#include "subsamplecommand.h"
#include "sharedutilities.h"
#include "deconvolutecommand.h"
+#include "getseqscommand.h"
#include "subsample.h"
//**********************************************************************************************************************
try {
CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "FLSSR", "none","fasta",false,false,true); parameters.push_back(pfasta);
CommandParameter pname("name", "InputTypes", "", "", "NameCount", "none", "none","name",false,false,true); parameters.push_back(pname);
+ CommandParameter ptaxonomy("taxonomy", "InputTypes", "", "", "none", "none", "none","taxonomy",false,false,true); parameters.push_back(ptaxonomy);
CommandParameter pcount("count", "InputTypes", "", "", "NameCount-CountGroup", "none", "none","count",false,false,true); parameters.push_back(pcount);
CommandParameter pgroup("group", "InputTypes", "", "", "CountGroup", "none", "none","group",false,false,true); parameters.push_back(pgroup);
CommandParameter plist("list", "InputTypes", "", "", "none", "FLSSR", "none","list",false,false,true); parameters.push_back(plist);
try {
string helpString = "";
helpString += "The sub.sample command is designed to be used as a way to normalize your data, or create a smaller set from your original set.\n";
- helpString += "The sub.sample command parameters are fasta, name, list, group, count, rabund, sabund, shared, groups, size, persample and label. You must provide a fasta, list, sabund, rabund or shared file as an input file.\n";
+ helpString += "The sub.sample command parameters are fasta, name, list, group, count, rabund, sabund, shared, taxonomy, groups, size, persample and label. You must provide a fasta, list, sabund, rabund or shared file as an input file.\n";
helpString += "The namefile is only used with the fasta file, not with the listfile, because the list file should contain all sequences.\n";
helpString += "The groups parameter allows you to specify which of the groups in your groupfile you would like included. The group names are separated by dashes.\n";
helpString += "The label parameter allows you to select what distance levels you would like, and are also separated by dashes.\n";
string pattern = "";
if (type == "fasta") { pattern = "[filename],subsample,[extension]"; }
- else if (type == "sabund") { pattern = "[filename],subsample,[extension]"; }
+ else if (type == "sabund") { pattern = "[filename],subsample,[extension]"; }
else if (type == "name") { pattern = "[filename],subsample,[extension]"; }
else if (type == "group") { pattern = "[filename],subsample,[extension]"; }
else if (type == "count") { pattern = "[filename],subsample,[extension]"; }
- else if (type == "list") { pattern = "[filename],subsample,[extension]"; }
+ else if (type == "list") { pattern = "[filename],[distance],subsample,[extension]"; }
+ else if (type == "taxonomy") { pattern = "[filename],subsample,[extension]"; }
else if (type == "shared") { pattern = "[filename],[distance],subsample,[extension]"; }
else if (type == "rabund") { pattern = "[filename],subsample,[extension]"; }
else { m->mothurOut("[ERROR]: No definition for type " + type + " output pattern.\n"); m->control_pressed = true; }
outputTypes["name"] = tempOutNames;
outputTypes["group"] = tempOutNames;
outputTypes["count"] = tempOutNames;
+ outputTypes["taxonomy"] = tempOutNames;
}
catch(exception& e) {
m->errorOut(e, "SubSampleCommand", "GetRelAbundCommand");
outputTypes["name"] = tempOutNames;
outputTypes["group"] = tempOutNames;
outputTypes["count"] = tempOutNames;
+ outputTypes["taxonomy"] = tempOutNames;
//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 = ""; }
//if the user has not given a path then, add inputdir. else leave path alone.
if (path == "") { parameters["count"] = inputDir + it->second; }
}
+
+ it = parameters.find("taxonomy");
+ //user has given a template file
+ if(it != parameters.end()){
+ path = m->hasPath(it->second);
+ //if the user has not given a path then, add inputdir. else leave path alone.
