5 * Created by Pat Schloss on 7/15/10.
6 * Copyright 2010 Schloss Lab. All rights reserved.
10 #include "seqerrorcommand.h"
11 #include "reportfile.h"
12 #include "qualityscores.h"
13 #include "refchimeratest.h"
15 //**********************************************************************************************************************
16 vector<string> SeqErrorCommand::getValidParameters(){
18 string Array[] = {"query", "reference", "name", "qfile", "report", "threshold", "inputdir", "outputdir"};
19 vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
23 m->errorOut(e, "SeqErrorCommand", "getValidParameters");
27 //**********************************************************************************************************************
28 SeqErrorCommand::SeqErrorCommand(){
30 abort = true; calledHelp = true;
31 vector<string> tempOutNames;
32 outputTypes["error.summary"] = tempOutNames;
33 outputTypes["error.seq"] = tempOutNames;
34 outputTypes["error.quality"] = tempOutNames;
35 outputTypes["error.qual.forward"] = tempOutNames;
36 outputTypes["error.qual.reverse"] = tempOutNames;
37 outputTypes["error.forward"] = tempOutNames;
38 outputTypes["error.reverse"] = tempOutNames;
39 outputTypes["error.count"] = tempOutNames;
40 outputTypes["error.matrix"] = tempOutNames;
43 m->errorOut(e, "SeqErrorCommand", "SeqErrorCommand");
47 //**********************************************************************************************************************
48 vector<string> SeqErrorCommand::getRequiredParameters(){
50 string Array[] = {"query","reference"};
51 vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
55 m->errorOut(e, "SeqErrorCommand", "getRequiredParameters");
59 //**********************************************************************************************************************
60 vector<string> SeqErrorCommand::getRequiredFiles(){
62 vector<string> myArray;
66 m->errorOut(e, "SeqErrorCommand", "getRequiredFiles");
70 //***************************************************************************************************************
72 SeqErrorCommand::SeqErrorCommand(string option) {
75 abort = false; calledHelp = false;
77 //allow user to run help
78 if(option == "help") { help(); abort = true; calledHelp = true; }
83 //valid paramters for this command
84 string AlignArray[] = {"query", "reference", "name", "qfile", "report", "threshold", "inputdir", "ignorechimeras", "outputdir"};
86 vector<string> myArray (AlignArray, AlignArray+(sizeof(AlignArray)/sizeof(string)));
88 OptionParser parser(option);
89 map<string,string> parameters = parser.getParameters();
91 ValidParameters validParameter;
92 map<string,string>::iterator it;
94 //check to make sure all parameters are valid for command
95 for (it = parameters.begin(); it != parameters.end(); it++) {
96 if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; }
99 //initialize outputTypes
100 vector<string> tempOutNames;
101 outputTypes["error.summary"] = tempOutNames;
102 outputTypes["error.seq"] = tempOutNames;
103 outputTypes["error.quality"] = tempOutNames;
104 outputTypes["error.qual.forward"] = tempOutNames;
105 outputTypes["error.qual.reverse"] = tempOutNames;
106 outputTypes["error.forward"] = tempOutNames;
107 outputTypes["error.reverse"] = tempOutNames;
108 outputTypes["error.count"] = tempOutNames;
109 outputTypes["error.matrix"] = tempOutNames;
112 //if the user changes the input directory command factory will send this info to us in the output parameter
113 string inputDir = validParameter.validFile(parameters, "inputdir", false);
114 if (inputDir == "not found"){ inputDir = ""; }
117 it = parameters.find("query");
118 //user has given a template file
119 if(it != parameters.end()){
120 path = m->hasPath(it->second);
121 //if the user has not given a path then, add inputdir. else leave path alone.
122 if (path == "") { parameters["query"] = inputDir + it->second; }
125 it = parameters.find("reference");
126 //user has given a template file
127 if(it != parameters.end()){
128 path = m->hasPath(it->second);
129 //if the user has not given a path then, add inputdir. else leave path alone.
130 if (path == "") { parameters["reference"] = inputDir + it->second; }
133 it = parameters.find("name");
134 //user has given a names file
135 if(it != parameters.end()){
136 path = m->hasPath(it->second);
137 //if the user has not given a path then, add inputdir. else leave path alone.
