| 1 | /********************************************************************** | 
| 2 | residue.cpp - Handle macromolecule residues. | 
| 3 |  | 
| 4 | Copyright (C) 2001, 2002  OpenEye Scientific Software, Inc. | 
| 5 | Some portions Copyright (C) 2001-2005 by Geoffrey R. Hutchison | 
| 6 |  | 
| 7 | This file is part of the Open Babel project. | 
| 8 | For more information, see <http://openbabel.sourceforge.net/> | 
| 9 |  | 
| 10 | This program is free software; you can redistribute it and/or modify | 
| 11 | it under the terms of the GNU General Public License as published by | 
| 12 | the Free Software Foundation version 2 of the License. | 
| 13 |  | 
| 14 | This program is distributed in the hope that it will be useful, | 
| 15 | but WITHOUT ANY WARRANTY; without even the implied warranty of | 
| 16 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the | 
| 17 | GNU General Public License for more details. | 
| 18 | ***********************************************************************/ | 
| 19 |  | 
| 20 | /********************************************************************** | 
| 21 | Global arrays Residue, ElemDesc and function GetResidueNumber were | 
| 22 | obtained in part or whole from RasMol2 by Roger Sayle. | 
| 23 | ***********************************************************************/ | 
| 24 |  | 
| 25 | /////////////////////////////////////////////////////////////////////////////// | 
| 26 | // File Includes | 
| 27 | /////////////////////////////////////////////////////////////////////////////// | 
| 28 |  | 
| 29 | #include "config.h" | 
| 30 |  | 
| 31 | #if HAVE_IOSTREAM | 
| 32 | #include <iostream> | 
| 33 | #elif HAVE_IOSTREAM_H | 
| 34 | #include <iostream.h> | 
| 35 | #endif | 
| 36 |  | 
| 37 | #if HAVE_FSTREAM | 
| 38 | #include <fstream> | 
| 39 | #elif HAVE_FSTREAM_H | 
| 40 | #include <fstream.h> | 
| 41 | #endif | 
| 42 |  | 
| 43 | #include "mol.hpp" | 
| 44 | #include "bitvec.hpp" | 
| 45 |  | 
| 46 | using namespace std; | 
| 47 |  | 
| 48 | namespace OpenBabel | 
| 49 | { | 
| 50 | /** \class OBResidue | 
| 51 | \brief Residue information | 
| 52 |  | 
| 53 | The residue information is drawn from PDB or MOL2 files (or similar), which | 
| 54 | track biomolecule information, | 
| 55 | and are stored in the OBResidue class. OBResidues are stored inside the | 
| 56 | OBAtom class and OBMol classes. | 
| 57 | The residue information for an atom can be requested in | 
| 58 | the following way: | 
| 59 | \code | 
| 60 | OBAtom *atom; | 
| 61 | OBResidue *r; | 
| 62 | atom = mol.GetAtom(1); | 
| 63 | r = atom->GetResidue(); | 
| 64 | \endcode | 
| 65 | The residue information for a molecule can be manipulated too: | 
| 66 | \code | 
| 67 | cout << "This molecule has " << mol.NumResidues() << " residues." << endl; | 
| 68 | OBResidue *r; | 
| 69 | r = mol.GetResidue(1); | 
| 70 | \endcode | 
| 71 | */ | 
| 72 |  | 
| 73 | /////////////////////////////////////////////////////////////////////////////// | 
| 74 | // Global Definitions | 
| 75 | /////////////////////////////////////////////////////////////////////////////// | 
| 76 |  | 
| 77 | #define MAXSETNO 40 | 
| 78 | #define MAXELEM  1024 | 
| 79 | #define MINELEM  29 | 
| 80 | #define MAXRES   100 | 
| 81 | #define MINRES   54 | 
| 82 |  | 
| 83 | /////////////////////////////////////////////////////////////////////////////// | 
| 84 | // Amino Acid Definitions | 
| 85 | /////////////////////////////////////////////////////////////////////////////// | 
| 86 |  | 
| 87 | #define AA_ALA (1<<1) | 
| 88 | #define AA_GLY (1<<2) | 
| 89 | #define AA_LEU (1<<3) | 
| 90 | #define AA_SER (1<<4) | 
| 91 | #define AA_VAL (1<<5) | 
| 92 | #define AA_THR (1<<6) | 
| 93 | #define AA_LYS (1<<7) | 
| 94 | #define AA_ASP (1<<8) | 
| 95 | #define AA_ILE (1<<9) | 
| 96 | #define AA_ASN (1<<10) | 
| 97 | #define AA_GLU (1<<11) | 
| 98 | #define AA_PRO (1<<12) | 
| 99 | #define AA_ARG (1<<13) | 
| 100 | #define AA_PHE (1<<14) | 
| 101 | #define AA_GLN (1<<15) | 
| 102 | #define AA_TYR (1<<16) | 
| 103 | #define AA_HIS (1<<17) | 
| 104 | #define AA_CYS (1<<18) | 
| 105 | #define AA_MET (1<<19) | 
| 106 | #define AA_TRP (1<<20) | 
| 107 |  | 
| 108 | //! Residue property definitions | 
| 109 | namespace OBAminoAcidProperty | 
| 110 | { | 
| 111 | static const unsigned int ACIDIC      =  0; | 
| 112 | static const unsigned int ACYCLIC     =  1; | 
| 113 | static const unsigned int ALIPHATIC   =  2; | 
| 114 | static const unsigned int AROMATIC    =  3; | 
| 115 | static const unsigned int BASIC       =  4; | 
| 116 | static const unsigned int BURIED      =  5; | 
| 117 | static const unsigned int CHARGED     =  6; | 
| 118 | static const unsigned int CYCLIC      =  7; | 
| 119 | static const unsigned int HYDROPHOBIC =  8; | 
| 120 | static const unsigned int LARGE       =  9; | 
| 121 | static const unsigned int MEDIUM      = 10; | 
| 122 | static const unsigned int NEGATIVE    = 11; | 
| 123 | static const unsigned int NEUTRAL     = 12; | 
| 124 | static const unsigned int POLAR       = 13; | 
| 125 | static const unsigned int POSITIVE    = 14; | 
| 126 | static const unsigned int SMALL       = 15; | 
| 127 | static const unsigned int SURFACE     = 16; | 
| 128 | } | 
| 129 |  | 
| 130 | //! Residue atom properties | 
| 131 | namespace OBResidueAtomProperty | 
| 132 | { | 
| 133 | static const unsigned int ALPHA_CARBON     = 0; | 
| 134 | static const unsigned int AMINO_BACKBONE   = 1; | 
| 135 | static const unsigned int BACKBONE         = 2; | 
| 136 | static const unsigned int CYSTEINE_SULPHUR = 3; | 
| 137 | static const unsigned int LIGAND           = 4; | 
| 138 | static const unsigned int NUCLEIC_BACKBONE = 5; | 
| 139 | static const unsigned int SHAPELY_BACKBONE = 6; | 
| 140 | static const unsigned int SHAPELY_SPECIAL  = 7; | 
| 141 | static const unsigned int SIDECHAIN        = 8; | 
| 142 | static const unsigned int SUGAR_PHOSPHATE  = 9; | 
| 143 | } | 
| 144 | /// Residue names | 
| 145 | namespace OBResidueIndex | 
| 146 | { | 
| 147 | static const unsigned int ALA   =  0; | 
| 148 | static const unsigned int GLY   =  1; | 
| 149 | static const unsigned int LEU   =  2; | 
| 150 | static const unsigned int SER   =  3; | 
