*/
#include "chimeraseqscommand.h"
+#include "bellerophon.h"
+#include "pintail.h"
//***************************************************************************************************************
else {
//valid paramters for this command
- string Array[] = {"fasta", "filter", "correction", "processors", "method" };
+ string Array[] = {"fasta", "filter", "correction", "processors", "method", "window", "increment", "template", "conservation", "quantile" };
vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
OptionParser parser(option);
if (fastafile == "not open") { abort = true; }
else if (fastafile == "not found") { fastafile = ""; mothurOut("fasta is a required parameter for the chimera.seqs command."); mothurOutEndLine(); abort = true; }
+ templatefile = validParameter.validFile(parameters, "template", true);
+ if (templatefile == "not open") { abort = true; }
+ else if (templatefile == "not found") { templatefile = ""; }
+
+ consfile = validParameter.validFile(parameters, "conservation", true);
+ if (consfile == "not open") { abort = true; }
+ else if (consfile == "not found") { consfile = ""; }
+
+ quanfile = validParameter.validFile(parameters, "quantile", true);
+ if (quanfile == "not open") { abort = true; }
+ else if (quanfile == "not found") { quanfile = ""; }
+
+
string temp;
- temp = validParameter.validFile(parameters, "filter", false); if (temp == "not found") { temp = "F"; }
+ temp = validParameter.validFile(parameters, "filter", false); if (temp == "not found") { temp = "T"; }
filter = isTrue(temp);
temp = validParameter.validFile(parameters, "correction", false); if (temp == "not found") { temp = "T"; }
correction = isTrue(temp);
- temp = validParameter.validFile(parameters, "processors", true); if (temp == "not found") { temp = "1"; }
+ temp = validParameter.validFile(parameters, "processors", false); if (temp == "not found") { temp = "1"; }
convert(temp, processors);
- method = validParameter.validFile(parameters, "method", false); if (method == "not found") { method = "bellerophon"; }
+ temp = validParameter.validFile(parameters, "window", false); if (temp == "not found") { temp = "0"; }
+ convert(temp, window);
+
+ temp = validParameter.validFile(parameters, "increment", false); if (temp == "not found") { temp = "25"; }
+ convert(temp, increment);
+
+ method = validParameter.validFile(parameters, "method", false); if (method == "not found") { method = "pintail"; }
+
+ if ((method == "pintail") && (templatefile == "")) { mothurOut("You must provide a template file with the pintail method."); mothurOutEndLine(); abort = true; }
+
}
}
mothurOut("The chimera.seqs command reads a fastafile and creates a sorted priority score list of potentially chimeric sequences (ideally, the sequences should already be aligned).\n");
mothurOut("The chimera.seqs command parameters are fasta, filter, correction, processors and method. fasta is required.\n");
mothurOut("The filter parameter allows you to specify if you would like to apply a 50% soft filter. The default is false. \n");
- mothurOut("The correction parameter allows you to ..... The default is true. \n");
+ mothurOut("The correction parameter allows you to put more emphasis on the distance between highly similar sequences and less emphasis on the differences between remote homologs. The default is true. \n");
mothurOut("The processors parameter allows you to specify how many processors you would like to use. The default is 1. \n");
- mothurOut("The method parameter allows you to specify the method for finding chimeric sequences. The default is bellerophon. \n");
+ mothurOut("The method parameter allows you to specify the method for finding chimeric sequences. The default is pintail. \n");
mothurOut("The chimera.seqs command should be in the following format: \n");
mothurOut("chimera.seqs(fasta=yourFastaFile, filter=yourFilter, correction=yourCorrection, processors=yourProcessors, method=bellerophon) \n");
mothurOut("Example: chimera.seqs(fasta=AD.align, filter=True, correction=true, processors=2, method=yourMethod) \n");
if (abort == true) { return 0; }
- //do soft filter
- if (filter) {
