#include "phylosummary.h"
#include "referencedb.h"
/**************************************************************************************************/
-Bayesian::Bayesian(string tfile, string tempFile, string method, int ksize, int cutoff, int i, int tid, bool f) :
+Bayesian::Bayesian(string tfile, string tempFile, string method, int ksize, int cutoff, int i, int tid, bool f, bool sh) :
Classify(), kmerSize(ksize), confidenceThreshold(cutoff), iters(i) {
try {
ReferenceDB* rdb = ReferenceDB::getInstance();
threadID = tid;
flip = f;
+ shortcuts = sh;
string baseName = tempFile;
if (baseName == "saved") { baseName = rdb->getSavedReference(); }
}
saveIn.close();
}
-
+FilesGood = false;
if(probFileTest && probFileTest2 && phyloTreeTest && probFileTest3 && FilesGood){
if (tempFile == "saved") { m->mothurOutEndLine(); m->mothurOut("Using sequences from " + rdb->getSavedReference() + " that are saved in memory."); m->mothurOutEndLine(); }
WordPairDiffArr.resize(numKmers);
for (int j = 0; j < wordGenusProb.size(); j++) { wordGenusProb[j].resize(genusNodes.size()); }
- ofstream out;
+ ofstream out;
ofstream out2;
#ifdef USE_MPI
#endif
- m->openOutputFile(probFileName, out);
+ if (shortcuts) {
+ m->openOutputFile(probFileName, out);
- //output mothur version
- out << "#" << m->getVersion() << endl;
+ //output mothur version
+ out << "#" << m->getVersion() << endl;
- out << numKmers << endl;
+ out << numKmers << endl;
- m->openOutputFile(probFileName2, out2);
+ m->openOutputFile(probFileName2, out2);
- //output mothur version
- out2 << "#" << m->getVersion() << endl;
+ //output mothur version
+ out2 << "#" << m->getVersion() << endl;
+ }
#ifdef USE_MPI
}
if (pid == 0) {
#endif
- out << i << '\t';
+ if (shortcuts) { out << i << '\t'; }
#ifdef USE_MPI
}
if (pid == 0) {
#endif
- out << k << '\t' << wordGenusProb[i][k] << '\t' ;
+ if (shortcuts) { out << k << '\t' << wordGenusProb[i][k] << '\t' ; }
#ifdef USE_MPI
}
if (pid == 0) {
#endif
- out << endl;
- out2 << probabilityInTemplate << '\t' << numNotZero << '\t' << log(probabilityInTemplate) << endl;
+ if (shortcuts) {
+ out << endl;
+ out2 << probabilityInTemplate << '\t' << numNotZero << '\t' << log(probabilityInTemplate) << endl;
+ }
#ifdef USE_MPI
}
if (pid == 0) {
#endif
- out.close();
- out2.close();
-
+ if (shortcuts) {
+ out.close();
+ out2.close();
+ }
#ifdef USE_MPI
}
#endif
class Bayesian : public Classify {
public:
- Bayesian(string, string, string, int, int, int, int, bool);
+ Bayesian(string, string, string, int, int, int, int, bool, bool);
~Bayesian();
string getTaxonomy(Sequence*);
}
fastaFile.close();
- database->generateDB();
+ if ((method == "kmer") && (!shortcuts)) {;} //don't print
+ else {database->generateDB(); }
}else if ((method == "kmer") && (!needToGenerate)) {
ifstream kmerFileTest(kmerDBName.c_str());
MPI_File inMPI;
MPI_Comm_rank(MPI_COMM_WORLD, &pid); //find out who we are
MPI_Comm_size(MPI_COMM_WORLD, &processors);
-
- //char* inFileName = new char[file.length()];
- //memcpy(inFileName, file.c_str(), file.length());
char inFileName[1024];
strcpy(inFileName, file.c_str());
string taxFile, templateFile, simpleTax;
vector<string> names;
int threadID;
- bool flip, flipped;
+ bool flip, flipped, shortcuts;
int readTaxonomy(string);
vector<string> parseTax(string);
CommandParameter pprobs("probs", "Boolean", "", "T", "", "", "",false,false); parameters.push_back(pprobs);
CommandParameter piters("iters", "Number", "", "100", "", "", "",false,true); parameters.push_back(piters);
CommandParameter psave("save", "Boolean", "", "F", "", "", "",false,false); parameters.push_back(psave);
+ CommandParameter pshortcuts("shortcuts", "Boolean", "", "T", "", "", "",false,false); parameters.push_back(pshortcuts);
CommandParameter pnumwanted("numwanted", "Number", "", "10", "", "", "",false,true); parameters.push_back(pnumwanted);
CommandParameter pinputdir("inputdir", "String", "", "", "", "", "",false,false); parameters.push_back(pinputdir);
CommandParameter poutputdir("outputdir", "String", "", "", "", "", "",false,false); parameters.push_back(poutputdir);
temp = validParameter.validFile(parameters, "probs", false); if (temp == "not found"){ temp = "true"; }
probs = m->isTrue(temp);
+
+ temp = validParameter.validFile(parameters, "shortcuts", false); if (temp == "not found"){ temp = "true"; }
+ writeShortcuts = m->isTrue(temp);
//temp = validParameter.validFile(parameters, "flip", false); if (temp == "not found"){ temp = "T"; }
//flip = m->isTrue(temp);
try {
if (abort == true) { if (calledHelp) { return 0; } return 2; }
- if(method == "bayesian"){ classify = new Bayesian(taxonomyFileName, templateFileName, search, kmerSize, cutoff, iters, rand(), flip); }
+ if(method == "bayesian"){ classify = new Bayesian(taxonomyFileName, templateFileName, search, kmerSize, cutoff, iters, rand(), flip, writeShortcuts); }
