//***************************************************************************************************************
-ChimeraSeqsCommand::ChimeraSeqsCommand(string option){
+ChimeraSeqsCommand::ChimeraSeqsCommand(string option) {
try {
abort = false;
//check for required parameters
fastafile = validParameter.validFile(parameters, "fasta", true);
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; }
+ else if (fastafile == "not found") { fastafile = ""; m->mothurOut("fasta is a required parameter for the chimera.seqs command."); m->mothurOutEndLine(); 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"){
else if (temp == "not found") { temp = "20"; }
convert(temp, numwanted);
- if ((search != "distance") && (search != "blast") && (search != "kmer")) { mothurOut(search + " is not a valid search."); mothurOutEndLine(); abort = true; }
+ if ((search != "distance") && (search != "blast") && (search != "kmer")) { m->mothurOut(search + " is not a valid search."); m->mothurOutEndLine(); abort = true; }
- if (((method != "bellerophon")) && (templatefile == "")) { mothurOut("You must provide a template file with the pintail, ccode, chimeraslayer or chimeracheck methods."); mothurOutEndLine(); abort = true; }
+ if (((method != "bellerophon")) && (templatefile == "")) { m->mothurOut("You must provide a template file with the pintail, ccode, chimeraslayer or chimeracheck methods."); m->mothurOutEndLine(); abort = true; }
}
}
catch(exception& e) {
- errorOut(e, "ChimeraSeqsCommand", "ChimeraSeqsCommand");
+ m->errorOut(e, "ChimeraSeqsCommand", "ChimeraSeqsCommand");
exit(1);
}
}
try {
//"fasta", "filter", "correction", "processors", "method", "window", "increment", "template", "conservation", "quantile", "mask", "numwanted", "ksize", "svg", "name"
- //mothurOut("chimera.seqs ASSUMES that your sequences are ALIGNED and if using a template that the template file sequences are the same length as the fasta file sequences.\n\n");
- mothurOut("The chimera.seqs command reads a fastafile and creates list of potentially chimeric sequences.\n");
- mothurOut("The chimera.seqs command parameters are fasta, filter, correction, processors, mask, method, window, increment, template, conservation, quantile, numwanted, ksize, svg, name, iters, search, realign.\n");
- mothurOut("The fasta parameter is always required and template is required if using pintail, ccode or chimeracheck.\n");
- mothurOut("The filter parameter allows you to specify if you would like to apply a vertical and 50% soft filter. \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.\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 pintail. Options include bellerophon, ccode and chimeracheck \n");
- mothurOut("The mask parameter allows you to specify a file containing one sequence you wish to use as a mask for the your sequences. \n");
- mothurOut("The window parameter allows you to specify the window size for searching for chimeras. \n");
- mothurOut("The increment parameter allows you to specify how far you move each window while finding chimeric sequences.\n");
- mothurOut("The template parameter allows you to enter a template file containing known non-chimeric sequences. \n");
- mothurOut("The conservation parameter allows you to enter a frequency file containing the highest bases frequency at each place in the alignment.\n");
- mothurOut("The quantile parameter allows you to enter a file containing quantiles for a template files sequences.\n");
- mothurOut("The numwanted parameter allows you to specify how many sequences you would each query sequence compared with.\n");
- mothurOut("The ksize parameter allows you to input kmersize. \n");
- mothurOut("The svg parameter allows you to specify whether or not you would like a svg file outputted for each query sequence.\n");
- mothurOut("The name parameter allows you to enter a file containing names of sequences you would like .svg files for.\n");
- mothurOut("The iters parameter allows you to specify the number of bootstrap iters to do with the chimeraslayer method.\n");
