//**********************************************************************************************************************
inline bool comparePriority(seqPNode first, seqPNode second) { return (first.numIdentical > second.numIdentical); }
+
+//**********************************************************************************************************************
+vector<string> PreClusterCommand::setParameters(){
+ try {
+ CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(pfasta);
+ CommandParameter pname("name", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(pname);
+ CommandParameter pdiffs("diffs", "Number", "", "0", "", "", "",false,false); parameters.push_back(pdiffs);
+ 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, "PreClusterCommand", "setParameters");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+string PreClusterCommand::getHelpString(){
+ try {
+ string helpString = "";
+ helpString += "The pre.cluster command groups sequences that are within a given number of base mismatches.\n";
+ helpString += "The pre.cluster command outputs a new fasta and name file.\n";
+ helpString += "The pre.cluster command parameters are fasta, names and diffs. The fasta parameter is required. \n";
+ helpString += "The names parameter allows you to give a list of seqs that are identical. This file is 2 columns, first column is name or representative sequence, second column is a list of its identical sequences separated by commas.\n";
+ helpString += "The diffs parameter allows you to specify maximum number of mismatched bases allowed between sequences in a grouping. The default is 1.\n";
+ helpString += "The pre.cluster command should be in the following format: \n";
+ helpString += "pre.cluster(fasta=yourFastaFile, names=yourNamesFile, diffs=yourMaxDiffs) \n";
+ helpString += "Example pre.cluster(fasta=amazon.fasta, diffs=2).\n";
+ helpString += "Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n";
+ return helpString;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "PreClusterCommand", "getHelpString");
+ exit(1);
+ }
+}
+
+//**********************************************************************************************************************
+PreClusterCommand::PreClusterCommand(){
+ try {
+ abort = true; calledHelp = true;
+ setParameters();
+ vector<string> tempOutNames;
+ outputTypes["fasta"] = tempOutNames;
+ outputTypes["name"] = tempOutNames;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "PreClusterCommand", "PreClusterCommand");
+ exit(1);
+ }
+}
//**********************************************************************************************************************
PreClusterCommand::PreClusterCommand(string option) {
try {
- abort = false;
+ abort = false; calledHelp = false;
//allow user to run help
- if(option == "help") { help(); abort = true; }
+ if(option == "help") { help(); abort = true; calledHelp = true; }
+ else if(option == "citation") { citation(); abort = true; calledHelp = true;}
else {
- //valid paramters for this command
- string Array[] = {"fasta", "name", "diffs", "outputdir","inputdir"};
- vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
+ vector<string> myArray = setParameters();
OptionParser parser(option);
map<string, string> parameters = parser.getParameters();
if (validParameter.isValidParameter(it2->first, myArray, it2->second) != true) { abort = true; }
}
+ //initialize outputTypes
+ vector<string> tempOutNames;
+ outputTypes["fasta"] = tempOutNames;
+ outputTypes["name"] = tempOutNames;
+
//if the user changes the input directory command factory will send this info to us in the output parameter
string inputDir = validParameter.validFile(parameters, "inputdir", false);
if (inputDir == "not found"){ inputDir = ""; }
it = parameters.find("fasta");
//user has given a template file
if(it != parameters.end()){
- path = hasPath(it->second);
+ path = m->hasPath(it->second);
//if the user has not given a path then, add inputdir. else leave path alone.
if (path == "") { parameters["fasta"] = inputDir + it->second; }
}
it = parameters.find("name");
//user has given a template file
if(it != parameters.end()){
- path = hasPath(it->second);
+ path = m->hasPath(it->second);
//if the user has not given a path then, add inputdir. else leave path alone.