else if(method == "knn"){ classify = new Knn(taxonomyFileName, templateFileName, search, kmerSize, gapOpen, gapExtend, match, misMatch, numWanted, rand()); }
else {
m->mothurOut(search + " is not a valid method option. I will run the command using bayesian.");
m->mothurOutEndLine();
- classify = new Bayesian(taxonomyFileName, templateFileName, search, kmerSize, cutoff, iters, rand(), flip);
+ classify = new Bayesian(taxonomyFileName, templateFileName, search, kmerSize, cutoff, iters, rand(), flip, writeShortcuts);
}
if (m->control_pressed) { delete classify; return 0; }
string extension = "";
if (i != 0) { extension = toString(i) + ".temp"; processIDS.push_back(i); }
- classifyData* tempclass = new classifyData((accnos + extension), probs, method, templateFileName, taxonomyFileName, (taxFileName + extension), (tempTaxFile + extension), filename, search, kmerSize, iters, numWanted, m, lines[i]->start, lines[i]->end, match, misMatch, gapOpen, gapExtend, cutoff, i, flip);
+ classifyData* tempclass = new classifyData((accnos + extension), probs, method, templateFileName, taxonomyFileName, (taxFileName + extension), (tempTaxFile + extension), filename, search, kmerSize, iters, numWanted, m, lines[i]->start, lines[i]->end, match, misMatch, gapOpen, gapExtend, cutoff, i, flip, writeShortcuts);
pDataArray.push_back(tempclass);
//MySeqSumThreadFunction is in header. It must be global or static to work with the threads.
string fastaFileName, templateFileName, countfile, distanceFileName, namefile, search, method, taxonomyFileName, outputDir, groupfile;
int processors, kmerSize, numWanted, cutoff, iters;
float match, misMatch, gapOpen, gapExtend;
- bool abort, probs, save, flip, hasName, hasCount;
+ bool abort, probs, save, flip, hasName, hasCount, writeShortcuts;
int driver(linePair*, string, string, string, string);
int createProcesses(string, string, string, string);
MothurOut* m;
float match, misMatch, gapOpen, gapExtend;
int count, kmerSize, threadID, cutoff, iters, numWanted;
- bool probs, flip;
+ bool probs, flip, writeShortcuts;
classifyData(){}
- classifyData(string acc, bool p, string me, string te, string tx, string a, string r, string f, string se, int ks, int i, int numW, MothurOut* mout, unsigned long long st, unsigned long long en, float ma, float misMa, float gapO, float gapE, int cut, int tid, bool fli) {
+ classifyData(string acc, bool p, string me, string te, string tx, string a, string r, string f, string se, int ks, int i, int numW, MothurOut* mout, unsigned long long st, unsigned long long en, float ma, float misMa, float gapO, float gapE, int cut, int tid, bool fli, bool wsh) {
accnos = acc;
taxonomyFileName = tx;
templateFileName = te;
probs = p;
count = 0;
flip = fli;
+ writeShortcuts = wsh;
}
};
//make classify
Classify* myclassify;
- if(pDataArray->method == "bayesian"){ myclassify = new Bayesian(pDataArray->taxonomyFileName, pDataArray->templateFileName, pDataArray->search, pDataArray->kmerSize, pDataArray->cutoff, pDataArray->iters, pDataArray->threadID, pDataArray->flip); }
+ if(pDataArray->method == "bayesian"){ myclassify = new Bayesian(pDataArray->taxonomyFileName, pDataArray->templateFileName, pDataArray->search, pDataArray->kmerSize, pDataArray->cutoff, pDataArray->iters, pDataArray->threadID, pDataArray->flip, pDataArray->writeShortcuts); }
else if(pDataArray->method == "knn"){ myclassify = new Knn(pDataArray->taxonomyFileName, pDataArray->templateFileName, pDataArray->search, pDataArray->kmerSize, pDataArray->gapOpen, pDataArray->gapExtend, pDataArray->match, pDataArray->misMatch, pDataArray->numWanted, pDataArray->threadID); }
else {
pDataArray->m->mothurOut(pDataArray->search + " is not a valid method option. I will run the command using bayesian.");
pDataArray->m->mothurOutEndLine();
- myclassify = new Bayesian(pDataArray->taxonomyFileName, pDataArray->templateFileName, pDataArray->search, pDataArray->kmerSize, pDataArray->cutoff, pDataArray->iters, pDataArray->threadID, pDataArray->flip);
+ myclassify = new Bayesian(pDataArray->taxonomyFileName, pDataArray->templateFileName, pDataArray->search, pDataArray->kmerSize, pDataArray->cutoff, pDataArray->iters, pDataArray->threadID, pDataArray->flip, pDataArray->writeShortcuts);
}
if (pDataArray->m->control_pressed) { delete myclassify; return 0; }
counts[i] = newCounts;
}
hasGroups = true;
+ m->setAllGroups(groups);
return 0;
}
try {
CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "none", "FNGLT",false,false); parameters.push_back(pfasta);
CommandParameter pshared("shared", "InputTypes", "", "", "none", "sharedGroup", "none",false,false); parameters.push_back(pshared);
- CommandParameter pname("name", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(pname);
- CommandParameter pgroup("group", "InputTypes", "", "", "none", "sharedGroup", "FNGLT",false,false); parameters.push_back(pgroup);