- mothurOut("The minsim parameter allows you .... \n");
- mothurOut("The mincov parameter allows you to specify minimum coverage by closest matches found in template. Default is 70, meaning 70%. \n");
- mothurOut("The minbs parameter allows you to specify minimum bootstrap support for calling a sequence chimeric. Default is 90, meaning 90%. \n");
- mothurOut("The minsnp parameter allows you to specify percent of SNPs to sample on each side of breakpoint for computing bootstrap support (default: 10) \n");
- mothurOut("The search parameter allows you to specify search method for finding the closest parent. Choices are distance, blast, and kmer, default distance. -used only by chimeraslayer. \n");
- mothurOut("The realign parameter allows you to realign the query to the potential paretns. Choices are true or false, default false. -used only by chimeraslayer. \n");
- mothurOut("NOT ALL PARAMETERS ARE USED BY ALL METHODS. Please look below for method specifics.\n\n");
- mothurOut("Details for each method: \n");
- mothurOut("\tpintail: \n");
- mothurOut("\t\tparameters: fasta=required, template=required, filter=F, mask=no mask, processors=1, window=300, increment=25, conservation=not required, but will improve speed, quantile=not required, but will greatly improve speed. \n");
- mothurOut("\t\tIf you have run chimera.seqs using pintail a .quan and .freq file will be created for your template, if you have not provided them for use in future command executions.\n");
- mothurOut("\tbellerophon: \n");
- mothurOut("\t\tparameters: fasta=required, filter=F, processors=1, window=1/4 length of seq, increment=25, correction=T. \n");
- mothurOut("\tccode: \n");
- mothurOut("\t\tparameters: fasta=required, template=required, filter=F, mask=no mask, processors=1, window=10% of length, numwanted=20\n");
- mothurOut("\tchimeracheck: \n");
- mothurOut("\t\tparameters: fasta=required, template=required, processors=1, increment=10, ksize=7, svg=F, name=none\n\n");
- mothurOut("\tchimeraslayer: \n");
- mothurOut("\t\tparameters: fasta=required, template=required, processors=1, increment=10, mask=no mask, numwanted=10, match=5, mismatch=-4, divergence=1.0, minsim=90, parents=5, iters=1000, window=100. \n\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, method=bellerophon, window=200) \n");
- mothurOut("Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFastaFile).\n\n");
+ //m->mothurOut("chimera.seqs ASSUMES that your sequences are ALIGNED and if using a template that the template file sequences are the same length as the fasta file sequences.\n\n");
+ m->mothurOut("The chimera.seqs command reads a fastafile and creates list of potentially chimeric sequences.\n");
+ m->mothurOut("The chimera.seqs command parameters are fasta, filter, correction, processors, mask, method, window, increment, template, conservation, quantile, numwanted, ksize, svg, name, iters, search, realign.\n");
+ m->mothurOut("The fasta parameter is always required and template is required if using pintail, ccode or chimeracheck.\n");
+ m->mothurOut("The filter parameter allows you to specify if you would like to apply a vertical and 50% soft filter. \n");
+ m->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.\n");
+ m->mothurOut("The processors parameter allows you to specify how many processors you would like to use. The default is 1. \n");
+ m->mothurOut("The method parameter allows you to specify the method for finding chimeric sequences. The default is pintail. Options include bellerophon, ccode and chimeracheck \n");
+ m->mothurOut("The mask parameter allows you to specify a file containing one sequence you wish to use as a mask for the your sequences. \n");
+ m->mothurOut("The window parameter allows you to specify the window size for searching for chimeras. \n");
+ m->mothurOut("The increment parameter allows you to specify how far you move each window while finding chimeric sequences.\n");
