1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139
|
/* massXpert - the true massist's program.
--------------------------------------
Copyright(C) 2006,2007 Filippo Rusconi
http://www.massxpert.org/massXpert
This file is part of the massXpert project.
The massxpert project is the successor to the "GNU polyxmass"
project that is an official GNU project package(see
www.gnu.org). The massXpert project is not endorsed by the GNU
project, although it is released ---in its entirety--- under the
GNU General Public License. A huge part of the code in massXpert
is actually a C++ rewrite of code in GNU polyxmass. As such
massXpert was started at the Centre National de la Recherche
Scientifique(FRANCE), that granted me the formal authorization to
publish it under this Free Software License.
This software is free software; you can redistribute it and/or
modify it under the terms of the GNU General Public
License version 3, as published by the Free Software Foundation.
This software is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
General Public License for more details.
You should have received a copy of the GNU General Public License
along with this software; if not, write to the
Free Software Foundation, Inc.,
51 Franklin St, Fifth Floor, Boston, MA 02110-1301, USA.
*/
/////////////////////// Local includes
#include "cleaver.hpp"
namespace massXpert
{
Cleaver::Cleaver(Polymer *polymer,
const PolChemDef *polChemDef,
const CleaveOptions &cleaveOptions,
const CalcOptions &calcOptions,
const IonizeRule &ionizeRule)
: mp_polymer(polymer),
mp_polChemDef(polChemDef),
m_cleaveOptions(cleaveOptions),
m_calcOptions(calcOptions),
m_ionizeRule(ionizeRule)
{
Q_ASSERT(mp_polymer && mp_polChemDef);
mp_oligomerList = 0;
}
Cleaver::Cleaver(const Cleaver &other)
: mp_polymer(other.mp_polymer),
mp_polChemDef(other.mp_polChemDef),
m_cleaveOptions(other.m_cleaveOptions),
m_calcOptions(other.m_calcOptions),
m_ionizeRule(other.m_ionizeRule)
{
Q_ASSERT(mp_polymer && mp_polChemDef);
mp_oligomerList = 0;
}
Cleaver::~Cleaver()
{
// We are not owner of the oligomer list, do not free it!
}
void
Cleaver::setOligomerList(OligomerList *oligomerList)
{
Q_ASSERT(oligomerList);
mp_oligomerList = oligomerList;
}
OligomerList *
Cleaver::oligomerList()
{
return mp_oligomerList;
}
bool
Cleaver::cleave(bool reset)
{
if (!mp_oligomerList)
qFatal("%s@%d -- The oligomer list is 0.", __FILE__, __LINE__);
// If the polymer sequence is empty, just return.
if (!mp_polymer->size())
return true;
// Ensure that the cleavage pattern was already parsed.
if (!m_cleaveOptions.motifList()->size())
{
if (!m_cleaveOptions.parse())
{
qDebug() << __FILE__ << __LINE__
<< "Failed to parse the cleavage options";
return false;
}
}
// qDebug() << __FILE__ << __LINE__
// << "number of motifs:"
// << mp_cleaveOptions->motifList()->size();
if (!fillIndexLists())
{
qDebug() << __FILE__ << __LINE__
<< "Index lists(cleave/nocleave) are empty."
"No oligomer generated.";
// We can return true, as no error condition was found but not
// oligomers were generated.
return true;
}
if (resolveCleavageNoCleavage() == -1)
{
qDebug() << __FILE__ << __LINE__
<< "Failed to resolve cleavage/nocleavage";
return false;
}
removeDuplicatesCleavage();
qSort(m_cleaveIndexList.begin(), m_cleaveIndexList.end());
// for (int debugIter = 0; debugIter < m_cleaveIndexList.size();
// ++debugIter)
// {
// qDebug() << __FILE__ << __LINE__
// << "Index:" << m_cleaveIndexList.at(debugIter);
// }
if (reset)
emptyOligomerList();
for (int iter = 0 ; iter <= m_cleaveOptions.partials(); ++iter)
{
if (cleavePartial(iter) == -1)
{
qDebug() << __FILE__ << __LINE__
<< "Failed to perform partial cleavage at index:"
<< iter;
return false;
}
}
// At this point we have the list of lists of oligomers, one list of
// oligomers for each partial cleavage.
while (m_cleaveIndexList.size())
m_cleaveIndexList.removeFirst();
while (m_noCleaveIndexList.size())
m_noCleaveIndexList.removeFirst();
return true;
}
int
Cleaver::fillIndexLists()
{
QList<CleaveMotif *> *motifList = m_cleaveOptions.motifList();
while (m_cleaveIndexList.size())
m_cleaveIndexList.removeFirst();
while (m_noCleaveIndexList.size())
m_noCleaveIndexList.removeFirst();
// Since version 2.3.0, the cleavage might be performed on a
// selected portion of a sequence only, not necessarily on the
// whole polymer sequence.