+ CommandParameter pname("name", "InputTypes", "", "", "NameCount", "none", "none",false,false); parameters.push_back(pname);
+ CommandParameter pcount("count", "InputTypes", "", "", "NameCount-CountGroup", "none", "none",false,false); parameters.push_back(pcount);
+ CommandParameter pgroup("group", "InputTypes", "", "", "CountGroup", "sharedGroup", "FNGLT",false,false); parameters.push_back(pgroup);
CommandParameter pdesign("design", "InputTypes", "", "", "none", "sharedGroup", "FNGLT",false,false); parameters.push_back(pdesign);
CommandParameter plist("list", "InputTypes", "", "", "none", "none", "FNGLT",false,false); parameters.push_back(plist);
CommandParameter ptaxonomy("taxonomy", "InputTypes", "", "", "none", "none", "FNGLT",false,false); parameters.push_back(ptaxonomy);
string helpString = "";
helpString += "The get.groups command selects sequences from a specfic group or set of groups from the following file types: fasta, name, group, list, taxonomy, design or shared file.\n";
helpString += "It outputs a file containing the sequences in the those specified groups, or a sharedfile containing only those groups.\n";
- helpString += "The get.groups command parameters are accnos, fasta, name, group, list, taxonomy, shared, design and groups. The group parameter is required, unless you have a current group file, or are using a shared file.\n";
+ helpString += "The get.groups command parameters are accnos, fasta, name, group, list, taxonomy, shared, design and groups. The group or count parameter is required, unless you have a current group or count file, or are using a shared file.\n";
helpString += "You must also provide an accnos containing the list of groups to get or set the groups parameter to the groups you wish to select.\n";
helpString += "The groups parameter allows you to specify which of the groups in your groupfile you would like. You can separate group names with dashes.\n";
helpString += "The get.groups command should be in the following format: get.groups(accnos=yourAccnos, fasta=yourFasta, group=yourGroupFile).\n";
else if (type == "taxonomy") { outputFileName = "pick" + m->getExtension(inputName); }
else if (type == "name") { outputFileName = "pick" + m->getExtension(inputName); }
else if (type == "group") { outputFileName = "pick" + m->getExtension(inputName); }
+ else if (type == "count") { outputFileName = "pick" + m->getExtension(inputName); }
else if (type == "list") { outputFileName = "pick" + m->getExtension(inputName); }
else if (type == "shared") { outputFileName = "pick" + m->getExtension(inputName); }
else if (type == "design") { outputFileName = "pick" + m->getExtension(inputName); }
outputTypes["list"] = tempOutNames;
outputTypes["shared"] = tempOutNames;
outputTypes["design"] = tempOutNames;
+ outputTypes["count"] = tempOutNames;
}
catch(exception& e) {
m->errorOut(e, "GetGroupsCommand", "GetGroupsCommand");
outputTypes["list"] = tempOutNames;
outputTypes["shared"] = tempOutNames;
outputTypes["design"] = tempOutNames;
+ outputTypes["count"] = tempOutNames;
//if the user changes the output directory command factory will send this info to us in the output parameter
//if the user has not given a path then, add inputdir. else leave path alone.
if (path == "") { parameters["design"] = inputDir + it->second; }
}
+
+ it = parameters.find("count");
+ //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["count"] = inputDir + it->second; }
+ }
}
else if (namefile == "not found") { namefile = ""; }
else { m->setNameFile(namefile); }
- groupfile = validParameter.validFile(parameters, "group", true);
- if (groupfile == "not open") { groupfile = ""; abort = true; }
- else if (groupfile == "not found") { groupfile = ""; }
- else { m->setGroupFile(groupfile); }
-
listfile = validParameter.validFile(parameters, "list", true);
if (listfile == "not open") { abort = true; }
else if (listfile == "not found") { listfile = ""; }
if (designfile == "not open") { designfile = ""; abort = true; }
else if (designfile == "not found") { designfile = ""; }
else { m->setDesignFile(designfile); }
+
+ countfile = validParameter.validFile(parameters, "count", true);
+ if (countfile == "not open") { countfile = ""; abort = true; }
+ else if (countfile == "not found") { countfile = ""; }
+ else { m->setCountTableFile(countfile); }
+
+ if ((namefile != "") && (countfile != "")) {
+ m->mothurOut("[ERROR]: you may only use one of the following: name or count."); m->mothurOutEndLine(); abort = true;
+ }
+
+ if ((groupfile != "") && (countfile != "")) {
+ m->mothurOut("[ERROR]: you may only use one of the following: group or count."); m->mothurOutEndLine(); abort=true;
+ }
+
- if ((sharedfile == "") && (groupfile == "") && (designfile == "")) {
+ if ((sharedfile == "") && (groupfile == "") && (designfile == "") && (countfile == "")) {
//is there are current file available for any of these?