| 151 | static const unsigned int VAL   =  4; | 
| 152 | static const unsigned int THR   =  5; | 
| 153 | static const unsigned int LYS   =  6; | 
| 154 | static const unsigned int ASP   =  7; | 
| 155 | static const unsigned int ILE   =  8; | 
| 156 | static const unsigned int ASN   =  9; | 
| 157 | static const unsigned int GLU   = 10; | 
| 158 | static const unsigned int PRO   = 11; | 
| 159 | static const unsigned int ARG   = 12; | 
| 160 | static const unsigned int PHE   = 13; | 
| 161 | static const unsigned int GLN   = 14; | 
| 162 | static const unsigned int TYR   = 15; | 
| 163 | static const unsigned int HIS   = 16; | 
| 164 | static const unsigned int CYS   = 17; | 
| 165 | static const unsigned int MET   = 18; | 
| 166 | static const unsigned int TRP   = 19; | 
| 167 | static const unsigned int ASX   = 20; | 
| 168 | static const unsigned int GLX   = 21; | 
| 169 | static const unsigned int PCA   = 22; | 
| 170 | static const unsigned int HYP   = 23; | 
| 171 | static const unsigned int A     = 24; | 
| 172 | static const unsigned int C     = 25; | 
| 173 | static const unsigned int G     = 26; | 
| 174 | static const unsigned int T     = 27; | 
| 175 | static const unsigned int U     = 28; | 
| 176 | static const unsigned int UPLUS = 29; | 
| 177 | static const unsigned int I     = 30; | 
| 178 | //static const unsigned int _1MA  = 31; | 
| 179 | //static const unsigned int _5MC  = 32; | 
| 180 | static const unsigned int OMC   = 33; | 
| 181 | //static const unsigned int _1MG  = 34; | 
| 182 | //static const unsigned int _2MG  = 35; | 
| 183 | static const unsigned int M2G   = 36; | 
| 184 | //static const unsigned int _7MG  = 37; | 
| 185 | static const unsigned int OMG   = 38; | 
| 186 | static const unsigned int YG    = 39; | 
| 187 | static const unsigned int H2U   = 40; | 
| 188 | //static const unsigned int _5MU  = 41; | 
| 189 | static const unsigned int PSU   = 42; | 
| 190 | static const unsigned int UNK   = 43; | 
| 191 | static const unsigned int ACE   = 44; | 
| 192 | static const unsigned int FOR   = 45; | 
| 193 | static const unsigned int HOH   = 46; | 
| 194 | static const unsigned int DOD   = 47; | 
| 195 | static const unsigned int SO4   = 48; | 
| 196 | static const unsigned int PO4   = 49; | 
| 197 | static const unsigned int NAD   = 50; | 
| 198 | static const unsigned int COA   = 51; | 
| 199 | static const unsigned int NAP   = 52; | 
| 200 | static const unsigned int NDP   = 53; | 
| 201 | } | 
| 202 | /// Residue types. | 
| 203 | namespace OBResidueProperty | 
| 204 | { | 
| 205 | static const unsigned int AMINO        = 0; | 
| 206 | static const unsigned int AMINO_NUCLEO = 1; | 
| 207 | static const unsigned int COENZYME     = 2; | 
| 208 | static const unsigned int ION          = 3; | 
| 209 | static const unsigned int NUCLEO       = 4; | 
| 210 | static const unsigned int PROTEIN      = 5; | 
| 211 | static const unsigned int PURINE       = 6; | 
| 212 | static const unsigned int PYRIMIDINE   = 7; | 
| 213 | static const unsigned int SOLVENT      = 8; | 
| 214 | static const unsigned int WATER        = 9; | 
| 215 | } | 
| 216 |  | 
| 217 | /////////////////////////////////////////////////////////////////////////////// | 
| 218 | // Amino Acid Property Definitions | 
| 219 | /////////////////////////////////////////////////////////////////////////////// | 
| 220 |  | 
| 221 | #define IS_ACIDIC(x)      ((x) & ((AA_ASP)|(AA_GLU))) | 
| 222 | #define IS_ACYCLIC(x)     ((x) & ((AA_ALA)|(AA_GLY)|(AA_LEU)|(AA_SER)| \ | 
| 223 | (AA_VAL)|(AA_THR)|(AA_LYS)|(AA_ASP)| \ | 
| 224 | (AA_ILE)|(AA_ASN)|(AA_GLU)|(AA_GLN)| \ | 
| 225 | (AA_CYS)|(AA_MET))) | 
| 226 | #define IS_ALIPHATIC(x)   ((x) & ((AA_ALA)|(AA_GLY)|(AA_ILE)|(AA_LEU)| \ | 
| 227 | (AA_VAL))) | 
| 228 | #define IS_AROMATIC(x)    ((x) & ((AA_HIS)|(AA_PHE)|(AA_TRP)|(AA_TYR))) | 
| 229 | #define IS_BASIC(x)       ((x) & ((AA_ARG)|(AA_HIS)|(AA_LYS))) | 
| 230 | #define IS_BURIED(x)      ((x) & ((AA_ALA)|(AA_CYS)|(AA_ILE)|(AA_LEU)| \ | 
| 231 | (AA_MET)|(AA_PHE)|(AA_TRP)|(AA_VAL))) | 
| 232 | #define IS_CHARGED(x)     ((x) & ((AA_ASP)|(AA_GLU)|(AA_ARG)|(AA_HIS)| \ | 
| 233 | (AA_LYS))) | 
| 234 | #define IS_CYCLIC(x)      ((x) & ((AA_HIS)|(AA_PHE)|(AA_PRO)|(AA_TRP)| \ | 
| 235 | (AA_TYR))) | 
| 236 | #define IS_HYDROPHOBIC(x) ((x) & ((AA_ALA)|(AA_LEU)|(AA_VAL)|(AA_ILE)| \ | 
| 237 | (AA_PRO)|(AA_PHE)|(AA_MET)|(AA_TRP))) | 
| 238 | #define IS_LARGE(x)       ((x) & ((AA_ARG)|(AA_PHE)|(AA_GLN)|(AA_TYR)| \ | 
| 239 | (AA_HIS)|(AA_LEU)|(AA_LYS)|(AA_ILE)| \ | 
| 240 | (AA_GLU)|(AA_MET)|(AA_TRP))) | 
| 241 | #define IS_MEDIUM(x)      ((x) & ((AA_VAL)|(AA_THR)|(AA_ASP)|(AA_ASN)| \ | 
| 242 | (AA_PRO)|(AA_CYS))) | 
| 243 | #define IS_NEGATIVE(x)    ((x) & ((AA_ASP)|(AA_GLU))) | 
| 244 | #define IS_NEUTRAL(x)     ((x) & ((AA_ALA)|(AA_GLY)|(AA_LEU)|(AA_SER)| \ | 
| 245 | (AA_VAL)|(AA_THR)|(AA_PHE)|(AA_GLN)| \ | 
| 246 | (AA_TYR)|(AA_HIS)|(AA_CYS)|(AA_MET)| \ | 
| 247 | (AA_TRP)|(AA_ILE)|(AA_ASN)|(AA_PRO))) | 
| 248 | #define IS_POLAR(x)       ((x) & ((AA_ASP)|(AA_ILE)|(AA_ASN)|(AA_GLU)| \ | 
| 249 | (AA_SER)|(AA_THR)|(AA_ARG)|(AA_GLN)| \ | 
| 250 | (AA_CYS)|(AA_HIS))) | 
| 251 | #define IS_POSITIVE(x)    ((x) & ((AA_ARG)|(AA_HIS)|(AA_LYS))) | 
| 252 | #define IS_SMALL(x)       ((x) & ((AA_ALA)|(AA_GLY)|(AA_SER))) | 
| 253 | #define IS_SURFACE(x)     ((x) & ((AA_THR)|(AA_LYS)|(AA_ASP)|(AA_ILE)| \ | 
| 254 | (AA_ASN)|(AA_GLU)|(AA_PRO)|(AA_ARG)| \ | 
| 255 | (AA_GLY)|(AA_SER)|(AA_GLN)|(AA_TYR)| \ | 
| 256 | (AA_HIS))) | 
| 257 |  | 
| 258 | //////////////////////////////////////////////////////////////////////////////// | 
| 259 | // Global Variables | 
| 260 | //////////////////////////////////////////////////////////////////////////////// | 
| 261 |  | 
| 262 | static char Residue[MAXRES][4] = { | 
| 263 | /*===============*/ | 
| 264 | /*  Amino Acids  */ | 
| 265 | /*===============*/ | 
| 266 |  | 
| 267 | /* Ordered by Cumulative Frequency in Brookhaven * | 
| 268 | * Protein Databank, December 1991               */ | 
| 269 |  | 
| 270 | "ALA", /* 8.4% */     "GLY", /* 8.3% */ | 
| 271 | "LEU", /* 8.0% */     "SER", /* 7.5% */ | 
| 272 | "VAL", /* 7.1% */     "THR", /* 6.4% */ | 
