5 * Created by Pat Schloss on 6/6/09.
6 * Copyright 2009 Patrick D. Schloss. All rights reserved.
10 #include "trimseqscommand.h"
11 #include "needlemanoverlap.hpp"
13 //**********************************************************************************************************************
14 vector<string> TrimSeqsCommand::getValidParameters(){
16 string Array[] = {"fasta", "flip", "oligos", "maxambig", "maxhomop", "group","minlength", "maxlength", "qfile",
17 "qthreshold", "qwindowaverage", "qstepsize", "qwindowsize", "qaverage", "rollaverage", "allfiles", "qtrim","tdiffs", "pdiffs", "bdiffs", "processors", "outputdir","inputdir"};
18 vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
22 m->errorOut(e, "TrimSeqsCommand", "getValidParameters");
26 //**********************************************************************************************************************
27 TrimSeqsCommand::TrimSeqsCommand(){
30 //initialize outputTypes
31 vector<string> tempOutNames;
32 outputTypes["fasta"] = tempOutNames;
33 outputTypes["qual"] = tempOutNames;
34 outputTypes["group"] = tempOutNames;
37 m->errorOut(e, "TrimSeqsCommand", "TrimSeqsCommand");
41 //**********************************************************************************************************************
42 vector<string> TrimSeqsCommand::getRequiredParameters(){
44 string Array[] = {"fasta"};
45 vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
49 m->errorOut(e, "TrimSeqsCommand", "getRequiredParameters");
53 //**********************************************************************************************************************
54 vector<string> TrimSeqsCommand::getRequiredFiles(){
56 vector<string> myArray;
60 m->errorOut(e, "TrimSeqsCommand", "getRequiredFiles");
64 //***************************************************************************************************************
66 TrimSeqsCommand::TrimSeqsCommand(string option) {
72 //allow user to run help
73 if(option == "help") { help(); abort = true; }
76 //valid paramters for this command
77 string AlignArray[] = {"fasta", "flip", "group","oligos", "maxambig", "maxhomop", "minlength", "maxlength", "qfile",
78 "qthreshold", "qwindowaverage", "qstepsize", "qwindowsize", "qaverage", "rollaverage", "allfiles", "qtrim","tdiffs", "pdiffs", "bdiffs", "processors", "outputdir","inputdir"};
80 vector<string> myArray (AlignArray, AlignArray+(sizeof(AlignArray)/sizeof(string)));
82 OptionParser parser(option);
83 map<string,string> parameters = parser.getParameters();
85 ValidParameters validParameter;
86 map<string,string>::iterator it;
88 //check to make sure all parameters are valid for command
89 for (it = parameters.begin(); it != parameters.end(); it++) {
90 if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; }
93 //initialize outputTypes
94 vector<string> tempOutNames;
95 outputTypes["fasta"] = tempOutNames;
96 outputTypes["qual"] = tempOutNames;
97 outputTypes["group"] = tempOutNames;
99 //if the user changes the input directory command factory will send this info to us in the output parameter
100 string inputDir = validParameter.validFile(parameters, "inputdir", false);
101 if (inputDir == "not found"){ inputDir = ""; }
104 it = parameters.find("fasta");
105 //user has given a template file
106 if(it != parameters.end()){
107 path = m->hasPath(it->second);
108 //if the user has not given a path then, add inputdir. else leave path alone.
109 if (path == "") { parameters["fasta"] = inputDir + it->second; }
112 it = parameters.find("oligos");
113 //user has given a template file
114 if(it != parameters.end()){
115 path = m->hasPath(it->second);
116 //if the user has not given a path then, add inputdir. else leave path alone.
117 if (path == "") { parameters["oligos"] = inputDir + it->second; }
120 it = parameters.find("qfile");
121 //user has given a template file
122 if(it != parameters.end()){
123 path = m->hasPath(it->second);
124 //if the user has not given a path then, add inputdir. else leave path alone.
125 if (path == "") { parameters["qfile"] = inputDir + it->second; }
128 it = parameters.find("group");
129 //user has given a template file
130 if(it != parameters.end()){
131 path = m->hasPath(it->second);
132 //if the user has not given a path then, add inputdir. else leave path alone.
133 if (path == "") { parameters["group"] = inputDir + it->second; }
138 //check for required parameters
139 fastaFile = validParameter.validFile(parameters, "fasta", true);
140 if (fastaFile == "not found") { m->mothurOut("fasta is a required parameter for the trim.seqs command."); m->mothurOutEndLine(); abort = true; }
141 else if (fastaFile == "not open") { abort = true; }
143 //if the user changes the output directory command factory will send this info to us in the output parameter
144 outputDir = validParameter.validFile(parameters, "outputdir", false); if (outputDir == "not found"){
146 outputDir += m->hasPath(fastaFile); //if user entered a file with a path then preserve it
150 //check for optional parameter and set defaults
151 // ...at some point should added some additional type checking...