+ if (path == "") { parameters["taxonomy"] = inputDir + it->second; }
+ }
}
//check for required parameters
if (groupfile == "not open") { groupfile = ""; abort = true; }
else if (groupfile == "not found") { groupfile = ""; }
else { m->setGroupFile(groupfile); }
+
+ taxonomyfile = validParameter.validFile(parameters, "taxonomy", true);
+ if (taxonomyfile == "not open") { taxonomyfile = ""; abort = true; }
+ else if (taxonomyfile == "not found") { taxonomyfile = ""; }
+ else { m->setTaxonomyFile(taxonomyfile); }
countfile = validParameter.validFile(parameters, "count", true);
if (countfile == "not open") { countfile = ""; abort = true; }
else if (countfile == "not found") { countfile = ""; }
else {
m->setCountTableFile(countfile);
- ct.readTable(countfile);
+ ct.readTable(countfile, true, false);
}
if ((namefile != "") && (countfile != "")) {
}
}
- if ((namefile != "") && (fastafile == "")) { m->mothurOut("You may only use a namefile with a fastafile."); m->mothurOutEndLine(); abort = true; }
+ if ((namefile != "") && ((fastafile == "") && (taxonomyfile == ""))) { m->mothurOut("You may only use a name file with a fasta file or taxonomy file."); m->mothurOutEndLine(); abort = true; }
+
+ if ((taxonomyfile != "") && ((fastafile == "") && (listfile == ""))) { m->mothurOut("You may only use a taxonomyfile with a fastafile or listfile."); m->mothurOutEndLine(); abort = true; }
+
if ((fastafile == "") && (listfile == "") && (sabundfile == "") && (rabundfile == "") && (sharedfile == "")) {
m->mothurOut("You must provide a fasta, list, sabund, rabund or shared file as an input file."); m->mothurOutEndLine(); abort = true; }
if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setCountTableFile(current); }
}
+ itTypes = outputTypes.find("taxonomy");
+ if (itTypes != outputTypes.end()) {
+ if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setTaxonomyFile(current); }
+ }
m->mothurOutEndLine();
m->mothurOut("Output File Names: "); m->mothurOutEndLine();
else{
itGroupCounts = groupCounts.find(group);
if (itGroupCounts != groupCounts.end()) {
- if (groupCounts[group] < size) { subset.insert(names[j]); groupCounts[group]++; }
+ if (itGroupCounts->second < size) { subset.insert(names[j]); (itGroupCounts->second)++; }
}
}
}
}
in.close();
out.close();
+
if (count != subset.size()) {
m->mothurOut("[ERROR]: The subset selected contained " + toString(subset.size()) + " sequences, but I only found " + toString(count) + " of those in the fastafile."); m->mothurOutEndLine();
m->mothurOut("/******************************************/"); m->mothurOutEndLine();
m->mothurOut("Done."); m->mothurOutEndLine();
- }
+
+ if (taxonomyfile != "") {
+ set<string> tempSubset;
+ //get new unique names from fasta file
+ //read through fasta file outputting only the names on the subsample list after deconvolute
+ ifstream in2;
+ m->openInputFile(outputFileName, in2);
+
+ while (!in2.eof()) {
+ Sequence seq(in2); m->gobble(in2);
+ if (seq.getName() != "") {
+ tempSubset.insert(seq.getName());
+ }
+ }
+ in2.close();
+
+ //send that list to getTax
+ int tcount = getTax(tempSubset);
+ if (tcount != tempSubset.size()) { m->mothurOut("[ERROR]: subsampled fasta file contains " + toString(tempSubset.size()) + " sequences, but I only found " + toString(tcount) + " in your taxonomy file, please correct."); m->mothurOutEndLine(); }
+ }
+ }else {
+ if (taxonomyfile != "") {
+ int tcount = getTax(subset);
+ if (tcount != subset.size()) { m->mothurOut("[ERROR]: subsampled fasta file contains " + toString(subset.size()) + " sequences, but I only found " + toString(tcount) + " in your taxonomy file, please correct."); m->mothurOutEndLine(); }
+
+ } //should only contain uniques.
+ }
outputTypes["fasta"].push_back(outputFileName); outputNames.push_back(outputFileName);
try {
//save mothurOut's binLabels to restore for next label
- vector<string> saveBinLabels = m->currentBinLabels;
+ vector<string> saveBinLabels = m->currentSharedBinLabels;
string thisOutputDir = outputDir;
if (outputDir == "") { thisOutputDir += m->hasPath(sharedfile); }
m->openOutputFile(outputFileName, out);
outputTypes["shared"].push_back(outputFileName); outputNames.push_back(outputFileName);
- m->currentBinLabels = subsampledLabels;
+ m->currentSharedBinLabels = subsampledLabels;
thislookup[0]->printHeaders(out);
//save mothurOut's binLabels to restore for next label
- m->currentBinLabels = saveBinLabels;
+ m->currentSharedBinLabels = saveBinLabels;
return 0;
//**********************************************************************************************************************
int SubSampleCommand::getSubSampleList() {
try {
-
- string thisOutputDir = outputDir;
- if (outputDir == "") { thisOutputDir += m->hasPath(listfile); }
- map<string, string> variables;
- variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(listfile));
- variables["[extension]"] = m->getExtension(listfile);
- string outputFileName = getOutputFileName("list", variables);
- ofstream out;
- m->openOutputFile(outputFileName, out);
- outputTypes["list"].push_back(outputFileName); outputNames.push_back(outputFileName);
-
+
+ if (namefile != "") { m->readNames(namefile, nameMap); }
+
InputData* input = new InputData(listfile, "list");
ListVector* list = input->getListVector();
string lastLabel = list->getLabel();
- //if the users enters label "0.06" and there is no "0.06" in their file use the next lowest label.