138 if (path == "") { parameters["name"] = inputDir + it->second; }
141 it = parameters.find("qfile");
142 //user has given a quality score file
143 if(it != parameters.end()){
144 path = m->hasPath(it->second);
145 //if the user has not given a path then, add inputdir. else leave path alone.
146 if (path == "") { parameters["qfile"] = inputDir + it->second; }
149 it = parameters.find("report");
150 //user has given a alignment report file
151 if(it != parameters.end()){
152 path = m->hasPath(it->second);
153 //if the user has not given a path then, add inputdir. else leave path alone.
154 if (path == "") { parameters["report"] = inputDir + it->second; }
158 //check for required parameters
159 queryFileName = validParameter.validFile(parameters, "query", true);
160 if (queryFileName == "not found") { m->mothurOut("query is a required parameter for the seq.error command."); m->mothurOutEndLine(); abort = true; }
161 else if (queryFileName == "not open") { abort = true; }
163 referenceFileName = validParameter.validFile(parameters, "reference", true);
164 if (referenceFileName == "not found") { m->mothurOut("reference is a required parameter for the seq.error command."); m->mothurOutEndLine(); abort = true; }
165 else if (referenceFileName == "not open") { abort = true; }
168 //check for optional parameters
169 namesFileName = validParameter.validFile(parameters, "name", true);
170 if(namesFileName == "not found"){ namesFileName = ""; }
172 qualFileName = validParameter.validFile(parameters, "qfile", true);
173 if(qualFileName == "not found"){ qualFileName = ""; }
175 reportFileName = validParameter.validFile(parameters, "report", true);
176 if(reportFileName == "not found"){ reportFileName = ""; }
178 if((reportFileName != "" && qualFileName == "") || (reportFileName == "" && qualFileName != "")){
179 m->mothurOut("if you use either a qual file or a report file, you have to have both.");
180 m->mothurOutEndLine();
184 outputDir = validParameter.validFile(parameters, "outputdir", false);
185 if (outputDir == "not found"){
187 outputDir += m->hasPath(queryFileName); //if user entered a file with a path then preserve it
190 //check for optional parameter and set defaults
191 // ...at some point should added some additional type checking...
192 temp = validParameter.validFile(parameters, "threshold", false); if (temp == "not found") { temp = "1.00"; }
193 convert(temp, threshold);
195 temp = validParameter.validFile(parameters, "ignorechimeras", false); if (temp == "not found") { temp = "1"; }
196 convert(temp, ignoreChimeras);
198 substitutionMatrix.resize(6);
199 for(int i=0;i<6;i++){ substitutionMatrix[i].resize(6,0); }
202 catch(exception& e) {
203 m->errorOut(e, "SeqErrorCommand", "SeqErrorCommand");
208 //**********************************************************************************************************************
210 void SeqErrorCommand::help(){
212 m->mothurOut("The seq.error command reads a query alignment file and a reference alignment file and creates .....\n");
213 m->mothurOut("Example seq.error(...).\n");
214 m->mothurOut("Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n");
215 m->mothurOut("For more details please check out the wiki http://www.mothur.org/wiki/seq.error .\n\n");
217 catch(exception& e) {
218 m->errorOut(e, "SeqErrorCommand", "help");
223 //***************************************************************************************************************
225 SeqErrorCommand::~SeqErrorCommand(){ /* void */ }
227 //***************************************************************************************************************