if (path == "") { parameters["name"] = inputDir + it->second; }
}
//check for required parameters
fastafile = validParameter.validFile(parameters, "fasta", true);
- if (fastafile == "not found") { m->mothurOut("fasta is a required parameter for the pre.cluster command."); m->mothurOutEndLine(); abort = true; }
+ if (fastafile == "not found") {
+ fastafile = m->getFastaFile();
+ if (fastafile != "") { m->mothurOut("Using " + fastafile + " 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 if (fastafile == "not open") { abort = true; }
+ else { m->setFastaFile(fastafile); }
//if the user changes the output directory command factory will send this info to us in the output parameter
outputDir = validParameter.validFile(parameters, "outputdir", false); if (outputDir == "not found"){
outputDir = "";
- outputDir += hasPath(fastafile); //if user entered a file with a path then preserve it
+ outputDir += m->hasPath(fastafile); //if user entered a file with a path then preserve it
}
//check for optional parameter and set defaults
namefile = validParameter.validFile(parameters, "name", true);
if (namefile == "not found") { namefile = ""; }
else if (namefile == "not open") { abort = true; }
- else { readNameFile(); }
+ else { readNameFile(); m->setNameFile(namefile); }
string temp = validParameter.validFile(parameters, "diffs", false); if(temp == "not found"){ temp = "1"; }
convert(temp, diffs);
exit(1);
}
}
-
-//**********************************************************************************************************************
-PreClusterCommand::~PreClusterCommand(){}
-//**********************************************************************************************************************
-
-void PreClusterCommand::help(){
- try {
- m->mothurOut("The pre.cluster command groups sequences that are within a given number of base mismatches.\n");
- m->mothurOut("The pre.cluster command outputs a new fasta and name file.\n");
- m->mothurOut("The pre.cluster command parameters are fasta, names and diffs. The fasta parameter is required. \n");
- m->mothurOut("The names parameter allows you to give a list of seqs that are identical. This file is 2 columns, first column is name or representative sequence, second column is a list of its identical sequences separated by commas.\n");
- m->mothurOut("The diffs parameter allows you to specify maximum number of mismatched bases allowed between sequences in a grouping. The default is 1.\n");
- m->mothurOut("The pre.cluster command should be in the following format: \n");
- m->mothurOut("pre.cluster(fasta=yourFastaFile, names=yourNamesFile, diffs=yourMaxDiffs) \n");
- m->mothurOut("Example pre.cluster(fasta=amazon.fasta, diffs=2).\n");
- m->mothurOut("Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n\n");
- }
- catch(exception& e) {
- m->errorOut(e, "PreClusterCommand", "help");
- exit(1);
- }
-}
//**********************************************************************************************************************
int PreClusterCommand::execute(){
try {
- if (abort == true) { return 0; }
+ if (abort == true) { if (calledHelp) { return 0; } return 2; }
+
+ int start = time(NULL);
//reads fasta file and return number of seqs
int numSeqs = readFASTA(); //fills alignSeqs and makes all seqs active
if (numSeqs == 0) { m->mothurOut("Error reading fasta file...please correct."); m->mothurOutEndLine(); return 0; }
if (diffs > length) { m->mothurOut("Error: diffs is greater than your sequence length."); m->mothurOutEndLine(); return 0; }
- string fileroot = outputDir + getRootName(getSimpleName(fastafile));
- string newFastaFile = fileroot + "precluster" + getExtension(fastafile);
- string newNamesFile = fileroot + "precluster.names";
- ofstream outFasta;
- ofstream outNames;
-
- openOutputFile(newFastaFile, outFasta);
- openOutputFile(newNamesFile, outNames);
-
+ //clear sizes since you only needed this info to build the alignSeqs seqPNode structs
+// sizes.clear();
+
//sort seqs by number of identical seqs
- alignSeqs.sort(comparePriority);
-
+ sort(alignSeqs.begin(), alignSeqs.end(), comparePriority);
+
int count = 0;
- int i = 0;
+
//think about running through twice...
- list<seqPNode>::iterator itList;
- list<seqPNode>::iterator itList2;
- for (itList = alignSeqs.begin(); itList != alignSeqs.end();) {
+ for (int i = 0; i < numSeqs; i++) {
- //try to merge it with all smaller seqs
- for (itList2 = alignSeqs.begin(); itList2 != alignSeqs.end();) {
-
- if (m->control_pressed) { outFasta.close(); outNames.close(); remove(newFastaFile.c_str()); remove(newNamesFile.c_str()); return 0; }
-
+ //are you active
+ // itActive = active.find(alignSeqs[i].seq.getName());
- if (itList->seq.getName() != itList2->seq.getName()) { //you don't want to merge with yourself
- //are you within "diff" bases
+ if (alignSeqs[i].active) { //this sequence has not been merged yet
+
+ //try to merge it with all smaller seqs
+ for (int j = i+1; j < numSeqs; j++) {
- int mismatch = calcMisMatches((*itList).seq.getAligned(), (*itList2).seq.getAligned());
-
- if (mismatch <= diffs) {
- //merge
- (*itList).names += ',' + (*itList2).names;
- (*itList).numIdentical += (*itList2).numIdentical;
+ if (m->control_pressed) { return 0; }
