From 49b8297d25caae7ad4cf1e5208a4a66fdfe071fe Mon Sep 17 00:00:00 2001 From: pschloss Date: Tue, 16 Jun 2009 21:18:51 +0000 Subject: [PATCH] a few minor things - pds --- Mothur.xcodeproj/project.pbxproj | 16 +++--- aligncommand.cpp | 90 ++++++++++++++++---------------- aligncommand.h | 10 ++-- heatmapsimcommand.cpp | 4 +- nastreport.cpp | 6 +++ nastreport.hpp | 1 + screenseqscommand.cpp | 8 +-- sequence.cpp | 2 +- 8 files changed, 72 insertions(+), 65 deletions(-) diff --git a/Mothur.xcodeproj/project.pbxproj b/Mothur.xcodeproj/project.pbxproj index 25e6296..e6a9c0c 100644 --- a/Mothur.xcodeproj/project.pbxproj +++ b/Mothur.xcodeproj/project.pbxproj @@ -277,12 +277,12 @@ 375AA1380F9E433D008EF9B8 /* readphylip.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; path = readphylip.h; sourceTree = SOURCE_ROOT; }; 377326630FAF16E0007ABB8B /* concensuscommand.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; path = concensuscommand.cpp; sourceTree = SOURCE_ROOT; }; 377326640FAF16E0007ABB8B /* concensuscommand.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; path = concensuscommand.h; sourceTree = SOURCE_ROOT; }; - 378598640FDD497000EF9D03 /* heatmapsimcommand.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; path = heatmapsimcommand.h; sourceTree = ""; }; - 378598650FDD497000EF9D03 /* heatmapsimcommand.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; path = heatmapsimcommand.cpp; sourceTree = ""; }; - 378598720FDD4C1500EF9D03 /* heatmapsim.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; path = heatmapsim.h; sourceTree = ""; }; - 378598730FDD4C1500EF9D03 /* heatmapsim.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; path = heatmapsim.cpp; sourceTree = ""; }; - 3785990E0FDD7E8E00EF9D03 /* optionparser.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; path = optionparser.h; sourceTree = ""; }; - 3785990F0FDD7E8E00EF9D03 /* optionparser.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; path = optionparser.cpp; sourceTree = ""; }; + 378598640FDD497000EF9D03 /* heatmapsimcommand.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; path = heatmapsimcommand.h; sourceTree = SOURCE_ROOT; }; + 378598650FDD497000EF9D03 /* heatmapsimcommand.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; path = heatmapsimcommand.cpp; sourceTree = SOURCE_ROOT; }; + 378598720FDD4C1500EF9D03 /* heatmapsim.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; path = heatmapsim.h; sourceTree = SOURCE_ROOT; }; + 378598730FDD4C1500EF9D03 /* heatmapsim.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; path = heatmapsim.cpp; sourceTree = SOURCE_ROOT; }; + 3785990E0FDD7E8E00EF9D03 /* optionparser.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; path = optionparser.h; sourceTree = SOURCE_ROOT; }; + 3785990F0FDD7E8E00EF9D03 /* optionparser.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; path = optionparser.cpp; sourceTree = SOURCE_ROOT; }; 378C1AEE0FB0644D004D63F5 /* filterseqscommand.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; path = filterseqscommand.cpp; sourceTree = SOURCE_ROOT; }; 378C1AEF0FB0644D004D63F5 /* filterseqscommand.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; path = filterseqscommand.h; sourceTree = SOURCE_ROOT; }; 378C1AF00FB0644D004D63F5 /* goodscoverage.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; path = goodscoverage.cpp; sourceTree = SOURCE_ROOT; }; @@ -477,8 +477,8 @@ 7E412FE90F8D3E2C00381DD0 /* libshuff.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; path = libshuff.cpp; sourceTree = SOURCE_ROOT; }; 7E4130F60F8E58FA00381DD0 /* dlibshuff.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; path = dlibshuff.cpp; sourceTree = SOURCE_ROOT; }; 7E4130F70F8E58FA00381DD0 /* dlibshuff.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; path = dlibshuff.h; sourceTree = SOURCE_ROOT; }; - 7E5A17AD0FE57292003C6A03 /* mergefilecommand.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; path = mergefilecommand.h; sourceTree = ""; }; - 7E5A17AE0FE57292003C6A03 /* mergefilecommand.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; path = mergefilecommand.cpp; sourceTree = ""; }; + 7E5A17AD0FE57292003C6A03 /* mergefilecommand.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; path = mergefilecommand.h; sourceTree = SOURCE_ROOT; }; + 7E5A17AE0FE57292003C6A03 /* mergefilecommand.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; path = mergefilecommand.cpp; sourceTree = SOURCE_ROOT; }; 7EC3D4500FA0FFF900338DA5 /* coverage.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; path = coverage.cpp; sourceTree = SOURCE_ROOT; }; 7EC3D4510FA0FFF900338DA5 /* coverage.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; path = coverage.h; sourceTree = SOURCE_ROOT; }; 7EC3D4520FA0FFF900338DA5 /* sharedanderberg.