if ((namefile != "") || (fastafile != "") || (listfile != "") || (taxfile != "")) {
//give priority to group, then shared
sharedfile = m->getSharedFile();
if (sharedfile != "") { m->mothurOut("Using " + sharedfile + " as input file for the shared parameter."); m->mothurOutEndLine(); }
else {
- m->mothurOut("You have no current groupfile or sharedfile and one is required."); m->mothurOutEndLine(); abort = true;
+ countfile = m->getCountTableFile();
+ if (countfile != "") { m->mothurOut("Using " + countfile + " as input file for the count parameter."); m->mothurOutEndLine(); }
+ else {
+ m->mothurOut("You have no current groupfile, countfile or sharedfile and one is required."); m->mothurOutEndLine(); abort = true;
+ }
}
}
}else {
designfile = m->getDesignFile();
if (designfile != "") { m->mothurOut("Using " + designfile + " as input file for the design parameter."); m->mothurOutEndLine(); }
else {
- m->mothurOut("You have no current groupfile or sharedfile or designfile and one is required."); m->mothurOutEndLine(); abort = true;
+ countfile = m->getCountTableFile();
+ if (countfile != "") { m->mothurOut("Using " + countfile + " as input file for the count parameter."); m->mothurOutEndLine(); }
+ else {
+ m->mothurOut("You have no current groupfile, designfile, countfile or sharedfile and one is required."); m->mothurOutEndLine(); abort = true;
+ }
+
}
}
}
if ((accnosfile == "") && (Groups.size() == 0)) { m->mothurOut("You must provide an accnos file or specify groups using the groups parameter."); m->mothurOutEndLine(); abort = true; }
- if ((fastafile == "") && (namefile == "") && (groupfile == "") && (designfile == "") && (sharedfile == "") && (listfile == "") && (taxfile == "")) { m->mothurOut("You must provide at least one of the following: fasta, name, taxonomy, group, shared, design or list."); m->mothurOutEndLine(); abort = true; }
- if ((groupfile == "") && ((namefile != "") || (fastafile != "") || (listfile != "") || (taxfile != ""))) { m->mothurOut("If using a fasta, name, taxonomy, group or list, then you must provide a group file."); m->mothurOutEndLine(); abort = true; }
-
- if ((namefile == "") && ((fastafile != "") || (taxfile != ""))){
- vector<string> files; files.push_back(fastafile); files.push_back(taxfile);
- parser.getNameFile(files);
- }
+ if ((fastafile == "") && (namefile == "") && (countfile == "") && (groupfile == "") && (designfile == "") && (sharedfile == "") && (listfile == "") && (taxfile == "")) { m->mothurOut("You must provide at least one of the following: fasta, name, taxonomy, group, shared, design, count or list."); m->mothurOutEndLine(); abort = true; }
+ if (((groupfile == "") && (countfile == "")) && ((namefile != "") || (fastafile != "") || (listfile != "") || (taxfile != ""))) { m->mothurOut("If using a fasta, name, taxonomy, group or list, then you must provide a group or count file."); m->mothurOutEndLine(); abort = true; }
+
+ if (countfile == "") {
+ if ((namefile == "") && ((fastafile != "") || (taxfile != ""))){
+ vector<string> files; files.push_back(fastafile); files.push_back(taxfile);
+ parser.getNameFile(files);
+ }
+ }
}
}
SharedUtil* util = new SharedUtil();
vector<string> gNamesOfGroups = groupMap->getNamesOfGroups();
util->setGroups(Groups, gNamesOfGroups);
+ m->setGroups(Groups);
groupMap->setNamesOfGroups(gNamesOfGroups);
delete util;
fillNames();
delete groupMap;
- }
+ }else if (countfile != ""){
+ if ((fastafile != "") || (listfile != "") || (taxfile != "")) {
+ m->mothurOut("\n[NOTE]: The count file should contain only unique names, so mothur assumes your fasta, list and taxonomy files also contain only uniques.\n\n");
+ }
+ CountTable ct;
+ ct.readTable(countfile);
+ if (!ct.hasGroupInfo()) { m->mothurOut("[ERROR]: your count file does not contain group info, aborting.\n"); return 0; }
+
+ vector<string> gNamesOfGroups = ct.getNamesOfGroups();
+ SharedUtil util;
+ util.setGroups(Groups, gNamesOfGroups);
+ m->setGroups(Groups);
+ for (int i = 0; i < Groups.size(); i++) {
+ vector<string> thisGroupsSeqs = ct.getNamesOfSeqs(Groups[i]);
+ for (int j = 0; j < thisGroupsSeqs.size(); j++) { names.insert(thisGroupsSeqs[j]); }
+ }
+ }
if (m->control_pressed) { return 0; }
if (namefile != "") { readName(); }
if (fastafile != "") { readFasta(); }
if (groupfile != "") { readGroup(); }
+ if (countfile != "") { readCount(); }
if (listfile != "") { readList(); }
if (taxfile != "") { readTax(); }
if (sharedfile != "") { readShared(); }
if (itTypes != outputTypes.end()) {
if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setDesignFile(current); }
}
+
+ itTypes = outputTypes.find("count");
+ if (itTypes != outputTypes.end()) {
+ if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setCountTableFile(current); }
+ }
}
return 0;
}
}