| 273 | "LYS", /* 5.8% */     "ASP", /* 5.5% */ | 
| 274 | "ILE", /* 5.2% */     "ASN", /* 4.9% */ | 
| 275 | "GLU", /* 4.9% */     "PRO", /* 4.4% */ | 
| 276 | "ARG", /* 3.8% */     "PHE", /* 3.7% */ | 
| 277 | "GLN", /* 3.5% */     "TYR", /* 3.5% */ | 
| 278 | "HIS", /* 2.3% */     "CYS", /* 2.0% */ | 
| 279 | "MET", /* 1.8% */     "TRP", /* 1.4% */ | 
| 280 |  | 
| 281 | "ASX", "GLX", "PCA", "HYP", | 
| 282 |  | 
| 283 | /*===================*/ | 
| 284 | /*  DNA Nucleotides  */ | 
| 285 | /*===================*/ | 
| 286 | "  A", "  C", "  G", "  T", | 
| 287 |  | 
| 288 | /*===================*/ | 
| 289 | /*  RNA Nucleotides  */ | 
| 290 | /*===================*/ | 
| 291 | "  U", " +U", "  I", "1MA", | 
| 292 | "5MC", "OMC", "1MG", "2MG", | 
| 293 | "M2G", "7MG", "OMG", " YG", | 
| 294 | "H2U", "5MU", "PSU", | 
| 295 |  | 
| 296 | /*=================*/ | 
| 297 | /*  Miscellaneous  */ | 
| 298 | /*=================*/ | 
| 299 | "UNK", "ACE", "FOR", "HOH", | 
| 300 | "DOD", "SO4", "PO4", "NAD", | 
| 301 | "COA", "NAP", "NDP" | 
| 302 | }; | 
| 303 |  | 
| 304 | /* Avoid SGI Compiler Warnings! */ | 
| 305 | static char ElemDesc[MAXELEM][4] = { | 
| 306 | { ' ', 'N', ' ', ' ' },  /* 0*/ | 
| 307 | { ' ', 'C', 'A', ' ' },  /* 1*/ | 
| 308 | { ' ', 'C', ' ', ' ' },  /* 2*/ | 
| 309 | { ' ', 'O', ' ', ' ' },  /* 3*/   /* 0-3   Amino Acid Backbone    */ | 
| 310 | { ' ', 'C', '\'', ' ' }, /* 4*/ | 
| 311 | { ' ', 'O', 'T', ' ' },  /* 5*/ | 
| 312 | { ' ', 'S', ' ', ' ' },  /* 6*/ | 
| 313 | { ' ', 'P', ' ', ' ' },  /* 7*/   /* 4-7   Shapely Amino Backbone */ | 
| 314 | { ' ', 'O', '1', 'P' },  /* 8*/ | 
| 315 | { ' ', 'O', '2', 'P' },  /* 9*/ | 
| 316 | { ' ', 'O', '5', '*' },  /*10*/ | 
| 317 | { ' ', 'C', '5', '*' },  /*11*/ | 
| 318 | { ' ', 'C', '4', '*' },  /*12*/ | 
| 319 | { ' ', 'O', '4', '*' },  /*13*/ | 
| 320 | { ' ', 'C', '3', '*' },  /*14*/ | 
| 321 | { ' ', 'O', '3', '*' },  /*15*/ | 
| 322 | { ' ', 'C', '2', '*' },  /*16*/ | 
| 323 | { ' ', 'O', '2', '*' },  /*17*/ | 
| 324 | { ' ', 'C', '1', '*' },  /*18*/   /* 7-18  Nucleic Acid Backbone  */ | 
| 325 | { ' ', 'C', 'A', '2' },  /*19*/   /* 19    Shapely Special        */ | 
| 326 | { ' ', 'S', 'G', ' ' },  /*20*/   /* 20    Cysteine Sulphur       */ | 
| 327 | { ' ', 'N', '1', ' ' },  /*21*/ | 
| 328 | { ' ', 'N', '2', ' ' },  /*22*/ | 
| 329 | { ' ', 'N', '3', ' ' },  /*23*/ | 
| 330 | { ' ', 'N', '4', ' ' },  /*24*/ | 
| 331 | { ' ', 'N', '6', ' ' },  /*25*/ | 
| 332 | { ' ', 'O', '2', ' ' },  /*26*/ | 
| 333 | { ' ', 'O', '4', ' ' },  /*27*/ | 
| 334 | { ' ', 'O', '6', ' ' }   /*28*/   /* 21-28 Nucleic Acid H-Bonding */ | 
| 335 | }; | 
| 336 |  | 
| 337 | static unsigned int ResNo  = MINRES; | 
| 338 | static unsigned int ElemNo = MINELEM; | 
| 339 |  | 
| 340 | /////////////////////////////////////////////////////////////////////////////// | 
| 341 | // Residue Functions | 
| 342 | /////////////////////////////////////////////////////////////////////////////// | 
| 343 |  | 
| 344 | static unsigned int GetAtomIDNumber(const char *atomid) | 
| 345 | { | 
| 346 | if (atomid != NULL) | 
| 347 | { | 
| 348 | int ch1 = toupper(atomid[0]); | 
| 349 | int ch2 = toupper(atomid[1]); | 
| 350 | int ch3 = toupper(atomid[2]); | 
| 351 | int ch4 = toupper(atomid[3]); | 
| 352 |  | 
| 353 | if (ch1 == ' ') | 
| 354 | { | 
| 355 | switch(ch2) | 
| 356 | { | 
| 357 | case 'C': | 
| 358 |  | 
| 359 | switch(ch3) | 
| 360 | { | 
| 361 | case 'A': | 
| 362 |  | 
| 363 | if (ch4 == ' ') | 
| 364 | return 1; | 
| 365 | else if (ch4 == '2') | 
| 366 | return 19; | 
| 367 |  | 
| 368 | break; | 
| 369 |  | 
| 370 | case ' ': | 
| 371 | if (ch4 == ' ') | 
| 372 | return 2; | 
| 373 | break; | 
| 374 |  | 
| 375 | case '\'': | 
| 376 | if (ch4 == ' ') | 
| 377 | return 4; | 
| 378 | break; | 
| 379 |  | 
| 380 | case '1': | 
| 381 | if (ch4 == '*') | 
| 382 | return 18; | 
| 383 | break; | 
| 384 |  | 
| 385 | case '2': | 
| 386 | if (ch4 == '*') | 
| 387 | return 16; | 
| 388 | break; | 
| 389 |  | 
| 390 | case '3': | 
| 391 | if (ch4 == '*') | 
| 392 | return 14; | 
| 393 | break; | 
| 394 |  | 
| 395 | case '4': | 
| 396 | if (ch4 == '*') | 
| 397 | return 12; | 
| 398 | break; | 
| 399 |  | 
| 400 | case '5': | 
| 401 | if (ch4 == '*') | 
| 402 | return 11; | 
| 403 | break; | 
| 404 |  | 
| 405 | } | 
| 406 |  | 
| 407 | break; | 
| 408 |  | 
| 409 | case 'N': | 
| 410 |  | 
| 411 | if (ch4 == ' ') | 
| 412 | { | 
| 413 | switch (ch3) | 
| 414 | { | 
| 415 | case ' ': | 
| 416 | return 0; | 
| 417 | case '1': | 
| 418 | return 21; | 
| 419 | case '2': | 
| 420 | return 22; | 
| 421 | case '3': | 
| 422 | return 23; | 
| 423 | case '4': | 
| 424 | return 24; | 
| 425 | case '6': | 
| 426 | return 25; | 
| 427 | } | 
| 428 | } | 
| 429 |  | 
| 430 | break; | 
| 431 |  | 
| 432 | case 'O': | 
| 433 |  | 
| 434 | switch(ch3) | 
| 435 | { | 
| 436 | case ' ': | 
| 437 |  | 
| 438 | if (ch4 == ' ') | 
| 439 | return 3; | 
| 440 |  | 
| 441 | break; | 
| 442 |  | 
| 443 | case 'T': | 
| 444 |  | 
| 445 | if (ch4 == ' ') | 
| 446 | return 5; | 
| 447 |  | 
| 448 | break; | 
| 449 |  | 
| 450 | case '1': | 
| 451 |  | 
| 452 | if (ch4 == 'P') | 
| 453 | return 8; | 
| 454 |  | 
| 455 | break; | 
| 456 |  | 
| 457 | case '2': | 
| 458 |  | 
| 459 | if (ch4 == 'P') | 
| 460 | return 9; | 
| 461 | else if (ch4 == '*') | 
| 462 | return 17; | 
| 463 | else if (ch4 == ' ') | 
| 464 | return 26; | 
| 465 |  | 
| 466 | break; | 
| 467 |  | 
| 468 | case '3': | 
| 469 |  | 
| 470 | if (ch4 == '*') | 
| 471 | return 15; | 
| 472 |  | 
| 473 | break; | 
| 474 |  | 
| 475 | case '4': | 
| 476 |  | 
| 477 | if (ch4 == '*') | 
| 478 | return 13; | 
| 479 | else if (ch4 == ' ') | 
| 480 | return 27; | 
| 481 |  | 
| 482 | break; | 
| 483 |  | 
| 484 | case '5': | 
| 485 |  | 
| 486 | if (ch4 == '*') | 
| 487 | return 10; | 
| 488 |  | 
| 489 | break; | 
| 490 |  | 
| 491 | case '6': | 
| 492 |  | 
| 493 | if (ch4 == ' ') | 
| 494 | return 28; | 
| 495 |  | 
| 496 | break; | 
| 497 | } | 
| 498 |  | 
| 499 | break; | 
| 500 |  | 
| 501 | case 'P': | 
| 502 |  | 
| 503 | if ((ch3 == ' ') && (ch4 == ' ')) | 
| 504 | return 7; | 
| 505 |  | 
| 506 | break; | 