+ //if the users enters label "0.06" and there is no "0.06" in their file use the next lowest label.
set<string> processedLabels;
set<string> userLabels = labels;
//file mismatch quit
if (list->getNumSeqs() != groupMap.getNumSeqs()) {
m->mothurOut("[ERROR]: your list file contains " + toString(list->getNumSeqs()) + " sequences, and your groupfile contains " + toString(groupMap.getNumSeqs()) + ", please correct.");
- m->mothurOutEndLine(); delete list; delete input; out.close(); outGroup.close(); return 0;
+ m->mothurOutEndLine(); delete list; delete input; outGroup.close(); return 0;
}
}else if (countfile != "") {
if (ct.hasGroupInfo()) {
//as long as you are not at the end of the file or done wih the lines you want
while((list != NULL) && ((allLines == 1) || (userLabels.size() != 0))) {
- if (m->control_pressed) { delete list; delete input; out.close(); return 0; }
+ if (m->control_pressed) { delete list; delete input; return 0; }
if(allLines == 1 || labels.count(list->getLabel()) == 1){
m->mothurOut(list->getLabel()); m->mothurOutEndLine();
- processList(list, out, subset);
+ processList(list, subset);
processedLabels.insert(list->getLabel());
userLabels.erase(list->getLabel());
list = input->getListVector(lastLabel);
m->mothurOut(list->getLabel()); m->mothurOutEndLine();
- processList(list, out, subset);
+ processList(list, subset);
processedLabels.insert(list->getLabel());
userLabels.erase(list->getLabel());
}
- if (m->control_pressed) { if (list != NULL) { delete list; } delete input; out.close(); return 0; }
+ if (m->control_pressed) { if (list != NULL) { delete list; } delete input; return 0; }
//output error messages about any remaining user labels
set<string>::iterator it;
m->mothurOut(list->getLabel()); m->mothurOutEndLine();
- processList(list, out, subset);
+ processList(list, subset);
delete list; list = NULL;
}
- out.close();
if (list != NULL) { delete list; }
delete input;
+
+ if (taxonomyfile != "") {
+ if (namefile == "") {
+ InputData input(listfile, "list");
+ ListVector* list = input.getListVector();
+ string lastLabel = list->getLabel();
+
+ for (int i = 0; i < list->getNumBins(); i++) {
+ vector<string> temp;
+ string bin = list->get(i);
+ m->splitAtComma(bin, temp);
+ for (int j = 0; j < temp.size(); j++) { vector<string> tempFakeOut; tempFakeOut.push_back(temp[j]); nameMap[temp[j]] = tempFakeOut; }
+ }
+ delete list;
+
+ int tcount = getTax(subset);
+ if (tcount != subset.size()) { m->mothurOut("[ERROR]: subsampled list file contains " + toString(subset.size()) + " sequences, but I only found " + toString(tcount) + " in your taxonomy file, did you forget a name file? Please correct."); m->mothurOutEndLine(); }
+ }else {
+ string tempAccnos = "temp.accnos";
+ ofstream outAccnos;
+ m->openOutputFile(tempAccnos, outAccnos);
+ for (set<string>::iterator it = subset.begin(); it != subset.end(); it++) { outAccnos << *it << endl; }
+ outAccnos.close();
+
+ m->mothurOut("Sampling taxonomy and name file... "); m->mothurOutEndLine();
+ string thisNameOutputDir = outputDir;
+ if (outputDir == "") { thisNameOutputDir += m->hasPath(namefile); }
+ map<string, string> variables;
+ variables["[filename]"] = thisNameOutputDir + m->getRootName(m->getSimpleName(namefile));
+ variables["[extension]"] = m->getExtension(namefile);
+ string outputNameFileName = getOutputFileName("name", variables);
+
+ string thisTaxOutputDir = outputDir;
+ if (outputDir == "") { thisTaxOutputDir += m->hasPath(taxonomyfile); }
+ variables["[filename]"] = thisTaxOutputDir + m->getRootName(m->getSimpleName(taxonomyfile));
+ variables["[extension]"] = m->getExtension(taxonomyfile);
+ string outputTaxFileName = getOutputFileName("taxonomy", variables);
+
+
+ //use unique.seqs to create new name and fastafile
+ string inputString = "dups=f, name=" + namefile + ", taxonomy=" + taxonomyfile + ", accnos=" + tempAccnos;
+ m->mothurOut("/******************************************/"); m->mothurOutEndLine();
+ m->mothurOut("Running command: get.seqs(" + inputString + ")"); m->mothurOutEndLine();
+ m->mothurCalling = true;
+
+ Command* getCommand = new GetSeqsCommand(inputString);