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; path = sharedanderberg.h; sourceTree = SOURCE_ROOT; }; diff --git a/aligncommand.cpp b/aligncommand.cpp index 2811f1f..e628908 100644 --- a/aligncommand.cpp +++ b/aligncommand.cpp @@ -34,14 +34,14 @@ AlignCommand::AlignCommand(string option){ try { -// globaldata = GlobalData::getInstance(); + // globaldata = GlobalData::getInstance(); abort = false; //allow user to run help if(option == "help") { help(); abort = true; } else { - + //valid paramters for this command string AlignArray[] = {"template","candidate","search","ksize","align","match","mismatch","gapopen","gapextend", "processors"}; vector myArray (AlignArray, AlignArray+(sizeof(AlignArray)/sizeof(string))); @@ -50,7 +50,7 @@ AlignCommand::AlignCommand(string option){ map parameters = parser.getParameters(); ValidParameters validParameter; - + //check to make sure all parameters are valid for command for (map::iterator it = parameters.begin(); it != parameters.end(); it++) { if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; } @@ -60,7 +60,7 @@ AlignCommand::AlignCommand(string option){ templateFileName = validParameter.validFile(parameters, "template", true); if (templateFileName == "not found") { cout << "template is a required parameter for the align.seqs command." << endl; 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; } else if (candidateFileName == "not open") { abort = true; } @@ -70,27 +70,27 @@ AlignCommand::AlignCommand(string option){ string temp; temp = validParameter.validFile(parameters, "ksize", false); if (temp == "not found"){ temp = "8"; } convert(temp, kmerSize); - + temp = validParameter.validFile(parameters, "match", false); if (temp == "not found"){ temp = "1.0"; } convert(temp, match); - + temp = validParameter.validFile(parameters, "mismatch", false); if (temp == "not found"){ temp = "-1.0"; } convert(temp, misMatch); - - temp = validParameter.validFile(parameters, "gapopen", false); if (temp == "not found"){ temp = "-1.0"; } + + temp = validParameter.validFile(parameters, "gapopen", false); if (temp == "not found"){ temp = "-2.0"; } convert(temp, gapOpen); - - temp = validParameter.validFile(parameters, "gapextend", false); if (temp == "not found"){ temp = "-2.0"; } + + temp = validParameter.validFile(parameters, "gapextend", false); if (temp == "not found"){ temp = "-1.0"; } convert(temp, gapExtend); - + temp = validParameter.validFile(parameters, "processors", false); if (temp == "not found"){ temp = "1"; } convert(temp, processors); - + search = validParameter.validFile(parameters, "search", false); if (search == "not found"){ search = "kmer"; } align = validParameter.validFile(parameters, "align", false); if (align == "not found"){ align = "needleman"; } } - + } 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"; @@ -114,8 +114,8 @@ AlignCommand::~AlignCommand(){ 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 fasta, candidate, search, ksize, align, match, mismatch, gapopen and gapextend. " << "\n"; - cout << "The fasta and candidate parameters are required." << "\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"; @@ -124,9 +124,9 @@ void AlignCommand::help(){ 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(fasta=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, fasta=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. fasta), '=' and parameters (i.e.yourFastaFile)." << "\n" << "\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"; } 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"; @@ -144,10 +144,10 @@ void AlignCommand::help(){ int AlignCommand::execute(){ try { if (abort == true) { return 0; } - + srand( (unsigned)time( NULL ) ); //needed to assign names to temporary files - + 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); } @@ -155,7 +155,7 @@ int AlignCommand::execute(){ 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); } else if(align == "blast") { alignment = new BlastAlignment(gapOpen, gapExtend, match, misMatch); } @@ -184,10 +184,11 @@ int AlignCommand::execute(){ } else{ vector positions; + processIDS.resize(0); ifstream inFASTA; openInputFile(candidateFileName, inFASTA); - + while(!inFASTA.eof()){ char c = inFASTA.get(); if(c == '>'){ positions.push_back(inFASTA.tellg()); } @@ -207,20 +208,16 @@ int AlignCommand::execute(){ lines.push_back(new linePair(startPos, numSeqsPerProcessor)); } createProcesses(alignFileName, reportFileName); - - //append and remove temp files - map::iterator it = processIDS.begin(); - rename((alignFileName + toString(it->second) + ".temp").c_str(), alignFileName.c_str()); - rename((reportFileName + toString(it->second) + ".temp").c_str(), alignFileName.c_str()); - it++; + rename((alignFileName + toString(processIDS[0]) + ".temp").c_str(), alignFileName.c_str()); + rename((reportFileName + toString(processIDS[0]) + ".temp").c_str(), reportFileName.c_str()); - for (; it != processIDS.end(); it++) { - appendAlignFiles((alignFileName + toString(it->second) + ".temp"), alignFileName); - remove((alignFileName + toString(it->second) + ".temp").c_str()); - - appendReportFiles((reportFileName + toString(it->second) + ".temp"), reportFileName); - remove((reportFileName + toString(it->second) + ".temp").c_str()); + for(int i=1;i 0) { - processIDS[lines[process]->numSeqs] = pid; //create map from line number to pid so you can append files in correct order later + processIDS.push_back(pid); //create map from line number to pid so you can append files in correct order later process++; }else if (pid == 0){ driver(lines[process], alignFileName + toString(getpid()) + ".temp", reportFileName + toString(getpid()) + ".temp"); @@ -317,8 +317,8 @@ void AlignCommand::createProcesses(string alignFileName, string reportFileName) } //force parent to wait until all the processes are done - for (map::iterator it = processIDS.begin(); it != processIDS.end(); it++) { - int temp = it->second; + for (int i=0;i processIDS; //end line, processid + vector processIDS; //processid vector lines; - + Database* templateDB; Alignment* alignment; - + int driver(linePair*, string, string); void createProcesses(string, string); void appendAlignFiles(string, string); @@ -43,7 +43,7 @@ private: string candidateFileName, templateFileName, distanceFileName, search, align; float match, misMatch, gapOpen, gapExtend; int processors, kmerSize; - + bool abort; }; diff --git a/heatmapsimcommand.cpp b/heatmapsimcommand.cpp index 68076d3..3b0d798 100644 --- a/heatmapsimcommand.cpp +++ b/heatmapsimcommand.cpp @@ -81,9 +81,9 @@ HeatMapSimCommand::HeatMapSimCommand(string option){ } calc = validParameter.validFile(parameters, "calc", false); - if (calc == "not found") { calc = "jclass-thetayc"; } + if (calc == "not found") { calc = "jest-thetayc"; } else { - if (calc == "default") { calc = "jclass-thetayc"; } + if (calc == "default") { calc = "jest-thetayc"; } } splitAtDash(calc, Estimators); diff --git a/nastreport.cpp b/nastreport.cpp index 0f361f1..d7be4dd 100644 --- a/nastreport.cpp +++ b/nastreport.cpp @@ -27,6 +27,12 @@ NastReport::NastReport(string candidateReportFName) { /******************************************************************************************************************/ +NastReport::~NastReport() { + candidateReportFile.close(); +} + +/******************************************************************************************************************/ + void NastReport::print(){ candidateReportFile << queryName << '\t' << queryLength << '\t' << templateName << '\t' << templateLength << '\t'; diff --git a/nastreport.hpp b/nastreport.hpp index be75efd..2be289c 100644 --- a/nastreport.hpp +++ b/nastreport.hpp @@ -19,6 +19,7 @@ class NastReport { public: NastReport(string); + ~NastReport(); void setCandidate(Sequence*); void setTemplate(Sequence*); void setSearchParameters(string, float); diff --git a/screenseqscommand.cpp b/screenseqscommand.cpp index 5789fd0..bc375de 100644 --- a/screenseqscommand.cpp +++ b/screenseqscommand.cpp @@ -51,10 +51,10 @@ ScreenSeqsCommand::ScreenSeqsCommand(string option){ //check for optional parameter and set defaults // ...at some point should added some additional type checking... string temp; - temp = validParameter.validFile(parameters, "start", false); if (temp == "not found") { temp = "-1"; } + temp = validParameter.validFile(parameters, "start", false); if (temp == "not found") { temp = "-1"; } convert(temp, startPos); - temp = validParameter.validFile(parameters, "end", false); if (temp == "not found") { temp = "-1"; } + temp = validParameter.validFile(parameters, "end", false); if (temp == "not found") { temp = "-1"; } convert(temp, endPos); temp = validParameter.validFile(parameters, "maxambig", false); if (temp == "not found") { temp = "-1"; } @@ -63,10 +63,10 @@ ScreenSeqsCommand::ScreenSeqsCommand(string option){ temp = validParameter.validFile(parameters, "maxhomop", false); if (temp == "not found") { temp = "-1"; } convert(temp, maxHomoP); - temp = validParameter.validFile(parameters, "minlength", false); if (temp == "not found") { temp = "-1"; } + temp = validParameter.validFile(parameters, "minlength", false); if (temp == "not found") { temp = "-1"; } convert(temp, minLength); - temp = validParameter.validFile(parameters, "maxlength", false); if (temp == "not found") { temp = "-1"; } + temp = validParameter.validFile(parameters, "maxlength", false); if (temp == "not found") { temp = "-1"; } convert(temp, maxLength); } diff --git a/sequence.cpp b/sequence.cpp index 580f68a..aa1f1c7 100644 --- a/sequence.cpp +++ b/sequence.cpp @@ -89,7 +89,7 @@ void Sequence::setName(string seqName) { void Sequence::setUnaligned(string sequence){ - if(sequence.find_first_of('-') != string::npos) { + if(sequence.find_first_of('.') != string::npos || sequence.find_first_of('-') != string::npos) { string temp = ""; for(int j=0;j