#include "needlemanoverlap.hpp"
#include "blastalign.hpp"
#include "noalign.hpp"
-#include "nast.hpp"
#include "ignoregaps.h"
#include "eachgapdist.h"
//**********************************************************************************************************************
-vector<string> PairwiseSeqsCommand::getValidParameters(){
+vector<string> PairwiseSeqsCommand::setParameters(){
try {
- string AlignArray[] = {"fasta","align","match","mismatch","gapopen","gapextend", "processors","calc","compress","cutoff","countends","output","outputdir","inputdir"};
- vector<string> myArray (AlignArray, AlignArray+(sizeof(AlignArray)/sizeof(string)));
- return myArray;
- }
- catch(exception& e) {
- m->errorOut(e, "PairwiseSeqsCommand", "getValidParameters");
- exit(1);
- }
-}
-//**********************************************************************************************************************
-vector<string> PairwiseSeqsCommand::getRequiredParameters(){
- try {
- string AlignArray[] = {"fasta"};
- vector<string> myArray (AlignArray, AlignArray+(sizeof(AlignArray)/sizeof(string)));
+ CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(pfasta);
+ CommandParameter palign("align", "Multiple", "needleman-gotoh-blast-noalign", "needleman", "", "", "",false,false); parameters.push_back(palign);
+ CommandParameter pmatch("match", "Number", "", "1.0", "", "", "",false,false); parameters.push_back(pmatch);
+ CommandParameter pmismatch("mismatch", "Number", "", "-1.0", "", "", "",false,false); parameters.push_back(pmismatch);
+ CommandParameter pgapopen("gapopen", "Number", "", "-2.0", "", "", "",false,false); parameters.push_back(pgapopen);
+ CommandParameter pgapextend("gapextend", "Number", "", "-1.0", "", "", "",false,false); parameters.push_back(pgapextend);
+ CommandParameter pprocessors("processors", "Number", "", "1", "", "", "",false,false); parameters.push_back(pprocessors);
+ CommandParameter poutput("output", "Multiple", "column-lt-square", "column", "", "", "",false,false); parameters.push_back(poutput);
+ CommandParameter pcalc("calc", "Multiple", "nogaps-eachgap-onegap", "onegap", "", "", "",false,false); parameters.push_back(pcalc);
+ CommandParameter pcountends("countends", "Boolean", "", "T", "", "", "",false,false); parameters.push_back(pcountends);
+ CommandParameter pcompress("compress", "Boolean", "", "F", "", "", "",false,false); parameters.push_back(pcompress);
+ CommandParameter pcutoff("cutoff", "Number", "", "1.0", "", "", "",false,false); parameters.push_back(pcutoff);
+ CommandParameter pinputdir("inputdir", "String", "", "", "", "", "",false,false); parameters.push_back(pinputdir);
+ CommandParameter poutputdir("outputdir", "String", "", "", "", "", "",false,false); parameters.push_back(poutputdir);
+
+ vector<string> myArray;
+ for (int i = 0; i < parameters.size(); i++) { myArray.push_back(parameters[i].name); }
return myArray;
}
catch(exception& e) {
- m->errorOut(e, "PairwiseSeqsCommand", "getRequiredParameters");
+ m->errorOut(e, "PairwiseSeqsCommand", "setParameters");
exit(1);
}
}
//**********************************************************************************************************************
-vector<string> PairwiseSeqsCommand::getRequiredFiles(){
+string PairwiseSeqsCommand::getHelpString(){
try {
- vector<string> myArray;
- return myArray;
+ string helpString = "";
+ helpString += "The pairwise.seqs command reads a fasta file and creates distance matrix.\n";
+ helpString += "The pairwise.seqs command parameters are fasta, align, match, mismatch, gapopen, gapextend, calc, output, cutoff and processors.\n";
+ helpString += "The fasta parameter is required. You may enter multiple fasta files by separating their names with dashes. ie. fasta=abrecovery.fasta-amzon.fasta \n";