+ getCommand->execute();
+
+ map<string, vector<string> > filenames = getCommand->getOutputFiles();
+
+ delete getCommand;
+ m->mothurCalling = false;
+
+ m->renameFile(filenames["name"][0], outputNameFileName);
+ m->renameFile(filenames["taxonomy"][0], outputTaxFileName);
+
+ outputTypes["name"].push_back(outputNameFileName); outputNames.push_back(outputNameFileName);
+ outputNames.push_back(outputTaxFileName); outputTypes["taxonomy"].push_back(outputTaxFileName);
+
+ m->mothurOut("/******************************************/"); m->mothurOutEndLine();
+
+ m->mothurOut("Done."); m->mothurOutEndLine();
+ }
+ }
return 0;
}
}
//**********************************************************************************************************************
-int SubSampleCommand::processList(ListVector*& list, ofstream& out, set<string>& subset) {
+int SubSampleCommand::processList(ListVector*& list, set<string>& subset) {
try {
-
+ string thisOutputDir = outputDir;
+ if (outputDir == "") { thisOutputDir += m->hasPath(listfile); }
+ map<string, string> variables;
+ variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(listfile));
+ variables["[extension]"] = m->getExtension(listfile);
+ variables["[distance]"] = list->getLabel();
+ string outputFileName = getOutputFileName("list", variables);
+ ofstream out;
+ m->openOutputFile(outputFileName, out);
+ outputTypes["list"].push_back(outputFileName); outputNames.push_back(outputFileName);
+
int numBins = list->getNumBins();
ListVector* temp = new ListVector();
temp->setLabel(list->getLabel());
+ vector<string> binLabels = list->getLabels();
+ vector<string> newLabels;
for (int i = 0; i < numBins; i++) {
if (m->control_pressed) { break; }
if (newNames != "") {
newNames = newNames.substr(0, newNames.length()-1); //rip off extra comma
temp->push_back(newNames);
+ newLabels.push_back(binLabels[i]);
}
}
+ temp->setLabels(newLabels);
delete list;
list = temp;
- if (m->control_pressed) { return 0; }
+ if (m->control_pressed) { out.close(); return 0; }
+ list->printHeaders(out);
list->print(out);
+ out.close();
return 0;
m->errorOut(e, "SubSampleCommand", "processSabund");
exit(1);
}
-}
+}
+
+//**********************************************************************************************************************
+int SubSampleCommand::getTax(set<string>& subset) {
+ try {
+
+ string thisTaxOutputDir = outputDir;
+ if (outputDir == "") { thisTaxOutputDir += m->hasPath(taxonomyfile); }
+ map<string, string> variables;
+ variables["[filename]"] = thisTaxOutputDir + m->getRootName(m->getSimpleName(taxonomyfile));
+ variables["[extension]"] = m->getExtension(taxonomyfile);
+ string outputTaxFileName = getOutputFileName("taxonomy", variables);
+ ofstream outTax;
+ m->openOutputFile(outputTaxFileName, outTax);
+ outputNames.push_back(outputTaxFileName); outputTypes["taxonomy"].push_back(outputTaxFileName);
+
+ //read through fasta file outputting only the names on the subsample list
+ ifstream inTax;
+ m->openInputFile(taxonomyfile, inTax);
+
+ string tname, tax;
+ int tcount = 0;
+ map<string, vector<string> >::iterator itNameMap;
+
+ while(!inTax.eof()){
+
+ if (m->control_pressed) { inTax.close(); outTax.close(); return 0; }
+
+ inTax >> tname; m->gobble(inTax); //read from first column
+ inTax >> tax; m->gobble(inTax); //read from second column
+
+ //does the subset contain a sequence that this sequence represents
+ itNameMap = nameMap.find(tname);
+ if (itNameMap != nameMap.end()) {
+ vector<string> nameRepresents = itNameMap->second;
+
+
+ for (int i = 0; i < nameRepresents.size(); i++){
+ if (subset.count(nameRepresents[i]) != 0) {
+ outTax << nameRepresents[i] << '\t' << tax << endl;
+ tcount++;
+
+ }
+ }
+ }else{ m->mothurOut("[ERROR]: " + tname + " is missing, please correct."); m->mothurOutEndLine(); }
+ }
+ inTax.close();
+ outTax.close();
+
+ return tcount;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "SubSampleCommand", "getTax");
+ exit(1);
+ }
+}
+
//**********************************************************************************************************************
projects / mothur.git / blobdiff