153 temp = validParameter.validFile(parameters, "flip", false);
154 if (temp == "not found"){ flip = 0; }
155 else if(m->isTrue(temp)) { flip = 1; }
157 temp = validParameter.validFile(parameters, "oligos", true);
158 if (temp == "not found"){ oligoFile = ""; }
159 else if(temp == "not open"){ abort = true; }
160 else { oligoFile = temp; }
162 temp = validParameter.validFile(parameters, "group", true);
163 if (temp == "not found"){ groupfile = ""; }
164 else if(temp == "not open"){ abort = true; }
165 else { groupfile = temp; }
167 temp = validParameter.validFile(parameters, "maxambig", false); if (temp == "not found") { temp = "-1"; }
168 convert(temp, maxAmbig);
170 temp = validParameter.validFile(parameters, "maxhomop", false); if (temp == "not found") { temp = "0"; }
171 convert(temp, maxHomoP);
173 temp = validParameter.validFile(parameters, "minlength", false); if (temp == "not found") { temp = "0"; }
174 convert(temp, minLength);
176 temp = validParameter.validFile(parameters, "maxlength", false); if (temp == "not found") { temp = "0"; }
177 convert(temp, maxLength);
179 temp = validParameter.validFile(parameters, "bdiffs", false); if (temp == "not found") { temp = "0"; }
180 convert(temp, bdiffs);
182 temp = validParameter.validFile(parameters, "pdiffs", false); if (temp == "not found") { temp = "0"; }
183 convert(temp, pdiffs);
185 temp = validParameter.validFile(parameters, "tdiffs", false); if (temp == "not found") { int tempTotal = pdiffs + bdiffs; temp = toString(tempTotal); }
186 convert(temp, tdiffs);
188 if(tdiffs == 0){ tdiffs = bdiffs + pdiffs; }
190 temp = validParameter.validFile(parameters, "qfile", true);
191 if (temp == "not found") { qFileName = ""; }
192 else if(temp == "not open") { abort = true; }
193 else { qFileName = temp; }
195 temp = validParameter.validFile(parameters, "qthreshold", false); if (temp == "not found") { temp = "0"; }
196 convert(temp, qThreshold);
198 temp = validParameter.validFile(parameters, "qtrim", false); if (temp == "not found") { temp = "F"; }
199 qtrim = m->isTrue(temp);
201 temp = validParameter.validFile(parameters, "rollaverage", false); if (temp == "not found") { temp = "0"; }
202 convert(temp, qRollAverage);
204 temp = validParameter.validFile(parameters, "qwindowaverage", false);if (temp == "not found") { temp = "0"; }
205 convert(temp, qWindowAverage);
207 temp = validParameter.validFile(parameters, "qwindowsize", false); if (temp == "not found") { temp = "100"; }
208 convert(temp, qWindowSize);
210 temp = validParameter.validFile(parameters, "qstepsize", false); if (temp == "not found") { temp = "10"; }
211 convert(temp, qWindowStep);
213 temp = validParameter.validFile(parameters, "qaverage", false); if (temp == "not found") { temp = "0"; }
214 convert(temp, qAverage);
216 temp = validParameter.validFile(parameters, "allfiles", false); if (temp == "not found") { temp = "F"; }
217 allFiles = m->isTrue(temp);
219 temp = validParameter.validFile(parameters, "processors", false); if (temp == "not found") { temp = "1"; }
220 convert(temp, processors);
222 if ((oligoFile != "") && (groupfile != "")) {
223 m->mothurOut("You given both a oligos file and a groupfile, only one is allowed."); m->mothurOutEndLine(); abort = true;
227 if(allFiles && (oligoFile == "") && (groupfile == "")){
228 m->mothurOut("You selected allfiles, but didn't enter an oligos or group file. Ignoring the allfiles request."); m->mothurOutEndLine();
230 if((qAverage != 0 && qThreshold != 0) && qFileName == ""){
231 m->mothurOut("You didn't provide a quality file name, quality criteria will be ignored."); m->mothurOutEndLine();
235 if(!flip && oligoFile=="" && !maxLength && !minLength && (maxAmbig==-1) && !maxHomoP && qFileName == ""){
236 m->mothurOut("You didn't set any options... quiting command."); m->mothurOutEndLine();
242 catch(exception& e) {
243 m->errorOut(e, "TrimSeqsCommand", "TrimSeqsCommand");
247 //**********************************************************************************************************************
249 void TrimSeqsCommand::help(){
251 m->mothurOut("The trim.seqs command reads a fastaFile and creates .....\n");
252 m->mothurOut("The trim.seqs command parameters are fasta, flip, oligos, group, maxambig, maxhomop, minlength, maxlength, qfile, qthreshold, qaverage, diffs, qtrim and allfiles.\n");
253 m->mothurOut("The fasta parameter is required.\n");
254 m->mothurOut("The group parameter allows you to enter a group file for your fasta file.\n");
255 m->mothurOut("The flip parameter will output the reverse compliment of your trimmed sequence. The default is false.\n");
256 m->mothurOut("The oligos parameter .... The default is "".\n");
257 m->mothurOut("The maxambig parameter .... The default is -1.\n");
258 m->mothurOut("The maxhomop parameter .... The default is 0.\n");
259 m->mothurOut("The minlength parameter .... The default is 0.\n");
260 m->mothurOut("The maxlength parameter .... The default is 0.\n");
261 m->mothurOut("The tdiffs parameter is used to specify the total number of differences allowed in the sequence. The default is pdiffs + bdiffs.\n");
262 m->mothurOut("The bdiffs parameter is used to specify the number of differences allowed in the barcode. The default is 0.\n");
263 m->mothurOut("The pdiffs parameter is used to specify the number of differences allowed in the primer. The default is 0.\n");
264 m->mothurOut("The qfile parameter .....\n");
265 m->mothurOut("The qthreshold parameter .... The default is 0.\n");
266 m->mothurOut("The qaverage parameter .... The default is 0.\n");
267 m->mothurOut("The allfiles parameter .... The default is F.\n");
268 m->mothurOut("The qtrim parameter .... The default is F.\n");
269 m->mothurOut("The trim.seqs command should be in the following format: \n");