+ helpString += "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";
+ helpString += "The match parameter allows you to specify the bonus for having the same base. The default is 1.0.\n";
+ helpString += "The mistmatch parameter allows you to specify the penalty for having different bases. The default is -1.0.\n";
+ helpString += "The gapopen parameter allows you to specify the penalty for opening a gap in an alignment. The default is -2.0.\n";
+ helpString += "The gapextend parameter allows you to specify the penalty for extending a gap in an alignment. The default is -1.0.\n";
+ helpString += "The calc parameter allows you to specify the method of calculating the distances. Your options are: nogaps, onegap or eachgap. The default is onegap.\n";
+ helpString += "The countends parameter allows you to specify whether to include terminal gaps in distance. Your options are: T or F. The default is T.\n";
+ helpString += "The cutoff parameter allows you to specify maximum distance to keep. The default is 1.0.\n";
+ helpString += "The output parameter allows you to specify format of your distance matrix. Options are column, lt, and square. The default is column.\n";
+ helpString += "The compress parameter allows you to indicate that you want the resulting distance file compressed. The default is false.\n";
+ helpString += "The pairwise.seqs command should be in the following format: \n";
+ helpString += "pairwise.seqs(fasta=yourfastaFile, align=yourAlignmentMethod) \n";
+ helpString += "Example pairwise.seqs(fasta=candidate.fasta, align=blast)\n";
+ helpString += "Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFastaFile).\n";
+ return helpString;
}
catch(exception& e) {
- m->errorOut(e, "PairwiseSeqsCommand", "getRequiredFiles");
+ m->errorOut(e, "PairwiseSeqsCommand", "getHelpString");
exit(1);
}
}
+
//**********************************************************************************************************************
PairwiseSeqsCommand::PairwiseSeqsCommand(){
try {
abort = true; calledHelp = true;
+ setParameters();
vector<string> tempOutNames;
outputTypes["phylip"] = tempOutNames;
outputTypes["column"] = tempOutNames;
if(option == "help") { help(); abort = true; calledHelp = true; }
else {
-
- //valid paramters for this command
- string AlignArray[] = {"fasta","align","match","mismatch","gapopen","gapextend", "processors","cutoff","compress","calc","countends","output","outputdir","inputdir"};
- vector<string> myArray (AlignArray, AlignArray+(sizeof(AlignArray)/sizeof(string)));
+ vector<string> myArray = setParameters();
OptionParser parser(option);
map<string, string> parameters = parser.getParameters();
if (inputDir == "not found"){ inputDir = ""; }
fastaFileName = validParameter.validFile(parameters, "fasta", false);
- if (fastaFileName == "not found") { m->mothurOut("fasta is a required parameter for the pairwise.seqs command."); m->mothurOutEndLine(); abort = true; }
+ if (fastaFileName == "not found") {
+ //if there is a current fasta file, use it
+ string filename = m->getFastaFile();
+ if (filename != "") { fastaFileNames.push_back(filename); m->mothurOut("Using " + filename + " as input file for the fasta parameter."); m->mothurOutEndLine(); }
+ else { m->mothurOut("You have no current fastafile and the fasta parameter is required."); m->mothurOutEndLine(); abort = true; }
+ }
else {
m->splitAtDash(fastaFileName, fastaFileNames);
//go through files and make sure they are good, if not, then disregard them
for (int i = 0; i < fastaFileNames.size(); i++) {
- if (inputDir != "") {
- string path = m->hasPath(fastaFileNames[i]);
- //if the user has not given a path then, add inputdir. else leave path alone.
