|
1
|
1 NAME
|
|
|
2 PDBFileUtil
|
|
|
3
|
|
|
4 SYNOPSIS
|
|
|
5 use PDBFileUtil ;
|
|
|
6
|
|
|
7 use PDBFileUtil qw(:all);
|
|
|
8
|
|
|
9 DESCRIPTION
|
|
|
10 PDBFileUtil module provides the following functions:
|
|
|
11
|
|
|
12 GenerateAtomOrHetatmRecordLine, GenerateAtomRecordLine,
|
|
|
13 GenerateConectRecordLine, GenerateEndRecordLine,
|
|
|
14 GenerateHeaderRecordLine, GenerateHeaderRecordTimeStamp,
|
|
|
15 GenerateHetatmRecordLine, GenerateTerRecordLine, GetAllResidues,
|
|
|
16 GetChainsAndResidues, GetConectRecordLines, GetExperimentalTechnique,
|
|
|
17 GetExperimentalTechniqueResolution, GetMinMaxCoords, GetPDBRecordType,
|
|
|
18 GetRecordTypesCount, IsAtomRecordType, IsConectRecordType,
|
|
|
19 IsEndmdlRecordType, IsHeaderRecordType, IsHetatmRecordType,
|
|
|
20 IsMasterRecordType, IsModelRecordType, IsPDBFile, IsSeqresRecordType,
|
|
|
21 IsTerRecordType, ParseAtomOrHetatmRecordLine, ParseAtomRecordLine,
|
|
|
22 ParseConectRecordLine, ParseExpdtaRecordLine, ParseHeaderRecordLine,
|
|
|
23 ParseHetatmRecordLine, ParseMasterRecordLine,
|
|
|
24 ParseRemark2ResolutionRecordLine, ParseSeqresRecordLine,
|
|
|
25 ParseTerRecordLine, ReadPDBFile
|
|
|
26
|
|
|
27 METHODS
|
|
|
28 GenerateAtomOrHetatmRecordLine
|
|
|
29 $RecordLine = GenerateAtomOrHetatmRecordLine($RecordType,
|
|
|
30 $AtomNumber, $AtomName, $AlternateLocation, $ResidueName,
|
|
|
31 $ChainID, $ResidueNumber, $InsertionCode, $X, $Y, $Z,
|
|
|
32 $Occupancy, $TemperatureFactor, $SegmentID,
|
|
|
33 $ElementSymbol, $AtomCharge);
|
|
|
34
|
|
|
35 Returns ATOM or HETATM record line.
|
|
|
36
|
|
|
37 GenerateAtomRecordLine
|
|
|
38 $RecordLine = GenerateAtomRecordLine($AtomNumber,
|
|
|
39 $AtomName, $AlternateLocation, $ResidueName, $ChainID,
|
|
|
40 $ResidueNumber, $InsertionCode, $X, $Y, $Z, $Occupancy,
|
|
|
41 $TemperatureFactor, $SegmentID, $ElementSymbol, $AtomCharge);
|
|
|
42
|
|
|
43 Returns ATOM record line.
|
|
|
44
|
|
|
45 GenerateConectRecordLine
|
|
|
46 $RecordLine = GenerateConectRecordLine($AtomNum, $BondedAtomNum1,
|
|
|
47 $BondedAtomNum2, $BondedAtomNum3, $BondedAtomNum4,
|
|
|
48 $HBondedAtomNum1, $HBondedAtomNum2, $SaltBridgedAtomNum1,
|
|
|
49 $HBondedAtomNum3, $HBondedAtomNum4, $SaltBridgedAtomNum2);
|
|
|
50
|
|
|
51 Returns CONECT record line.
|
|
|
52
|
|
|
53 GenerateHeaderRecordLine
|
|
|
54 $RecordLine = GenerateHeaderRecordLine($IDCode, [$Classification,
|
|
|
55 $Date]);
|
|
|
56
|
|
|
57 Returns HEADER record line.
|
|
|
58
|
|
|
59 GenerateHeaderRecordTimeStamp
|
|
|
60 $Date = GenerateHeaderRecordTimeStamp();
|
|
|
61
|
|
|
62 Returns PDB header time stamp.
|
|
|
63
|
|
|
64 GenerateHetatmRecordLine
|
|
|
65 $RecordLine = GenerateHetatmRecordLine($AtomNumber, $AtomName,
|
|
|
66 $AlternateLocation, $ResidueName, $ChainID, $ResidueNumber,
|
|
|
67 $InsertionCode, $X, $Y, $Z, $Occupancy, $TemperatureFactor,
|
|
|
68 $SegmentID, $ElementSymbol, $AtomCharge);