229 int SeqErrorCommand::execute(){
231 if (abort == true) { if (calledHelp) { return 0; } return 2; }
233 string errorSummaryFileName = queryFileName.substr(0,queryFileName.find_last_of('.')) + ".error.summary";
234 m->openOutputFile(errorSummaryFileName, errorSummaryFile);
235 outputNames.push_back(errorSummaryFileName); outputTypes["error.summary"].push_back(errorSummaryFileName);
238 string errorSeqFileName = queryFileName.substr(0,queryFileName.find_last_of('.')) + ".error.seq";
239 m->openOutputFile(errorSeqFileName, errorSeqFile);
240 outputNames.push_back(errorSeqFileName); outputTypes["error.seq"].push_back(errorSeqFileName);
242 getReferences(); //read in reference sequences - make sure there's no ambiguous bases
244 map<string, int> weights;
245 if(namesFileName != ""){ weights = getWeights(); }
248 m->openInputFile(queryFileName, queryFile);
254 QualityScores quality;
255 vector<vector<int> > qualForwardMap;
256 vector<vector<int> > qualReverseMap;
258 if(qualFileName != "" && reportFileName != ""){
259 m->openInputFile(qualFileName, qualFile);
260 report = ReportFile(reportFile, reportFileName);
262 qualForwardMap.resize(1000);
263 qualReverseMap.resize(1000);
264 for(int i=0;i<1000;i++){
265 qualForwardMap[i].assign(100,0);
266 qualReverseMap[i].assign(100,0);
271 int totalMatches = 0;
273 vector<int> misMatchCounts(11, 0);
277 map<string, int>::iterator it;
278 map<char, vector<int> > qScoreErrorMap;
279 qScoreErrorMap['m'].assign(41, 0);
280 qScoreErrorMap['s'].assign(41, 0);
281 qScoreErrorMap['i'].assign(41, 0);
282 qScoreErrorMap['a'].assign(41, 0);
284 map<char, vector<int> > errorForward;
285 errorForward['m'].assign(1000,0);
286 errorForward['s'].assign(1000,0);
287 errorForward['i'].assign(1000,0);
288 errorForward['d'].assign(1000,0);
289 errorForward['a'].assign(1000,0);
291 map<char, vector<int> > errorReverse;
292 errorReverse['m'].assign(1000,0);
293 errorReverse['s'].assign(1000,0);
294 errorReverse['i'].assign(1000,0);
295 errorReverse['d'].assign(1000,0);
296 errorReverse['a'].assign(1000,0);
299 string errorChimeraFileName = queryFileName.substr(0,queryFileName.find_last_of('.')) + ".error.chimera";
300 RefChimeraTest chimeraTest(referenceSeqs, errorChimeraFileName);
301 outputNames.push_back(errorChimeraFileName); outputTypes["error.chimera"].push_back(errorChimeraFileName);
303 vector<string> megaAlignVector(numRefs, "");
310 if (m->control_pressed) { errorSummaryFile.close(); errorSeqFile.close(); for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; }
312 Sequence query(queryFile);
313 cout << "gotQuery" << endl;
315 int numParentSeqs = chimeraTest.analyzeQuery(query.getName(), query.getAligned());
316 int closestRefIndex = chimeraTest.getClosestRefIndex();
318 if(numParentSeqs > 1 && ignoreChimeras == 1) { ignoreSeq = 1; }
319 else { ignoreSeq = 0; }
321 Compare minCompare = getErrors(query, referenceSeqs[closestRefIndex]);
323 if(namesFileName != ""){
324 it = weights.find(query.getName());
325 minCompare.weight = it->second;
327 else{ minCompare.weight = 1; }
329 printErrorData(minCompare, numParentSeqs);
333 for(int i=0;i<minCompare.total;i++){
334 char letter = minCompare.sequence[i];
336 errorForward[letter][i] += minCompare.weight;
337 errorReverse[letter][minCompare.total-i-1] += minCompare.weight;
341 if(qualFileName != "" && reportFileName != ""){
342 report = ReportFile(reportFile);
343 cout << "gotReport" << endl;
345 // int origLength = report.getQueryLength();
346 int startBase = report.getQueryStart();
347 int endBase = report.getQueryEnd();
349 quality = QualityScores(qualFile);