CoordinateList coordinateList = m_calcOptions.coordinateList();
Coordinates *coordinates = coordinateList.first();
int startIndex = coordinates->start();
int endIndex = coordinates->end();
for (int iter = 0; iter < motifList->size(); ++iter)
{
CleaveMotif *cleaveMotif = motifList->at(iter);
Q_ASSERT(cleaveMotif);
int index = startIndex -1;
while (1)
{
index = findCleaveMotif(*cleaveMotif, index + 1, endIndex);
if (index == -1)
break;
// Do not forget: The position at which the motif is found
// in the polymer sequence is not necessarily the position
// at which the cleavage will effectively occur. Indeed,
// let's say that we found such motif in the polymer
// sequence: "KKRKGP". This motif was extracted from a
// cleave spec that had a pattern like this: "KKRK/GP". What
// we see here is that the cleavage occurs after the fourth
// monomer! And we must realize that the 'index' returned
// above corresponds to the index of the first 'K' in
// "KKRKGP" motif that was found in the polymer
// sequence. Thus we have to take into account the offset
//(+4, in our example, WHICH IS A POSITION and not an
// index, which is why we need to remove 1 below) of the
// cleavage:
int cleavageIndex = index + cleaveMotif->offset() - 1;
if (cleavageIndex < 0)
continue;
if (cleavageIndex >= endIndex)
break;
// qDebug() << __FILE__ << __LINE__
// << "Found new cleavage index:"
// << cleavageIndex;
if (cleaveMotif->isForCleave())
{
m_cleaveIndexList.append(cleavageIndex);
// qDebug() << __FILE__ << __LINE__
// << "For cleavage, index:" << cleavageIndex;
}
else
{
m_noCleaveIndexList.append(cleavageIndex);
// qDebug() << __FILE__ << __LINE__
// << "Not for cleavage";
}
}
// End of
// while (1)
}
// End of
// for (int iter = 0; iter < motifList->size(); ++iter)
// Note that returning 0 is not an error condition, because a
// sequence where no site is found whatsoever will result in 0.
return m_cleaveIndexList.size() + m_noCleaveIndexList.size();
}
int
Cleaver::resolveCleavageNoCleavage()
{
for (int iter = 0; iter < m_noCleaveIndexList.size(); ++iter)
{
int noCleaveIndex = m_noCleaveIndexList.at(iter);
for(int jter = 0; jter < m_cleaveIndexList.size(); ++jter)
{
int cleaveIndex = m_cleaveIndexList.at(jter);
if (noCleaveIndex == cleaveIndex)
m_cleaveIndexList.removeAt(jter);
}
}
return m_cleaveIndexList.size();
}
int
Cleaver::removeDuplicatesCleavage()
{
for (int iter = 0; iter < m_cleaveIndexList.size(); ++iter)
{
int index = m_cleaveIndexList.at(iter);
int foundItemIndex = m_cleaveIndexList.indexOf(index, iter + 1);
if (foundItemIndex != -1)
{
m_cleaveIndexList.removeAt(foundItemIndex);
--iter;
}
}
return m_cleaveIndexList.size();
}
int
Cleaver::findCleaveMotif(CleaveMotif &cleaveMotif,
int startIndex, int endIndex)
{
bool noGood = false;
int firstIndex = 0;
QList<const Monomer *> monomerList = mp_polymer->monomerList();
const QStringList &codeList = cleaveMotif.codeList();
//We have to iterate in the polymer sequence starting at 'index', in
//search for a sequence element identical to the sequence in the
//'cleaveMotif'.
// This means that if
// cleavemotif->m_motifList [0] = "Lys"
// cleavemotif->m_motifList [1] = "Pro"
// the, we want to search in the polymer list of monomers the same
// sequence by iterating in this list from index 'index' onwards,
// and we stop searching when the list's end is found or if
// list [n] = "Lys" and
// list [n+1] = "Pro".
if (mp_polymer->size() == 0)
return 0;
if (codeList.size() == 0)
return -1;
if (startIndex < 0)
return -1;
if (endIndex >= mp_polymer->size())
return -1;
// Seed the routine by setting 'first' to the first motif in the
// codeList (in our example this is "Lys").