| 507 |  | 
| 508 | case 'S': | 
| 509 |  | 
| 510 | if (ch4 == ' ') | 
| 511 | { | 
| 512 | if (ch3 == ' ') | 
| 513 | return 6; | 
| 514 | else if (ch3 == 'G') | 
| 515 | return 20; | 
| 516 | } | 
| 517 |  | 
| 518 | break; | 
| 519 | } | 
| 520 | } | 
| 521 |  | 
| 522 | unsigned int refno; | 
| 523 | for( refno = MINELEM ; refno < ElemNo ; refno++ ) | 
| 524 | if( !strncmp(ElemDesc[refno], atomid, 4) ) | 
| 525 | return refno; | 
| 526 |  | 
| 527 | if ( ElemNo < MAXELEM - 1 ) | 
| 528 | { | 
| 529 | ElemNo++; | 
| 530 | ElemDesc[refno][0] = (char) ch1; | 
| 531 | ElemDesc[refno][1] = (char) ch2; | 
| 532 | ElemDesc[refno][2] = (char) ch3; | 
| 533 | ElemDesc[refno][3] = (char) ch4; | 
| 534 | return refno; | 
| 535 | } | 
| 536 | else | 
| 537 | { | 
| 538 | obErrorLog.ThrowError(__FUNCTION__, "Maximum number of atom ids exceeded", obWarning); | 
| 539 | return 0; | 
| 540 | } | 
| 541 | } | 
| 542 | else | 
| 543 | { | 
| 544 | obErrorLog.ThrowError(__FUNCTION__, "NULL Atom IDs specified", obWarning); | 
| 545 | return 0; | 
| 546 | } | 
| 547 | } | 
| 548 |  | 
| 549 | static unsigned int GetResidueNumber(const char *res) | 
| 550 | { | 
| 551 | if (res != NULL) | 
| 552 | { | 
| 553 | int ch1 = toupper(res[0]); | 
| 554 | int ch2 = toupper(res[1]); | 
| 555 | int ch3 = toupper(res[2]); | 
| 556 |  | 
| 557 | switch( ch1 ) | 
| 558 | { | 
| 559 | case(' '): | 
| 560 |  | 
| 561 | if( ch2 == ' ' ) | 
| 562 | { | 
| 563 | switch( ch3 ) | 
| 564 | { | 
| 565 | case('A'):  return( 24 ); | 
| 566 | case('C'):  return( 25 ); | 
| 567 | case('G'):  return( 26 ); | 
| 568 | case('T'):  return( 27 ); | 
| 569 | case('U'):  return( 28 ); | 
| 570 | case('I'):  return( 30 ); | 
| 571 | } | 
| 572 | } | 
| 573 | else if( ch2 == '+' ) | 
| 574 | { | 
| 575 | if( ch3 == 'U' ) | 
| 576 | return( 29 ); | 
| 577 | } | 
| 578 | else if( ch2 == 'Y' ) | 
| 579 | { | 
| 580 | if( ch3 == 'G' ) | 
| 581 | return( 39 ); | 
| 582 | } | 
| 583 |  | 
| 584 | break; | 
| 585 |  | 
| 586 | case('0'): | 
| 587 |  | 
| 588 | if( ch2 == 'M' ) | 
| 589 | { | 
| 590 | if( ch3 == 'C' ) | 
| 591 | return( 33 ); | 
| 592 | else if( ch3 == 'G' ) | 
| 593 | return( 38 ); | 
| 594 | } | 
| 595 |  | 
| 596 | break; | 
| 597 |  | 
| 598 | case('1'): | 
| 599 |  | 
| 600 | if( ch2 == 'M' ) | 
| 601 | { | 
| 602 | if( ch3 == 'A' ) | 
| 603 | return( 31 ); | 
| 604 | else if( ch3 == 'G' ) | 
| 605 | return( 34 ); | 
| 606 | } | 
| 607 |  | 
| 608 | break; | 
| 609 |  | 
| 610 | case('2'): | 
| 611 |  | 
| 612 | if( ch2 == 'M' ) | 
| 613 | if( ch3 == 'G' ) | 
| 614 | return( 35 ); | 
| 615 |  | 
| 616 | break; | 
| 617 |  | 
| 618 | case('5'): | 
| 619 |  | 
| 620 | if( ch2 == 'M' ) | 
| 621 | { | 
| 622 | if( ch3 == 'C' ) | 
| 623 | return( 32 ); | 
| 624 | else if( ch3 == 'U' ) | 
| 625 | return( 41 ); | 
| 626 | } | 
| 627 |  | 
| 628 | break; | 
| 629 |  | 
| 630 | case('7'): | 
| 631 |  | 
| 632 | if( ch2 == 'M' ) | 
| 633 | if( ch3 == 'G' ) | 
| 634 | return( 37 ); | 
| 635 |  | 
| 636 | break; | 
| 637 |  | 
| 638 | case('A'): | 
| 639 |  | 
| 640 | if( ch2 == 'L' ) | 
| 641 | { | 
| 642 | if( ch3 == 'A' ) | 
| 643 | return(  0 ); | 
| 644 | } | 
| 645 | else if( ch2 == 'S' ) | 
| 646 | { | 
| 647 | if( ch3 == 'P' ) | 
| 648 | return(  7 ); | 
| 649 | else if( ch3 == 'N' ) | 
| 650 | return(  9 ); | 
| 651 | else if( ch3 == 'X' ) | 
| 652 | return( 20 ); | 
| 653 | } | 
| 654 | else if( ch2 == 'R' ) | 
| 655 | { | 
| 656 | if( ch3 == 'G' ) | 
| 657 | return( 12 ); | 
| 658 | } | 
| 659 | else if( ch2 == 'C' ) | 
| 660 | { | 
| 661 | if( ch3 == 'E' ) | 
| 662 | return( 44 ); | 
| 663 | } | 
| 664 | else if( ch2 == 'D' ) | 
| 665 | { | 
| 666 | if( ch3 == 'E' ) | 
| 667 | return( 24 );    /* "ADE" -> "  A" */ | 
| 668 | } | 
| 669 |  | 
| 670 | break; | 
| 671 |  | 
| 672 | case('C'): | 
| 673 |  | 
| 674 | if( ch2 == 'Y' ) | 
| 675 | { | 
| 676 | if( ch3 == 'S' ) | 
| 677 | return( 17 ); | 
| 678 | else if( ch3 == 'H' ) | 
| 679 | return( 17 );    /* "CYH" -> "CYS" */ | 
| 680 | else if( ch3 == 'T' ) | 
| 681 | return( 25 );    /* "CYT" -> "  C" */ | 
| 682 | } | 
| 683 | else if( ch2 == 'O' ) | 
| 684 | { | 
| 685 | if( ch3 == 'A' ) | 
| 686 | return( 51 ); | 
| 687 | } | 
| 688 | else if( ch2 == 'P' ) | 
| 689 | { | 
| 690 | if( ch3 == 'R' ) | 
| 691 | return( 11 );    /* "CPR" -> "PRO" */ | 
| 692 | } | 
| 693 | else if( ch2 == 'S' ) | 
| 694 | { | 
| 695 | if( ch3 == 'H' ) | 
| 696 | return( 17 );    /* "CSH" -> "CYS" */ | 
| 697 | else if( ch3 == 'M' ) | 
| 698 | return( 17 );    /* "CSM" -> "CYS" */ | 
| 699 | } | 
| 700 |  | 
| 701 | break; | 
| 702 |  | 
| 703 | case('D'): | 
| 704 |  | 
| 705 | if( ch2 == 'O' ) | 
| 706 | { | 
| 707 | if( ch3 == 'D' ) | 
| 708 | return( 47 ); | 
| 709 | } | 
| 710 | else if( ch2 == '2' ) | 
| 711 | { | 
| 712 | if( ch3 == 'O' ) | 
| 713 | return( 47 );    /* "D2O" -> "DOD" */ | 
| 714 | } | 
| 715 |  | 
| 716 | break; | 
| 717 |  | 
| 718 | case('F'): | 
| 719 |  | 
| 720 | if( ch2 == 'O' ) | 
| 721 | if( ch3 == 'R' ) | 
| 722 | return( 45 ); | 
| 723 |  | 
| 724 | break; | 
| 725 |  | 
| 726 | case('G'): | 
| 727 |  | 
| 728 | if( ch2 == 'L' ) | 
| 729 | { | 
| 730 | if( ch3 == 'Y' ) | 
| 731 | return(  1 ); | 
| 732 | else if( ch3 == 'U' ) | 
| 733 | return( 10 ); | 
| 734 | else if( ch3 == 'N' ) | 
| 735 | return( 14 ); | 
| 736 | else if( ch3 == 'X' ) | 
| 737 | return( 21 ); | 
| 738 | } | 
| 739 | else if( ch2 == 'U' ) | 
| 740 | { | 
| 741 | if( ch3 == 'A' ) | 
| 742 | return( 26 );    /* "GUA" -> "  G" */ | 
| 743 | } | 
| 744 |  | 
| 745 | break; | 
| 746 |  | 
| 747 | case('H'): | 
| 748 |  | 
| 749 | if( ch2 == 'I' ) | 
| 750 | { | 
| 751 | if( ch3 == 'S' ) | 
| 752 | return( 16 ); | 
| 753 | } | 
| 754 | else if( ch2 == 'O' ) | 
| 755 | { | 
| 756 | if( ch3 == 'H' ) | 
| 757 | return( 46 ); | 
| 758 | } | 
| 759 | else if( ch2 == 'Y' ) | 
| 760 | { | 
| 761 | if( ch3 == 'P' ) | 
| 762 | return( 23 ); | 
| 763 | } | 
| 764 | else if( ch2 == '2' ) | 
| 765 | { | 
| 766 | if( ch3 == 'O' ) | 
| 767 | return( 46 );    /* "H20" -> "HOH" */ | 
| 768 | else if( ch3 == 'U' ) | 
| 769 | return( 40 ); | 
| 770 | } | 
| 771 |  | 
| 772 | break; | 
| 773 |  | 
| 774 | case('I'): | 