- string optionString = "fasta=" + fastafile + ", soft=50.0, vertical=F";
- filterSeqs = new FilterSeqsCommand(optionString);
- filterSeqs->execute();
- delete filterSeqs;
-
- //reset fastafile to filtered file
- fastafile = getRootName(fastafile) + "filter.fasta";
- }
-
- //read in sequences
- readSeqs();
-
- //int numSeqs = seqs.size();
-
- //find average midpoint of seqs
- midpoint = findAverageMidPoint();
-
- //create 2 vectors of sequences, 1 for left side and one for right side
- vector<Sequence> left; vector<Sequence> right;
-
- for (int i = 0; i < seqs.size(); i++) {
- //save left side
- string seqLeft = seqs[i].getAligned();
- seqLeft = seqLeft.substr(0, midpoint);
- Sequence tempLeft(seqs[i].getName(), seqLeft);
- left.push_back(tempLeft);
-
- //save right side
- string seqRight = seqs[i].getAligned();
- seqRight = seqRight.substr(midpoint+1, (seqRight.length()-midpoint-1));
- Sequence tempRight(seqs[i].getName(), seqRight);
- right.push_back(tempRight);
- }
+ if (method == "bellerophon") { chimera = new Bellerophon(fastafile); }
+ else if (method == "pintail") { chimera = new Pintail(fastafile, templatefile);
+ //saves time to avoid generating it
+ if (consfile != "") { chimera->setCons(consfile); }
+ else { chimera->setCons(""); }
+
+ //saves time to avoid generating it
+ if (quanfile != "") { chimera->setQuantiles(quanfile); }
+ else { chimera->setQuantiles(""); }
+ }else { mothurOut("Not a valid method."); mothurOutEndLine(); return 0; }
+
+ //set user options
+ chimera->setFilter(filter);
+ chimera->setCorrection(correction);
+ chimera->setProcessors(processors);
+ chimera->setWindow(window);
+ chimera->setIncrement(increment);
- //this should be parallelized
- //perference = sum of (| distance of my left to sequence j's left - distance of my right to sequence j's right | )
- //create a matrix containing the distance from left to left and right to right
- //calculate distances
- SparseMatrix* SparseLeft = new SparseMatrix();
- SparseMatrix* SparseRight = new SparseMatrix();
+ //find chimeras
+ chimera->getChimeras();
- createSparseMatrix(0, left.size(), SparseLeft, left);
- createSparseMatrix(0, right.size(), SparseRight, right);
+ string outputFileName = getRootName(fastafile) + method + ".chimeras";
+ ofstream out;
+ openOutputFile(outputFileName, out);
+ //print results
+ chimera->print(out);
- //vector<SeqMap> distMapRight;
- //vector<SeqMap> distMapLeft;
+ out.close();
- // Create a data structure to quickly access the distance information.
- // It consists of a vector of distance maps, where each map contains
- // all distances of a certain sequence. Vector and maps are accessed
- // via the index of a sequence in the distance matrix
- //distMapRight = vector<SeqMap>(globaldata->gListVector->size());
- //distMapLeft = vector<SeqMap>(globaldata->gListVector->size());
- for (MatData currentCell = SparseLeft->begin(); currentCell != SparseLeft->end(); currentCell++) {
- //distMapLeft[currentCell->row][currentCell->column] = currentCell->dist;
- }
- for (MatData currentCell = SparseRight->begin(); currentCell != SparseRight->end(); currentCell++) {
- //distMapRight[currentCell->row][currentCell->column] = currentCell->dist;
- }
-
-
- //fill preference structure
- //generatePreferences(distMapLeft, distMapRight);
+ delete chimera;
-
- //output results to screen
- mothurOutEndLine();
- mothurOut("\t\t"); mothurOutEndLine();
- //mothurOut("Minimum:\t" + toString(startPosition[0]) + "\t" + toString(endPosition[0]) + "\t" + toString(seqLength[0]) + "\t" + toString(ambigBases[0]) + "\t" + toString(longHomoPolymer[0])); mothurOutEndLine();
- //mothurOut("2.5%-tile:\t" + toString(startPosition[ptile0_25]) + "\t" + toString(endPosition[ptile0_25]) + "\t" + toString(seqLength[ptile0_25]) + "\t" + toString(ambigBases[ptile0_25]) + "\t"+ toString(longHomoPolymer[ptile0_25])); mothurOutEndLine();
- //mothurOut("25%-tile:\t" + toString(startPosition[ptile25]) + "\t" + toString(endPosition[ptile25]) + "\t" + toString(seqLength[ptile25]) + "\t" + toString(ambigBases[ptile25]) + "\t" + toString(longHomoPolymer[ptile25])); mothurOutEndLine();