+ m->mothurOut("The template parameter allows you to enter a template file containing known non-chimeric sequences. \n");
+ m->mothurOut("The conservation parameter allows you to enter a frequency file containing the highest bases frequency at each place in the alignment.\n");
+ m->mothurOut("The quantile parameter allows you to enter a file containing quantiles for a template files sequences.\n");
+ m->mothurOut("The numwanted parameter allows you to specify how many sequences you would each query sequence compared with.\n");
+ m->mothurOut("The ksize parameter allows you to input kmersize. \n");
+ m->mothurOut("The svg parameter allows you to specify whether or not you would like a svg file outputted for each query sequence.\n");
+ m->mothurOut("The name parameter allows you to enter a file containing names of sequences you would like .svg files for.\n");
+ m->mothurOut("The iters parameter allows you to specify the number of bootstrap iters to do with the chimeraslayer method.\n");
+ m->mothurOut("The minsim parameter allows you .... \n");
+ m->mothurOut("The mincov parameter allows you to specify minimum coverage by closest matches found in template. Default is 70, meaning 70%. \n");
+ m->mothurOut("The minbs parameter allows you to specify minimum bootstrap support for calling a sequence chimeric. Default is 90, meaning 90%. \n");
+ m->mothurOut("The minsnp parameter allows you to specify percent of SNPs to sample on each side of breakpoint for computing bootstrap support (default: 10) \n");
+ m->mothurOut("The search parameter allows you to specify search method for finding the closest parent. Choices are distance, blast, and kmer, default distance. -used only by chimeraslayer. \n");
+ m->mothurOut("The realign parameter allows you to realign the query to the potential paretns. Choices are true or false, default false. -used only by chimeraslayer. \n");
+ m->mothurOut("NOT ALL PARAMETERS ARE USED BY ALL METHODS. Please look below for method specifics.\n\n");
+ m->mothurOut("Details for each method: \n");
+ m->mothurOut("\tpintail: \n");
+ m->mothurOut("\t\tparameters: fasta=required, template=required, filter=F, mask=no mask, processors=1, window=300, increment=25, conservation=not required, but will improve speed, quantile=not required, but will greatly improve speed. \n");
+ m->mothurOut("\t\tIf you have run chimera.seqs using pintail a .quan and .freq file will be created for your template, if you have not provided them for use in future command executions.\n");
+ m->mothurOut("\tbellerophon: \n");
+ m->mothurOut("\t\tparameters: fasta=required, filter=F, processors=1, window=1/4 length of seq, increment=25, correction=T. \n");
+ m->mothurOut("\tccode: \n");
+ m->mothurOut("\t\tparameters: fasta=required, template=required, filter=F, mask=no mask, processors=1, window=10% of length, numwanted=20\n");
+ m->mothurOut("\tchimeracheck: \n");
+ m->mothurOut("\t\tparameters: fasta=required, template=required, processors=1, increment=10, ksize=7, svg=F, name=none\n\n");
+ m->mothurOut("\tchimeraslayer: \n");
+ m->mothurOut("\t\tparameters: fasta=required, template=required, processors=1, increment=10, mask=no mask, numwanted=10, match=5, mismatch=-4, divergence=1.0, minsim=90, parents=5, iters=1000, window=100. \n\n");
+ m->mothurOut("The chimera.seqs command should be in the following format: \n");
+ m->mothurOut("chimera.seqs(fasta=yourFastaFile, filter=yourFilter, correction=yourCorrection, processors=yourProcessors, method=bellerophon) \n");
+ m->mothurOut("Example: chimera.seqs(fasta=AD.align, filter=True, correction=true, method=bellerophon, window=200) \n");
+ m->mothurOut("Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFastaFile).\n\n");
}
catch(exception& e) {
- errorOut(e, "ChimeraSeqsCommand", "help");
+ m->errorOut(e, "ChimeraSeqsCommand", "help");
exit(1);
}
}
else if (method == "ccode") { chimera = new Ccode(fastafile, outputDir); }
else if (method == "chimeracheck") { chimera = new ChimeraCheckRDP(fastafile, outputDir); }