350 cout << "gotQuality" << endl;
353 cout << "not ignoring" << endl;
354 quality.updateQScoreErrorMap(qScoreErrorMap, minCompare.sequence, startBase, endBase, minCompare.weight);
355 cout << "updateQScoreErrorMap" << endl;
356 quality.updateForwardMap(qualForwardMap, startBase, endBase, minCompare.weight);
357 cout << "updateForwardMap" << endl;
358 quality.updateReverseMap(qualReverseMap, startBase, endBase, minCompare.weight);
359 cout << "updateReverseMap" << endl;
363 if(minCompare.errorRate < threshold && !ignoreSeq){
364 totalBases += (minCompare.total * minCompare.weight);
365 totalMatches += minCompare.matches * minCompare.weight;
366 if(minCompare.mismatches > maxMismatch){
367 maxMismatch = minCompare.mismatches;
368 misMatchCounts.resize(maxMismatch + 1, 0);
370 misMatchCounts[minCompare.mismatches] += minCompare.weight;
373 megaAlignVector[closestRefIndex] += query.getInlineSeq() + '\n';
377 cout << "end of loop:\t" << index << endl;
379 if(index % 1000 == 0){ cout << index << endl; }
382 errorSummaryFile.close();
383 errorSeqFile.close();
385 if(qualFileName != "" && reportFileName != ""){
386 printErrorQuality(qScoreErrorMap);
387 printQualityFR(qualForwardMap, qualReverseMap);
390 printErrorFRFile(errorForward, errorReverse);
392 if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; }
394 string errorCountFileName = queryFileName.substr(0,queryFileName.find_last_of('.')) + ".error.count";
395 ofstream errorCountFile;
396 m->openOutputFile(errorCountFileName, errorCountFile);
397 outputNames.push_back(errorCountFileName); outputTypes["error.count"].push_back(errorCountFileName);
398 m->mothurOut("Overall error rate:\t" + toString((double)(totalBases - totalMatches) / (double)totalBases) + "\n\n");
399 m->mothurOut("Errors\tSequences\n");
400 errorCountFile << "Errors\tSequences\n";
401 for(int i=0;i<misMatchCounts.size();i++){
402 m->mothurOut(toString(i) + '\t' + toString(misMatchCounts[i]) + '\n');
403 errorCountFile << i << '\t' << misMatchCounts[i] << endl;
405 errorCountFile.close();
407 if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; }
411 string megAlignmentFileName = queryFileName.substr(0,queryFileName.find_last_of('.')) + ".error.ref-query";
412 ofstream megAlignmentFile;
413 m->openOutputFile(megAlignmentFileName, megAlignmentFile);
414 outputNames.push_back(megAlignmentFileName); outputTypes["error.ref-query"].push_back(megAlignmentFileName);
416 for(int i=0;i<numRefs;i++){
417 megAlignmentFile << referenceSeqs[i].getInlineSeq() << endl;
418 megAlignmentFile << megaAlignVector[i] << endl;
422 m->mothurOutEndLine();
423 m->mothurOut("Output File Names: "); m->mothurOutEndLine();
424 for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); }
425 m->mothurOutEndLine();
429 catch(exception& e) {
430 m->errorOut(e, "SeqErrorCommand", "execute");
435 //***************************************************************************************************************
437 void SeqErrorCommand::getReferences(){
440 ifstream referenceFile;
441 m->openInputFile(referenceFileName, referenceFile);
443 int numAmbigSeqs = 0;
446 int minEndPos = 100000;
448 while(referenceFile){
449 Sequence currentSeq(referenceFile);
450 int numAmbigs = currentSeq.getAmbigBases();
451 if(numAmbigs > 0){ numAmbigSeqs++; }
453 int startPos = currentSeq.getStartPos();
454 if(startPos > maxStartPos) { maxStartPos = startPos; }
456 int endPos = currentSeq.getEndPos();
457 if(endPos < minEndPos) { minEndPos = endPos; }
458 referenceSeqs.push_back(currentSeq);
459 m->gobble(referenceFile);
461 referenceFile.close();
462 numRefs = referenceSeqs.size();