|
|
|
69
|
|
|
70 Returns HETATM record line.
|
|
|
71
|
|
|
72 GenerateEndRecordLine
|
|
|
73 $RecordLine = GenerateEndRecordLine();
|
|
|
74
|
|
|
75 Returns END record line.
|
|
|
76
|
|
|
77 GenerateTerRecordLine
|
|
|
78 $RecordLine = GenerateTerRecordLine($SerialNumber, [$ResidueName,
|
|
|
79 $ChainID, $ResidueNumber, $InsertionCode]);
|
|
|
80
|
|
|
81 Returns TER record line.
|
|
|
82
|
|
|
83 GetAllResidues
|
|
|
84 $ResiduesDataRef = GetAllResidues($PDBRecordLinesRef);
|
|
|
85
|
|
|
86 Gets residue information using ATOM/HETATM records and returns a
|
|
|
87 reference to a hash with following key/value pairs:
|
|
|
88
|
|
|
89 $ResiduesDataRef->{ResidueNames} - Array of all the residues
|
|
|
90 $ResiduesDataRef->{ResidueCount}{$ResidueName} - Count of residues
|
|
|
91 $ResiduesDataRef->{AtomResidueNames}} - Array of all ATOM residues
|
|
|
92 $ResiduesDataRef->{AtomResidueCount}{$ResidueName} - Count of
|
|
|
93 residues in ATOM records
|
|
|
94 $ResiduesDataRef->{HetatomResidueNames} - List of all HETATM
|
|
|
95 residues
|
|
|
96 $ResiduesDataRef->{HetatmResidueCount}{$ResidueName} - Count of
|
|
|
97 residues HETATM records
|
|
|
98
|
|
|
99 ATOM/HETATM records after the first ENDMDL records are simply
|
|
|
100 ingnored.
|
|
|
101
|
|
|
102 GetChainsAndResidues
|
|
|
103 $ChainsDataRef = GetChainsAndResidues($PDBRecordLinesRef,
|
|
|
104 [$RecordsSource, $GetChainResiduesBeyondTERFlag,
|
|
|
105 $GetRecordLinesFlag]);
|
|
|
106
|
|
|
107 Gets chains and residue information using ATOM/HETATM or SEQRES
|
|
|
108 records and returns a reference to a hash with these keys:
|
|
|
109
|
|
|
110 $ChainsDataRef->{ChainIDs} - List of chain IDs with 'None' for
|
|
|
111 no IDs
|
|
|
112 $ChainsDataRef->{Residues}{$ChainID} - List of residues in order
|
|
|
113 of their appearance in a chain
|
|
|
114 $ChainsDataRef->{ResidueCount}{$ChainID}{$ResidueName} - Count of
|
|
|
115 residues in a chain
|
|
|
116
|
|
|
117 Chains and residue data can be extacted using either ATOM/HETATM
|
|
|
118 records or SEQRES records. ATOM/HETATM records after the first
|
|
|
119 ENDMDL records are simply ingnored.
|
|
|
120
|
|
|
121 GetConectRecordLines
|
|
|
122 $ConectRecordLinesRef = GetConectRecordLines($PDBRecordLinesRef,
|
|
|
123 $AtomNumbersMapRef);
|
|
|
124
|
|
|
125 Collects CONECT record lines for specific atom number, modified
|
|
|
126 specified data to exclude any atom number not present in the list of
|
|
|
127 specified atom numbers and returns a reference to list of CONECT
|
|
|
128 record lines.
|
|
|
129
|
|
|
130 GetExperimentalTechnique
|
|
|
131 $ExperimentalTechnique = GetExperimentalTechnique($PDBRecordLinesRef);
|
|
|
132
|
|
|
133 Returns *ExperimentalTechnique* value retrieved from EXPDATA record
|
|
|
134 line.