270 m->mothurOut("trim.seqs(fasta=yourFastaFile, flip=yourFlip, oligos=yourOligos, maxambig=yourMaxambig, \n");
271 m->mothurOut("maxhomop=yourMaxhomop, minlength=youMinlength, maxlength=yourMaxlength) \n");
272 m->mothurOut("Example trim.seqs(fasta=abrecovery.fasta, flip=..., oligos=..., maxambig=..., maxhomop=..., minlength=..., maxlength=...).\n");
273 m->mothurOut("Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n");
274 m->mothurOut("For more details please check out the wiki http://www.mothur.org/wiki/Trim.seqs .\n\n");
277 catch(exception& e) {
278 m->errorOut(e, "TrimSeqsCommand", "help");
284 //***************************************************************************************************************
286 TrimSeqsCommand::~TrimSeqsCommand(){ /* do nothing */ }
288 //***************************************************************************************************************
290 int TrimSeqsCommand::execute(){
293 if (abort == true) { return 0; }
295 numFPrimers = 0; //this needs to be initialized
297 vector<string> fastaFileNames;
298 vector<string> qualFileNames;
300 string trimSeqFile = outputDir + m->getRootName(m->getSimpleName(fastaFile)) + "trim.fasta";
301 outputNames.push_back(trimSeqFile); outputTypes["fasta"].push_back(trimSeqFile);
302 string scrapSeqFile = outputDir + m->getRootName(m->getSimpleName(fastaFile)) + "scrap.fasta";
303 outputNames.push_back(scrapSeqFile); outputTypes["fasta"].push_back(scrapSeqFile);
304 string trimQualFile = outputDir + m->getRootName(m->getSimpleName(fastaFile)) + "trim.qual";
305 string scrapQualFile = outputDir + m->getRootName(m->getSimpleName(fastaFile)) + "scrap.qual";
306 if (qFileName != "") { outputNames.push_back(trimQualFile); outputNames.push_back(scrapQualFile); outputTypes["qual"].push_back(trimQualFile); outputTypes["qual"].push_back(scrapQualFile); }
307 string groupFile = "";
308 if (groupfile == "") { groupFile = outputDir + m->getRootName(m->getSimpleName(fastaFile)) + "groups"; }
310 groupFile = outputDir + m->getRootName(m->getSimpleName(groupfile)) + "trim.groups";
311 outputNames.push_back(groupFile); outputTypes["group"].push_back(groupFile);
312 groupMap = new GroupMap(groupfile);
316 for (int i = 0; i < groupMap->namesOfGroups.size(); i++) {
317 groupToIndex[groupMap->namesOfGroups[i]] = i;
318 groupVector.push_back(groupMap->namesOfGroups[i]);
319 fastaFileNames.push_back((outputDir + m->getRootName(m->getSimpleName(fastaFile)) + groupMap->namesOfGroups[i] + ".fasta"));
321 //we append later, so we want to clear file
323 m->openOutputFile(fastaFileNames[i], outRemove);
326 qualFileNames.push_back((outputDir + m->getRootName(m->getSimpleName(qFileName)) + groupMap->namesOfGroups[i] + ".qual"));
328 m->openOutputFile(qualFileNames[i], outRemove2);
333 comboStarts = fastaFileNames.size()-1;
337 outputNames.push_back(groupFile); outputTypes["group"].push_back(groupFile);
338 getOligos(fastaFileNames, qualFileNames);
341 vector<unsigned long int> fastaFilePos;
342 vector<unsigned long int> qFilePos;
344 setLines(fastaFile, qFileName, fastaFilePos, qFilePos);
346 for (int i = 0; i < (fastaFilePos.size()-1); i++) {
347 lines.push_back(new linePair(fastaFilePos[i], fastaFilePos[(i+1)]));
348 if (qFileName != "") { qLines.push_back(new linePair(qFilePos[i], qFilePos[(i+1)])); }
350 if(qFileName == "") { qLines = lines; } //files with duds
352 #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux)
354 driverCreateTrim(fastaFile, qFileName, trimSeqFile, scrapSeqFile, trimQualFile, scrapQualFile, groupFile, fastaFileNames, qualFileNames, lines[0], qLines[0]);
356 createProcessesCreateTrim(fastaFile, qFileName, trimSeqFile, scrapSeqFile, trimQualFile, scrapQualFile, groupFile, fastaFileNames, qualFileNames);
359 driverCreateTrim(fastaFile, qFileName, trimSeqFile, scrapSeqFile, trimQualFile, scrapQualFile, groupFile, fastaFileNames, qualFileNames, lines[0], qLines[0]);
362 if (m->control_pressed) { return 0; }
364 for(int i=0;i<fastaFileNames.size();i++){
366 if (m->isBlank(fastaFileNames[i])) { remove(fastaFileNames[i].c_str()); }
367 else if (filesToRemove.count(fastaFileNames[i]) > 0) { remove(fastaFileNames[i].c_str()); }
371 m->openInputFile(fastaFileNames[i], inFASTA);
373 string outGroupFilename = outputDir + m->getRootName(m->getSimpleName(fastaFileNames[i])) + "groups";
374 m->openOutputFile(outGroupFilename, outGroups);
375 outputNames.push_back(outGroupFilename); outputTypes["group"].push_back(outGroupFilename);
377 string thisGroup = "";
378 if (i > comboStarts) {
379 map<string, int>::iterator itCombo;
380 for(itCombo=combos.begin();itCombo!=combos.end(); itCombo++){
381 if(itCombo->second == i){ thisGroup = itCombo->first; combos.erase(itCombo); break; }
383 }else{ thisGroup = groupVector[i]; }
385 while(!inFASTA.eof()){
386 if(inFASTA.get() == '>'){
388 outGroups << seqName << '\t' << thisGroup << endl;
390 while (!inFASTA.eof()) { char c = inFASTA.get(); if (c == 10 || c == 13){ break; } }
398 for(int i=0;i<qualFileNames.size();i++){
399 if (m->isBlank(qualFileNames[i])) { remove(qualFileNames[i].c_str()); }
400 else if (filesToRemove.count(qualFileNames[i]) > 0) { remove(qualFileNames[i].c_str()); }
404 m->openInputFile(qualFileNames[i], inQual);
405 // ofstream outGroups;
407 // string thisGroup = "";
408 // if (i > comboStarts) {
409 // map<string, int>::iterator itCombo;
410 // for(itCombo=combos.begin();itCombo!=combos.end(); itCombo++){
411 // if(itCombo->second == i){ thisGroup = itCombo->first; combos.erase(itCombo); break; }
414 // else{ thisGroup = groupVector[i]; }
422 if (m->control_pressed) {
423 for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); }
427 m->mothurOutEndLine();