//**********************************************************************************************************************
+int GetGroupsCommand::readCount(){
+ try {
+ string thisOutputDir = outputDir;
+ if (outputDir == "") { thisOutputDir += m->hasPath(countfile); }
+ string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(countfile)) + getOutputFileNameTag("count", countfile);
+
+ ofstream out;
+ m->openOutputFile(outputFileName, out);
+
+ ifstream in;
+ m->openInputFile(countfile, in);
+
+ bool wroteSomething = false;
+ int selectedCount = 0;
+
+ string headers = m->getline(in); m->gobble(in);
+ vector<string> columnHeaders = m->splitWhiteSpace(headers);
+
+ vector<string> groups;
+ map<int, string> originalGroupIndexes;
+ map<string, int> GroupIndexes;
+ set<int> indexOfGroupsChosen;
+ for (int i = 2; i < columnHeaders.size(); i++) { groups.push_back(columnHeaders[i]); originalGroupIndexes[i-2] = columnHeaders[i]; }
+ //sort groups to keep consistent with how we store the groups in groupmap
+ sort(groups.begin(), groups.end());
+ for (int i = 0; i < groups.size(); i++) { GroupIndexes[groups[i]] = i; }
+ sort(Groups.begin(), Groups.end());
+ out << "Representative_Sequence\ttotal\t";
+ for (int i = 0; i < Groups.size(); i++) { out << Groups[i] << '\t'; indexOfGroupsChosen.insert(GroupIndexes[Groups[i]]); }
+ out << endl;
+
+ string name; int oldTotal;
+ while (!in.eof()) {
+
+ if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; }
+
+ in >> name; m->gobble(in); in >> oldTotal; m->gobble(in);
+ if (m->debug) { m->mothurOut("[DEBUG]: " + name + '\t' + toString(oldTotal) + "\n"); }
+
+ if (names.count(name) != 0) {
+ //if group info, then read it
+ vector<int> selectedCounts; int thisTotal = 0; int temp;
+ for (int i = 0; i < groups.size(); i++) {
+ int thisIndex = GroupIndexes[originalGroupIndexes[i]];
+ in >> temp; m->gobble(in);
+ if (indexOfGroupsChosen.count(thisIndex) != 0) { //we want this group
+ selectedCounts.push_back(temp); thisTotal += temp;
+ }
+ }
+
+ out << name << '\t' << thisTotal << '\t';
+ for (int i = 0; i < selectedCounts.size(); i++) { out << selectedCounts[i] << '\t'; }
+ out << endl;
+
+ wroteSomething = true;
+ selectedCount+= thisTotal;
+ }else { m->getline(in); }
+
+ m->gobble(in);
+ }
+ in.close();
+ out.close();
+
+ if (wroteSomething == false) { m->mothurOut("Your file does NOT contain sequences from the groups you wish to get."); m->mothurOutEndLine(); }
+ outputTypes["count"].push_back(outputFileName); outputNames.push_back(outputFileName);
+
+ m->mothurOut("Selected " + toString(selectedCount) + " sequences from your count file."); m->mothurOutEndLine();
+
+ return 0;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "GetGroupsCommand", "readCount");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
int GetGroupsCommand::readDesign(){
try {
string thisOutputDir = outputDir;
map<string, string> uniqueToRedundant; //if a namefile is given and the first column name is not selected
//then the other files need to change the unique name in their file to match.
//only add the names that need to be changed to keep the map search quick
- string accnosfile, fastafile, namefile, groupfile, listfile, designfile, taxfile, outputDir, groups, sharedfile;
+ string accnosfile, countfile, fastafile, namefile, groupfile, listfile, designfile, taxfile, outputDir, groups, sharedfile;
bool abort;
vector<string> outputNames, Groups;
GroupMap* groupMap;
int readFasta();
int readName();
int readGroup();
+ int readCount();
int readList();
int readTax();
int fillNames();
: Classify(), num(n), search(method) {
try {
threadID = tid;
+ shortcuts = true;
//create search database and names vector
generateDatabaseAndNames(tfile, tempFile, method, kmerSize, gapOpen, gapExtend, match, misMatch);
vector<string> MGClusterCommand::setParameters(){
try {
CommandParameter pblast("blast", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(pblast);
- CommandParameter pname("name", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(pname);
- CommandParameter pcount("count", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(pcount);
+ CommandParameter pname("name", "InputTypes", "", "", "NameCount", "none", "ColumnName",false,false); parameters.push_back(pname);
+ CommandParameter pcount("count", "InputTypes", "", "", "NameCount", "none", "none",false,false); parameters.push_back(pcount);
CommandParameter plength("length", "Number", "", "5", "", "", "",false,false); parameters.push_back(plength);
CommandParameter ppenalty("penalty", "Number", "", "0.10", "", "", "",false,false); parameters.push_back(ppenalty);
CommandParameter pcutoff("cutoff", "Number", "", "0.70", "", "", "",false,false); parameters.push_back(pcutoff);
//if the user has not given a path then, add inputdir. else leave path alone.