|
|
|
135
|
|
|
136 GetExperimentalTechniqueResolution
|
|
|
137 ($Resolution, $ResolutionUnits) = GetExperimentalTechniqueResolution(
|
|
|
138 $PDBRecordLinesRef);
|
|
|
139
|
|
|
140 Returns *Resolution* and *ResolutionUnits* values from REMARK 2
|
|
|
141 RESOLUTION record line.
|
|
|
142
|
|
|
143 GetMinMaxCoords
|
|
|
144 ($XMin, $YMin, $ZMin, $XMax, $YMax, $ZMax) =
|
|
|
145 GetMinMaxCoords($PDBRecordLinesRef);
|
|
|
146
|
|
|
147 Returns minimum and maximum XYZ coordinates for ATOM/HETATM records.
|
|
|
148
|
|
|
149 GetPDBRecordType
|
|
|
150 $RecordType = GetPDBRecordType($RecordLine);
|
|
|
151
|
|
|
152 Returns type of *RecordLine*.
|
|
|
153
|
|
|
154 GetRecordTypesCount
|
|
|
155 $RecordTypeDataRef = GetRecordTypesCount($PDBRecordLinesRef,
|
|
|
156 [$SpecifiedRecordType, $GetRecordLinesFlag]);
|
|
|
157
|
|
|
158 Counts the number of each record type or a $SpecifiedRecordType and
|
|
|
159 returns a reference to data type with following key/value pairs:
|
|
|
160
|
|
|
161 $RecordTypeDataRef->{RecordTypes} - An array of unique record types
|
|
|
162 in order of their presence in the file
|
|
|
163 $RecordTypeDataRef->{Count}{$RecordType} - Count of each record type
|
|
|
164 $RecordTypeDataRef->{Lines}{$RecordType} - Optional lines data for a
|
|
|
165 specific record type.
|
|
|
166
|
|
|
167 IsAtomRecordType
|
|
|
168 $Status = IsAtomRecordType($RecordLine);
|
|
|
169
|
|
|
170 Returns 1 or 0 based on whether it's a ATOM record line.
|
|
|
171
|
|
|
172 IsConectRecordType
|
|
|
173 $Status = IsAtomConectType($RecordLine);
|
|
|
174
|
|
|
175 Returns 1 or 0 based on whether it's a CONECT record line.
|
|
|
176
|
|
|
177 IsEndmdlRecordType
|
|
|
178 $Status = IsEndmdlRecordType($RecordLine);
|
|
|
179
|
|
|
180 Returns 1 or 0 based on whether it's a ENDMDL a record line.
|
|
|
181
|
|
|
182 IsHeaderRecordType
|
|
|
183 $Status = IsHeaderRecordType($RecordLine);
|
|
|
184
|
|
|
185 Returns 1 or 0 based on whether it's a HEADER a record line.
|
|
|
186
|
|
|
187 IsHetatmRecordType
|
|
|
188 $Status = IsHetatmRecordType($RecordLine);
|
|
|
189
|
|
|
190 Returns 1 or 0 based on whether it's a HETATM a record line.
|
|
|
191
|
|
|
192 IsMasterRecordType
|
|
|
193 $Status = IsMasterRecordType($RecordLine);
|
|
|
194
|
|
|
195 Returns 1 or 0 based on whether it's a MASTER a record line.
|
|
|
196
|
|
|
197 IsModelRecordType
|
|
|
198 $Status = IsModelRecordType($RecordLine);
|
|
|
199
|
|
|
200 Returns 1 or 0 based on whether it's a MODEL record line.
|
|
|
201
|
|
|
202 IsPDBFile
|
|
|
203 $Status = IsPDBFile($PDBFile);
|
|
|
204
|
|
|
205 Returns 1 or 0 based on whether it's a PDB file.
|
|
|
206
|
|
|
207 IsSeqresRecordType
|
|
|
208 $Status = IsSeqresRecordType($RecordLine);
|
|
|
209
|
|
|
210 Returns 1 or 0 based on whether it's SEQRES a record line.
|
|
|
211
|
|
|
212 IsTerRecordType
|
|
|
213 $Status = IsTerRecordType($RecordLine);