465 for(int i=0;i<numRefs;i++){
466 referenceSeqs[i].padToPos(maxStartPos);
467 referenceSeqs[i].padFromPos(minEndPos);
470 if(numAmbigSeqs != 0){
471 m->mothurOut("Warning: " + toString(numAmbigSeqs) + " reference sequences have ambiguous bases, these bases will be ignored\n");
475 catch(exception& e) {
476 m->errorOut(e, "SeqErrorCommand", "getReferences");
481 //***************************************************************************************************************
483 Compare SeqErrorCommand::getErrors(Sequence query, Sequence reference){
485 if(query.getAlignLength() != reference.getAlignLength()){
486 m->mothurOut("Warning: " + toString(query.getName()) + " and " + toString(reference.getName()) + " are different lengths\n");
488 int alignLength = query.getAlignLength();
490 string q = query.getAligned();
491 string r = reference.getAligned();
496 for(int i=0;i<alignLength;i++){
497 if(r[i] != 'N' && q[i] != '.' && r[i] != '.' && (q[i] != '-' || r[i] != '-')){ // no missing data and no double gaps
501 if(r[i] == 'A'){ errors.AA++; errors.matches++; errors.sequence += 'm'; }
502 if(r[i] == 'T'){ errors.AT++; errors.sequence += 's'; }
503 if(r[i] == 'G'){ errors.AG++; errors.sequence += 's'; }
504 if(r[i] == 'C'){ errors.AC++; errors.sequence += 's'; }
505 if(r[i] == '-'){ errors.Ai++; errors.sequence += 'i'; }
507 else if(q[i] == 'T'){
508 if(r[i] == 'A'){ errors.TA++; errors.sequence += 's'; }
509 if(r[i] == 'T'){ errors.TT++; errors.matches++; errors.sequence += 'm'; }
510 if(r[i] == 'G'){ errors.TG++; errors.sequence += 's'; }
511 if(r[i] == 'C'){ errors.TC++; errors.sequence += 's'; }
512 if(r[i] == '-'){ errors.Ti++; errors.sequence += 'i'; }
514 else if(q[i] == 'G'){
515 if(r[i] == 'A'){ errors.GA++; errors.sequence += 's'; }
516 if(r[i] == 'T'){ errors.GT++; errors.sequence += 's'; }
517 if(r[i] == 'G'){ errors.GG++; errors.matches++; errors.sequence += 'm'; }
518 if(r[i] == 'C'){ errors.GC++; errors.sequence += 's'; }
519 if(r[i] == '-'){ errors.Gi++; errors.sequence += 'i'; }
521 else if(q[i] == 'C'){
522 if(r[i] == 'A'){ errors.CA++; errors.sequence += 's'; }
523 if(r[i] == 'T'){ errors.CT++; errors.sequence += 's'; }
524 if(r[i] == 'G'){ errors.CG++; errors.sequence += 's'; }
525 if(r[i] == 'C'){ errors.CC++; errors.matches++; errors.sequence += 'm'; }
526 if(r[i] == '-'){ errors.Ci++; errors.sequence += 'i'; }
528 else if(q[i] == 'N'){
529 if(r[i] == 'A'){ errors.NA++; errors.sequence += 'a'; }
530 if(r[i] == 'T'){ errors.NT++; errors.sequence += 'a'; }
531 if(r[i] == 'G'){ errors.NG++; errors.sequence += 'a'; }
532 if(r[i] == 'C'){ errors.NC++; errors.sequence += 'a'; }
533 if(r[i] == '-'){ errors.Ni++; errors.sequence += 'a'; }
535 else if(q[i] == '-' && r[i] != '-'){
536 if(r[i] == 'A'){ errors.dA++; errors.sequence += 'd'; }
537 if(r[i] == 'T'){ errors.dT++; errors.sequence += 'd'; }
538 if(r[i] == 'G'){ errors.dG++; errors.sequence += 'd'; }
539 if(r[i] == 'C'){ errors.dC++; errors.sequence += 'd'; }
544 else if(q[i] == '.' && r[i] != '.'){ // reference extends beyond query
545 if(started == 1){ break; }
547 else if(q[i] != '.' && r[i] == '.'){ // query extends beyond reference
548 if(started == 1){ break; }
550 else if(q[i] == '.' && r[i] == '.'){ // both are missing data
551 if(started == 1){ break; }
555 errors.mismatches = errors.total-errors.matches;
556 errors.errorRate = (double)(errors.total-errors.matches) / (double)errors.total;
557 errors.queryName = query.getName();
558 errors.refName = reference.getName();
562 catch(exception& e) {
563 m->errorOut(e, "SeqErrorCommand", "getErrors");