428 m->mothurOut("Output File Names: "); m->mothurOutEndLine();
429 for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); }
430 m->mothurOutEndLine();
435 catch(exception& e) {
436 m->errorOut(e, "TrimSeqsCommand", "execute");
441 /**************************************************************************************/
443 int TrimSeqsCommand::driverCreateTrim(string filename, string qFileName, string trimFile, string scrapFile, string trimQFile, string scrapQFile, string groupFile, vector<string> fastaNames, vector<string> qualNames, linePair* line, linePair* qline) {
448 int able = m->openOutputFile(trimFile, outFASTA);
451 m->openOutputFile(scrapFile, scrapFASTA);
456 m->openOutputFile(trimQFile, outQual);
457 m->openOutputFile(scrapQFile, scrapQual);
462 if (oligoFile != "") {
463 m->openOutputFile(groupFile, outGroups);
467 m->openInputFile(filename, inFASTA);
468 inFASTA.seekg(line->start);
471 if(qFileName != "") { m->openInputFile(qFileName, qFile); qFile.seekg(qline->start); }
478 if (m->control_pressed) {
479 inFASTA.close(); outFASTA.close(); scrapFASTA.close();
480 if (oligoFile != "") { outGroups.close(); }
485 for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); }
493 Sequence currSeq(inFASTA); m->gobble(inFASTA);
495 QualityScores currQual;
497 currQual = QualityScores(qFile, currSeq.getNumBases()); m->gobble(qFile);
500 string origSeq = currSeq.getUnaligned();
502 int groupBar, groupPrime;
503 string trashCode = "";
504 int currentSeqsDiffs = 0;
507 if(qThreshold != 0) { success = currQual.stripQualThreshold(currSeq, qThreshold); }
508 else if(qAverage != 0) { success = currQual.cullQualAverage(currSeq, qAverage); }
509 else if(qRollAverage != 0) { success = currQual.stripQualRollingAverage(currSeq, qRollAverage); }
510 else if(qWindowAverage != 0){ success = currQual.stripQualWindowAverage(currSeq, qWindowStep, qWindowSize, qWindowAverage); }
512 if (qtrim == 1 && (origSeq.length() != currSeq.getUnaligned().length())) {
513 success = 0; //if you don't want to trim and the sequence does not meet quality requirements, move to scrap
516 if(!success) { trashCode += 'q'; }
519 if(barcodes.size() != 0){
520 success = stripBarcode(currSeq, currQual, groupBar);
521 if(success > bdiffs) { trashCode += 'b'; }
522 else{ currentSeqsDiffs += success; }
525 if(numFPrimers != 0){
526 success = stripForward(currSeq, currQual, groupPrime);
527 if(success > pdiffs) { trashCode += 'f'; }
528 else{ currentSeqsDiffs += success; }
531 if (currentSeqsDiffs > tdiffs) { trashCode += 't'; }
533 if(numRPrimers != 0){
534 success = stripReverse(currSeq, currQual);
535 if(!success) { trashCode += 'r'; }
538 if(minLength > 0 || maxLength > 0){
539 success = cullLength(currSeq);
540 if(!success) { trashCode += 'l'; }
543 success = cullHomoP(currSeq);
544 if(!success) { trashCode += 'h'; }
547 success = cullAmbigs(currSeq);
548 if(!success) { trashCode += 'n'; }
551 if(flip){ currSeq.reverseComplement(); currQual.flipQScores(); } // should go last
553 if(trashCode.length() == 0){
554 currSeq.setAligned(currSeq.getUnaligned());
555 currSeq.printSequence(outFASTA);
556 currQual.printQScores(outQual);
558 if(barcodes.size() != 0){
559 string thisGroup = groupVector[groupBar];
560 int indexToFastaFile = groupBar;
561 if (primers.size() != 0){
562 //does this primer have a group
563 if (groupVector[groupPrime] != "") {
564 thisGroup += "." + groupVector[groupPrime];
565 indexToFastaFile = combos[thisGroup];
568 outGroups << currSeq.getName() << '\t' << thisGroup << endl;
571 m->openOutputFileAppend(fastaNames[indexToFastaFile], outTemp);
572 //currSeq.printSequence(*fastaFileNames[indexToFastaFile]);
573 currSeq.printSequence(outTemp);
577 //currQual.printQScores(*qualFileNames[indexToFastaFile]);
579 m->openOutputFileAppend(qualNames[indexToFastaFile], outTemp2);
580 currQual.printQScores(outTemp2);
586 if (groupfile != "") {
587 string thisGroup = groupMap->getGroup(currSeq.getName());
589 if (thisGroup != "not found") {
590 outGroups << currSeq.getName() << '\t' << thisGroup << endl;
593 m->openOutputFileAppend(fastaNames[groupToIndex[thisGroup]], outTemp);
594 currSeq.printSequence(outTemp);
598 m->openOutputFileAppend(qualNames[groupToIndex[thisGroup]], outTemp2);
599 currQual.printQScores(outTemp2);
604 m->mothurOut(currSeq.getName() + " is not in your groupfile, adding to group XXX."); m->mothurOutEndLine();
605 outGroups << currSeq.getName() << '\t' << "XXX" << endl;
607 m->mothurOut("[ERROR]: " + currSeq.getName() + " will not be added to any .group.fasta or .group.qual file."); m->mothurOutEndLine();
613 currSeq.setName(currSeq.getName() + '|' + trashCode);
614 currSeq.setUnaligned(origSeq);
615 currSeq.setAligned(origSeq);
616 currSeq.printSequence(scrapFASTA);
617 currQual.printQScores(scrapQual);
622 #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux)
623 unsigned long int pos = inFASTA.tellg();
624 if ((pos == -1) || (pos >= line->end)) { break; }
626 if (inFASTA.eof()) { break; }
630 if((count) % 1000 == 0){ m->mothurOut(toString(count)); m->mothurOutEndLine(); }
634 if((count) % 1000 != 0){ m->mothurOut(toString(count)); m->mothurOutEndLine(); }
640 if (oligoFile != "") { outGroups.close(); }
641 if(qFileName != "") { qFile.close(); scrapQual.close(); outQual.close(); }
645 catch(exception& e) {
646 m->errorOut(e, "TrimSeqsCommand", "driverCreateTrim");
651 /**************************************************************************************************/
653 int TrimSeqsCommand::createProcessesCreateTrim(string filename, string qFileName, string trimFile, string scrapFile, string trimQFile, string scrapQFile, string groupFile, vector<string> fastaNames, vector<string> qualNames) {
655 #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux)