- //mothurOut("Median: \t" + toString(startPosition[ptile50]) + "\t" + toString(endPosition[ptile50]) + "\t" + toString(seqLength[ptile50]) + "\t" + toString(ambigBases[ptile50]) + "\t" + toString(longHomoPolymer[ptile50])); mothurOutEndLine();
- //mothurOut("75%-tile:\t" + toString(startPosition[ptile75]) + "\t" + toString(endPosition[ptile75]) + "\t" + toString(seqLength[ptile75]) + "\t" + toString(ambigBases[ptile75]) + "\t" + toString(longHomoPolymer[ptile75])); mothurOutEndLine();
- //mothurOut("97.5%-tile:\t" + toString(startPosition[ptile97_5]) + "\t" + toString(endPosition[ptile97_5]) + "\t" + toString(seqLength[ptile97_5]) + "\t" + toString(ambigBases[ptile97_5]) + "\t" + toString(longHomoPolymer[ptile97_5])); mothurOutEndLine();
- //mothurOut("Maximum:\t" + toString(startPosition[ptile100]) + "\t" + toString(endPosition[ptile100]) + "\t" + toString(seqLength[ptile100]) + "\t" + toString(ambigBases[ptile100]) + "\t" + toString(longHomoPolymer[ptile100])); mothurOutEndLine();
- //mothurOut("# of Seqs:\t" + toString(numSeqs)); mothurOutEndLine();
-
- //outSummary.close();
return 0;
- }
- catch(exception& e) {
- errorOut(e, "ChimeraSeqsCommand", "execute");
- exit(1);
- }
-}
-
-//***************************************************************************************************************
-void ChimeraSeqsCommand::readSeqs(){
- try {
- ifstream inFASTA;
- openInputFile(fastafile, inFASTA);
-
- //read in seqs and store in vector
- while(!inFASTA.eof()){
- Sequence current(inFASTA);
-
- seqs.push_back(current);
-
- gobble(inFASTA);
- }
- inFASTA.close();
-
- }
- catch(exception& e) {
- errorOut(e, "ChimeraSeqsCommand", "readSeqs");
- exit(1);
- }
-}
-
-
-//***************************************************************************************************************
-int ChimeraSeqsCommand::findAverageMidPoint(){
- try {
- int totalMids = 0;
- int averageMid = 0;
- //loop through the seqs and find midpoint
- for (int i = 0; i < seqs.size(); i++) {
-
- //get unaligned sequence
- seqs[i].setUnaligned(seqs[i].getUnaligned()); //if you read an aligned file the unaligned is really aligned, so we need to make sure its unaligned
-
- string unaligned = seqs[i].getUnaligned();
- string aligned = seqs[i].getAligned();
-
- //find midpoint of this seq
- int count = 0;
- int thismid = 0;
- for (int j = 0; j < aligned.length(); j++) {
-
- thismid++;
-
- //if you are part of the unaligned sequence increment
- if (isalpha(aligned[j])) { count++; }
-
- //if you have reached the halfway point stop
- if (count >= (unaligned.length() / 2)) { break; }
- }
-
- //add this mid to total
- totalMids += thismid;
-
- }
-
- averageMid = (totalMids / seqs.size());
-
- return averageMid;
-
-
}
catch(exception& e) {
- errorOut(e, "ChimeraSeqsCommand", "findAverageMidPoint");
- exit(1);
- }
-}
-
-/***************************************************************************************************************/
-int ChimeraSeqsCommand::createSparseMatrix(int startSeq, int endSeq, SparseMatrix* sparse, vector<Sequence> s){
- try {
-
- for(int i=startSeq; i<endSeq; i++){
-
- for(int j=0;j<i;j++){
-
- //distCalculator->calcDist(s.get(i), s.get(j));
- float dist = distCalculator->getDist();
-
- PCell temp(i, j, dist);
- sparse->addCell(temp);
-
- }
- }
-
-
- return 1;
- }
- catch(exception& e) {
- errorOut(e, "ChimeraSeqsCommand", "createSparseMatrix");
- exit(1);
- }
-}
-/***************************************************************************************************************
-void ChimeraSeqsCommand::generatePreferences(vector<SeqMap> left, vector<SeqMap> right){
- try {
-
- for (int i = 0; i < left.size(); i++) {
-
- int iscore = 0;
- float closestLeft = 100000.0;
- float closestRight = 100000.0;
-
- for (int j = 0; j < left.size(); j++) {
-
- //iscore += abs(left
-
- }
-
- }
-
- }
- catch(exception& e) {
- errorOut(e, "ChimeraSeqsCommand", "generatePreferences");
+ errorOut(e, "ChimeraSeqsCommand", "execute");
exit(1);
}
}
/**************************************************************************************************/
-/**************************************************************************************************/
-
projects / mothur.git / blobdiff