#include "blastalign.hpp"
#include "noalign.hpp"
-#include "kmerdb.hpp"
-#include "suffixdb.hpp"
-#include "blastdb.hpp"
-
#include "nast.hpp"
#include "nastreport.hpp"
//check for required parameters
templateFileName = validParameter.validFile(parameters, "template", true);
- if (templateFileName == "not found") { cout << "template is a required parameter for the align.seqs command." << endl; abort = true; }
+ if (templateFileName == "not found") {
+ mothurOut("template is a required parameter for the align.seqs command.");
+ mothurOutEndLine();
+ abort = true;
+ }
else if (templateFileName == "not open") { abort = true; }
candidateFileName = validParameter.validFile(parameters, "candidate", true);
- if (candidateFileName == "not found") { cout << "candidate is a required parameter for the align.seqs command." << endl; abort = true; }
+ if (candidateFileName == "not found") {
+ mothurOut("candidate is a required parameter for the align.seqs command.");
+ mothurOutEndLine();
+ abort = true;
+ }
else if (candidateFileName == "not open") { abort = true; }
//check for optional parameter and set defaults
}
catch(exception& e) {
- cout << "Standard Error: " << e.what() << " has occurred in the AlignCommand class Function AlignCommand. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
+ errorOut(e, "AlignCommand", "AlignCommand");
exit(1);
}
- catch(...) {
- cout << "An unknown error has occurred in the AlignCommand class function AlignCommand. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
- exit(1);
- }
}
//**********************************************************************************************************************
void AlignCommand::help(){
try {
- cout << "The align.seqs command reads a file containing sequences and creates an alignment file and a report file." << "\n";
- cout << "The align.seqs command parameters are template, candidate, search, ksize, align, match, mismatch, gapopen and gapextend. " << "\n";
- cout << "The template and candidate parameters are required." << "\n";
- cout << "The search parameter allows you to specify the method to find most similar template. Your options are: suffix, kmer and blast. The default is kmer." << "\n";
- cout << "The align parameter allows you to specify the alignment method to use. Your options are: gotoh, needleman, blast and noalign. The default is needleman." << "\n";
- cout << "The ksize parameter allows you to specify the kmer size for finding most similar template to candidate. The default is 7." << "\n";
- cout << "The match parameter allows you to specify the bonus for having the same base. The default is 1.0." << "\n";
- cout << "The mistmatch parameter allows you to specify the penalty for having different bases. The default is -1.0." << "\n";
- cout << "The gapopen parameter allows you to specify the penalty for opening a gap in an alignment. The default is -1.0." << "\n";
- cout << "The gapextend parameter allows you to specify the penalty for extending a gap in an alignment. The default is -2.0." << "\n";
- cout << "The align.seqs command should be in the following format: " << "\n";
- cout << "align.seqs(template=yourTemplateFile, candidate=yourCandidateFile, align=yourAlignmentMethod, search=yourSearchmethod, ksize=yourKmerSize, match=yourMatchBonus, mismatch=yourMismatchpenalty, gapopen=yourGapopenPenalty, gapextend=yourGapExtendPenalty) " << "\n";
- cout << "Example align.seqs(candidate=candidate.fasta, template=core.filtered, align=kmer, search=gotoh, ksize=8, match=2.0, mismatch=3.0, gapopen=-2.0, gapextend=-1.0)" << "\n";
- cout << "Note: No spaces between parameter labels (i.e. candidate), '=' and parameters (i.e.yourFastaFile)." << "\n" << "\n";
+ mothurOut("The align.seqs command reads a file containing sequences and creates an alignment file and a report file.\n");
+ mothurOut("The align.seqs command parameters are template, candidate, search, ksize, align, match, mismatch, gapopen and gapextend.\n");
+ mothurOut("The template and candidate parameters are required.\n");
+ mothurOut("The search parameter allows you to specify the method to find most similar template. Your options are: suffix, kmer and blast. The default is kmer.\n");
+ mothurOut("The align parameter allows you to specify the alignment method to use. Your options are: gotoh, needleman, blast and noalign. The default is needleman.\n");