660 //loop through and create all the processes you want
661 while (process != processors) {
665 processIDS.push_back(pid); //create map from line number to pid so you can append files in correct order later
668 for (int i = 0; i < fastaNames.size(); i++) {
669 fastaNames[i] = (fastaNames[i] + toString(getpid()) + ".temp");
670 //clear old file if it exists
672 m->openOutputFile(fastaNames[i], temp);
675 qualNames[i] = (qualNames[i] + toString(getpid()) + ".temp");
676 //clear old file if it exists
678 m->openOutputFile(qualNames[i], temp2);
683 driverCreateTrim(filename, qFileName, (trimFile + toString(getpid()) + ".temp"), (scrapFile + toString(getpid()) + ".temp"), (trimQFile + toString(getpid()) + ".temp"), (scrapQFile + toString(getpid()) + ".temp"), (groupFile + toString(getpid()) + ".temp"), fastaNames, qualNames, lines[process], qLines[process]);
686 m->mothurOut("[ERROR]: unable to spawn the necessary processes."); m->mothurOutEndLine();
687 for (int i = 0; i < processIDS.size(); i++) { kill (processIDS[i], SIGINT); }
693 for (int i = 0; i < fastaNames.size(); i++) {
694 //clear old file if it exists
696 m->openOutputFile(fastaNames[i], temp);
699 //clear old file if it exists
701 m->openOutputFile(qualNames[i], temp2);
706 driverCreateTrim(filename, qFileName, trimFile, scrapFile, trimQFile, scrapQFile, groupFile, fastaNames, qualNames, lines[0], qLines[0]);
709 //force parent to wait until all the processes are done
710 for (int i=0;i<processIDS.size();i++) {
711 int temp = processIDS[i];
716 for(int i=0;i<processIDS.size();i++){
717 m->mothurOut("Appending files from process " + processIDS[i]); m->mothurOutEndLine();
719 m->appendFiles((trimFile + toString(processIDS[i]) + ".temp"), trimFile);
720 remove((trimFile + toString(processIDS[i]) + ".temp").c_str());
721 m->appendFiles((scrapFile + toString(processIDS[i]) + ".temp"), scrapFile);
722 remove((scrapFile + toString(processIDS[i]) + ".temp").c_str());
724 m->mothurOut("Done with fasta files"); m->mothurOutEndLine();
727 m->appendFiles((trimQFile + toString(processIDS[i]) + ".temp"), trimQFile);
728 remove((trimQFile + toString(processIDS[i]) + ".temp").c_str());
729 m->appendFiles((scrapQFile + toString(processIDS[i]) + ".temp"), scrapQFile);
730 remove((scrapQFile + toString(processIDS[i]) + ".temp").c_str());
732 m->mothurOut("Done with quality files"); m->mothurOutEndLine();
735 m->appendFiles((groupFile + toString(processIDS[i]) + ".temp"), groupFile);
736 remove((groupFile + toString(processIDS[i]) + ".temp").c_str());
738 m->mothurOut("Done with group file"); m->mothurOutEndLine();
740 for (int j = 0; j < fastaNames.size(); j++) {
741 m->appendFiles((fastaNames[j] + toString(processIDS[i]) + ".temp"), fastaNames[j]);
742 remove((fastaNames[j] + toString(processIDS[i]) + ".temp").c_str());
746 for (int j = 0; j < qualNames.size(); j++) {
747 m->appendFiles((qualNames[j] + toString(processIDS[i]) + ".temp"), qualNames[j]);
748 remove((qualNames[j] + toString(processIDS[i]) + ".temp").c_str());
752 if (allFiles) { m->mothurOut("Done with allfiles"); m->mothurOutEndLine(); }
758 catch(exception& e) {
759 m->errorOut(e, "TrimSeqsCommand", "createProcessesCreateTrim");
764 /**************************************************************************************************/
766 int TrimSeqsCommand::setLines(string filename, string qfilename, vector<unsigned long int>& fastaFilePos, vector<unsigned long int>& qfileFilePos) {
769 //set file positions for fasta file
770 fastaFilePos = m->divideFile(filename, processors);
772 if (qfilename == "") { return processors; }
774 //get name of first sequence in each chunk
775 map<string, int> firstSeqNames;
776 for (int i = 0; i < (fastaFilePos.size()-1); i++) {
778 m->openInputFile(filename, in);
779 in.seekg(fastaFilePos[i]);
782 firstSeqNames[temp.getName()] = i;
787 //seach for filePos of each first name in the qfile and save in qfileFilePos
789 m->openInputFile(qfilename, inQual);
792 while(!inQual.eof()){
793 input = m->getline(inQual);
795 if (input.length() != 0) {
796 if(input[0] == '>'){ //this is a sequence name line
797 istringstream nameStream(input);
799 string sname = ""; nameStream >> sname;
800 sname = sname.substr(1);
802 map<string, int>::iterator it = firstSeqNames.find(sname);
804 if(it != firstSeqNames.end()) { //this is the start of a new chunk
805 unsigned long int pos = inQual.tellg();
806 qfileFilePos.push_back(pos - input.length() - 1);
807 firstSeqNames.erase(it);
812 if (firstSeqNames.size() == 0) { break; }
817 if (firstSeqNames.size() != 0) {
818 for (map<string, int>::iterator it = firstSeqNames.begin(); it != firstSeqNames.end(); it++) {
819 m->mothurOut(it->first + " is in your fasta file and not in your quality file, not using quality file."); m->mothurOutEndLine();
825 //get last file position of qfile
827 unsigned long int size;
829 //get num bytes in file
830 pFile = fopen (qfilename.c_str(),"rb");
831 if (pFile==NULL) perror ("Error opening file");
833 fseek (pFile, 0, SEEK_END);
838 qfileFilePos.push_back(size);
842 catch(exception& e) {
843 m->errorOut(e, "TrimSeqsCommand", "setLines");
847 //***************************************************************************************************************
849 void TrimSeqsCommand::getOligos(vector<string>& outFASTAVec, vector<string>& outQualVec){
852 m->openInputFile(oligoFile, inOligos);
856 string type, oligo, group;
858 //int indexPrimer = 0;
860 while(!inOligos.eof()){
861 inOligos >> type; m->gobble(inOligos);
864 while (!inOligos.eof()) { char c = inOligos.get(); if (c == 10 || c == 13){ break; } } // get rest of line if there's any crap there
867 //make type case insensitive
868 for(int i=0;i<type.length();i++){ type[i] = toupper(type[i]); }
