}
else if (templateFileName == "not open") { abort = true; }
- groupfile = validParameter.validFile(parameters, "group", true);
- if (groupfile == "not open") { abort = true; }
- else if (groupfile == "not found") { groupfile = ""; }
+ groupfile = validParameter.validFile(parameters, "group", false);
+ if (groupfile == "not found") { groupfile = ""; }
+ else {
+ splitAtDash(groupfile, groupfileNames);
+
+ //go through files and make sure they are good, if not, then disregard them
+ for (int i = 0; i < groupfileNames.size(); i++) {
+ if (inputDir != "") {
+ string path = hasPath(groupfileNames[i]);
+ //if the user has not given a path then, add inputdir. else leave path alone.
+ if (path == "") { groupfileNames[i] = inputDir + groupfileNames[i]; }
+ }
+ int ableToOpen;
+
+ #ifdef USE_MPI
+ int pid;
+ MPI_Comm_size(MPI_COMM_WORLD, &processors); //set processors to the number of mpi processes running
+ MPI_Comm_rank(MPI_COMM_WORLD, &pid); //find out who we are
+
+ if (pid == 0) {
+ #endif
+
+ ifstream in;
+ ableToOpen = openInputFile(groupfileNames[i], in);
+ in.close();
+
+ #ifdef USE_MPI
+ for (int j = 1; j < processors; j++) {
+ MPI_Send(&ableToOpen, 1, MPI_INT, j, 2001, MPI_COMM_WORLD);
+ }
+ }else{
+ MPI_Status status;
+ MPI_Recv(&ableToOpen, 1, MPI_INT, 0, 2001, MPI_COMM_WORLD, &status);
+ }
+
+ #endif
+ if (ableToOpen == 1) { m->mothurOut("Unable to match group file with fasta file."); m->mothurOutEndLine(); abort = true; }
+
+ }
+ }
fastaFileName = validParameter.validFile(parameters, "fasta", false);
if (fastaFileName == "not found") { m->mothurOut("fasta is a required parameter for the classify.seqs command."); m->mothurOutEndLine(); abort = true; }
if (namefileNames.size() != fastaFileNames.size()) { abort = true; m->mothurOut("If you provide a name file, you must have one for each fasta file."); m->mothurOutEndLine(); }
}
+ if (groupfile != "") {
+ if (groupfileNames.size() != fastaFileNames.size()) { abort = true; m->mothurOut("If you provide a group file, you must have one for each fasta file."); m->mothurOutEndLine(); }
+ }
+
//check for optional parameter and set defaults
// ...at some point should added some additional type checking...
string temp;
m->mothurOut("It took " + toString(time(NULL) - start) + " secs to classify " + toString(numFastaSeqs) + " sequences."); m->mothurOutEndLine(); m->mothurOutEndLine();
start = time(NULL);
- PhyloSummary taxaSum(taxonomyFileName, groupfile);
+ PhyloSummary taxaSum(taxonomyFileName, groupfileNames[s]);
if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } delete classify; return 0; }
m->mothurOut(name + " is not in your name file please correct."); m->mothurOutEndLine(); exit(1);
}else{
for (int i = 0; i < itNames->second; i++) {
- taxaSum.addSeqToTree(name+toString(i), taxon); //add it as many times as there are identical seqs
+ taxaSum.addSeqToTree(name, taxon); //add it as many times as there are identical seqs
}
}
}
m->mothurOut("Output File Names: "); m->mothurOutEndLine();
for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); }
m->mothurOutEndLine();
-
}
delete classify;
*/
#include "trimseqscommand.h"
+#include "needlemanoverlap.hpp"
+#include "nast.hpp"
//***************************************************************************************************************
else {
//valid paramters for this command
string AlignArray[] = {"fasta", "flip", "oligos", "maxambig", "maxhomop", "minlength", "maxlength", "qfile",
- "qthreshold", "qaverage", "allfiles", "qtrim", "processors", "outputdir","inputdir"};
+ "qthreshold", "qaverage", "allfiles", "qtrim","diffs", "processors", "outputdir","inputdir"};
vector<string> myArray (AlignArray, AlignArray+(sizeof(AlignArray)/sizeof(string)));
temp = validParameter.validFile(parameters, "maxlength", false); if (temp == "not found") { temp = "0"; }
convert(temp, maxLength);
+ temp = validParameter.validFile(parameters, "diffs", false); if (temp == "not found") { temp = "0"; }
+ convert(temp, diffs);
+
temp = validParameter.validFile(parameters, "qfile", true);
if (temp == "not found") { qFileName = ""; }
else if(temp == "not open") { abort = true; }
void TrimSeqsCommand::help(){
try {
m->mothurOut("The trim.seqs command reads a fastaFile and creates .....\n");
- m->mothurOut("The trim.seqs command parameters are fasta, flip, oligos, maxambig, maxhomop, minlength, maxlength, qfile, qthreshold, qaverage, qtrim and allfiles.\n");