+ mothurOut("The ksize parameter allows you to specify the kmer size for finding most similar template to candidate. The default is 8.\n");
+ mothurOut("The match parameter allows you to specify the bonus for having the same base. The default is 1.0.\n");
+ mothurOut("The mistmatch parameter allows you to specify the penalty for having different bases. The default is -1.0.\n");
+ mothurOut("The gapopen parameter allows you to specify the penalty for opening a gap in an alignment. The default is -1.0.\n");
+ mothurOut("The gapextend parameter allows you to specify the penalty for extending a gap in an alignment. The default is -2.0.\n");
+ mothurOut("The align.seqs command should be in the following format: \n");
+ mothurOut("align.seqs(template=yourTemplateFile, candidate=yourCandidateFile, align=yourAlignmentMethod, search=yourSearchmethod, ksize=yourKmerSize, match=yourMatchBonus, mismatch=yourMismatchpenalty, gapopen=yourGapopenPenalty, gapextend=yourGapExtendPenalty) \n");
+ mothurOut("Example align.seqs(candidate=candidate.fasta, template=core.filtered, align=kmer, search=gotoh, ksize=8, match=2.0, mismatch=3.0, gapopen=-2.0, gapextend=-1.0)\n");
+ mothurOut("Note: No spaces between parameter labels (i.e. candidate), '=' and parameters (i.e.yourFastaFile).\n\n");
}
catch(exception& e) {
- cout << "Standard Error: " << e.what() << " has occurred in the AlignCommand class Function help. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
+ errorOut(e, "AlignCommand", "help");
exit(1);
}
- catch(...) {
- cout << "An unknown error has occurred in the AlignCommand class function help. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
- exit(1);
- }
}
try {
if (abort == true) { return 0; }
- if(search == "kmer") { templateDB = new KmerDB(templateFileName, kmerSize); }
- else if(search == "suffix") { templateDB = new SuffixDB(templateFileName); }
- else if(search == "blast") { templateDB = new BlastDB(templateFileName, gapOpen, gapExtend, match, misMatch); }
- else {
- cout << search << " is not a valid search option. I will run the command using kmer, ksize=8." << endl; kmerSize = 8;
- templateDB = new KmerDB(templateFileName, kmerSize);
- }
-
- if(align == "gotoh") { alignment = new GotohOverlap(gapOpen, gapExtend, match, misMatch, 3000); }
- else if(align == "needleman") { alignment = new NeedlemanOverlap(gapOpen, match, misMatch, 3000); }
+ templateDB = new AlignmentDB(templateFileName, search, kmerSize, gapOpen, gapExtend, match, misMatch);
+ int longestBase = templateDB->getLongestBase();
+
+ if(align == "gotoh") { alignment = new GotohOverlap(gapOpen, gapExtend, match, misMatch, longestBase); }
+ else if(align == "needleman") { alignment = new NeedlemanOverlap(gapOpen, match, misMatch, longestBase); }
else if(align == "blast") { alignment = new BlastAlignment(gapOpen, gapExtend, match, misMatch); }
else if(align == "noalign") { alignment = new NoAlign(); }
else {
- cout << align << " is not a valid alignment option. I will run the command using needleman." << endl;
- alignment = new NeedlemanOverlap(gapOpen, match, misMatch, 3000);
+ mothurOut(align + " is not a valid alignment option. I will run the command using needleman.");
+ mothurOutEndLine();
+ alignment = new NeedlemanOverlap(gapOpen, match, misMatch, longestBase);
}
+ mothurOut("Aligning sequences...");
+ mothurOutEndLine();
string alignFileName = candidateFileName.substr(0,candidateFileName.find_last_of(".")+1) + "align";
string reportFileName = candidateFileName.substr(0,candidateFileName.find_last_of(".")+1) + "align.report";
inFASTA.close();
lines.push_back(new linePair(0, numFastaSeqs));
-
+
driver(lines[0], alignFileName, reportFileName);
}
ifstream inFASTA;
openInputFile(candidateFileName, inFASTA);
+ string input;
while(!inFASTA.eof()){
- char c = inFASTA.get();
- if(c == '>'){ int pos = inFASTA.tellg(); positions.push_back(pos-1); }
- while (!inFASTA.eof()) { c = inFASTA.get(); if (c == 10 || c == 13){ break; } } // get rest of line if there's any crap there
+ input = getline(inFASTA);
+ if (input.length() != 0) {
+ if(input[0] == '>'){ int pos = inFASTA.tellg(); positions.push_back(pos - input.length() - 1); }
+ }
}
inFASTA.close();