QString firstCode = codeList.first();
// And now iterate (starting from 'index') in the polymer
// sequence's list of monomers in search for a monomer having the
// proper code ("Lys").
int iterIndex = startIndex;
while (iterIndex < endIndex)
{
const Monomer *monomer = monomerList.at(iterIndex);
if (monomer->code() != firstCode)
{
// The currently iterated code is not the one we
// search. So go one code further in the sequence.
++iterIndex;
continue;
}
// If we are here, then that means that we actually found on
// monomer code in the sequence that matches the one we are
// looking for.
firstIndex = iterIndex;
noGood = false;
// Now that we have anchored our search at firstIndex in the
// polymer sequence, continue with next monomer and check if
// it matches the next monomer in the motif we are looking
// for.
for (int iter = 1; iter < codeList.size(); ++iter)
{
if (iterIndex + iter >= endIndex)
{
noGood = true;
break;
}
QString nextCode = codeList.at(iter);
monomer = monomerList.at(iterIndex + iter);
if (monomer->code() == nextCode)
continue;
else
{
noGood = true;
break;
}
}
// End of
// for (int iter = 1; iter < codeList.size(); ++iter)
if (noGood)
{
++iterIndex;
continue;
}
else
{
return firstIndex;
}
}
// End of
// while (iterIndex < monomerList.size())
return -1;
}
bool
Cleaver::accountCleaveRule(CleaveRule *cleaveRule,
CleaveOligomer *oligomer)
{
Q_ASSERT(cleaveRule);
Q_ASSERT(oligomer);
const QList<Atom *> &refList =
oligomer->polymer()->polChemDef()->atomList();
// For each Coordinates element in the oligomer, we have to ensure
// we apply the formula(s) that is/are required.
int coordinatesCount = static_cast<CoordinateList *>(oligomer)->size();
// qDebug() << __FILE__ << __LINE__
// << "Coordinates count:" << coordinatesCount;
for (int iter = 0; iter < coordinatesCount; ++iter)
{
Coordinates *coordinates =
static_cast<CoordinateList *>(oligomer)->at(iter);
if (!cleaveRule->leftCode().isEmpty())
{
// The formula has to be there.
Formula ruleFormula = cleaveRule->leftFormula();
Q_ASSERT(!ruleFormula.formula().isEmpty());
// What is the monomer at the left end of current oligomer ?
const Monomer &monomer = oligomer->atLeftEnd();
if (monomer.code() == cleaveRule->leftCode())
{
// qDebug() << __FILE__ << __LINE__
// << "Matched left code:" << cleaveRule->leftCode();
// But, this is not going to be real true, if the
// monomer is acutally the left-end monomer of the
// polymer sequence, because then that would mean that
// there was no cleavage on this monomer, thus no rule
// to apply.
if (!coordinates->start())
{
// The monomer is not the left-end monomer, so the
// match is real. Account for the formula !
if (!ruleFormula.accountMasses(refList, oligomer))
return false;
}
}
}
if (!cleaveRule->rightCode().isEmpty())
{
// The formula has to be there.
Formula ruleFormula = cleaveRule->rightFormula();
Q_ASSERT(!ruleFormula.formula().isEmpty());
// What is the monomer at the right end of current oligomer ?
const Monomer &monomer = oligomer->atRightEnd();
if (monomer.code() == cleaveRule->rightCode())
{
// qDebug() << __FILE__ << __LINE__
// << "Matched right code:" << cleaveRule->rightCode();
// But, this is not going to be real true, if the
// monomer is acutally the right-end monomer of the
// polymer sequence, because then that would mean that
// there was no cleavage on this monomer, thus no rule
// to apply.
if (coordinates->end() != mp_polymer->size() - 1)
{
// The monomer is not the right-end monomer, so
// the match is real. Account for the formula !
if (!ruleFormula.accountMasses(refList, oligomer))
return false;
}
}
}
}
return true;
}
int
Cleaver::cleavePartial(int partialCleavageValue)
{
bool oligomerIsPolymer = false;
int iter = 0;
static int leftIndex = 0;
static int rightIndex = 0;
Q_ASSERT(partialCleavageValue >= 0);
OligomerList partialOligomerList;
// Since version 2.3.0, the cleavage might be performed on a
// selected portion of a sequence only, not necessarily on the
// whole polymer sequence. We have to know these values because
// when we create oligomer we'll have to set the coordinates of
// the monomers correctly.