- if (path == "") { fastaFileNames[i] = inputDir + fastaFileNames[i]; }
- }
-
- int ableToOpen;
- ifstream in;
-
- ableToOpen = m->openInputFile(fastaFileNames[i], in, "noerror");
-
- //if you can't open it, try default location
- if (ableToOpen == 1) {
- if (m->getDefaultPath() != "") { //default path is set
- string tryPath = m->getDefaultPath() + m->getSimpleName(fastaFileNames[i]);
- m->mothurOut("Unable to open " + fastaFileNames[i] + ". Trying default " + tryPath); m->mothurOutEndLine();
- ifstream in2;
- ableToOpen = m->openInputFile(tryPath, in2, "noerror");
- in2.close();
- fastaFileNames[i] = tryPath;
+ bool ignore = false;
+ if (fastaFileNames[i] == "current") {
+ fastaFileNames[i] = m->getFastaFile();
+ if (fastaFileNames[i] != "") { m->mothurOut("Using " + fastaFileNames[i] + " as input file for the fasta parameter where you had given current."); m->mothurOutEndLine(); }
+ else {
+ m->mothurOut("You have no current fastafile, ignoring current."); m->mothurOutEndLine(); ignore=true;
+ //erase from file list
+ fastaFileNames.erase(fastaFileNames.begin()+i);
+ i--;
}
}
- //if you can't open it, try output location
- if (ableToOpen == 1) {
- if (m->getOutputDir() != "") { //default path is set
- string tryPath = m->getOutputDir() + m->getSimpleName(fastaFileNames[i]);
- m->mothurOut("Unable to open " + fastaFileNames[i] + ". Trying output directory " + tryPath); m->mothurOutEndLine();
- ifstream in2;
- ableToOpen = m->openInputFile(tryPath, in2, "noerror");
- in2.close();
- fastaFileNames[i] = tryPath;
+ if (!ignore) {
+
+ if (inputDir != "") {
+ string path = m->hasPath(fastaFileNames[i]);
+ //if the user has not given a path then, add inputdir. else leave path alone.
+ if (path == "") { fastaFileNames[i] = inputDir + fastaFileNames[i]; }
}
- }
+
+ int ableToOpen;
+ ifstream in;
+
+ ableToOpen = m->openInputFile(fastaFileNames[i], in, "noerror");
- in.close();
+ //if you can't open it, try default location
+ if (ableToOpen == 1) {
+ if (m->getDefaultPath() != "") { //default path is set
+ string tryPath = m->getDefaultPath() + m->getSimpleName(fastaFileNames[i]);
+ m->mothurOut("Unable to open " + fastaFileNames[i] + ". Trying default " + tryPath); m->mothurOutEndLine();
+ ifstream in2;
+ ableToOpen = m->openInputFile(tryPath, in2, "noerror");
+ in2.close();
+ fastaFileNames[i] = tryPath;
+ }
+ }
+
+ //if you can't open it, try output location
+ if (ableToOpen == 1) {
+ if (m->getOutputDir() != "") { //default path is set
+ string tryPath = m->getOutputDir() + m->getSimpleName(fastaFileNames[i]);
+ m->mothurOut("Unable to open " + fastaFileNames[i] + ". Trying output directory " + tryPath); m->mothurOutEndLine();
+ ifstream in2;
+ ableToOpen = m->openInputFile(tryPath, in2, "noerror");
+ in2.close();
+ fastaFileNames[i] = tryPath;
+ }
+ }
+
+ in.close();
- if (ableToOpen == 1) {
- m->mothurOut("Unable to open " + fastaFileNames[i] + ". It will be disregarded."); m->mothurOutEndLine();
- //erase from file list
- fastaFileNames.erase(fastaFileNames.begin()+i);
- i--;
+ if (ableToOpen == 1) {
+ m->mothurOut("Unable to open " + fastaFileNames[i] + ". It will be disregarded."); m->mothurOutEndLine();
+ //erase from file list
+ fastaFileNames.erase(fastaFileNames.begin()+i);
+ i--;
+ }
}
}
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);
+ temp = validParameter.validFile(parameters, "processors", false); if (temp == "not found"){ temp = m->getProcessors(); }
+ m->setProcessors(temp);
+ convert(temp, processors);
temp = validParameter.validFile(parameters, "cutoff", false); if(temp == "not found"){ temp = "1.0"; }
convert(temp, cutoff);
exit(1);
