_segment(prevCompId, prevAtomName, compId, atomName)\
                    or is_ligand(prevCompId, compId)\
                    or is_metal_ion(compId, atomName)\
@@ -1753,7 +1753,9 @@ def exitTree_chain_classification_statement(self, ctx: AmberPTParser.Tree_chain_
 
     # Enter a parse tree produced by AmberPTParser#format_function.
     def enterFormat_function(self, ctx: AmberPTParser.Format_functionContext):
+
         try:
+
             if ctx.Fortran_format_A():
                 g = self.__a_format_pat.search(str(ctx.Fortran_format_A())).groups()
                 # self.__cur_column_len = int(g[0])
@@ -1766,6 +1768,7 @@ def enterFormat_function(self, ctx: AmberPTParser.Format_functionContext):
                 g = self.__e_format_pat.search(str(ctx.Fortran_format_E())).groups()
                 # self.__cur_column_len = int(g[0])
                 self.__cur_word_len = int(g[1])
+
         except AttributeError:
             # self.__cur_column_len = None
             self.__cur_word_len = None

wwpdb/utils/nmr/mr/AriaMRParserListener.py

@@ -2933,6 +2933,7 @@ def exitAtom_pair(self, ctx: AriaMRParser.Atom_pairContext):  # pylint: disable=
 
     # Enter a parse tree produced by AriaMRParser#atom_selection.
     def enterAtom_selection(self, ctx: AriaMRParser.Atom_selectionContext):
+
         try:
 
             atom_sel = {'atom_id': str(ctx.Simple_name(1)).upper()}

wwpdb/utils/nmr/mr/CharmmCRDParserListener.py

@@ -241,7 +241,7 @@ def is_metal_elem(prev_atom_name, prev_seq_id, seq_id):
                         atomName = _atomName
                         retrievedAtomNumList.append(atomNum)
 
-                if (terminus[atomNum - 1] and ancAtomName.endswith('T'))\
+                if (0 < atomNum < len(terminus) + 1 and terminus[atomNum - 1] and ancAtomName.endswith('T'))\
                    or is_segment(prevAsymId, prevCompId, prevAtomName, asymId, compId, atomName)\
                    or is_ligand(prevCompId, compId)\
                    or is_metal_ion(compId, atomName)\
@@ -956,6 +956,7 @@ def enterAtom_coordinate(self, ctx: CharmmCRDParser.Atom_coordinateContext):  #
     def exitAtom_coordinate(self, ctx: CharmmCRDParser.Atom_coordinateContext):
 
         try:
+
             nr = int(str(ctx.Integer(0)))
             seqId = int(str(ctx.Integer(1)))
 

wwpdb/utils/nmr/mr/CharmmCRDReader.py

@@ -76,7 +76,7 @@ def setLexerMaxErrorReport(self, maxErrReport):
     def setParserMaxErrorReport(self, maxErrReport):
         self.__maxParserErrorReport = maxErrReport
 
-    def parse(self, ptFilePath, cifFilePath=None, isFilePath=True):
+    def parse(self, crdFilePath, cifFilePath=None, isFilePath=True):
         """ Parse CHARMM CRD file.
             @return: CharmmCRDParserListener for success or None otherwise, ParserErrorListener, LexerErrorListener.
         """
@@ -86,25 +86,25 @@ def parse(self, ptFilePath, cifFilePath=None, isFilePath=True):
         try:
 
             if isFilePath:
-                ptString = None
+                crdString = None
 
-                if not os.access(ptFilePath, os.R_OK):
+                if not os.access(crdFilePath, os.R_OK):
                     if self.__verbose:
-                        self.__lfh.write(f"CharmmCRDReader.parse() {ptFilePath} is not accessible.\n")
+                        self.__lfh.write(f"CharmmCRDReader.parse() {crdFilePath} is not accessible.\n")
                     return None, None, None
 
-                ifh = open(ptFilePath, 'r')  # pylint: disable=consider-using-with
+                ifh = open(crdFilePath, 'r')  # pylint: disable=consider-using-with
                 input = InputStream(ifh.read())
 
             else:
-                ptFilePath, ptString = None, ptFilePath
+                crdFilePath, crdString = None, crdFilePath
 
-                if ptString is None or len(ptString) == 0:
+                if crdString is None or len(crdString) == 0:
                     if self.__verbose:
                         self.__lfh.write("CharmmCRDReader.parse() Empty string.\n")
                     return None, None, None
 
-                input = InputStream(ptString)
+                input = InputStream(crdString)
 
             if cifFilePath is not None:
                 if not os.access(cifFilePath, os.R_OK):
@@ -120,7 +120,7 @@ def parse(self, ptFilePath, cifFilePath=None, isFilePath=True):
             lexer = CharmmCRDLexer(input)
             lexer.removeErrorListeners()
 
-            lexer_error_listener = LexerErrorListener(ptFilePath, maxErrorReport=self.__maxLexerErrorReport)
+            lexer_error_listener = LexerErrorListener(crdFilePath, maxErrorReport=self.__maxLexerErrorReport)
             lexer.addErrorListener(lexer_error_listener)
 
             messageList = lexer_error_listener.getMessageList()
@@ -137,7 +137,7 @@ def parse(self, ptFilePath, cifFilePath=None, isFilePath=True):
             # try with simpler/faster SLL prediction mode
             parser._interp.predictionMode = PredictionMode.SLL  # pylint: disable=protected-access
             parser.removeErrorListeners()
-            parser_error_listener = ParserErrorListener(ptFilePath, maxErrorReport=self.__maxParserErrorReport)
+            parser_error_listener = ParserErrorListener(crdFilePath, maxErrorReport=self.__maxParserErrorReport)
             parser.addErrorListener(parser_error_listener)
             tree = parser.charmm_crd()
 
@@ -159,7 +159,7 @@ def parse(self, ptFilePath, cifFilePath=None, isFilePath=True):
                         self.__lfh.write(f"{description['input']}\n")
                         self.__lfh.write(f"{description['marker']}\n")
             elif messageList is None and cifFilePath is None:
-                parser_error_listener = ParserErrorListener(ptFilePath, maxErrorReport=self.__maxParserErrorReport)
+                parser_error_listener = ParserErrorListener(crdFilePath, maxErrorReport=self.__maxParserErrorReport)
 
             if self.__verbose:
                 if listener.warningMessage is not None and len(listener.warningMessage) > 0:
@@ -177,7 +177,7 @@ def parse(self, ptFilePath, cifFilePath=None, isFilePath=True):
             """ debug code
         except Exception as e:
             if self.__verbose and isFilePath:
-                self.__lfh.write(f"+CharmmCRDReader.parse() ++ Error - {ptFilePath!r} - {str(e)}\n")
+                self.__lfh.write(f"+CharmmCRDReader.parse() ++ Error - {crdFilePath!r} - {str(e)}\n")
             return None, None, None
             """
         finally:

wwpdb/utils/nmr/mr/GromacsPTParserListener.py

@@ -285,7 +285,7 @@ def is_metal_elem(prev_atom_name, prev_seq_id, seq_id):
                         atomName = _atomName
                         retrievedAtomNumList.append(atomNum)
 
-                if (terminus[atomNum - 1] and ancAtomName.endswith('T'))\
+                if (0 < atomNum < len(terminus) + 1 and terminus[atomNum - 1] and ancAtomName.endswith('T'))\
                    or is_segment(prevCompId, prevAtomName, compId, atomName)\
                    or is_ligand(prevCompId, compId)\
                    or is_metal_ion(compId, atomName)\