driver(lines[0], alignFileName, reportFileName);
#endif
- cout << "It took " << time(NULL) - start << " secs to align " << numFastaSeqs << " sequences" << endl;
- cout << endl;
-
-
+ mothurOut("It took " + toString(time(NULL) - start) + " secs to align " + toString(numFastaSeqs) + " sequences.");
+ mothurOutEndLine();
+ mothurOutEndLine();
return 0;
}
catch(exception& e) {
- cout << "Standard Error: " << e.what() << " has occurred in the AlignCommand class Function execute. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
+ errorOut(e, "AlignCommand", "execute");
exit(1);
}
- catch(...) {
- cout << "An unknown error has occurred in the AlignCommand class function execute. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
- exit(1);
- }
}
//**********************************************************************************************************************
ifstream inFASTA;
openInputFile(candidateFileName, inFASTA);
+
inFASTA.seekg(line->start);
-
+
for(int i=0;i<line->numSeqs;i++){
Sequence* candidateSeq = new Sequence(inFASTA);
+
+ if (candidateSeq->getUnaligned().length() > alignment->getnRows()) {
+ alignment->resize(candidateSeq->getUnaligned().length()+1);
+ }
+
report.setCandidate(candidateSeq);
-
+
Sequence temp = templateDB->findClosestSequence(candidateSeq);
Sequence* templateSeq = &temp;
-
+
report.setTemplate(templateSeq);
report.setSearchParameters(search, templateDB->getSearchScore());
-
+
Nast nast(alignment, candidateSeq, templateSeq);
+
report.setAlignmentParameters(align, alignment);
+
report.setNastParameters(nast);
-
+
alignmentFile << '>' << candidateSeq->getName() << '\n' << candidateSeq->getAligned() << endl;
-
+
report.print();
- delete candidateSeq;
+ delete candidateSeq;
+
}
alignmentFile.close();
return 1;
}
catch(exception& e) {
- cout << "Standard Error: " << e.what() << " has occurred in the AlignCommand class Function driver. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
+ errorOut(e, "AlignCommand", "driver");
exit(1);
}
- catch(...) {
- cout << "An unknown error has occurred in the AlignCommand class function driver. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
- exit(1);
- }
}
/**************************************************************************************************/
}else if (pid == 0){
driver(lines[process], alignFileName + toString(getpid()) + ".temp", reportFileName + toString(getpid()) + ".temp");
exit(0);
- }else { cout << "unable to spawn the necessary processes." << endl; exit(0); }
+ }else { mothurOut("unable to spawn the necessary processes."); mothurOutEndLine(); exit(0); }
}
//force parent to wait until all the processes are done
#endif
}
catch(exception& e) {
- cout << "Standard Error: " << e.what() << " has occurred in the AlignCommand class Function createProcesses. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
+ errorOut(e, "AlignCommand", "createProcesses");
exit(1);
}
- catch(...) {
- cout << "An unknown error has occurred in the AlignCommand class function createProcesses. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
- exit(1);
- }
}
/**************************************************************************************************/
output.close();
}
catch(exception& e) {
- cout << "Standard Error: " << e.what() << " has occurred in the DistanceCommand class Function appendFiles. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
+ errorOut(e, "AlignCommand", "appendAlignFiles");
exit(1);
}
- catch(...) {
- cout << "An unknown error has occurred in the DistanceCommand class function appendFiles. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
- exit(1);
- }
}
/**************************************************************************************************/
output.close();
}
catch(exception& e) {
- cout << "Standard Error: " << e.what() << " has occurred in the DistanceCommand class Function appendFiles. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
+ errorOut(e, "AlignCommand", "appendReportFiles");
exit(1);
}
- catch(...) {
- cout << "An unknown error has occurred in the DistanceCommand class function appendFiles. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
- exit(1);
- }
}
//**********************************************************************************************************************