568 //***************************************************************************************************************
570 map<string, int> SeqErrorCommand::getWeights(){
572 m->openInputFile(namesFileName, nameFile);
575 string redundantSeqs;
576 map<string, int> nameCountMap;
579 nameFile >> seqName >> redundantSeqs;
580 nameCountMap[seqName] = m->getNumNames(redundantSeqs);
587 //***************************************************************************************************************
589 void SeqErrorCommand::printErrorHeader(){
591 errorSummaryFile << "query\treference\tweight\t";
592 errorSummaryFile << "AA\tAT\tAG\tAC\tTA\tTT\tTG\tTC\tGA\tGT\tGG\tGC\tCA\tCT\tCG\tCC\tNA\tNT\tNG\tNC\tAi\tTi\tGi\tCi\tNi\tdA\tdT\tdG\tdC\t";
593 errorSummaryFile << "insertions\tdeletions\tsubstitutions\tambig\tmatches\tmismatches\ttotal\terror\tnumparents\n";
595 errorSummaryFile << setprecision(6);
596 errorSummaryFile.setf(ios::fixed);
598 catch(exception& e) {
599 m->errorOut(e, "SeqErrorCommand", "printErrorHeader");
604 //***************************************************************************************************************
606 void SeqErrorCommand::printErrorData(Compare error, int numParentSeqs){
609 errorSummaryFile << error.queryName << '\t' << error.refName << '\t' << error.weight << '\t';
610 errorSummaryFile << error.AA << '\t' << error.AT << '\t' << error.AG << '\t' << error.AC << '\t';
611 errorSummaryFile << error.TA << '\t' << error.TT << '\t' << error.TG << '\t' << error.TC << '\t';
612 errorSummaryFile << error.GA << '\t' << error.GT << '\t' << error.GG << '\t' << error.GC << '\t';
613 errorSummaryFile << error.CA << '\t' << error.CT << '\t' << error.CG << '\t' << error.CC << '\t';
614 errorSummaryFile << error.NA << '\t' << error.NT << '\t' << error.NG << '\t' << error.NC << '\t';
615 errorSummaryFile << error.Ai << '\t' << error.Ti << '\t' << error.Gi << '\t' << error.Ci << '\t' << error.Ni << '\t';
616 errorSummaryFile << error.dA << '\t' << error.dT << '\t' << error.dG << '\t' << error.dC << '\t';
618 errorSummaryFile << error.Ai + error.Ti + error.Gi + error.Ci << '\t'; //insertions
619 errorSummaryFile << error.dA + error.dT + error.dG + error.dC << '\t'; //deletions
620 errorSummaryFile << error.mismatches - (error.Ai + error.Ti + error.Gi + error.Ci) - (error.dA + error.dT + error.dG + error.dC) - (error.NA + error.NT + error.NG + error.NC + error.Ni) << '\t'; //substitutions
621 errorSummaryFile << error.NA + error.NT + error.NG + error.NC + error.Ni << '\t'; //ambiguities
622 errorSummaryFile << error.matches << '\t' << error.mismatches << '\t' << error.total << '\t' << error.errorRate << '\t' << numParentSeqs << endl;
624 errorSeqFile << '>' << error.queryName << "\tref:" << error.refName << '\n' << error.sequence << endl;
626 int a=0; int t=1; int g=2; int c=3;
629 if(numParentSeqs == 1 || ignoreChimeras == 0){
630 substitutionMatrix[a][a] += error.weight * error.AA;
631 substitutionMatrix[a][t] += error.weight * error.TA;
632 substitutionMatrix[a][g] += error.weight * error.GA;
633 substitutionMatrix[a][c] += error.weight * error.CA;
634 substitutionMatrix[a][gap] += error.weight * error.dA;
635 substitutionMatrix[a][n] += error.weight * error.NA;
637 substitutionMatrix[t][a] += error.weight * error.AT;
638 substitutionMatrix[t][t] += error.weight * error.TT;
639 substitutionMatrix[t][g] += error.weight * error.GT;
640 substitutionMatrix[t][c] += error.weight * error.CT;
641 substitutionMatrix[t][gap] += error.weight * error.dT;
642 substitutionMatrix[t][n] += error.weight * error.NT;
644 substitutionMatrix[g][a] += error.weight * error.AG;