CoordinateList coordinateList = m_calcOptions.coordinateList();
Coordinates *coordinates = coordinateList.first();
int startIndex = coordinates->start();
int endIndex = coordinates->end();
leftIndex = startIndex;
rightIndex = 0;
// Iterate in the array of indices where the cleavages should occur.
for (iter = 0; iter < m_cleaveIndexList.size(); ++iter)
{
// Make sure, if the partial cleavage is very large, for
// example, that it will not lead us to access the polymer
// sequence at a position larger than its upper boundary.
// Imagine cutting a polymer with only one Met residue with
// cyanogen bromide: m_cleaveIndexList will contain a single
// element: the index at which the methionine occurs in the
// polymer sequence(and there is a single one). Now, Imagine
// that we are asked to perform a cleavage with
// 'partialCleavageValue' of 2. The way we do it is that we fetch the
// index in the list of cleavage indices(m_cleaveIndexList) two
// positions farther than the position we are iterating:
// int partCleave = iter + partialCleavageValue;
// Now, if m_cleaveIndexList contains a single element, asking
// for this m_cleaveIndexList.at(iter + partialCleavageValue) will
// go out of the boundaries of the list, since it has a single
// item and partialCleavageValue is 2. This is what we are willing to
// avoid.
int partCleave = iter + partialCleavageValue;
if (partCleave >= m_cleaveIndexList.size())
{
if (iter == 0)
oligomerIsPolymer = true;
break;
}
rightIndex = m_cleaveIndexList.at(partCleave);
QString name = QString("%1#%2")
.arg(partialCleavageValue)
.arg(iter + 1);
CleaveOligomer *oligomer =
new CleaveOligomer(mp_polymer,
name, m_cleaveOptions.name(),
Ponderable(),
leftIndex, rightIndex, partialCleavageValue);
partialOligomerList.append(oligomer);
leftIndex = m_cleaveIndexList.at(iter) + 1;
}
// End of
// for (int iter = 0; iter < m_cleaveIndexList.size(); iter=+)
// Do not forget the right-end oligomer ! And be sure to determine
// what's its real left end index !
if (oligomerIsPolymer)
leftIndex = startIndex;
else
leftIndex = m_cleaveIndexList.at(--iter) + 1;
// 'iter' is used to construct the name of the oligomer, so we have
// to increment it once because we did not have the opportunity to
// increment it between the last but one oligomer and this one.
++iter;
// Remove 1 because the oligomer is described using indices and not
// positions.
rightIndex = endIndex;
QString name = QString("%1#%2")
.arg(partialCleavageValue)
.arg(iter + 1);
CleaveOligomer *oligomer =
new CleaveOligomer(mp_polymer,
name, m_cleaveOptions.name(),
Ponderable(),
leftIndex, rightIndex, partialCleavageValue);
partialOligomerList.append(oligomer);
// At this point all the skeleton oligomers have been computed for
// the given partialCleavageValue. We still have to perform the
// cross-link analysis prior to both calculate the masses and
// perform the ionization of all the generated oligomers. Note that
// making cross-link analysis is only useful in case the cleavage is
// full(partialCleavageValue == 0).
if (!partialCleavageValue)
{
if (m_calcOptions.monomerEntities() & MXT_MONOMER_CHEMENT_CROSS_LINK)
{
if (analyzeCrossLinks(&partialOligomerList) == -1)
{
return false;
}
}
}
// Finally, we can now perform the mass calculations and the
// ionization. We will use each oligomer in the oligomerList as a
// template for creating new oligomers(with different z values) and
// all the new oligomers will be appended to waitOligomerList. Each
// time a template oligomer will have been used, it will be removed
// from oligomerList. Once all the oligomers in oligomerList will
// have been used, and thus removed, all the newly allocated
// oligomers in waitOligomerList will be moved to oligomerList.
OligomerList waitOligomerList;
while (partialOligomerList.size())
{
CleaveOligomer *iterOligomer =
static_cast<CleaveOligomer *>(partialOligomerList.takeFirst());
// We do not ask that the oligomer be ionized yet, because we
// have to first account for potential cleavage rules! Thus we
// pass an uninitialized ionization rule with IonizeRule().