+ m->mothurOut("The trim.seqs command parameters are fasta, flip, oligos, maxambig, maxhomop, minlength, maxlength, qfile, qthreshold, qaverage, diffs, qtrim and allfiles.\n");
m->mothurOut("The fasta parameter is required.\n");
m->mothurOut("The flip parameter .... The default is 0.\n");
m->mothurOut("The oligos parameter .... The default is "".\n");
m->mothurOut("The maxhomop parameter .... The default is 0.\n");
m->mothurOut("The minlength parameter .... The default is 0.\n");
m->mothurOut("The maxlength parameter .... The default is 0.\n");
+ m->mothurOut("The diffs parameter .... The default is 0.\n");
m->mothurOut("The qfile parameter .....\n");
m->mothurOut("The qthreshold parameter .... The default is 0.\n");
m->mothurOut("The qaverage parameter .... The default is 0.\n");
m->errorOut(e, "TrimSeqsCommand", "getOligos");
exit(1);
}
-
}
-
//***************************************************************************************************************
bool TrimSeqsCommand::stripBarcode(Sequence& seq, int& group){
string rawSequence = seq.getUnaligned();
bool success = 0; //guilty until proven innocent
+ //can you find the barcode
for(map<string,int>::iterator it=barcodes.begin();it!=barcodes.end();it++){
string oligo = it->first;
if(rawSequence.length() < oligo.length()){ //let's just assume that the barcodes are the same length
break;
}
}
+
+ //if you found the barcode or if you don't want to allow for diffs
+ if ((diffs == 0) || (success == 1)) { return success; }
+
+ else { //try aligning and see if you can find it
+ //can you find the barcode
+ for(map<string,int>::iterator it=barcodes.begin();it!=barcodes.end();it++){
+ string oligo = it->first;
+ if(rawSequence.length() < oligo.length()){ //let's just assume that the barcodes are the same length
+ success = 0;
+ break;
+ }
+
+ //use needleman to align first barcode.length()+numdiffs of sequence to each barcode
+ Alignment* alignment = new NeedlemanOverlap(-2.0, 1.0, -1.0, (oligo.length()+diffs+1));
+ Sequence* templateSeq = new Sequence("temp", rawSequence.substr(0,(oligo.length()+diffs)));
+ Sequence* candidateSeq = new Sequence("temp2", oligo);
+ Nast nast(alignment, candidateSeq, templateSeq);
+
+ oligo = candidateSeq->getAligned();
+ cout << "barcode = " << oligo << " raw = " << rawSequence.substr(0,(oligo.length())) << endl;
+ delete alignment;
+ delete templateSeq;
+ delete candidateSeq;
+
+ if(compareDNASeq(oligo, rawSequence.substr(0,oligo.length()))){
+ group = it->second;
+ seq.setUnaligned(rawSequence.substr(0,oligo.length()));
+ success = 1;
+ break;
+ }
+ }
+ }
return success;
}
}
}
+ //if you found the primer or if you don't want to allow for diffs
+ if ((diffs == 0) || (success == 1)) { return success; }
+
+ else { //try aligning and see if you can find it
+ //can you find the primer
+ for(int i=0;i<numFPrimers;i++){
+ string oligo = forPrimer[i];
+ if(rawSequence.length() < oligo.length()){
+ success = 0;
+ break;
+ }
+
+ //use needleman to align first primer.length()+numdiffs of sequence to each primer
+ Alignment* alignment = new NeedlemanOverlap(-2.0, 1.0, -1.0, (oligo.length()+diffs+1));
+ Sequence* templateSeq = new Sequence("temp", rawSequence.substr(0,(oligo.length()+diffs)));
+ Sequence* candidateSeq = new Sequence("temp2", oligo);
+ Nast nast(alignment, candidateSeq, templateSeq);
+
+ oligo = candidateSeq->getAligned();
+
+ delete alignment;
+ delete templateSeq;
+ delete candidateSeq;
+
+ if(compareDNASeq(oligo, rawSequence.substr(0,oligo.length()))){
+ seq.setUnaligned(rawSequence.substr(0,oligo.length()));
+ success = 1;
+ break;
+ }
+ }
+ }
+
return success;
}
for(int i=0;i<length;i++){
if(oligo[i] != seq[i]){
- if(oligo[i] == 'A' || oligo[i] == 'T' || oligo[i] == 'G' || oligo[i] == 'C') { success = 0; }
+ if(oligo[i] == 'A' || oligo[i] == 'T' || oligo[i] == 'G' || oligo[i] == 'C') { success = 0; }
else if((oligo[i] == 'N' || oligo[i] == 'I') && (seq[i] == 'N')) { success = 0; }
else if(oligo[i] == 'R' && (seq[i] != 'A' && seq[i] != 'G')) { success = 0; }
else if(oligo[i] == 'Y' && (seq[i] != 'C' && seq[i] != 'T')) { success = 0; }
else if(oligo[i] == 'H' && (seq[i] != 'A' && seq[i] != 'T' && seq[i] != 'C')) { success = 0; }
else if(oligo[i] == 'V' && (seq[i] != 'A' && seq[i] != 'C' && seq[i] != 'G')) { success = 0; }
- if(success == 0) { break; }
+ if(success == 0) { break; }
}
else{
success = 1;
projects / mothur.git / commitdiff