|
|
|
214
|
|
|
215 Returns 1 or 0 based on whether it's a TER record line.
|
|
|
216
|
|
|
217 ParseAtomOrHetatmRecordLine
|
|
|
218 ($AtomNumber, $AtomName, $AlternateLocation, $ResidueName, $ChainID,
|
|
|
219 $ResidueNumber, $InsertionCode, $X, $Y, $Z, $Occupancy,
|
|
|
220 $TemperatureFactor, $SegmentID, $ElementSymbol, $AtomCharge) =
|
|
|
221 ParseAtomOrHetatmRecordLine($RecordLine);
|
|
|
222
|
|
|
223 Parses ATOM or HETATM record line.
|
|
|
224
|
|
|
225 ParseAtomRecordLine
|
|
|
226 ($AtomNumber, $AtomName, $AlternateLocation, $ResidueName, $ChainID,
|
|
|
227 $ResidueNumber, $InsertionCode, $X, $Y, $Z, $Occupancy,
|
|
|
228 $TemperatureFactor, $SegmentID, $ElementSymbol, $AtomCharge) =
|
|
|
229 ParseAtomRecordLine($RecordLine);
|
|
|
230
|
|
|
231 Parses ATOM record line.
|
|
|
232
|
|
|
233 ParseConectRecordLine
|
|
|
234 ($AtomNum, $BondedAtomNum1, $BondedAtomNum2, $BondedAtomNum3,
|
|
|
235 $BondedAtomNum4, $HBondedAtomNum1, $HBondedAtomNum2,
|
|
|
236 $SaltBridgedAtomNum1, $HBondedAtomNum3, $HBondedAtomNum4,
|
|
|
237 $SaltBridgedAtomNum2) = ParseConectRecordLine($RecordLine);
|
|
|
238
|
|
|
239 Parses CONECT record line.
|
|
|
240
|
|
|
241 ParseExpdtaRecordLine
|
|
|
242 ($ContinuationNum, $ExperimentalTechnique) = ParseExpdtaRecordLine($Line);
|
|
|
243
|
|
|
244 Parses EXPDTA record line.
|
|
|
245
|
|
|
246 ParseHeaderRecordLine
|
|
|
247 ($Classification, $DepositionDate, $IDCode) = ParseHeaderRecordLine($RecordLine);
|
|
|
248
|
|
|
249 Parses HEADER record line
|
|
|
250
|
|
|
251 ParseHetatmRecordLine
|
|
|
252 ($AtomNumber, $AtomName, $AlternateLocation, $ResidueName, $ChainID,
|
|
|
253 $ResidueNumber, $InsertionCode, $X, $Y, $Z, $Occupancy,
|
|
|
254 $TemperatureFactor, $SegmentID, $ElementSymbol, $AtomCharge) =
|
|
|
255 ParseHetatmRecordLine($RecordLine);
|
|
|
256
|
|
|
257 Parses HETATM record line.
|
|
|
258
|
|
|
259 ParseMasterRecordLine
|
|
|
260 ($NumOfRemarkRecords, $NumOfHetRecords, $NumOfHelixRecords,
|
|
|
261 $NumOfSheetRecords, $NumOfTurnRecords, $NumOfSiteRecords,
|
|
|
262 $NumOfTransformationsRecords, $NumOfAtomAndHetatmRecords,
|
|
|
263 $NumOfTerRecords, $NumOfConectRecords, $NumOfSeqresRecords) =
|
|
|
264 ParseMasterRecordLine($RecordLine);
|
|
|
265
|
|
|
266 Parses MASTER ecord line.
|
|
|
267
|
|
|
268 ParseRemark2ResolutionRecordLine
|
|
|
269 ($Resolution, $ResolutionUnits) = ParseRemark2ResolutionRecordLine(
|
|
|
270 $RecordLine);
|
|
|
271
|
|
|
272 Parses REMARK 2 RESOLUTION record line.
|
|
|
273
|
|
|
274 ParseSeqresRecordLine
|
|
|
275 ($RecordSerialNumber, $ChainID, $NumOfResidues, $ResidueNames) =
|
|
|
276 ParseSeqresRecordLine($RecordLine);
|
|
|
277
|
|
|
278 Parses SEQRES record line.
|
|
|
279
|
|
|
280 ParseTerRecordLine
|
|
|
281 ($SerialNumber, $ResidueName, $ChainID, $ResidueNumber, $InsertionCode) =
|
|
|
282 ParseTerRecordLine($RecordLine);
|
|
|
283
|
|
|
284 Parses TER record line.
|
|
|
285
|
|
|
286 ReadPDBFile
|
|
|
287 $PDBRecordLinesRef = ReadPDBFile($PDBFile);
|
|
|
288
|
|
|
289 Reads PDB file and returns reference to record lines.
|
|
|
290
|
|
|
291 AUTHOR
|
|
|
292 Manish Sud <msud@san.rr.com>
|
|
|
293
|
|
|
294 SEE ALSO
|
|
|
295 FileUtil.pm, SequenceFileUtil.pm, TextUtil.pm
|
|
|
296
|
|
|
297 COPYRIGHT
|
|
|
298 Copyright (C) 2015 Manish Sud. All rights reserved.
|
|
|
299
|
|
|
300 This file is part of MayaChemTools.
|
|
|
301
|
|
|
302 MayaChemTools is free software; you can redistribute it and/or modify it
|
|
|
303 under the terms of the GNU Lesser General Public License as published by
|
|
|
304 the Free Software Foundation; either version 3 of the License, or (at
|
|
|
305 your option) any later version.
|
|
|
306
|