}
}
-//**********************************************************************************************************************
-PairwiseSeqsCommand::~PairwiseSeqsCommand(){}
-//**********************************************************************************************************************
-
-void PairwiseSeqsCommand::help(){
- try {
- m->mothurOut("The pairwise.seqs command reads a fasta file and creates distance matrix.\n");
- m->mothurOut("The pairwise.seqs command parameters are fasta, align, match, mismatch, gapopen, gapextend, calc, output, cutoff and processors.\n");
- m->mothurOut("The fasta parameter is required. You may enter multiple fasta files by separating their names with dashes. ie. fasta=abrecovery.fasta-amzon.fasta \n");
- m->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");
- m->mothurOut("The match parameter allows you to specify the bonus for having the same base. The default is 1.0.\n");
- m->mothurOut("The mistmatch parameter allows you to specify the penalty for having different bases. The default is -1.0.\n");
- m->mothurOut("The gapopen parameter allows you to specify the penalty for opening a gap in an alignment. The default is -2.0.\n");
- m->mothurOut("The gapextend parameter allows you to specify the penalty for extending a gap in an alignment. The default is -1.0.\n");
- m->mothurOut("The calc parameter allows you to specify the method of calculating the distances. Your options are: nogaps, onegap or eachgap. The default is onegap.\n");
- m->mothurOut("The countends parameter allows you to specify whether to include terminal gaps in distance. Your options are: T or F. The default is T.\n");
- m->mothurOut("The cutoff parameter allows you to specify maximum distance to keep. The default is 1.0.\n");
- m->mothurOut("The output parameter allows you to specify format of your distance matrix. Options are column, lt, and square. The default is column.\n");
- m->mothurOut("The compress parameter allows you to indicate that you want the resulting distance file compressed. The default is false.\n");
- m->mothurOut("The pairwise.seqs command should be in the following format: \n");
- m->mothurOut("pairwise.seqs(fasta=yourfastaFile, align=yourAlignmentMethod) \n");
- m->mothurOut("Example pairwise.seqs(fasta=candidate.fasta, align=blast)\n");
- m->mothurOut("Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFastaFile).\n\n");
- }
- catch(exception& e) {
- m->errorOut(e, "PairwiseSeqsCommand", "help");
- exit(1);
- }
-}
-
-
//**********************************************************************************************************************
int PairwiseSeqsCommand::execute(){
delete distCalculator;
+ //set phylip file as new current phylipfile
+ string current = "";
+ itTypes = outputTypes.find("phylip");
+ if (itTypes != outputTypes.end()) {
+ if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setPhylipFile(current); }
+ }
+
+ //set column file as new current columnfile
+ itTypes = outputTypes.find("column");
+ if (itTypes != outputTypes.end()) {
+ if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setColumnFile(current); }
+ }
+
m->mothurOutEndLine();
m->mothurOut("Output File Name: "); m->mothurOutEndLine();
for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); }
alignment->resize(alignDB.get(j).getUnaligned().length()+1);
}
- Sequence* seqI = new Sequence(alignDB.get(i).getName(), alignDB.get(i).getAligned());
- Sequence* seqJ = new Sequence(alignDB.get(j).getName(), alignDB.get(j).getAligned());
+ Sequence seqI(alignDB.get(i).getName(), alignDB.get(i).getAligned());
+ Sequence seqJ(alignDB.get(j).getName(), alignDB.get(j).getAligned());