if (path == "") { parameters["name"] = inputDir + it->second; }
}
+
+ it = parameters.find("count");
+ //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["count"] = inputDir + it->second; }
+ }
}
exit(1);
}
}
+//**********************************************************************************************************************
+bool MothurOut::isSubset(vector<string> bigset, vector<string> subset) {
+ try {
+
+
+ if (subset.size() > bigset.size()) { return false; }
+
+ //check if each guy in suset is also in bigset
+ for (int i = 0; i < subset.size(); i++) {
+ bool match = false;
+ for (int j = 0; j < bigset.size(); j++) {
+ if (subset[i] == bigset[j]) { match = true; break; }
+ }
+
+ //you have a guy in subset that had no match in bigset
+ if (match == false) { return false; }
+ }
+
+ return true;
+
+ }
+ catch(exception& e) {
+ errorOut(e, "MothurOut", "isSubset");
+ exit(1);
+ }
+}
/***********************************************************************/
int MothurOut::mothurRemove(string filename){
try {
void splitAtChar(string&, string&, char);
int removeConfidences(string&);
string makeList(vector<string>&);
+ bool isSubset(vector<string>, vector<string>); //bigSet, subset
//math operation
int factorial(int num);
try {
map<string, int>::iterator itFind = name2Taxonomy.find(seqName);
- if (itFind != name2Taxonomy.end()) { return name2Taxonomy[seqName]; }
+ if (itFind != name2Taxonomy.end()) { return itFind->second; }
else { m->mothurOut("Cannot find " + seqName + ". Mismatch with taxonomy and template files. Cannot continue."); m->mothurOutEndLine(); exit(1);}
}
catch(exception& e) {
try {
CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "none", "FNGLT",false,false); parameters.push_back(pfasta);
CommandParameter pshared("shared", "InputTypes", "", "", "none", "sharedGroup", "none",false,false); parameters.push_back(pshared);
- CommandParameter pname("name", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(pname);
- CommandParameter pgroup("group", "InputTypes", "", "", "none", "sharedGroup", "FNGLT",false,false); parameters.push_back(pgroup);
- CommandParameter pdesign("design", "InputTypes", "", "", "none", "sharedGroup", "FNGLT",false,false); parameters.push_back(pdesign);
+ CommandParameter pname("name", "InputTypes", "", "", "NameCount", "none", "none",false,false); parameters.push_back(pname);
+ CommandParameter pcount("count", "InputTypes", "", "", "NameCount-CountGroup", "none", "none",false,false); parameters.push_back(pcount);
+ CommandParameter pgroup("group", "InputTypes", "", "", "CountGroup", "sharedGroup", "FNGLT",false,false); parameters.push_back(pgroup); CommandParameter pdesign("design", "InputTypes", "", "", "none", "sharedGroup", "FNGLT",false,false); parameters.push_back(pdesign);
CommandParameter plist("list", "InputTypes", "", "", "none", "none", "FNGLT",false,false); parameters.push_back(plist);
CommandParameter ptaxonomy("taxonomy", "InputTypes", "", "", "none", "none", "FNGLT",false,false); parameters.push_back(ptaxonomy);
CommandParameter paccnos("accnos", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(paccnos);
string RemoveGroupsCommand::getHelpString(){
try {
string helpString = "";
- helpString += "The remove.groups command removes sequences from a specfic group or set of groups from the following file types: fasta, name, group, list, taxonomy, design or sharedfile.\n";
+ helpString += "The remove.groups command removes sequences from a specfic group or set of groups from the following file types: fasta, name, group, count, list, taxonomy, design or sharedfile.\n";
helpString += "It outputs a file containing the sequences NOT in the those specified groups, or with a sharedfile eliminates the groups you selected.\n";
- helpString += "The remove.groups command parameters are accnos, fasta, name, group, list, taxonomy, shared, design and groups. The group parameter is required, unless you have a current group file or are using a sharedfile.\n";
+ helpString += "The remove.groups command parameters are accnos, fasta, name, group, list, taxonomy, shared, design and groups. The group or count parameter is required, unless you have a current group or count file or are using a sharedfile.\n";
helpString += "You must also provide an accnos containing the list of groups to remove or set the groups parameter to the groups you wish to remove.\n";
helpString += "The groups parameter allows you to specify which of the groups in your groupfile you would like removed. You can separate group names with dashes.\n";
helpString += "The remove.groups command should be in the following format: remove.groups(accnos=yourAccnos, fasta=yourFasta, group=yourGroupFile).\n";
else if (type == "taxonomy") { outputFileName = "pick" + m->getExtension(inputName); }
else if (type == "name") { outputFileName = "pick" + m->getExtension(inputName); }
else if (type == "group") { outputFileName = "pick" + m->getExtension(inputName); }
+ else if (type == "count") { outputFileName = "pick" + m->getExtension(inputName); }
else if (type == "list") { outputFileName = "pick" + m->getExtension(inputName); }
else if (type == "shared") { outputFileName = "pick" + m->getExtension(inputName); }
else if (type == "design") { outputFileName = "pick" + m->getExtension(inputName); }
outputTypes["list"] = tempOutNames;
outputTypes["shared"] = tempOutNames;
outputTypes["design"] = tempOutNames;
+ outputTypes["count"] = tempOutNames;
}
catch(exception& e) {
m->errorOut(e, "RemoveGroupsCommand", "RemoveGroupsCommand");
outputTypes["list"] = tempOutNames;
outputTypes["shared"] = tempOutNames;
outputTypes["design"] = tempOutNames;
+ outputTypes["count"] = tempOutNames;
//if the user changes the output directory command factory will send this info to us in the output parameter
//if the user has not given a path then, add inputdir. else leave path alone.
if (path == "") { parameters["design"] = inputDir + it->second; }
}
+
+ it = parameters.find("count");
+ //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["count"] = inputDir + it->second; }
+ }
}
else if (sharedfile == "not found") { sharedfile = ""; }
else { m->setSharedFile(sharedfile); }
- groupfile = validParameter.validFile(parameters, "group", true);
- if (groupfile == "not open") { groupfile = ""; abort = true; }
- else if (groupfile == "not found") { groupfile = ""; }
- else { m->setGroupFile(groupfile); }
- if ((sharedfile == "") && (groupfile == "") && (designfile == "")) {
+ countfile = validParameter.validFile(parameters, "count", true);
+ if (countfile == "not open") { countfile = ""; abort = true; }
+ else if (countfile == "not found") { countfile = ""; }
+ else { m->setCountTableFile(countfile); }
+
+ if ((namefile != "") && (countfile != "")) {
+ m->mothurOut("[ERROR]: you may only use one of the following: name or count."); m->mothurOutEndLine(); abort = true;
+ }
+
+ if ((groupfile != "") && (countfile != "")) {
+ m->mothurOut("[ERROR]: you may only use one of the following: group or count."); m->mothurOutEndLine(); abort=true;
+ }
+
+
+ if ((sharedfile == "") && (groupfile == "") && (designfile == "") && (countfile == "")) {
//is there are current file available for any of these?