645 substitutionMatrix[g][t] += error.weight * error.TG;
646 substitutionMatrix[g][g] += error.weight * error.GG;
647 substitutionMatrix[g][c] += error.weight * error.CG;
648 substitutionMatrix[g][gap] += error.weight * error.dG;
649 substitutionMatrix[g][n] += error.weight * error.NG;
651 substitutionMatrix[c][a] += error.weight * error.AC;
652 substitutionMatrix[c][t] += error.weight * error.TC;
653 substitutionMatrix[c][g] += error.weight * error.GC;
654 substitutionMatrix[c][c] += error.weight * error.CC;
655 substitutionMatrix[c][gap] += error.weight * error.dC;
656 substitutionMatrix[c][n] += error.weight * error.NC;
658 substitutionMatrix[gap][a] += error.weight * error.Ai;
659 substitutionMatrix[gap][t] += error.weight * error.Ti;
660 substitutionMatrix[gap][g] += error.weight * error.Gi;
661 substitutionMatrix[gap][c] += error.weight * error.Ci;
662 substitutionMatrix[gap][n] += error.weight * error.Ni;
665 catch(exception& e) {
666 m->errorOut(e, "SeqErrorCommand", "printErrorData");
671 //***************************************************************************************************************
673 void SeqErrorCommand::printSubMatrix(){
675 string subMatrixFileName = queryFileName.substr(0,queryFileName.find_last_of('.')) + ".error.matrix";
676 ofstream subMatrixFile;
677 m->openOutputFile(subMatrixFileName, subMatrixFile);
678 outputNames.push_back(subMatrixFileName); outputTypes["error.matrix"].push_back(subMatrixFileName);
679 vector<string> bases(6);
686 vector<int> refSums(5,1);
688 for(int i=0;i<5;i++){
689 subMatrixFile << "\tr" << bases[i];
691 for(int j=0;j<6;j++){
692 refSums[i] += substitutionMatrix[i][j];
695 subMatrixFile << endl;
697 for(int i=0;i<6;i++){
698 subMatrixFile << 'q' << bases[i];
699 for(int j=0;j<5;j++){
700 subMatrixFile << '\t' << substitutionMatrix[j][i];
702 subMatrixFile << endl;
705 subMatrixFile << "total";
706 for(int i=0;i<5;i++){
707 subMatrixFile << '\t' << refSums[i];
709 subMatrixFile << endl;
710 subMatrixFile.close();
712 catch(exception& e) {
713 m->errorOut(e, "SeqErrorCommand", "printSubMatrix");
717 //***************************************************************************************************************
719 void SeqErrorCommand::printErrorFRFile(map<char, vector<int> > errorForward, map<char, vector<int> > errorReverse){
721 string errorForwardFileName = queryFileName.substr(0,queryFileName.find_last_of('.')) + ".error.seq.forward";
722 ofstream errorForwardFile;
723 m->openOutputFile(errorForwardFileName, errorForwardFile);
724 outputNames.push_back(errorForwardFileName); outputTypes["error.forward"].push_back(errorForwardFileName);
726 errorForwardFile << "position\ttotalseqs\tmatch\tsubstitution\tinsertion\tdeletion\tambiguous" << endl;
727 for(int i=0;i<1000;i++){
728 float match = (float)errorForward['m'][i];
729 float subst = (float)errorForward['s'][i];
730 float insert = (float)errorForward['i'][i];
731 float del = (float)errorForward['d'][i];
732 float amb = (float)errorForward['a'][i];
733 float total = match + subst + insert + del + amb;
734 if(total == 0){ break; }
735 errorForwardFile << i+1 << '\t' << total << '\t' << match/total << '\t' << subst/total << '\t' << insert/total << '\t' << del/total << '\t' << amb/total << endl;
737 errorForwardFile.close();
739 string errorReverseFileName = queryFileName.substr(0,queryFileName.find_last_of('.')) + ".error.seq.reverse";
740 ofstream errorReverseFile;
741 m->openOutputFile(errorReverseFileName, errorReverseFile);
742 outputNames.push_back(errorReverseFileName); outputTypes["error.reverse"].push_back(errorReverseFileName);