- Nast(alignment, seqI, seqJ);
+ alignment->align(seqI.getUnaligned(), seqJ.getUnaligned());
+ seqI.setAligned(alignment->getSeqAAln());
+ seqJ.setAligned(alignment->getSeqBAln());
+
- distCalculator->calcDist(*seqI, *seqJ);
+ distCalculator->calcDist(seqI, seqJ);
double dist = distCalculator->getDist();
- delete seqI; delete seqJ;
-
if(dist <= cutoff){
if (output == "column") { outFile << alignDB.get(i).getName() << ' ' << alignDB.get(j).getName() << ' ' << dist << endl; }
}
alignment->resize(alignDB.get(j).getUnaligned().length()+1);
}
- Sequence* seqI = new Sequence(alignDB.get(i).getName(), alignDB.get(i).getAligned());
- Sequence* seqJ = new Sequence(alignDB.get(j).getName(), alignDB.get(j).getAligned());
+ Sequence seqI(alignDB.get(i).getName(), alignDB.get(i).getAligned());
+ Sequence seqJ(alignDB.get(j).getName(), alignDB.get(j).getAligned());
- Nast(alignment, seqI, seqJ);
+ alignment->align(seqI.getUnaligned(), seqJ.getUnaligned());
+ seqI.setAligned(alignment->getSeqAAln());
+ seqJ.setAligned(alignment->getSeqBAln());
- distCalculator->calcDist(*seqI, *seqJ);
+ distCalculator->calcDist(seqI, seqJ);
double dist = distCalculator->getDist();
-
- delete seqI; delete seqJ;
outFile << dist << '\t';
}
alignment->resize(alignDB.get(j).getUnaligned().length()+1);
}
- Sequence* seqI = new Sequence(alignDB.get(i).getName(), alignDB.get(i).getAligned());
- Sequence* seqJ = new Sequence(alignDB.get(j).getName(), alignDB.get(j).getAligned());
+ Sequence seqI(alignDB.get(i).getName(), alignDB.get(i).getAligned());
+ Sequence seqJ(alignDB.get(j).getName(), alignDB.get(j).getAligned());
- Nast(alignment, seqI, seqJ);
+ alignment->align(seqI.getUnaligned(), seqJ.getUnaligned());
+ seqI.setAligned(alignment->getSeqAAln());
+ seqJ.setAligned(alignment->getSeqBAln());
- distCalculator->calcDist(*seqI, *seqJ);
+ distCalculator->calcDist(seqI, seqJ);
double dist = distCalculator->getDist();
- delete seqI; delete seqJ;
-
if(dist <= cutoff){
outputString += (alignDB.get(i).getName() + ' ' + alignDB.get(j).getName() + ' ' + toString(dist) + '\n');
}
alignment->resize(alignDB.get(j).getUnaligned().length()+1);
}
- Sequence* seqI = new Sequence(alignDB.get(i).getName(), alignDB.get(i).getAligned());
- Sequence* seqJ = new Sequence(alignDB.get(j).getName(), alignDB.get(j).getAligned());
+ Sequence seqI(alignDB.get(i).getName(), alignDB.get(i).getAligned());
+ Sequence seqJ(alignDB.get(j).getName(), alignDB.get(j).getAligned());
- Nast(alignment, seqI, seqJ);
+ alignment->align(seqI.getUnaligned(), seqJ.getUnaligned());
+ seqI.setAligned(alignment->getSeqAAln());
+ seqJ.setAligned(alignment->getSeqBAln());
- distCalculator->calcDist(*seqI, *seqJ);
+ distCalculator->calcDist(seqI, seqJ);
double dist = distCalculator->getDist();
- delete seqI; delete seqJ;
-
outputString += toString(dist) + "\t";
}
alignment->resize(alignDB.get(j).getUnaligned().length()+1);
}
- Sequence* seqI = new Sequence(alignDB.get(i).getName(), alignDB.get(i).getAligned());
- Sequence* seqJ = new Sequence(alignDB.get(j).getName(), alignDB.get(j).getAligned());
+ Sequence seqI(alignDB.get(i).getName(), alignDB.get(i).getAligned());
+ Sequence seqJ(alignDB.get(j).getName(), alignDB.get(j).getAligned());
- Nast(alignment, seqI, seqJ);
+ alignment->align(seqI.getUnaligned(), seqJ.getUnaligned());
+ seqI.setAligned(alignment->getSeqAAln());
+ seqJ.setAligned(alignment->getSeqBAln());
- distCalculator->calcDist(*seqI, *seqJ);
+ distCalculator->calcDist(seqI, seqJ);
double dist = distCalculator->getDist();
- delete seqI; delete seqJ;
-
outputString += toString(dist) + "\t";
}