if ((namefile != "") || (fastafile != "") || (listfile != "") || (taxfile != "")) {
//give priority to group, then shared
sharedfile = m->getSharedFile();
if (sharedfile != "") { m->mothurOut("Using " + sharedfile + " as input file for the shared parameter."); m->mothurOutEndLine(); }
else {
- m->mothurOut("You have no current groupfile or sharedfile and one is required."); m->mothurOutEndLine(); abort = true;
+ countfile = m->getCountTableFile();
+ if (countfile != "") { m->mothurOut("Using " + countfile + " as input file for the count parameter."); m->mothurOutEndLine(); }
+ else {
+ m->mothurOut("You have no current groupfile, countfile or sharedfile and one is required."); m->mothurOutEndLine(); abort = true;
+ }
}
}
}else {
designfile = m->getDesignFile();
if (designfile != "") { m->mothurOut("Using " + designfile + " as input file for the design parameter."); m->mothurOutEndLine(); }
else {
- m->mothurOut("You have no current groupfile or sharedfile or designfile and one is required."); m->mothurOutEndLine(); abort = true;
+ countfile = m->getCountTableFile();
+ if (countfile != "") { m->mothurOut("Using " + countfile + " as input file for the count parameter."); m->mothurOutEndLine(); }
+ else {
+ m->mothurOut("You have no current groupfile, designfile, countfile or sharedfile and one is required."); m->mothurOutEndLine(); abort = true;
+ }
+
}
}
}
if ((accnosfile == "") && (Groups.size() == 0)) { m->mothurOut("You must provide an accnos file containing group names or specify groups using the groups parameter."); m->mothurOutEndLine(); abort = true; }
- if ((fastafile == "") && (namefile == "") && (groupfile == "") && (sharedfile == "") && (designfile == "") && (listfile == "") && (taxfile == "")) { m->mothurOut("You must provide at least one of the following: fasta, name, taxonomy, group, shared, design or list."); m->mothurOutEndLine(); abort = true; }
- if ((groupfile == "") && ((namefile != "") || (fastafile != "") || (listfile != "") || (taxfile != ""))) { m->mothurOut("If using a fasta, name, taxonomy, group or list, then you must provide a group file."); m->mothurOutEndLine(); abort = true; }
-
- if ((namefile == "") && ((fastafile != "") || (taxfile != ""))){
- vector<string> files; files.push_back(fastafile); files.push_back(taxfile);
- parser.getNameFile(files);
- }
-
+ if ((fastafile == "") && (namefile == "") && (countfile == "") && (groupfile == "") && (designfile == "") && (sharedfile == "") && (listfile == "") && (taxfile == "")) { m->mothurOut("You must provide at least one of the following: fasta, name, taxonomy, group, shared, design, count or list."); m->mothurOutEndLine(); abort = true; }
+ if (((groupfile == "") && (countfile == "")) && ((namefile != "") || (fastafile != "") || (listfile != "") || (taxfile != ""))) { m->mothurOut("If using a fasta, name, taxonomy, group or list, then you must provide a group or count file."); m->mothurOutEndLine(); abort = true; }
+
+ if (countfile == "") {
+ if ((namefile == "") && ((fastafile != "") || (taxfile != ""))){
+ vector<string> files; files.push_back(fastafile); files.push_back(taxfile);
+ parser.getNameFile(files);
+ }
+ }
}
}
fillNames();
delete groupMap;
- }
+ }else if (countfile != ""){
+ if ((fastafile != "") || (listfile != "") || (taxfile != "")) {
+ m->mothurOut("\n[NOTE]: The count file should contain only unique names, so mothur assumes your fasta, list and taxonomy files also contain only uniques.\n\n");
+ }
+ CountTable ct;
+ ct.readTable(countfile);
+ if (!ct.hasGroupInfo()) { m->mothurOut("[ERROR]: your count file does not contain group info, aborting.\n"); return 0; }
+
+ vector<string> gNamesOfGroups = ct.getNamesOfGroups();
+ SharedUtil util;
+ util.setGroups(Groups, gNamesOfGroups);
+ vector<string> namesOfSeqs = ct.getNamesOfSeqs();
+ sort(Groups.begin(), Groups.end());
+
+ for (int i = 0; i < namesOfSeqs.size(); i++) {
+ vector<string> thisSeqsGroups = ct.getGroups(namesOfSeqs[i]);
+ if (m->isSubset(Groups, thisSeqsGroups)) { //you only have seqs from these groups so remove you
+ names.insert(namesOfSeqs[i]);
+ }
+ }
+ }
+
if (m->control_pressed) { return 0; }
if (namefile != "") { readName(); }
if (fastafile != "") { readFasta(); }
if (groupfile != "") { readGroup(); }
+ if (countfile != "") { readCount(); }
if (listfile != "") { readList(); }
if (taxfile != "") { readTax(); }
if (sharedfile != "") { readShared(); }
if (itTypes != outputTypes.end()) {
if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setDesignFile(current); }
}
+
+ itTypes = outputTypes.find("count");
+ if (itTypes != outputTypes.end()) {
+ if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setCountTableFile(current); }
+ }
}
return 0;
}
}