// iterOligomer->calculateMasses(*mp_calcOptions,
// *mp_ionizeRule); This was a bug in the release versions up
// to 1.6.1.
iterOligomer->calculateMasses(&m_calcOptions);
// At this point we should test if the oligomer has to be
// processed using cleavage rules.
for(int jter = 0; jter < m_cleaveOptions.ruleList()->size(); ++jter)
{
// Note that the accounting of the cleavage rule is
// performed as if the oligomer was charged 1. This is why
// we have to ionize the oligomer only after we have
// completed the determination of its atomic composition.
CleaveRule *cleaveRule = m_cleaveOptions.ruleList()->at(jter);
// qDebug() << __FILE__ << __LINE__
// << "Accounting for cleaverule:"
// << cleaveRule->name();
// qDebug() << __FILE__ << __LINE__
// << "Oligomer mono mass before:" << iterOligomer->mono();
if (!accountCleaveRule(cleaveRule, iterOligomer))
return -1;
// qDebug() << __FILE__ << __LINE__
// << "Oligomer mono mass after:" << iterOligomer->mono();
}
// At this point we can finally ionize the oligomer ! Remember
// that we have to ionize the oligomer as expected in the
// cleavage options. Because the ionization changes the values
// in the oligomer, and we need a new oligomer each time, we
// duplicate the oligomer each time we need it.
int startIonizeLevel = m_cleaveOptions.startIonizeLevel();
int endIonizeLevel = m_cleaveOptions.endIonizeLevel() + 1;
IonizeRule ionizeRule(m_ionizeRule);
for(int kter = startIonizeLevel; kter < endIonizeLevel; ++kter)
{
ionizeRule.setLevel(kter);
CleaveOligomer *newOligomer = new CleaveOligomer(*iterOligomer);
if (newOligomer->ionize(ionizeRule) == -1)
{
delete newOligomer;
return -1;
}
// The name was set already during the creation of the
// template oligomer. All we have to add to the name is the
// ionization level.
QString name = iterOligomer->name() +
QString("#z=%3").arg(newOligomer->charge());
newOligomer->setName(name);
waitOligomerList.append(newOligomer);
}
// We can delete the template oligomer that was already removed
// from the oligomerList(use of QList::takeFirst()).
delete iterOligomer;
}
// At this point we should transfer all the oligomers from the
// waitOligomerList to the initial oligomerList.
while (waitOligomerList.size())
{
Oligomer *iterOligomer = waitOligomerList.takeFirst();
partialOligomerList.append(iterOligomer);
}
// Finally transfer all the oligomers generated for this partial
// cleavage to the list of ALL the oligomers.
int oligomerCount = partialOligomerList.size();
while (partialOligomerList.size())
{
Oligomer *iterOligomer = partialOligomerList.takeFirst();
mp_oligomerList->append(iterOligomer);
}
return oligomerCount;
}
int
Cleaver::analyzeCrossLinks(OligomerList *oligomerList)
{
Q_ASSERT(oligomerList);
QList<Oligomer *> crossLinkedOligomerList;
// General overview:
// Iterate in the polymer's list of cross-links and for each
// cross-link find the oligomer that contains the first monomer
// involved in the cross-link. This first found oligomer should
// serve as a seed to pull-down all the oligomers cross-linked to
// it.
const CrossLinkList &crossLinkList = mp_polymer->crossLinkList();
for (int iter = 0; iter < crossLinkList.size(); ++iter)
{
CrossLink *crossLink = crossLinkList.at(iter);
// With that crossLink, find an oligomer that encompasses the
// first monomer of the cross-link.
const Monomer *firstMonomer = crossLink->firstMonomer();
Q_ASSERT(firstMonomer);
// What oligomer does encompass that monomer ?
int foundIndex = 0;
Oligomer *firstOligomer =
oligomerList->findOligomerEncompassing(firstMonomer, &foundIndex);
if (firstOligomer)
{
// At this point we should turn this oligomer into a
// cross-linked oligomer, so that we can continue performing its
// cross-link analysis. To do that we allocate a list of
// oligomers for this cross-linked oligomer, were we'll store
// this first oligomer and then all the "pulled-down" oligomers.