| 775 |  | 
| 776 | if( ch2 == 'L' ) | 
| 777 | if( ch3 == 'E' ) | 
| 778 | return(  8 ); | 
| 779 |  | 
| 780 | break; | 
| 781 |  | 
| 782 | case('L'): | 
| 783 |  | 
| 784 | if( ch2 == 'E' ) | 
| 785 | { | 
| 786 | if( ch3 == 'U' ) | 
| 787 | return(  2 ); | 
| 788 | } | 
| 789 | else if( ch2 == 'Y' ) | 
| 790 | { | 
| 791 | if( ch3 == 'S' ) | 
| 792 | return(  6 ); | 
| 793 | } | 
| 794 |  | 
| 795 | break; | 
| 796 |  | 
| 797 | case('M'): | 
| 798 |  | 
| 799 | if( ch2 == 'E' ) | 
| 800 | { | 
| 801 | if( ch3 == 'T' ) | 
| 802 | return( 18 ); | 
| 803 | } | 
| 804 | else if( ch2 == '2' ) | 
| 805 | { | 
| 806 | if( ch3 == 'G' ) | 
| 807 | return( 36 ); | 
| 808 | } | 
| 809 |  | 
| 810 | break; | 
| 811 |  | 
| 812 | case('N'): | 
| 813 |  | 
| 814 | if( ch2 == 'A' ) | 
| 815 | { | 
| 816 | if( ch3 == 'D' ) | 
| 817 | return( 50 ); | 
| 818 | else if( ch3 == 'P' ) | 
| 819 | return( 52 ); | 
| 820 | } | 
| 821 | else if( ch2 == 'D' ) | 
| 822 | { | 
| 823 | if( ch3 == 'P' ) | 
| 824 | return( 53 ); | 
| 825 | } | 
| 826 |  | 
| 827 | break; | 
| 828 |  | 
| 829 | case('P'): | 
| 830 |  | 
| 831 | if( ch2 == 'R' ) | 
| 832 | { | 
| 833 | if( ch3 == 'O' ) | 
| 834 | return( 11 ); | 
| 835 | } | 
| 836 | else if( ch2 == 'H' ) | 
| 837 | { | 
| 838 | if( ch3 == 'E' ) | 
| 839 | return( 13 ); | 
| 840 | } | 
| 841 | else if( ch2 == 'C' ) | 
| 842 | { | 
| 843 | if( ch3 == 'A' ) | 
| 844 | return( 22 ); | 
| 845 | } | 
| 846 | else if( ch2 == 'O' ) | 
| 847 | { | 
| 848 | if( ch3 == '4' ) | 
| 849 | return( 49 ); | 
| 850 | } | 
| 851 | else if( ch2 == 'S' ) | 
| 852 | { | 
| 853 | if( ch3 == 'U' ) | 
| 854 | return( 42 ); | 
| 855 | } | 
| 856 |  | 
| 857 | break; | 
| 858 |  | 
| 859 | case('S'): | 
| 860 |  | 
| 861 | if( ch2 == 'E' ) | 
| 862 | { | 
| 863 | if( ch3 == 'R' ) | 
| 864 | return(  3 ); | 
| 865 | } | 
| 866 | else if( ch2 == 'O' ) | 
| 867 | { | 
| 868 | if( ch3 == '4' ) | 
| 869 | return( 48 ); | 
| 870 | else if( ch3 == 'L' ) | 
| 871 | return( 46 );    /* "SOL" -> "HOH" */ | 
| 872 | } | 
| 873 | else if( ch2 == 'U' ) | 
| 874 | { | 
| 875 | if( ch3 == 'L' ) | 
| 876 | return( 48 );    /* "SUL" -> "SO4" */ | 
| 877 | } | 
| 878 |  | 
| 879 | break; | 
| 880 |  | 
| 881 | case('T'): | 
| 882 |  | 
| 883 | if( ch2 == 'H' ) | 
| 884 | { | 
| 885 | if( ch3 == 'R' ) | 
| 886 | return(  5 ); | 
| 887 | else if( ch3 == 'Y' ) | 
| 888 | return( 27 );    /* "THY" -> "  T" */ | 
| 889 | } | 
| 890 | else if( ch2 == 'Y' ) | 
| 891 | { | 
| 892 | if( ch3 == 'R' ) | 
| 893 | return( 15 ); | 
| 894 | } | 
| 895 | else if( ch2 == 'R' ) | 
| 896 | { | 
| 897 | if( ch3 == 'P' ) | 
| 898 | return( 19 ); | 
| 899 | else if( ch3 == 'Y' ) | 
| 900 | return( 19 );    /* "TRY" -> "TRP" */ | 
| 901 | } | 
| 902 | else if( ch2 == 'I' ) | 
| 903 | { | 
| 904 | if( ch3 == 'P' ) | 
| 905 | return( 46 );    /* "TIP" -> "HOH" */ | 
| 906 | } | 
| 907 |  | 
| 908 | break; | 
| 909 |  | 
| 910 | case('U'): | 
| 911 |  | 
| 912 | if( ch2 == 'N' ) | 
| 913 | { | 
| 914 | if( ch3 == 'K' ) | 
| 915 | return( 43 ); | 
| 916 | } | 
| 917 | else if( ch2 == 'R' ) | 
| 918 | { | 
| 919 | if( ch3 == 'A' ) | 
| 920 | return( 28 );    /* "URA" -> "  U" */ | 
| 921 | else if( ch3 == 'I' ) | 
| 922 | return( 28 );    /* "URI" -> "  U" */ | 
| 923 | } | 
| 924 |  | 
| 925 | break; | 
| 926 |  | 
| 927 | case('V'): | 
| 928 |  | 
| 929 | if( ch2 == 'A' ) | 
| 930 | if( ch3 == 'L' ) | 
| 931 | return(  4 ); | 
| 932 |  | 
| 933 | break; | 
| 934 |  | 
| 935 | case('W'): | 
| 936 |  | 
| 937 | if( ch2 == 'A' ) | 
| 938 | if( ch3 == 'T' ) | 
| 939 | return( 46 );    /* "WAT" -> "HOH" */ | 
| 940 |  | 
| 941 | break; | 
| 942 | } | 
| 943 |  | 
| 944 | unsigned int refno; | 
| 945 | for( refno = MINRES; refno < ResNo ; refno++ ) | 
| 946 | if( !strncmp(Residue[refno],res,3) ) | 
| 947 | return refno; | 
| 948 |  | 
| 949 | if ( ResNo < MAXRES - 1 ) | 
| 950 | { | 
| 951 | ResNo++; | 
| 952 | Residue[refno][0] = (char) ch1; | 
| 953 | Residue[refno][1] = (char) ch2; | 
| 954 | Residue[refno][2] = (char) ch3; | 
| 955 | return refno; | 
| 956 | } | 
| 957 | } | 
| 958 |  | 
| 959 | return OBResidueIndex::UNK; | 
| 960 | } | 
| 961 |  | 
| 962 | static void SetResidueKeys(const char   *residue, | 
| 963 | unsigned int &reskey, | 
| 964 | unsigned int &aakey) | 
| 965 | { | 
| 966 | reskey = GetResidueNumber(residue); | 
| 967 | switch(reskey) | 
| 968 | { | 
| 969 | case OBResidueIndex::ALA: | 
| 970 | aakey = AA_ALA; | 
| 971 | break; | 
| 972 | case OBResidueIndex::GLY: | 
| 973 | aakey = AA_GLY; | 
| 974 | break; | 
| 975 | case OBResidueIndex::LEU: | 
| 976 | aakey = AA_LEU; | 
| 977 | break; | 
| 978 | case OBResidueIndex::SER: | 
| 979 | aakey = AA_SER; | 
| 980 | break; | 
| 981 | case OBResidueIndex::VAL: | 
| 982 | aakey = AA_VAL; | 
| 983 | break; | 
| 984 | case OBResidueIndex::THR: | 
| 985 | aakey = AA_THR; | 
| 986 | break; | 
| 987 | case OBResidueIndex::LYS: | 
| 988 | aakey = AA_LYS; | 
| 989 | break; | 
| 990 | case OBResidueIndex::ASP: | 
| 991 | aakey = AA_ASP; | 
| 992 | break; | 
| 993 | case OBResidueIndex::ILE: | 
| 994 | aakey = AA_ILE; | 
| 995 | break; | 
| 996 | case OBResidueIndex::ASN: | 
| 997 | aakey = AA_ASN; | 
| 998 | break; | 
| 999 | case OBResidueIndex::GLU: | 
| 1000 | aakey = AA_GLU; | 
| 1001 | break; | 
| 1002 | case OBResidueIndex::PRO: | 
| 1003 | aakey = AA_PRO; | 
| 1004 | break; | 
| 1005 | case OBResidueIndex::ARG: | 
| 1006 | aakey = AA_ARG; | 
| 1007 | break; | 
| 1008 | case OBResidueIndex::PHE: | 
| 1009 | aakey = AA_PHE; | 
| 1010 | break; | 
| 1011 | case OBResidueIndex::GLN: | 
| 1012 | aakey = AA_GLN; | 
| 1013 | break; | 
| 1014 | case OBResidueIndex::TYR: | 
| 1015 | aakey = AA_TYR; | 
| 1016 | break; | 
| 1017 | case OBResidueIndex::HIS: | 
| 1018 | aakey = AA_HIS; | 
| 1019 | break; | 
| 1020 | case OBResidueIndex::CYS: | 
| 1021 | aakey = AA_CYS; | 
| 1022 | break; | 
| 1023 | case OBResidueIndex::MET: | 
| 1024 | aakey = AA_MET; | 
| 1025 | break; | 
| 1026 | case OBResidueIndex::TRP: | 
| 1027 | aakey = AA_TRP; | 
| 1028 | break; | 
| 1029 | default: | 
| 1030 | aakey = 0; | 
| 1031 | break; | 
| 1032 | } | 
| 1033 | } | 
| 1034 |  | 