+
+ if (alignSeqs[j].active) { //this sequence has not been merged yet
+ //are you within "diff" bases
+ int mismatch = calcMisMatches(alignSeqs[i].seq.getAligned(), alignSeqs[j].seq.getAligned());
- itList2 = alignSeqs.erase(itList2); //itList2--;
- count++;
- }else{ itList2++; }
- }else{ itList2++; }
+ if (mismatch <= diffs) {
+ //merge
+ alignSeqs[i].names += ',' + alignSeqs[j].names;
+ alignSeqs[i].numIdentical += alignSeqs[j].numIdentical;
- }
-
- //ouptut this sequence
- printData(outFasta, outNames, (*itList));
-
- //remove sequence
- itList = alignSeqs.erase(itList);
-
- i++;
+ alignSeqs[j].active = 0;
+ alignSeqs[j].numIdentical = 0;
+ count++;
+ }
+ }//end if j active
+ }//end if i != j
+ //remove from active list
+ alignSeqs[i].active = 0;
+
+ }//end if active i
if(i % 100 == 0) { m->mothurOut(toString(i) + "\t" + toString(numSeqs - count) + "\t" + toString(count)); m->mothurOutEndLine(); }
}
-
- if(i % 100 != 0) { m->mothurOut(toString(i) + "\t" + toString(numSeqs - count) + "\t" + toString(count)); m->mothurOutEndLine(); }
- outFasta.close();
- outNames.close();
+ if(numSeqs % 100 != 0) { m->mothurOut(toString(numSeqs) + "\t" + toString(numSeqs - count) + "\t" + toString(count)); m->mothurOutEndLine(); }
+
- if (m->control_pressed) { remove(newFastaFile.c_str()); remove(newNamesFile.c_str()); return 0; }
+ string fileroot = outputDir + m->getRootName(m->getSimpleName(fastafile));
- m->mothurOut("Total number of sequences before precluster was " + toString(numSeqs) + "."); m->mothurOutEndLine();
- m->mothurOut("pre.cluster removed " + toString(count) + " sequences."); m->mothurOutEndLine();
+ string newFastaFile = fileroot + "precluster" + m->getExtension(fastafile);
+ string newNamesFile = fileroot + "precluster.names";
- if (m->control_pressed) { remove(newFastaFile.c_str()); remove(newNamesFile.c_str()); return 0; }
+ if (m->control_pressed) { return 0; }
+
+ m->mothurOut("Total number of sequences before precluster was " + toString(alignSeqs.size()) + "."); m->mothurOutEndLine();
+ m->mothurOut("pre.cluster removed " + toString(count) + " sequences."); m->mothurOutEndLine(); m->mothurOutEndLine();
+ printData(newFastaFile, newNamesFile);
+
+ m->mothurOut("It took " + toString(time(NULL) - start) + " secs to cluster " + toString(numSeqs) + " sequences."); m->mothurOutEndLine();
+
+ if (m->control_pressed) { m->mothurRemove(newFastaFile); m->mothurRemove(newNamesFile); return 0; }
m->mothurOutEndLine();
m->mothurOut("Output File Names: "); m->mothurOutEndLine();
- m->mothurOut(newFastaFile); m->mothurOutEndLine();
- m->mothurOut(newNamesFile); m->mothurOutEndLine();
+ m->mothurOut(newFastaFile); m->mothurOutEndLine(); outputNames.push_back(newFastaFile); outputTypes["fasta"].push_back(newFastaFile);
+ m->mothurOut(newNamesFile); m->mothurOutEndLine(); outputNames.push_back(newNamesFile); outputTypes["name"].push_back(newNamesFile);
m->mothurOutEndLine();
-
+
+ //set fasta file as new current fastafile
+ string current = "";
+ itTypes = outputTypes.find("fasta");
+ if (itTypes != outputTypes.end()) {
+ if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setFastaFile(current); }
+ }
+
+ itTypes = outputTypes.find("name");
+ if (itTypes != outputTypes.end()) {
+ if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setNameFile(current); }
+ }
+
return 0;
}
//ifstream inNames;
ifstream inFasta;
- //openInputFile(namefile, inNames);
- openInputFile(fastafile, inFasta);
+ //m->openInputFile(namefile, inNames);
+ m->openInputFile(fastafile, inFasta);
//string firstCol, secondCol, nameString;
length = 0;
//inNames >> firstCol >> secondCol;
//nameString = secondCol;
- //gobble(inNames);
+ //m->gobble(inNames);
//int size = 1;
//while (secondCol.find_first_of(',') != -1) {
// size++;
// secondCol = secondCol.substr(secondCol.find_first_of(',')+1, secondCol.length());
//}
- Sequence seq(inFasta); gobble(inFasta);
+ Sequence seq(inFasta); m->gobble(inFasta);
if (seq.getName() != "") { //can get "" if commented line is at end of fasta file
if (namefile != "") {
/**************************************************************************************************/
-void PreClusterCommand::printData(ofstream& outFasta, ofstream& outNames, seqPNode thisSeq){
+void PreClusterCommand::printData(string newfasta, string newname){
try {
- thisSeq.seq.printSequence(outFasta);
- outNames << thisSeq.seq.getName() << '\t' << thisSeq.names << endl;
+ ofstream outFasta;
+ ofstream outNames;
+
+ m->openOutputFile(newfasta, outFasta);
+ m->openOutputFile(newname, outNames);
+
+
+ for (int i = 0; i < alignSeqs.size(); i++) {
+ if (alignSeqs[i].numIdentical != 0) {
+ alignSeqs[i].seq.printSequence(outFasta);
+ outNames << alignSeqs[i].seq.getName() << '\t' << alignSeqs[i].names << endl;
+ }
+ }
+
+ outFasta.close();
+ outNames.close();
+
}
catch(exception& e) {
m->errorOut(e, "PreClusterCommand", "printData");
void PreClusterCommand::readNameFile(){
try {
ifstream in;
- openInputFile(namefile, in);
+ m->openInputFile(namefile, in);
string firstCol, secondCol;
while (!in.eof()) {
- in >> firstCol >> secondCol; gobble(in);
+ in >> firstCol >> secondCol; m->gobble(in);
names[firstCol] = secondCol;
int size = 1;
projects / mothur.git / blobdiff