else if (method == "chimeraslayer") { chimera = new ChimeraSlayer(search, realign, fastafile); }
- else { mothurOut("Not a valid method."); mothurOutEndLine(); return 0; }
+ else { m->mothurOut("Not a valid method."); m->mothurOutEndLine(); return 0; }
//set user options
- if (maskfile == "default") { mothurOut("I am using the default 236627 EU009184.1 Shigella dysenteriae str. FBD013."); mothurOutEndLine(); }
+ if (maskfile == "default") { m->mothurOut("I am using the default 236627 EU009184.1 Shigella dysenteriae str. FBD013."); m->mothurOutEndLine(); }
chimera->setCons(consfile);
chimera->setQuantiles(quanfile);
chimera->setMinBS(minBS);
chimera->setMinSNP(minSNP);
chimera->setIters(iters);
- chimera->setTemplateFile(templatefile);
+
string outputFileName = outputDir + getRootName(getSimpleName(fastafile)) + method + maskfile + ".chimeras";
string accnosFileName = outputDir + getRootName(getSimpleName(fastafile)) + method + maskfile + ".accnos";
-
+ bool hasAccnos = true;
- if ((method != "bellerophon") && (method != "chimeracheck")) {
- if (chimera->getUnaligned()) {
- mothurOut("Your template sequences are different lengths, please correct."); mothurOutEndLine();
- delete chimera;
- return 0;
- }
- }else if (method == "bellerophon") {//run bellerophon separately since you need to read entire fastafile to run it
+ if (method == "bellerophon") {//run bellerophon separately since you need to read entire fastafile to run it
chimera->getChimeras();
ofstream out;
out.close();
out2.close();
+ //delete accnos file if its blank
+ if (isBlank(accnosFileName)) { remove(accnosFileName.c_str()); hasAccnos = false; }
+
+ m->mothurOutEndLine();
+ m->mothurOut("Output File Names: "); m->mothurOutEndLine();
+ m->mothurOut(outputFileName); m->mothurOutEndLine();
+ if (hasAccnos) { m->mothurOut(accnosFileName); m->mothurOutEndLine(); }
+ m->mothurOutEndLine();
+
return 0;
}
+ //reads template
+ chimera->setTemplateFile(templatefile);
+
+ if (method != "chimeracheck") {
+ if (chimera->getUnaligned()) {
+ m->mothurOut("Your template sequences are different lengths, please correct."); m->mothurOutEndLine();
+ delete chimera;
+ return 0;
+ }
+ }
+
//some methods need to do prep work before processing the chimeras
chimera->doPrep();
chimera->printHeader(outHeader);
outHeader.close();
-
+
//break up file
#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux)
if(processors == 1){
driver(lines[0], outputFileName, fastafile, accnosFileName);
+ //delete accnos file if its blank
+ if (isBlank(accnosFileName)) { remove(accnosFileName.c_str()); hasAccnos = false; }
+
}else{
vector<int> positions;
processIDS.resize(0);
createProcesses(outputFileName, fastafile, accnosFileName);
rename((outputFileName + toString(processIDS[0]) + ".temp").c_str(), outputFileName.c_str());
- rename((accnosFileName + toString(processIDS[0]) + ".temp").c_str(), accnosFileName.c_str());
- //append alignment and report files
+ //append output files
for(int i=1;i<processors;i++){
appendOutputFiles((outputFileName + toString(processIDS[i]) + ".temp"), outputFileName);
remove((outputFileName + toString(processIDS[i]) + ".temp").c_str());
+ }
+
+ vector<string> nonBlankAccnosFiles;
+ //delete blank accnos files generated with multiple processes
+ for(int i=0;i<processors;i++){
+ if (!(isBlank(accnosFileName + toString(processIDS[i]) + ".temp"))) {
+ nonBlankAccnosFiles.push_back(accnosFileName + toString(processIDS[i]) + ".temp");
+ }else { remove((accnosFileName + toString(processIDS[i]) + ".temp").c_str()); }
+ }
+
+ //append accnos files
+ if (nonBlankAccnosFiles.size() != 0) {
+ rename(nonBlankAccnosFiles[0].c_str(), accnosFileName.c_str());
- appendOutputFiles((accnosFileName + toString(processIDS[i]) + ".temp"), accnosFileName);
- remove((accnosFileName + toString(processIDS[i]) + ".temp").c_str());
+ for (int h=1; h < nonBlankAccnosFiles.size(); h++) {
+ appendOutputFiles(nonBlankAccnosFiles[h], accnosFileName);
+ remove(nonBlankAccnosFiles[h].c_str());