// Remove the cross-link from the main list of oligomers so
// that we do not stumble upon it in the next analysis
// steps.
oligomerList->removeAt(foundIndex);
// Set the cross-linked oligomer apart.
crossLinkedOligomerList.append(firstOligomer);
// Finally deeply scrutinize the oligomer.
analyzeCrossLinkedOligomer(firstOligomer, oligomerList);
}
else
{
// qDebug() << __FILE__ << __LINE__
// << "Cross-link at index" << iter
// << "did not find any oligomer for its first monomer "
// "partner";
}
}
// At this point we have terminated analyzing all the oligomers for
// the partial cleavage. All we have to do is move all the
// crossLinked oligomers from the crossLinkedOligomerList to
// oligomerList.
while (crossLinkedOligomerList.size())
{
Oligomer *oligomer = crossLinkedOligomerList.takeAt(0);
oligomerList->append(oligomer);
}
crossLinkedOligomerList.clear();
// Return the number of cross-linked/non-cross-linked oligomers
// alltogether.
return oligomerList->size();
}
int
Cleaver::analyzeCrossLinkedOligomer(Oligomer *oligomer,
OligomerList *oligomerList)
{
Q_ASSERT(oligomer);
Q_ASSERT(oligomerList);
const CrossLinkList &crossLinkList = mp_polymer->crossLinkList();
OligomerList clearanceOligomerList;
// 'oligomer' is the first oligomer in the cross-link series of
// oligomers. It is the "seeding" oligomer with which to pull-down
// all the others. Prepend to its name the "cl-" string to let it
// know it is cross-linked.
QString name = oligomer->name();
name.prepend("cl-");
oligomer->setName(name);
// Iterate in the 'oligomer' and for each monomer get any
// cross-linked oligomer out of the list of cross-links.
for (int iter = oligomer->startIndex();
iter < oligomer->endIndex() + 1; ++iter)
{
const Monomer *monomer = mp_polymer->at(iter);
// What crossLinks do involve this monomer ?
QList<int> crossLinkIndices;
int ret =
crossLinkList.crossLinksInvolvingMonomer(monomer,
&crossLinkIndices);
if (ret)
{
// At least one cross-link involves the monomer currently
// iterated in the oligomer being analysed.
int index = 0;
foreach(index, crossLinkIndices)
{
CrossLink *crossLink = crossLinkList.at(index);
// qDebug() << __FILE__ << __LINE__
// << crossLink->name();
// First off, we can add the cross-link to the list of
// cross-links of the oligomer(we'll need them to be
// able to perform mass calculations). Note that this is
// only copying the pointer to the actual cross-link in
// the polymer's list of cross-links. Note also that a
// cross-link might not be found more than once(the
// call below first checks that the cross-link is not
// already in the list).
if (!oligomer->addCrossLink(crossLink))
{
// qDebug() << __FILE__ << __LINE__
// << "The cross-link:"
// << crossLink->name()
// << "was already in the"
// << oligomer
// << "oligomer's list of cross-links: "
// "not duplicated.";
}
else
{
// qDebug() << __FILE__ << __LINE__
// << "The cross-link:"
// << crossLink->name()
// << "was added to the"
// << oligomer
// << "oligomer's list of cross-links.";
}
const Monomer *iterMonomer = 0;
foreach(iterMonomer, *(crossLink->monomerList()))
{
// qDebug() << __FILE__ << __LINE__
// << iterMonomer->name();
int foundIndex = 0;
Oligomer *foundOligomer =
oligomerList->findOligomerEncompassing(iterMonomer,
&foundIndex);
if (foundOligomer)
{
// qDebug() << __FILE__ << __LINE__
// << foundOligomer->name() << foundIndex;
// One oligomer in the original oligomer list
// encompasses a monomer that seems to be
// cross-linked to the 'monomer' being iterated
// in in the currently analyzed oligomer. Move
// that oligomer to the clearance list of
// oligomer that will need to be further
// analyzed later.
oligomerList->removeAt(foundIndex);
clearanceOligomerList.append(foundOligomer);
// Update the name of the oligomer with the name
// of the new foundOligomer.