872 for(int i=0;i<oligo.length();i++){
873 oligo[i] = toupper(oligo[i]);
874 if(oligo[i] == 'U') { oligo[i] = 'T'; }
877 if(type == "FORWARD"){
880 // get rest of line in case there is a primer name
881 while (!inOligos.eof()) {
882 char c = inOligos.get();
883 if (c == 10 || c == 13){ break; }
884 else if (c == 32 || c == 9){;} //space or tab
888 //check for repeat barcodes
889 map<string, int>::iterator itPrime = primers.find(oligo);
890 if (itPrime != primers.end()) { m->mothurOut("primer " + oligo + " is in your oligos file already."); m->mothurOutEndLine(); }
892 primers[oligo]=index; index++;
893 groupVector.push_back(group);
896 outFASTAVec.push_back((outputDir + m->getRootName(m->getSimpleName(fastaFile)) + group + ".fasta"));
898 outQualVec.push_back((outputDir + m->getRootName(m->getSimpleName(qFileName)) + group + ".qual"));
900 if (group == "") { //if there is not a group for this primer, then this file will not get written to, but we add it to keep the indexes correct
901 filesToRemove.insert((outputDir + m->getRootName(m->getSimpleName(fastaFile)) + group + ".fasta"));
903 filesToRemove.insert((outputDir + m->getRootName(m->getSimpleName(qFileName)) + group + ".qual"));
906 outputNames.push_back((outputDir + m->getRootName(m->getSimpleName(fastaFile)) + group + ".fasta"));
907 outputTypes["fasta"].push_back((outputDir + m->getRootName(m->getSimpleName(fastaFile)) + group + ".fasta"));
909 outputNames.push_back((outputDir + m->getRootName(m->getSimpleName(qFileName)) + group + ".qual"));
910 outputTypes["qual"].push_back((outputDir + m->getRootName(m->getSimpleName(qFileName)) + group + ".qual"));
916 else if(type == "REVERSE"){
917 Sequence oligoRC("reverse", oligo);
918 oligoRC.reverseComplement();
919 revPrimer.push_back(oligoRC.getUnaligned());
921 else if(type == "BARCODE"){
924 //check for repeat barcodes
925 map<string, int>::iterator itBar = barcodes.find(oligo);
926 if (itBar != barcodes.end()) { m->mothurOut("barcode " + oligo + " is in your oligos file already."); m->mothurOutEndLine(); }
928 barcodes[oligo]=index; index++;
929 groupVector.push_back(group);
932 outputNames.push_back((outputDir + m->getRootName(m->getSimpleName(fastaFile)) + group + ".fasta"));
933 outputNames.push_back((outputDir + m->getRootName(m->getSimpleName(fastaFile)) + group + ".fasta"));
934 outFASTAVec.push_back((outputDir + m->getRootName(m->getSimpleName(fastaFile)) + group + ".fasta"));
936 outQualVec.push_back((outputDir + m->getRootName(m->getSimpleName(qFileName)) + group + ".qual"));
937 outputNames.push_back((outputDir + m->getRootName(m->getSimpleName(qFileName)) + group + ".qual"));
938 outputTypes["qual"].push_back((outputDir + m->getRootName(m->getSimpleName(qFileName)) + group + ".qual"));
942 }else{ m->mothurOut(type + " is not recognized as a valid type. Choices are forward, reverse, and barcode. Ignoring " + oligo + "."); m->mothurOutEndLine(); }
949 //add in potential combos
951 comboStarts = outFASTAVec.size()-1;
952 for (map<string, int>::iterator itBar = barcodes.begin(); itBar != barcodes.end(); itBar++) {
953 for (map<string, int>::iterator itPrime = primers.begin(); itPrime != primers.end(); itPrime++) {
954 if (groupVector[itPrime->second] != "") { //there is a group for this primer
955 outputNames.push_back((outputDir + m->getRootName(m->getSimpleName(qFileName)) + groupVector[itBar->second] + "." + groupVector[itPrime->second] + ".fasta"));
956 outputTypes["fasta"].push_back((outputDir + m->getRootName(m->getSimpleName(qFileName)) + groupVector[itBar->second] + "." + groupVector[itPrime->second] + ".fasta"));
957 outFASTAVec.push_back((outputDir + m->getRootName(m->getSimpleName(fastaFile)) + groupVector[itBar->second] + "." + groupVector[itPrime->second] + ".fasta"));
958 combos[(groupVector[itBar->second] + "." + groupVector[itPrime->second])] = outFASTAVec.size()-1;
961 outQualVec.push_back((outputDir + m->getRootName(m->getSimpleName(qFileName)) + groupVector[itBar->second] + "." + groupVector[itPrime->second] + ".qual"));
962 outputNames.push_back((outputDir + m->getRootName(m->getSimpleName(qFileName)) + groupVector[itBar->second] + "." + groupVector[itPrime->second] + ".qual"));
963 outputTypes["qual"].push_back((outputDir + m->getRootName(m->getSimpleName(qFileName)) + groupVector[itBar->second] + "." + groupVector[itPrime->second] + ".qual"));
970 numFPrimers = primers.size();
971 numRPrimers = revPrimer.size();
974 catch(exception& e) {
975 m->errorOut(e, "TrimSeqsCommand", "getOligos");
979 //***************************************************************************************************************
981 int TrimSeqsCommand::stripBarcode(Sequence& seq, QualityScores& qual, int& group){
984 string rawSequence = seq.getUnaligned();
985 int success = bdiffs + 1; //guilty until proven innocent
987 //can you find the barcode
988 for(map<string,int>::iterator it=barcodes.begin();it!=barcodes.end();it++){
989 string oligo = it->first;
990 if(rawSequence.length() < oligo.length()){ //let's just assume that the barcodes are the same length
991 success = bdiffs + 10; //if the sequence is shorter than the barcode then bail out
995 if(compareDNASeq(oligo, rawSequence.substr(0,oligo.length()))){
997 seq.setUnaligned(rawSequence.substr(oligo.length()));
999 if(qual.getName() != ""){
1000 qual.trimQScores(oligo.length(), -1);
1008 //if you found the barcode or if you don't want to allow for diffs
1010 if ((bdiffs == 0) || (success == 0)) { return success; }
1012 else { //try aligning and see if you can find it
1017 Alignment* alignment;
1018 if (barcodes.size() > 0) {
1019 map<string,int>::iterator it=barcodes.begin();
1021 for(it;it!=barcodes.end();it++){
1022 if(it->first.length() > maxLength){