| 1035 | /////////////////////////////////////////////////////////////////////////////// | 
| 1036 | // OBResidue: Constructors / Destructor | 
| 1037 | /////////////////////////////////////////////////////////////////////////////// | 
| 1038 |  | 
| 1039 | OBResidue::OBResidue() | 
| 1040 | { | 
| 1041 | _chain    = 'A'; | 
| 1042 | _idx      = 0; | 
| 1043 | _aakey    = 0; | 
| 1044 | _reskey   = OBResidueIndex::UNK; | 
| 1045 | _resnum   = 0; | 
| 1046 | _resname  = ""; | 
| 1047 | _vdata.clear(); | 
| 1048 | } | 
| 1049 |  | 
| 1050 | OBResidue::OBResidue(const OBResidue &src) | 
| 1051 | // Currently does not copy vdata information | 
| 1052 | { | 
| 1053 | _chain    = src._chain; | 
| 1054 | _aakey    = src._aakey; | 
| 1055 | _reskey   = src._reskey; | 
| 1056 | _resnum   = src._resnum; | 
| 1057 | _resname  = src._resname; | 
| 1058 | _atomid   = src._atomid; | 
| 1059 | _hetatm   = src._hetatm; | 
| 1060 | _sernum   = src._sernum; | 
| 1061 | } | 
| 1062 |  | 
| 1063 | OBResidue::~OBResidue() | 
| 1064 | { | 
| 1065 | vector<OBAtom*>::iterator a; | 
| 1066 | for ( a = _atoms.begin() ; a != _atoms.end() ; a++ ) | 
| 1067 | (*a)->SetResidue(NULL); | 
| 1068 | _atoms.clear(); | 
| 1069 | if (!_vdata.empty()) | 
| 1070 | { | 
| 1071 | vector<OBGenericData*>::iterator m; | 
| 1072 | for (m = _vdata.begin();m != _vdata.end();m++) | 
| 1073 | delete *m; | 
| 1074 | _vdata.clear(); | 
| 1075 | } | 
| 1076 | } | 
| 1077 |  | 
| 1078 | /////////////////////////////////////////////////////////////////////////////// | 
| 1079 | // OBResidue: Operator Overloads | 
| 1080 | /////////////////////////////////////////////////////////////////////////////// | 
| 1081 |  | 
| 1082 | OBResidue &OBResidue::operator = (const OBResidue &src) | 
| 1083 | //copy residue information | 
| 1084 | // Currently does not copy vdata informtion | 
| 1085 | { | 
| 1086 | if (this != &src) | 
| 1087 | { | 
| 1088 | _chain    = src._chain; | 
| 1089 | _aakey    = src._aakey; | 
| 1090 | _reskey   = src._reskey; | 
| 1091 | _resnum   = src._resnum; | 
| 1092 | _resname  = src._resname; | 
| 1093 | _atomid   = src._atomid; | 
| 1094 | _hetatm   = src._hetatm; | 
| 1095 | _sernum   = src._sernum; | 
| 1096 | } | 
| 1097 |  | 
| 1098 | return(*this); | 
| 1099 | } | 
| 1100 |  | 
| 1101 | /////////////////////////////////////////////////////////////////////////////// | 
| 1102 | // OBResidue: Data Access / Manipulation | 
| 1103 | /////////////////////////////////////////////////////////////////////////////// | 
| 1104 |  | 
| 1105 | void OBResidue::AddAtom(OBAtom *atom) | 
| 1106 | { | 
| 1107 | if (atom != NULL) | 
| 1108 | { | 
| 1109 | atom->SetResidue(this); | 
| 1110 |  | 
| 1111 | _atoms.push_back(atom); | 
| 1112 | _atomid.push_back(""); | 
| 1113 | _hetatm.push_back(false); | 
| 1114 | _sernum.push_back(0); | 
| 1115 | } | 
| 1116 | } | 
| 1117 |  | 
| 1118 | void OBResidue::InsertAtom(OBAtom *atom) | 
| 1119 | { | 
| 1120 | if (atom != NULL) | 
| 1121 | { | 
| 1122 | atom->SetResidue(this); | 
| 1123 |  | 
| 1124 | _atoms.push_back(atom); | 
| 1125 | _atomid.push_back(""); | 
| 1126 | _hetatm.push_back(false); | 
| 1127 | _sernum.push_back(0); | 
| 1128 | } | 
| 1129 | } | 
| 1130 |  | 
| 1131 | void OBResidue::RemoveAtom(OBAtom *atom) | 
| 1132 | { | 
| 1133 | if (atom != NULL) | 
| 1134 | { | 
| 1135 | for ( unsigned int i = 0 ; i < _atoms.size() ; i++ ) | 
| 1136 | { | 
| 1137 | if (_atoms[i] == atom) | 
| 1138 | { | 
| 1139 | atom->SetResidue(NULL); | 
| 1140 | _atoms.erase(_atoms.begin() + i); | 
| 1141 | _atomid.erase(_atomid.begin() + i); | 
| 1142 | _hetatm.erase(_hetatm.begin() + i); | 
| 1143 | _sernum.erase(_sernum.begin() + i); | 
| 1144 | } | 
| 1145 | } | 
| 1146 | } | 
| 1147 | } | 
| 1148 |  | 
| 1149 | void OBResidue::Clear(void) | 
| 1150 | { | 
| 1151 | for (unsigned int i = 0 ; i < _atoms.size() ; i++ ) | 
| 1152 | _atoms[i]->SetResidue(NULL); | 
| 1153 |  | 
| 1154 | _chain   = 'A'; | 
| 1155 | _idx     = 0; | 
| 1156 | _aakey   = 0; | 
| 1157 | _reskey  = OBResidueIndex::UNK; | 
| 1158 | _resnum  = 0; | 
| 1159 | _resname = ""; | 
| 1160 |  | 
| 1161 | _atoms.clear(); | 
| 1162 | _atomid.clear(); | 
| 1163 | _hetatm.clear(); | 
| 1164 | _sernum.clear(); | 
| 1165 | } | 
| 1166 |  | 
| 1167 | void OBResidue::SetChain(char chain) | 
| 1168 | { | 
| 1169 | _chain = chain; | 
| 1170 | } | 
| 1171 |  | 
| 1172 | void OBResidue::SetChainNum(unsigned int chainnum) | 
| 1173 | { | 
| 1174 | _chain = (char) ('A' + chainnum - 1); | 
| 1175 | } | 
| 1176 |  | 
| 1177 | void OBResidue::SetIdx(unsigned int idx) | 
| 1178 | { | 
| 1179 | _idx = idx; | 
| 1180 | } | 
| 1181 |  | 
| 1182 | void OBResidue::SetName(const string &name) | 
| 1183 | { | 
| 1184 | _resname = name; | 
| 1185 | SetResidueKeys(_resname.c_str(), _reskey, _aakey); | 
| 1186 | } | 
| 1187 |  | 
| 1188 | void OBResidue::SetNum(unsigned int resnum) | 
| 1189 | { | 
| 1190 | _resnum = resnum; | 
| 1191 | } | 
| 1192 |  | 
| 1193 | void OBResidue::SetAtomID(OBAtom *atom, const string &id) | 
| 1194 | { | 
| 1195 | for ( unsigned int i = 0 ; i < _atoms.size() ; i++ ) | 
| 1196 | if (_atoms[i] == atom) | 
| 1197 | _atomid[i] = id; | 
| 1198 | } | 
| 1199 |  | 
| 1200 | void OBResidue::SetHetAtom(OBAtom *atom, bool hetatm) | 
| 1201 | { | 
| 1202 | for ( unsigned int i = 0 ; i < _atoms.size() ; i++ ) | 
| 1203 | if (_atoms[i] == atom) | 
| 1204 | _hetatm[i] = hetatm; | 
| 1205 | } | 
| 1206 |  | 
| 1207 | void OBResidue::SetSerialNum(OBAtom *atom, unsigned int sernum) | 
| 1208 | { | 
| 1209 | for ( unsigned int i = 0 ; i < _atoms.size() ; i++ ) | 
| 1210 | if (_atoms[i] == atom) | 
| 1211 | _sernum[i] = sernum; | 
| 1212 | } | 
| 1213 |  | 
| 1214 | vector<OBAtom*> OBResidue::GetAtoms(void) const | 
| 1215 | { | 
| 1216 | return _atoms; | 
| 1217 | } | 
| 1218 |  | 
| 1219 | vector<OBBond*> OBResidue::GetBonds(bool exterior) const | 
| 1220 | { | 
| 1221 | OBAtom         *atom; | 
| 1222 | vector<OBBond*> bonds; | 
| 1223 | OBBitVec        idxs; | 
| 1224 | unsigned int    sz; | 
| 1225 |  | 
| 1226 | sz = (unsigned int) _atoms.size(); | 
| 1227 | for ( unsigned int i = 0 ; i < sz ; i++ ) | 
| 1228 | { | 
| 1229 | atom = _atoms[i]; | 
| 1230 | OBBond *bond; | 