744 errorReverseFile << "position\ttotalseqs\tmatch\tsubstitution\tinsertion\tdeletion\tambiguous" << endl;
745 for(int i=0;i<1000;i++){
746 float match = (float)errorReverse['m'][i];
747 float subst = (float)errorReverse['s'][i];
748 float insert = (float)errorReverse['i'][i];
749 float del = (float)errorReverse['d'][i];
750 float amb = (float)errorReverse['a'][i];
751 float total = match + subst + insert + del + amb;
752 if(total == 0){ break; }
753 errorReverseFile << i+1 << '\t' << total << '\t' << match/total << '\t' << subst/total << '\t' << insert/total << '\t' << del/total << '\t' << amb/total << endl;
755 errorReverseFile.close();
757 catch(exception& e) {
758 m->errorOut(e, "SeqErrorCommand", "printErrorFRFile");
763 //***************************************************************************************************************
765 void SeqErrorCommand::printErrorQuality(map<char, vector<int> > qScoreErrorMap){
768 string errorQualityFileName = queryFileName.substr(0,queryFileName.find_last_of('.')) + ".error.quality";
769 ofstream errorQualityFile;
770 m->openOutputFile(errorQualityFileName, errorQualityFile);
771 outputNames.push_back(errorQualityFileName); outputTypes["error.quality"].push_back(errorQualityFileName);
773 errorQualityFile << "qscore\tmatches\tsubstitutions\tinsertions\tambiguous" << endl;
774 for(int i=0;i<41;i++){
775 errorQualityFile << i << '\t' << qScoreErrorMap['m'][i] << '\t' << qScoreErrorMap['s'][i] << '\t' << qScoreErrorMap['i'][i] << '\t'<< qScoreErrorMap['a'][i] << endl;
777 errorQualityFile.close();
779 catch(exception& e) {
780 m->errorOut(e, "SeqErrorCommand", "printErrorFRFile");
786 //***************************************************************************************************************
788 void SeqErrorCommand::printQualityFR(vector<vector<int> > qualForwardMap, vector<vector<int> > qualReverseMap){
795 for(int i=0;i<qualForwardMap.size();i++){
796 for(int j=0;j<qualForwardMap[i].size();j++){
797 if(qualForwardMap[i][j] != 0){
798 if(lastRow < i) { lastRow = i+2; }
799 if(lastColumn < j) { lastColumn = j+2; }
804 string qualityForwardFileName = queryFileName.substr(0,queryFileName.find_last_of('.')) + ".error.qual.forward";
805 ofstream qualityForwardFile;
806 m->openOutputFile(qualityForwardFileName, qualityForwardFile);
807 outputNames.push_back(qualityForwardFileName); outputTypes["error.qual.forward"].push_back(qualityForwardFileName);
809 for(int i=0;i<lastColumn;i++){ qualityForwardFile << '\t' << i; } qualityForwardFile << endl;
811 for(int i=0;i<lastRow;i++){
812 qualityForwardFile << i+1;
813 for(int j=0;j<lastColumn;j++){
814 qualityForwardFile << '\t' << qualForwardMap[i][j];
817 qualityForwardFile << endl;
819 qualityForwardFile.close();
822 string qualityReverseFileName = queryFileName.substr(0,queryFileName.find_last_of('.')) + ".error.qual.reverse";
823 ofstream qualityReverseFile;
824 m->openOutputFile(qualityReverseFileName, qualityReverseFile);
825 outputNames.push_back(qualityReverseFileName); outputTypes["error.qual.reverse"].push_back(qualityReverseFileName);
827 for(int i=0;i<lastColumn;i++){ qualityReverseFile << '\t' << i; } qualityReverseFile << endl;
828 for(int i=0;i<lastRow;i++){
830 qualityReverseFile << i+1;
831 for(int j=0;j<lastColumn;j++){
832 qualityReverseFile << '\t' << qualReverseMap[i][j];
834 qualityReverseFile << endl;
836 qualityReverseFile.close();
838 catch(exception& e) {
839 m->errorOut(e, "SeqErrorCommand", "printErrorFRFile");
845 //***************************************************************************************************************