+ }
+ }else{ hasAccnos = false; }
- }
}
#else
lines.push_back(new linePair(0, numSeqs));
driver(lines[0], outputFileName, fastafile, accnosFileName);
+
+ //delete accnos file if its blank
+ if (isBlank(accnosFileName)) { remove(accnosFileName.c_str()); hasAccnos = false; }
#endif
- //mothurOut("Output File Names: ");
- //if ((filter) && (method == "bellerophon")) { mothurOut(
+ //m->mothurOut("Output File Names: ");
+ //if ((filter) && (method == "bellerophon")) { m->mothurOut(
//if (outputDir == "") { fastafile = getRootName(fastafile) + "filter.fasta"; }
// else { fastafile = outputDir + getRootName(getSimpleName(fastafile)) + "filter.fasta"; }
delete chimera;
- if (method == "chimeracheck") { remove(accnosFileName.c_str()); mothurOutEndLine(); mothurOut("This method does not determine if a sequence is chimeric, but allows you to make that determination based on the IS values."); mothurOutEndLine(); }
+ if (method == "chimeracheck") { remove(accnosFileName.c_str()); m->mothurOutEndLine(); m->mothurOut("This method does not determine if a sequence is chimeric, but allows you to make that determination based on the IS values."); m->mothurOutEndLine(); }
+
+ m->mothurOutEndLine();
+ m->mothurOut("Output File Names: "); m->mothurOutEndLine();
+ m->mothurOut(outputFileName); m->mothurOutEndLine();
+ if (hasAccnos) { m->mothurOut(accnosFileName); m->mothurOutEndLine(); }
+ m->mothurOutEndLine();
+
+
- mothurOutEndLine(); mothurOut("It took " + toString(time(NULL) - start) + " secs to check " + toString(numSeqs) + " sequences."); mothurOutEndLine();
+ m->mothurOutEndLine(); m->mothurOut("It took " + toString(time(NULL) - start) + " secs to check " + toString(numSeqs) + " sequences."); m->mothurOutEndLine();
return 0;
}
catch(exception& e) {
- errorOut(e, "ChimeraSeqsCommand", "execute");
+ m->errorOut(e, "ChimeraSeqsCommand", "execute");
exit(1);
}
}//**********************************************************************************************************************
if (candidateSeq->getName() != "") { //incase there is a commented sequence at the end of a file
if ((candidateSeq->getAligned().length() != templateSeqsLength) && (method != "chimeracheck")) { //chimeracheck does not require seqs to be aligned
- mothurOut(candidateSeq->getName() + " is not the same length as the template sequences. Skipping."); mothurOutEndLine();
+ m->mothurOut(candidateSeq->getName() + " is not the same length as the template sequences. Skipping."); m->mothurOutEndLine();
}else{
//find chimeras
chimera->getChimeras(candidateSeq);
delete candidateSeq;
//report progress
- if((i+1) % 100 == 0){ mothurOut("Processing sequence: " + toString(i+1)); mothurOutEndLine(); }
+ if((i+1) % 100 == 0){ m->mothurOut("Processing sequence: " + toString(i+1)); m->mothurOutEndLine(); }
}
//report progress
- if((line->numSeqs) % 100 != 0){ mothurOut("Processing sequence: " + toString(line->numSeqs)); mothurOutEndLine(); }
+ if((line->numSeqs) % 100 != 0){ m->mothurOut("Processing sequence: " + toString(line->numSeqs)); m->mothurOutEndLine(); }
out.close();
out2.close();
return 1;
}
catch(exception& e) {
- errorOut(e, "ChimeraSeqsCommand", "driver");
+ m->errorOut(e, "ChimeraSeqsCommand", "driver");
exit(1);
}
}
}else if (pid == 0){
driver(lines[process], outputFileName + toString(getpid()) + ".temp", filename, accnos + toString(getpid()) + ".temp");
exit(0);
- }else { mothurOut("unable to spawn the necessary processes."); mothurOutEndLine(); exit(0); }
+ }else { m->mothurOut("unable to spawn the necessary processes."); m->mothurOutEndLine(); exit(0); }
}
//force parent to wait until all the processes are done
#endif
}
catch(exception& e) {
- errorOut(e, "ChimeraSeqsCommand", "createProcesses");
+ m->errorOut(e, "ChimeraSeqsCommand", "createProcesses");
exit(1);
}
}
output.close();
}
catch(exception& e) {
- errorOut(e, "ChimeraSeqsCommand", "appendOuputFiles");
+ m->errorOut(e, "ChimeraSeqsCommand", "appendOuputFiles");
exit(1);
}
}
projects / mothur.git / blobdiff