| 1231 | vector<OBEdgeBase*>::iterator b; | 
| 1232 | for (bond = atom->BeginBond(b) ; bond ; bond = atom->NextBond(b)) | 
| 1233 | { | 
| 1234 | if (!idxs.BitIsOn(bond->GetIdx())) | 
| 1235 | { | 
| 1236 | if (!exterior) | 
| 1237 | { | 
| 1238 | if (bond->GetNbrAtom(atom)->GetResidue() == this) | 
| 1239 | bonds.push_back(&(*bond)); | 
| 1240 | } | 
| 1241 | else | 
| 1242 | bonds.push_back(&(*bond)); | 
| 1243 |  | 
| 1244 | idxs.SetBitOn(bond->GetIdx()); | 
| 1245 | } | 
| 1246 | } | 
| 1247 | } | 
| 1248 |  | 
| 1249 | return bonds; | 
| 1250 | } | 
| 1251 |  | 
| 1252 | string OBResidue::GetName(void) const | 
| 1253 | { | 
| 1254 | return _resname; | 
| 1255 | } | 
| 1256 |  | 
| 1257 | unsigned int OBResidue::GetNum(void) const | 
| 1258 | { | 
| 1259 | return _resnum; | 
| 1260 | } | 
| 1261 |  | 
| 1262 | unsigned int OBResidue::GetNumAtoms(void) const | 
| 1263 | { | 
| 1264 | return (unsigned int)_atoms.size(); | 
| 1265 | } | 
| 1266 |  | 
| 1267 | char OBResidue::GetChain(void) const | 
| 1268 | { | 
| 1269 | return _chain; | 
| 1270 | } | 
| 1271 |  | 
| 1272 | unsigned int OBResidue::GetChainNum(void) const | 
| 1273 | { | 
| 1274 | if (isdigit(_chain)) | 
| 1275 | return (_chain - '0'); | 
| 1276 | else | 
| 1277 | return (_chain - 'A' + 1); | 
| 1278 | } | 
| 1279 |  | 
| 1280 | unsigned int OBResidue::GetIdx(void) const | 
| 1281 | { | 
| 1282 | return(_idx); | 
| 1283 | } | 
| 1284 |  | 
| 1285 | unsigned int OBResidue::GetResKey(void) const | 
| 1286 | { | 
| 1287 | return(_reskey); | 
| 1288 | } | 
| 1289 |  | 
| 1290 | string OBResidue::GetAtomID(OBAtom *atom) const | 
| 1291 | { | 
| 1292 | for ( unsigned int i = 0 ; i < _atoms.size() ; i++ ) | 
| 1293 | if (_atoms[i] == atom) | 
| 1294 | return _atomid[i]; | 
| 1295 | return ""; | 
| 1296 | } | 
| 1297 |  | 
| 1298 | unsigned int OBResidue::GetSerialNum(OBAtom *atom) const | 
| 1299 | { | 
| 1300 | for ( unsigned int i = 0 ; i < _atoms.size() ; i++ ) | 
| 1301 | if (_atoms[i] == atom) | 
| 1302 | return _sernum[i]; | 
| 1303 | return 0; | 
| 1304 | } | 
| 1305 |  | 
| 1306 | bool OBResidue::IsHetAtom(OBAtom *atom) const | 
| 1307 | { | 
| 1308 | for ( unsigned int i = 0 ; i < _atoms.size() ; i++ ) | 
| 1309 | if (_atoms[i] == atom) | 
| 1310 | return _hetatm[i]; | 
| 1311 | return false; | 
| 1312 | } | 
| 1313 |  | 
| 1314 | /////////////////////////////////////////////////////////////////////////////// | 
| 1315 | // OBResidue: Iteration Utilities | 
| 1316 | /////////////////////////////////////////////////////////////////////////////// | 
| 1317 |  | 
| 1318 | OBAtom *OBResidue::BeginAtom(vector<OBAtom*>::iterator &i) | 
| 1319 | { | 
| 1320 | i = _atoms.begin(); | 
| 1321 | return ((i == _atoms.end()) ? NULL : *i); | 
| 1322 | } | 
| 1323 |  | 
| 1324 | OBAtom *OBResidue::NextAtom(vector<OBAtom*>::iterator &i) | 
| 1325 | { | 
| 1326 | i++; | 
| 1327 | return ((i == _atoms.end()) ? NULL : *i); | 
| 1328 | } | 
| 1329 |  | 
| 1330 | /////////////////////////////////////////////////////////////////////////////// | 
| 1331 | // OBResidue: Information Functions | 
| 1332 | /////////////////////////////////////////////////////////////////////////////// | 
| 1333 |  | 
| 1334 | bool OBResidue::GetAminoAcidProperty(int property) const | 
| 1335 | { | 
| 1336 | switch(property) | 
| 1337 | { | 
| 1338 | case OBAminoAcidProperty::ACIDIC: | 
| 1339 | return IS_ACIDIC(_aakey)      != 0; | 
| 1340 | case OBAminoAcidProperty::ACYCLIC: | 
| 1341 | return IS_ACYCLIC(_aakey)     != 0; | 
| 1342 | case OBAminoAcidProperty::ALIPHATIC: | 
| 1343 | return IS_ALIPHATIC(_aakey)   != 0; | 
| 1344 | case OBAminoAcidProperty::AROMATIC: | 
| 1345 | return IS_AROMATIC(_aakey)    != 0; | 
| 1346 | case OBAminoAcidProperty::BASIC: | 
| 1347 | return IS_BASIC(_aakey)       != 0; | 
| 1348 | case OBAminoAcidProperty::BURIED: | 
| 1349 | return IS_BURIED(_aakey)      != 0; | 
| 1350 | case OBAminoAcidProperty::CHARGED: | 
| 1351 | return IS_CHARGED(_aakey)     != 0; | 
| 1352 | case OBAminoAcidProperty::CYCLIC: | 
| 1353 | return IS_CYCLIC(_aakey)      != 0; | 
| 1354 | case OBAminoAcidProperty::HYDROPHOBIC: | 
| 1355 | return IS_HYDROPHOBIC(_aakey) != 0; | 
| 1356 | case OBAminoAcidProperty::LARGE: | 
| 1357 | return IS_LARGE(_aakey)       != 0; | 
| 1358 | case OBAminoAcidProperty::MEDIUM: | 
| 1359 | return IS_MEDIUM(_aakey)      != 0; | 
| 1360 | case OBAminoAcidProperty::NEGATIVE: | 
| 1361 | return IS_NEGATIVE(_aakey)    != 0; | 
| 1362 | case OBAminoAcidProperty::NEUTRAL: | 
| 1363 | return IS_NEUTRAL(_aakey)     != 0; | 
| 1364 | case OBAminoAcidProperty::POLAR: | 
| 1365 | return IS_POLAR(_aakey)       != 0; | 
| 1366 | case OBAminoAcidProperty::POSITIVE: | 
| 1367 | return IS_POSITIVE(_aakey)    != 0; | 
| 1368 | case OBAminoAcidProperty::SMALL: | 
| 1369 | return IS_SMALL(_aakey)       != 0; | 
| 1370 | case OBAminoAcidProperty::SURFACE: | 
| 1371 | return IS_SURFACE(_aakey)     != 0; | 
| 1372 | default: | 
| 1373 | return false; | 
| 1374 | } | 
| 1375 | } | 
| 1376 |  | 
| 1377 | bool OBResidue::GetAtomProperty(OBAtom *atom, int property) const | 
| 1378 | { | 
| 1379 | if (atom != NULL) | 
| 1380 | { | 
| 1381 | unsigned int atomid = GetAtomIDNumber(GetAtomID(atom).c_str()); | 
| 1382 |  | 
| 1383 | switch(property) | 
| 1384 | { | 
| 1385 | case OBResidueAtomProperty::ALPHA_CARBON: | 
| 1386 | return (atomid == 1); | 
| 1387 |  | 
| 1388 | case OBResidueAtomProperty::AMINO_BACKBONE: | 
| 1389 | return (atomid <= 3); | 
| 1390 |  | 
| 1391 | case OBResidueAtomProperty::BACKBONE: | 
| 1392 | return (atomid <= 18); | 
| 1393 |  | 
| 1394 | case OBResidueAtomProperty::CYSTEINE_SULPHUR: | 
| 1395 | return (atomid == 20); | 
| 1396 |  | 
| 1397 | case OBResidueAtomProperty::LIGAND: | 
| 1398 | return IsHetAtom(atom) && | 
| 1399 | !GetResidueProperty(OBResidueProperty::SOLVENT); | 
| 1400 |  | 
| 1401 | case OBResidueAtomProperty::NUCLEIC_BACKBONE: | 
| 1402 | return ((atomid >= 7) && (atomid <= 18)); | 
| 1403 |  | 
| 1404 | case OBResidueAtomProperty::SHAPELY_BACKBONE: | 
| 1405 | return (atomid <= 7); | 
| 1406 |  | 
| 1407 | case OBResidueAtomProperty::SHAPELY_SPECIAL: | 
| 1408 | return (atomid == 19); | 
| 1409 |  | 