QString name = QString("%1+%2")
.arg(oligomer->name())
.arg(foundOligomer->name());
oligomer->setName(name);
}
}
}
// End of
// foreach(index, crossLinkIndices)
}
}
// At this point we have one oligomer which we know is cross-linked
// at least once(with another oligomer or the cross-link is between
// two or more monomers in the same oligomer, think cyan fluorescent
// protein). If monomers in that same oligomer were cross-linked to
// other monomers in other oligomers, then these oligomers should by
// now have been moved from the original list of oligomers
//(oligomerList) to the clearance list of oligomers
//(clearanceOligomerList). We have to iterate in each oligomer of that
// clearance list and for each of its monomers, check if it has a
// cross-link to any oligomer still in the original oligomerList
//(this is what I call "pull-down" stuff). Found oligomers are
// appended to the clearanceOligomerList.
while (clearanceOligomerList.size())
{
Oligomer *iterOligomer = clearanceOligomerList.first();
for(int iter = iterOligomer->startIndex();
iter < iterOligomer->endIndex() + 1; ++iter)
{
const Monomer *monomer = mp_polymer->at(iter);
// qDebug() << __FILE__ << __LINE__
// << monomer->name();
// What crossLinks do involve this monomer ?
QList<int> crossLinkIndices;
int ret =
crossLinkList.crossLinksInvolvingMonomer(monomer,
&crossLinkIndices);
if (ret)
{
// At least one cross-link involves the monomer currently
// iterated in the iterOligomer being analysed.
int index = 0;
foreach(index, crossLinkIndices)
{
CrossLink *crossLink = crossLinkList.at(index);
// qDebug() << __FILE__ << __LINE__
// << crossLink->name();
// First off, we can add the cross-link to the list of
// cross-links of the oligomer(we'll need them to be
// able to perform mass calculations). Note that this is
// only copying the pointer to the actual cross-link in
// the polymer's list of cross-links. Note also that a
// cross-link might not be found more than once(the
// call below first checks that the cross-link is not
// already in the list).
if (!oligomer->addCrossLink(crossLink))
{
// qDebug() << __FILE__ << __LINE__
// << "The cross-link:"
// << crossLink->name()
// << "was already in the"
// << oligomer
// << "oligomer's list of cross-links: "
// "not duplicated.";
}
else
{
// qDebug() << __FILE__ << __LINE__
// << "The cross-link:"
// << crossLink->name()
// << "was added to the"
// << oligomer
// << "oligomer's list of cross-links.";
}
const Monomer *iterMonomer = 0;
foreach(iterMonomer, *(crossLink->monomerList()))
{
// qDebug() << __FILE__ << __LINE__
// << iterMonomer->name();
int foundIndex = 0;
Oligomer *foundOligomer =
oligomerList->findOligomerEncompassing(iterMonomer,
&foundIndex);
if (foundOligomer)
{
// qDebug() << __FILE__ << __LINE__
// << foundOligomer->name() << foundIndex;
// One oligomer in the original oligomer list
// encompasses a monomer that seems to be
// cross-linked to the 'monomer' being iterated
// in in the currently analyzed oligomer. Move
// that oligomer to the clearance list of
// oligomer that will need to be further
// analyzed later.
oligomerList->removeAt(foundIndex);
clearanceOligomerList.append(foundOligomer);
// Update the name of the oligomer with the name
// of the new foundOligomer.
QString name = QString("%1+%2")
.arg(oligomer->name())
.arg(foundOligomer->name());
oligomer->setName(name);
}
}
}
// End of
// foreach(index, crossLinkIndices)
}
// End of(ret) ie cross-links involved monomer
}
// End of
// for (int iter = iterOligomer->startIndex();
// iter < iterOligomer->endIndex() + 1; ++iter)
// At this point this quarantinized oligomer might be removed
// from the clearance clearanceOligomerList and its coordinates
// be appended to the 'oligomer' list of coordinates. Then, the
// quanrantinized oligomer might be destroyed.
clearanceOligomerList.removeFirst();
oligomer->appendCoordinates(iterOligomer);
delete iterOligomer;
}
// At this point, all the oligomers in the clearance oligomer list
// have all been dealt with, return the number of cross-linked
// oligomers in this oligomer.
// for (int iter = 0; iter < oligomer->crossLinkList()->size(); ++iter)
// qDebug() << __FILE__ << __LINE__
// << "Finished for oligomer:" <<
// oligomer->crossLinkList()->at(iter)->name();
return static_cast<CoordinateList *>(oligomer)->size();
}
void
Cleaver::emptyOligomerList()
{
while (!mp_oligomerList->isEmpty())
{
delete mp_oligomerList->first();
}
}
} // namespace massXpert
|