1023 maxLength = it->first.length();
1026 alignment = new NeedlemanOverlap(-1.0, 1.0, -1.0, (maxLength+bdiffs+1));
1028 }else{ alignment = NULL; }
1030 //can you find the barcode
1036 for(map<string,int>::iterator it=barcodes.begin();it!=barcodes.end();it++){
1037 string oligo = it->first;
1038 // int length = oligo.length();
1040 if(rawSequence.length() < maxLength){ //let's just assume that the barcodes are the same length
1041 success = bdiffs + 10;
1045 //use needleman to align first barcode.length()+numdiffs of sequence to each barcode
1046 alignment->align(oligo, rawSequence.substr(0,oligo.length()+bdiffs));
1047 oligo = alignment->getSeqAAln();
1048 string temp = alignment->getSeqBAln();
1050 int alnLength = oligo.length();
1052 for(int i=oligo.length()-1;i>=0;i--){
1053 if(oligo[i] != '-'){ alnLength = i+1; break; }
1055 oligo = oligo.substr(0,alnLength);
1056 temp = temp.substr(0,alnLength);
1059 int numDiff = countDiffs(oligo, temp);
1061 // cout << oligo << '\t' << temp << '\t' << numDiff << endl;
1063 if(numDiff < minDiff){
1066 minGroup = it->second;
1068 for(int i=0;i<alnLength;i++){
1074 else if(numDiff == minDiff){
1080 if(minDiff > bdiffs) { success = minDiff; } //no good matches
1081 else if(minCount > 1) { success = bdiffs + 100; } //can't tell the difference between multiple barcodes
1082 else{ //use the best match
1084 seq.setUnaligned(rawSequence.substr(minPos));
1086 if(qual.getName() != ""){
1087 qual.trimQScores(minPos, -1);
1092 if (alignment != NULL) { delete alignment; }
1095 // cout << success << endl;
1100 catch(exception& e) {
1101 m->errorOut(e, "TrimSeqsCommand", "stripBarcode");
1107 //***************************************************************************************************************
1109 int TrimSeqsCommand::stripForward(Sequence& seq, QualityScores& qual, int& group){
1111 string rawSequence = seq.getUnaligned();
1112 int success = pdiffs + 1; //guilty until proven innocent
1114 //can you find the primer
1115 for(map<string,int>::iterator it=primers.begin();it!=primers.end();it++){
1116 string oligo = it->first;
1117 if(rawSequence.length() < oligo.length()){ //let's just assume that the primers are the same length
1118 success = pdiffs + 10; //if the sequence is shorter than the barcode then bail out
1122 if(compareDNASeq(oligo, rawSequence.substr(0,oligo.length()))){
1124 seq.setUnaligned(rawSequence.substr(oligo.length()));
1125 if(qual.getName() != ""){
1126 qual.trimQScores(oligo.length(), -1);
1134 //if you found the barcode or if you don't want to allow for diffs
1136 if ((pdiffs == 0) || (success == 0)) { return success; }
1138 else { //try aligning and see if you can find it
1143 Alignment* alignment;
1144 if (primers.size() > 0) {
1145 map<string,int>::iterator it=primers.begin();
1147 for(it;it!=primers.end();it++){
1148 if(it->first.length() > maxLength){
1149 maxLength = it->first.length();
1152 alignment = new NeedlemanOverlap(-1.0, 1.0, -1.0, (maxLength+pdiffs+1));
1154 }else{ alignment = NULL; }
1156 //can you find the barcode
1162 for(map<string,int>::iterator it=primers.begin();it!=primers.end();it++){
1163 string oligo = it->first;
1164 // int length = oligo.length();
1166 if(rawSequence.length() < maxLength){
1167 success = pdiffs + 100;
1171 //use needleman to align first barcode.length()+numdiffs of sequence to each barcode
1172 alignment->align(oligo, rawSequence.substr(0,oligo.length()+pdiffs));
1173 oligo = alignment->getSeqAAln();
1174 string temp = alignment->getSeqBAln();
1176 int alnLength = oligo.length();
1178 for(int i=oligo.length()-1;i>=0;i--){
1179 if(oligo[i] != '-'){ alnLength = i+1; break; }
1181 oligo = oligo.substr(0,alnLength);
1182 temp = temp.substr(0,alnLength);
1185 int numDiff = countDiffs(oligo, temp);
1187 // cout << oligo << '\t' << temp << '\t' << numDiff << endl;
1189 if(numDiff < minDiff){
1192 minGroup = it->second;
1194 for(int i=0;i<alnLength;i++){
1200 else if(numDiff == minDiff){
1206 if(minDiff > pdiffs) { success = minDiff; } //no good matches
1207 else if(minCount > 1) { success = pdiffs + 10; } //can't tell the difference between multiple primers
1208 else{ //use the best match
1210 seq.setUnaligned(rawSequence.substr(minPos));
1211 if(qual.getName() != ""){
1212 qual.trimQScores(minPos, -1);
1217 if (alignment != NULL) { delete alignment; }
1224 catch(exception& e) {
1225 m->errorOut(e, "TrimSeqsCommand", "stripForward");
1230 //***************************************************************************************************************
1232 bool TrimSeqsCommand::stripReverse(Sequence& seq, QualityScores& qual){
1234 string rawSequence = seq.getUnaligned();
1235 bool success = 0; //guilty until proven innocent
1237 for(int i=0;i<numRPrimers;i++){
1238 string oligo = revPrimer[i];
1240 if(rawSequence.length() < oligo.length()){
1245 if(compareDNASeq(oligo, rawSequence.substr(rawSequence.length()-oligo.length(),oligo.length()))){
1246 seq.setUnaligned(rawSequence.substr(0,rawSequence.length()-oligo.length()));
1247 if(qual.getName() != ""){
1248 qual.trimQScores(-1, rawSequence.length()-oligo.length());
1257 catch(exception& e) {
1258 m->errorOut(e, "TrimSeqsCommand", "stripReverse");
1263 //***************************************************************************************************************
1265 bool TrimSeqsCommand::cullLength(Sequence& seq){
1268 int length = seq.getNumBases();
1269 bool success = 0; //guilty until proven innocent
1271 if(length >= minLength && maxLength == 0) { success = 1; }
1272 else if(length >= minLength && length <= maxLength) { success = 1; }
1273 else { success = 0; }
1278 catch(exception& e) {
1279 m->errorOut(e, "TrimSeqsCommand", "cullLength");
