//**********************************************************************************************************************
inline bool comparePriority(seqPNode first, seqPNode second) { return (first.numIdentical > second.numIdentical); }
//**********************************************************************************************************************
+vector<string> PreClusterCommand::getValidParameters(){
+ try {
+ string Array[] = {"fasta", "name", "diffs", "outputdir","inputdir"};
+ vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
+ return myArray;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "PreClusterCommand", "getValidParameters");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+PreClusterCommand::PreClusterCommand(){
+ try {
+ abort = true;
+ //initialize outputTypes
+ vector<string> tempOutNames;
+ outputTypes["fasta"] = tempOutNames;
+ outputTypes["name"] = tempOutNames;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "PreClusterCommand", "PreClusterCommand");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+vector<string> PreClusterCommand::getRequiredParameters(){
+ try {
+ string Array[] = {"fasta"};
+ vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
+ return myArray;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "PreClusterCommand", "getRequiredParameters");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+vector<string> PreClusterCommand::getRequiredFiles(){
+ try {
+ vector<string> myArray;
+ return myArray;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "PreClusterCommand", "getRequiredFiles");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
-PreClusterCommand::PreClusterCommand(string option){
+PreClusterCommand::PreClusterCommand(string option) {
try {
abort = false;
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") { mothurOut("fasta is a required parameter for the pre.cluster command."); mothurOutEndLine(); abort = true; }
+ if (fastafile == "not found") { m->mothurOut("fasta is a required parameter for the pre.cluster command."); m->mothurOutEndLine(); abort = true; }
else if (fastafile == "not open") { abort = true; }
//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
}
catch(exception& e) {
- errorOut(e, "PreClusterCommand", "PreClusterCommand");
+ m->errorOut(e, "PreClusterCommand", "PreClusterCommand");
exit(1);
}
}
void PreClusterCommand::help(){
try {
- mothurOut("The pre.cluster command groups sequences that are within a given number of base mismatches.\n");
- mothurOut("The pre.cluster command outputs a new fasta and name file.\n");
- mothurOut("The pre.cluster command parameters are fasta, names and diffs. The fasta parameter is required. \n");
- 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");
- mothurOut("The diffs parameter allows you to specify maximum number of mismatched bases allowed between sequences in a grouping. The default is 1.\n");
- mothurOut("The pre.cluster command should be in the following format: \n");
- mothurOut("pre.cluster(fasta=yourFastaFile, names=yourNamesFile, diffs=yourMaxDiffs) \n");
- mothurOut("Example pre.cluster(fasta=amazon.fasta, diffs=2).\n");
- mothurOut("Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n\n");
+ 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) {
- errorOut(e, "PreClusterCommand", "help");
+ m->errorOut(e, "PreClusterCommand", "help");
exit(1);
}
}
if (abort == true) { return 0; }
+ int start = time(NULL);
+
//reads fasta file and return number of seqs
int numSeqs = readFASTA(); //fills alignSeqs and makes all seqs active
+
+ if (m->control_pressed) { return 0; }
- if (numSeqs == 0) { mothurOut("Error reading fasta file...please correct."); mothurOutEndLine(); return 0; }
- if (diffs > length) { mothurOut("Error: diffs is greater than your sequence length."); mothurOutEndLine(); return 0; }
+ 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; }
//clear sizes since you only needed this info to build the alignSeqs seqPNode structs
// sizes.clear();
//try to merge it with all smaller seqs
for (int j = i+1; j < numSeqs; j++) {
+
+ 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());
//remove from active list
alignSeqs[i].active = 0;
+
}//end if active i
- if(i % 100 == 0) { cout << i << '\t' << numSeqs - count << '\t' << count << endl; }
+ if(i % 100 == 0) { m->mothurOut(toString(i) + "\t" + toString(numSeqs - count) + "\t" + toString(count)); m->mothurOutEndLine(); }
}
- string fileroot = outputDir + getRootName(getSimpleName(fastafile));
+ if(numSeqs % 100 != 0) { m->mothurOut(toString(numSeqs) + "\t" + toString(numSeqs - count) + "\t" + toString(count)); m->mothurOutEndLine(); }
+
+
+ string fileroot = outputDir + m->getRootName(m->getSimpleName(fastafile));