| 1410 | case OBResidueAtomProperty::SIDECHAIN: | 
| 1411 | return GetResidueProperty(OBResidueProperty::AMINO_NUCLEO) && | 
| 1412 | (atomid > 18); | 
| 1413 |  | 
| 1414 | case OBResidueAtomProperty::SUGAR_PHOSPHATE: | 
| 1415 | return (atomid == 7); | 
| 1416 | } | 
| 1417 | } | 
| 1418 |  | 
| 1419 | return false; | 
| 1420 | } | 
| 1421 |  | 
| 1422 | bool OBResidue::GetResidueProperty(int property) const | 
| 1423 | { | 
| 1424 | switch(property) | 
| 1425 | { | 
| 1426 | case OBResidueProperty::AMINO: | 
| 1427 | return (_reskey <= OBResidueIndex::HYP); | 
| 1428 |  | 
| 1429 | case OBResidueProperty::AMINO_NUCLEO: | 
| 1430 | return (_reskey <= OBResidueIndex::PSU); | 
| 1431 |  | 
| 1432 | case OBResidueProperty::COENZYME: | 
| 1433 | return (_reskey >= OBResidueIndex::NAD) && | 
| 1434 | (_reskey <= OBResidueIndex::NDP); | 
| 1435 |  | 
| 1436 | case OBResidueProperty::ION: | 
| 1437 | return (_reskey == OBResidueIndex::SO4) || | 
| 1438 | (_reskey == OBResidueIndex::PO4); | 
| 1439 |  | 
| 1440 | case OBResidueProperty::NUCLEO: | 
| 1441 | return (_reskey >= OBResidueIndex::A) && | 
| 1442 | (_reskey <= OBResidueIndex::PSU); | 
| 1443 |  | 
| 1444 | case OBResidueProperty::PROTEIN: | 
| 1445 | return (_reskey <= OBResidueIndex::HYP) || | 
| 1446 | ((_reskey >= OBResidueIndex::UNK) && | 
| 1447 | (_reskey <= OBResidueIndex::FOR)); | 
| 1448 |  | 
| 1449 | case OBResidueProperty::PURINE: | 
| 1450 | return (_reskey == OBResidueIndex::A) || | 
| 1451 | (_reskey == OBResidueIndex::G); | 
| 1452 |  | 
| 1453 | case OBResidueProperty::PYRIMIDINE: | 
| 1454 | return (_reskey == OBResidueIndex::C) || | 
| 1455 | (_reskey == OBResidueIndex::T); | 
| 1456 |  | 
| 1457 | case OBResidueProperty::SOLVENT: | 
| 1458 | return (_reskey >= OBResidueIndex::HOH) && | 
| 1459 | (_reskey <= OBResidueIndex::PO4); | 
| 1460 |  | 
| 1461 | case OBResidueProperty::WATER: | 
| 1462 | return (_reskey == OBResidueIndex::HOH) || | 
| 1463 | (_reskey == OBResidueIndex::DOD); | 
| 1464 |  | 
| 1465 | default: | 
| 1466 | return false; | 
| 1467 | } | 
| 1468 | } | 
| 1469 |  | 
| 1470 | bool OBResidue::IsResidueType(int restype) const | 
| 1471 | { | 
| 1472 | return ((int)_reskey == restype); | 
| 1473 | } | 
| 1474 |  | 
| 1475 | // OBGenericData methods | 
| 1476 | bool OBResidue::HasData(string &s) | 
| 1477 | //returns true if the generic attribute/value pair exists | 
| 1478 | { | 
| 1479 | if (_vdata.empty()) | 
| 1480 | return(false); | 
| 1481 |  | 
| 1482 | vector<OBGenericData*>::iterator i; | 
| 1483 |  | 
| 1484 | for (i = _vdata.begin();i != _vdata.end();i++) | 
| 1485 | if ((*i)->GetAttribute() == s) | 
| 1486 | return(true); | 
| 1487 |  | 
| 1488 | return(false); | 
| 1489 | } | 
| 1490 |  | 
| 1491 | bool OBResidue::HasData(const char *s) | 
| 1492 | //returns true if the generic attribute/value pair exists | 
| 1493 | { | 
| 1494 | if (_vdata.empty()) | 
| 1495 | return(false); | 
| 1496 |  | 
| 1497 | vector<OBGenericData*>::iterator i; | 
| 1498 |  | 
| 1499 | for (i = _vdata.begin();i != _vdata.end();i++) | 
| 1500 | if ((*i)->GetAttribute() == s) | 
| 1501 | return(true); | 
| 1502 |  | 
| 1503 | return(false); | 
| 1504 | } | 
| 1505 |  | 
| 1506 | bool OBResidue::HasData(unsigned int dt) | 
| 1507 | //returns true if the generic attribute/value pair exists | 
| 1508 | { | 
| 1509 | if (_vdata.empty()) | 
| 1510 | return(false); | 
| 1511 |  | 
| 1512 | vector<OBGenericData*>::iterator i; | 
| 1513 |  | 
| 1514 | for (i = _vdata.begin();i != _vdata.end();i++) | 
| 1515 | if ((*i)->GetDataType() == dt) | 
| 1516 | return(true); | 
| 1517 |  | 
| 1518 | return(false); | 
| 1519 | } | 
| 1520 |  | 
| 1521 | OBGenericData *OBResidue::GetData(string &s) | 
| 1522 | //returns the value given an attribute | 
| 1523 | { | 
| 1524 | vector<OBGenericData*>::iterator i; | 
| 1525 |  | 
| 1526 | for (i = _vdata.begin();i != _vdata.end();i++) | 
| 1527 | if ((*i)->GetAttribute() == s) | 
| 1528 | return(*i); | 
| 1529 |  | 
| 1530 | return(NULL); | 
| 1531 | } | 
| 1532 |  | 
| 1533 | OBGenericData *OBResidue::GetData(const char *s) | 
| 1534 | //returns the value given an attribute | 
| 1535 | { | 
| 1536 | vector<OBGenericData*>::iterator i; | 
| 1537 |  | 
| 1538 | for (i = _vdata.begin();i != _vdata.end();i++) | 
| 1539 | if ((*i)->GetAttribute() == s) | 
| 1540 | return(*i); | 
| 1541 |  | 
| 1542 | return(NULL); | 
| 1543 | } | 
| 1544 |  | 
| 1545 | OBGenericData *OBResidue::GetData(unsigned int dt) | 
| 1546 | { | 
| 1547 | vector<OBGenericData*>::iterator i; | 
| 1548 | for (i = _vdata.begin();i != _vdata.end();i++) | 
| 1549 | if ((*i)->GetDataType() == dt) | 
| 1550 | return(*i); | 
| 1551 | return(NULL); | 
| 1552 | } | 
| 1553 |  | 
| 1554 | void OBResidue::DeleteData(unsigned int dt) | 
| 1555 | { | 
| 1556 | vector<OBGenericData*> vdata; | 
| 1557 | vector<OBGenericData*>::iterator i; | 
| 1558 | for (i = _vdata.begin();i != _vdata.end();i++) | 
| 1559 | if ((*i)->GetDataType() == dt) | 
| 1560 | delete *i; | 
| 1561 | else | 
| 1562 | vdata.push_back(*i); | 
| 1563 | _vdata = vdata; | 
| 1564 | } | 
| 1565 |  | 
| 1566 | void OBResidue::DeleteData(vector<OBGenericData*> &vg) | 
| 1567 | { | 
| 1568 | vector<OBGenericData*> vdata; | 
| 1569 | vector<OBGenericData*>::iterator i,j; | 
| 1570 |  | 
| 1571 | bool del; | 
| 1572 | for (i = _vdata.begin();i != _vdata.end();i++) | 
| 1573 | { | 
| 1574 | del = false; | 
| 1575 | for (j = vg.begin();j != vg.end();j++) | 
| 1576 | if (*i == *j) | 
| 1577 | { | 
| 1578 | del = true; | 
| 1579 | break; | 
| 1580 | } | 
| 1581 | if (del) | 
| 1582 | delete *i; | 
| 1583 | else | 
| 1584 | vdata.push_back(*i); | 
| 1585 | } | 
| 1586 | _vdata = vdata; | 
| 1587 | } | 
| 1588 |  | 
| 1589 | void OBResidue::DeleteData(OBGenericData *gd) | 
| 1590 | { | 
| 1591 | vector<OBGenericData*>::iterator i; | 
| 1592 | for (i = _vdata.begin();i != _vdata.end();i++) | 
| 1593 | if (*i == gd) | 
| 1594 | { | 
| 1595 | delete *i; | 
| 1596 | _vdata.erase(i); | 
| 1597 | } | 
| 1598 |  | 
| 1599 | } | 
| 1600 |  | 
| 1601 | } // end namespace OpenBabel | 
| 1602 |  | 
| 1603 | //! \file residue.cpp | 
| 1604 | //! \brief Handle macromolecule residues. |