1285 //***************************************************************************************************************
1287 bool TrimSeqsCommand::cullHomoP(Sequence& seq){
1289 int longHomoP = seq.getLongHomoPolymer();
1290 bool success = 0; //guilty until proven innocent
1292 if(longHomoP <= maxHomoP){ success = 1; }
1293 else { success = 0; }
1297 catch(exception& e) {
1298 m->errorOut(e, "TrimSeqsCommand", "cullHomoP");
1304 //***************************************************************************************************************
1306 bool TrimSeqsCommand::cullAmbigs(Sequence& seq){
1308 int numNs = seq.getAmbigBases();
1309 bool success = 0; //guilty until proven innocent
1311 if(numNs <= maxAmbig) { success = 1; }
1312 else { success = 0; }
1316 catch(exception& e) {
1317 m->errorOut(e, "TrimSeqsCommand", "cullAmbigs");
1323 //***************************************************************************************************************
1325 bool TrimSeqsCommand::compareDNASeq(string oligo, string seq){
1328 int length = oligo.length();
1330 for(int i=0;i<length;i++){
1332 if(oligo[i] != seq[i]){
1333 if(oligo[i] == 'A' || oligo[i] == 'T' || oligo[i] == 'G' || oligo[i] == 'C') { success = 0; }
1334 else if((oligo[i] == 'N' || oligo[i] == 'I') && (seq[i] == 'N')) { success = 0; }
1335 else if(oligo[i] == 'R' && (seq[i] != 'A' && seq[i] != 'G')) { success = 0; }
1336 else if(oligo[i] == 'Y' && (seq[i] != 'C' && seq[i] != 'T')) { success = 0; }
1337 else if(oligo[i] == 'M' && (seq[i] != 'C' && seq[i] != 'A')) { success = 0; }
1338 else if(oligo[i] == 'K' && (seq[i] != 'T' && seq[i] != 'G')) { success = 0; }
1339 else if(oligo[i] == 'W' && (seq[i] != 'T' && seq[i] != 'A')) { success = 0; }
1340 else if(oligo[i] == 'S' && (seq[i] != 'C' && seq[i] != 'G')) { success = 0; }
1341 else if(oligo[i] == 'B' && (seq[i] != 'C' && seq[i] != 'T' && seq[i] != 'G')) { success = 0; }
1342 else if(oligo[i] == 'D' && (seq[i] != 'A' && seq[i] != 'T' && seq[i] != 'G')) { success = 0; }
1343 else if(oligo[i] == 'H' && (seq[i] != 'A' && seq[i] != 'T' && seq[i] != 'C')) { success = 0; }
1344 else if(oligo[i] == 'V' && (seq[i] != 'A' && seq[i] != 'C' && seq[i] != 'G')) { success = 0; }
1346 if(success == 0) { break; }
1355 catch(exception& e) {
1356 m->errorOut(e, "TrimSeqsCommand", "compareDNASeq");
1361 //***************************************************************************************************************
1363 int TrimSeqsCommand::countDiffs(string oligo, string seq){
1366 int length = oligo.length();
1369 for(int i=0;i<length;i++){
1371 if(oligo[i] != seq[i]){
1372 if(oligo[i] == 'A' || oligo[i] == 'T' || oligo[i] == 'G' || oligo[i] == 'C' || oligo[i] == '-' || oligo[i] == '.') { countDiffs++; }
1373 else if((oligo[i] == 'N' || oligo[i] == 'I') && (seq[i] == 'N')) { countDiffs++; }
1374 else if(oligo[i] == 'R' && (seq[i] != 'A' && seq[i] != 'G')) { countDiffs++; }
1375 else if(oligo[i] == 'Y' && (seq[i] != 'C' && seq[i] != 'T')) { countDiffs++; }
1376 else if(oligo[i] == 'M' && (seq[i] != 'C' && seq[i] != 'A')) { countDiffs++; }
1377 else if(oligo[i] == 'K' && (seq[i] != 'T' && seq[i] != 'G')) { countDiffs++; }
1378 else if(oligo[i] == 'W' && (seq[i] != 'T' && seq[i] != 'A')) { countDiffs++; }
1379 else if(oligo[i] == 'S' && (seq[i] != 'C' && seq[i] != 'G')) { countDiffs++; }
1380 else if(oligo[i] == 'B' && (seq[i] != 'C' && seq[i] != 'T' && seq[i] != 'G')) { countDiffs++; }
1381 else if(oligo[i] == 'D' && (seq[i] != 'A' && seq[i] != 'T' && seq[i] != 'G')) { countDiffs++; }
1382 else if(oligo[i] == 'H' && (seq[i] != 'A' && seq[i] != 'T' && seq[i] != 'C')) { countDiffs++; }
1383 else if(oligo[i] == 'V' && (seq[i] != 'A' && seq[i] != 'C' && seq[i] != 'G')) { countDiffs++; }
1390 catch(exception& e) {
1391 m->errorOut(e, "TrimSeqsCommand", "countDiffs");
1396 //***************************************************************************************************************
1398 //bool TrimSeqsCommand::stripQualThreshold(Sequence& seq, ifstream& qFile){
1401 // string rawSequence = seq.getUnaligned();
1402 // int seqLength = seq.getNumBases();
1403 // bool success = 0; //guilty until proven innocent
1407 // if (name[0] == '>') { if(name.substr(1) != seq.getName()) { m->mothurOut("sequence name mismatch btwn fasta: " + seq.getName() + " and qual file: " + name); m->mothurOutEndLine(); } }
1409 // while (!qFile.eof()) { char c = qFile.get(); if (c == 10 || c == 13){ break; } }
1412 // int end = seqLength;
1414 // for(int i=0;i<seqLength;i++){
1417 // if(score < qThreshold){
1422 // for(int i=end+1;i<seqLength;i++){
1426 // seq.setUnaligned(rawSequence.substr(0,end));
1430 // catch(exception& e) {
1431 // m->errorOut(e, "TrimSeqsCommand", "stripQualThreshold");
1436 //***************************************************************************************************************
1438 //bool TrimSeqsCommand::cullQualAverage(Sequence& seq, ifstream& qFile){
1440 // string rawSequence = seq.getUnaligned();
1441 // int seqLength = seq.getNumBases();
1442 // bool success = 0; //guilty until proven innocent
1446 // if (name[0] == '>') { if(name.substr(1) != seq.getName()) { m->mothurOut("sequence name mismatch btwn fasta: " + seq.getName() + " and qual file: " + name); m->mothurOutEndLine(); } }
1448 // while (!qFile.eof()) { char c = qFile.get(); if (c == 10 || c == 13){ break; } }
1451 // float average = 0;
1453 // for(int i=0;i<seqLength;i++){
1455 // average += score;
1457 // average /= seqLength;
1459 // if(average >= qAverage) { success = 1; }
1460 // else { success = 0; }
1464 // catch(exception& e) {
1465 // m->errorOut(e, "TrimSeqsCommand", "cullQualAverage");
1470 //***************************************************************************************************************