//**********************************************************************************************************************
+int RemoveGroupsCommand::readCount(){
+ try {
+ string thisOutputDir = outputDir;
+ if (outputDir == "") { thisOutputDir += m->hasPath(countfile); }
+ string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(countfile)) + getOutputFileNameTag("count", countfile);
+
+ ofstream out;
+ m->openOutputFile(outputFileName, out);
+
+ ifstream in;
+ m->openInputFile(countfile, in);
+
+ bool wroteSomething = false;
+ int removedCount = 0;
+
+ string headers = m->getline(in); m->gobble(in);
+ vector<string> columnHeaders = m->splitWhiteSpace(headers);
+
+ vector<string> groups;
+ map<int, string> originalGroupIndexes;
+ map<string, int> GroupIndexes;
+ set<int> indexOfGroupsChosen;
+ for (int i = 2; i < columnHeaders.size(); i++) { groups.push_back(columnHeaders[i]); originalGroupIndexes[i-2] = columnHeaders[i]; }
+ //sort groups to keep consistent with how we store the groups in groupmap
+ sort(groups.begin(), groups.end());
+ for (int i = 0; i < groups.size(); i++) { GroupIndexes[groups[i]] = i; }
+
+ vector<string> groupsToKeep;
+ for (int i = 0; i < groups.size(); i++) {
+ if (!m->inUsersGroups(groups[i], Groups)) { groupsToKeep.push_back(groups[i]); }
+ }
+ sort(groupsToKeep.begin(), groupsToKeep.end());
+ out << "Representative_Sequence\ttotal\t";
+ for (int i = 0; i < groupsToKeep.size(); i++) { out << groupsToKeep[i] << '\t'; indexOfGroupsChosen.insert(GroupIndexes[groupsToKeep[i]]); }
+ out << endl;
+
+ string name; int oldTotal;
+ while (!in.eof()) {
+
+ if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; }
+
+ in >> name; m->gobble(in); in >> oldTotal; m->gobble(in);
+ if (m->debug) { m->mothurOut("[DEBUG]: " + name + '\t' + toString(oldTotal) + "\n"); }
+
+ if (names.count(name) == 0) {
+ //if group info, then read it
+ vector<int> selectedCounts; int thisTotal = 0; int temp;
+ for (int i = 0; i < groups.size(); i++) {
+ int thisIndex = GroupIndexes[originalGroupIndexes[i]];
+ in >> temp; m->gobble(in);
+ if (indexOfGroupsChosen.count(thisIndex) != 0) { //we want this group
+ selectedCounts.push_back(temp); thisTotal += temp;
+ }
+ }
+
+ out << name << '\t' << thisTotal << '\t';
+ for (int i = 0; i < selectedCounts.size(); i++) { out << selectedCounts[i] << '\t'; }
+ out << endl;
+
+ wroteSomething = true;
+ removedCount+= (oldTotal - thisTotal);
+ }else { m->getline(in); removedCount += oldTotal; }
+
+ m->gobble(in);
+ }
+ in.close();
+ out.close();
+
+ if (wroteSomething == false) { m->mothurOut("Your file does NOT contain sequences from the groups you wish to get."); m->mothurOutEndLine(); }
+ outputTypes["count"].push_back(outputFileName); outputNames.push_back(outputFileName);
+
+ m->mothurOut("Removed " + toString(removedCount) + " sequences from your count file."); m->mothurOutEndLine();
+
+ return 0;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "RemoveGroupsCommand", "readCount");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
int RemoveGroupsCommand::readDesign(){
try {
string thisOutputDir = outputDir;
private:
set<string> names;
- string accnosfile, fastafile, namefile, groupfile, designfile, listfile, taxfile, outputDir, groups, sharedfile;
+ string accnosfile, fastafile, namefile, groupfile, countfile, designfile, listfile, taxfile, outputDir, groups, sharedfile;
bool abort;
vector<string> outputNames, Groups;
GroupMap* groupMap;
int readShared();
int readName();
int readGroup();
+ int readCount();
int readList();
int readTax();
int fillNames();
for (int j = 0; j < listNames.size(); j++) {
int num = groupNamesSeqs.count(listNames[j]);
- if (num == 0) { error = 1; m->mothurOut("[ERROR]: " + listNames[j] + " is in your listfile and not in your groupfile. Please correct."); m->mothurOutEndLine(); }
- else { groupNamesSeqs.erase(listNames[j]); }
+ if (num == 0) {
+ error = 1;
+ if (groupfile != "") {
+ m->mothurOut("[ERROR]: " + listNames[j] + " is in your listfile and not in your groupfile. Please correct."); m->mothurOutEndLine(); }
+ else{ m->mothurOut("[ERROR]: " + listNames[j] + " is in your listfile and not in your count file. Please correct."); m->mothurOutEndLine(); }
+ }else { groupNamesSeqs.erase(listNames[j]); }
}
}
//if the user only entered invalid groups
if (userGroups.size() == 0) {
- m->mothurOut("You provided no valid groups. I will run the command using all the groups in your groupfile."); m->mothurOutEndLine();
+ m->mothurOut("You provided no valid groups. I will run the command using all the groups in your file."); m->mothurOutEndLine();
for (int i = 0; i < allGroups.size(); i++) {
userGroups.push_back(allGroups[i]);
}
projects / mothur.git / commitdiff