- string newFastaFile = fileroot + "precluster" + getExtension(fastafile);
+ string newFastaFile = fileroot + "precluster" + m->getExtension(fastafile);
string newNamesFile = fileroot + "precluster.names";
+ if (m->control_pressed) { return 0; }
- mothurOut("Total number of sequences before precluster was " + toString(alignSeqs.size()) + "."); mothurOutEndLine();
- mothurOut("pre.cluster removed " + toString(count) + " sequences."); mothurOutEndLine();
+ 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) { remove(newFastaFile.c_str()); remove(newNamesFile.c_str()); return 0; }
+
+ m->mothurOutEndLine();
+ m->mothurOut("Output File Names: "); 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();
return 0;
}
catch(exception& e) {
- errorOut(e, "PreClusterCommand", "execute");
- exit(1);
- }
-}
-/**************************************************************************************************
-int PreClusterCommand::readFASTA(){
- try {
-// ifstream inFasta;
-// openInputFile(fastafile, inFasta);
-// length = 0;
-//// map<string, string>::iterator it;
-//
-// while (!inFasta.eof()) {
-// Sequence temp(inFasta); //read seq
-//
-// if (temp.getName() != "") {
-// if (namefile != "") {
-// //make sure fasta and name files match
-// it = names.find(temp.getName());
-// if (it == names.end()) { mothurOut(temp.getName() + " is not in your names file, please correct."); mothurOutEndLine(); exit(1); }
-// }else { sizes[temp.getName()] = 1; }
-//
-// seqPNode tempNode(sizes[temp.getName()], temp);
-// alignSeqs.push_back(tempNode);
-// active[temp.getName()] = true;
-// }
-// gobble(inFasta);
-// }
-// inFasta.close();
-//
-// if (alignSeqs.size() != 0) { length = alignSeqs[0].seq.getAligned().length(); }
-//
- return alignSeqs.size();
- }
- catch(exception& e) {
- errorOut(e, "PreClusterCommand", "readFASTA");
+ m->errorOut(e, "PreClusterCommand", "execute");
exit(1);
}
}
+
/**************************************************************************************************/
-//this seems to require the names and fasta file to be in the same order???
+
+//this requires the names and fasta file to be in the same order
+
int PreClusterCommand::readFASTA(){
try {
//ifstream inNames;
ifstream inFasta;
- //openInputFile(namefile, inNames);
- openInputFile(fastafile, inFasta);
+ //m->openInputFile(namefile, inNames);
+ m->openInputFile(fastafile, inFasta);
//string firstCol, secondCol, nameString;
length = 0;
while (!inFasta.eof()) {
-
+
+ if (m->control_pressed) { inFasta.close(); return 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 != "") {
itSize = sizes.find(seq.getName());
- if (itSize == sizes.end()) { mothurOut(seq.getName() + " is not in your names file, please correct."); mothurOutEndLine(); exit(1); }
+ if (itSize == sizes.end()) { m->mothurOut(seq.getName() + " is not in your names file, please correct."); m->mothurOutEndLine(); exit(1); }
else{
seqPNode tempNode(itSize->second, seq, names[seq.getName()]);
alignSeqs.push_back(tempNode);
- if (seq.getAligned().length() > length) { length = alignSeqs[0].seq.getAligned().length(); }
+ if (seq.getAligned().length() > length) { length = seq.getAligned().length(); }
}
}else { //no names file, you are identical to yourself
seqPNode tempNode(1, seq, seq.getName());
alignSeqs.push_back(tempNode);
- if (seq.getAligned().length() > length) { length = alignSeqs[0].seq.getAligned().length(); }
+ if (seq.getAligned().length() > length) { length = seq.getAligned().length(); }
}
}
}
}
catch(exception& e) {
- errorOut(e, "PreClusterCommand", "readFASTA");
+ m->errorOut(e, "PreClusterCommand", "readFASTA");
exit(1);
}
}
return numBad;
}
catch(exception& e) {
- errorOut(e, "PreClusterCommand", "calcMisMatches");
+ m->errorOut(e, "PreClusterCommand", "calcMisMatches");
exit(1);
}
}
ofstream outFasta;
ofstream outNames;
- openOutputFile(newfasta, outFasta);
- openOutputFile(newname, outNames);
+ m->openOutputFile(newfasta, outFasta);
+ m->openOutputFile(newname, outNames);
for (int i = 0; i < alignSeqs.size(); i++) {
}
catch(exception& e) {
- errorOut(e, "PreClusterCommand", "printData");
+ m->errorOut(e, "PreClusterCommand", "printData");
exit(1);
}
}
/**************************************************************************************************/
+
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;
- while (secondCol.find_first_of(',') != -1) {
- size++;
- secondCol = secondCol.substr(secondCol.find_first_of(',')+1, secondCol.length());
+
+ for(int i=0;i<secondCol.size();i++){
+ if(secondCol[i] == ','){ size++; }
}
sizes[firstCol] = size;
}
in.close();
}
catch(exception& e) {
- errorOut(e, "PreClusterCommand", "readNameFile");
+ m->errorOut(e, "PreClusterCommand", "readNameFile");
exit(1);
}
}
projects / mothur.git / blobdiff