A79234D713C74BF6002B08E2 /* mothurfisher.cpp in Sources */ = {isa = PBXBuildFile; fileRef = A79234D613C74BF6002B08E2 /* mothurfisher.cpp */; };
A795840D13F13CD900F201D5 /* countgroupscommand.cpp in Sources */ = {isa = PBXBuildFile; fileRef = A795840C13F13CD900F201D5 /* countgroupscommand.cpp */; };
A799F5B91309A3E000AEEFA0 /* makefastqcommand.cpp in Sources */ = {isa = PBXBuildFile; fileRef = A799F5B81309A3E000AEEFA0 /* makefastqcommand.cpp */; };
+ A7A0671A1562946F0095C8C5 /* listotulabelscommand.cpp in Sources */ = {isa = PBXBuildFile; fileRef = A7A067191562946F0095C8C5 /* listotulabelscommand.cpp */; };
+ A7A0671F1562AC3E0095C8C5 /* makecontigscommand.cpp in Sources */ = {isa = PBXBuildFile; fileRef = A7A0671E1562AC3E0095C8C5 /* makecontigscommand.cpp */; };
A7A32DAA14DC43B00001D2E5 /* sortseqscommand.cpp in Sources */ = {isa = PBXBuildFile; fileRef = A7A32DA914DC43B00001D2E5 /* sortseqscommand.cpp */; };
A7A3C8C914D041AD00B1BFBE /* otuassociationcommand.cpp in Sources */ = {isa = PBXBuildFile; fileRef = A7A3C8C714D041AD00B1BFBE /* otuassociationcommand.cpp */; };
A7A61F2D130062E000E05B6B /* amovacommand.cpp in Sources */ = {isa = PBXBuildFile; fileRef = A7A61F2C130062E000E05B6B /* amovacommand.cpp */; };
A795840C13F13CD900F201D5 /* countgroupscommand.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; path = countgroupscommand.cpp; sourceTree = "<group>"; };
A799F5B71309A3E000AEEFA0 /* makefastqcommand.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; path = makefastqcommand.h; sourceTree = "<group>"; };
A799F5B81309A3E000AEEFA0 /* makefastqcommand.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; path = makefastqcommand.cpp; sourceTree = "<group>"; };
+ A7A067191562946F0095C8C5 /* listotulabelscommand.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; path = listotulabelscommand.cpp; sourceTree = "<group>"; };
+ A7A0671C156294810095C8C5 /* listotulabelscommand.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; path = listotulabelscommand.h; sourceTree = "<group>"; };
+ A7A0671D1562AC230095C8C5 /* makecontigscommand.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; path = makecontigscommand.h; sourceTree = "<group>"; };
+ A7A0671E1562AC3E0095C8C5 /* makecontigscommand.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; path = makecontigscommand.cpp; sourceTree = "<group>"; };
A7A32DA914DC43B00001D2E5 /* sortseqscommand.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; path = sortseqscommand.cpp; sourceTree = "<group>"; };
A7A32DAC14DC43D10001D2E5 /* sortseqscommand.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; path = sortseqscommand.h; sourceTree = "<group>"; };
A7A3C8C714D041AD00B1BFBE /* otuassociationcommand.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; path = otuassociationcommand.cpp; sourceTree = "<group>"; };
A7E9B73B12D37EC400DA6239 /* libshuffcommand.cpp */,
A7E9B73E12D37EC400DA6239 /* listseqscommand.h */,
A7E9B73D12D37EC400DA6239 /* listseqscommand.cpp */,
+ A7A0671C156294810095C8C5 /* listotulabelscommand.h */,
+ A7A067191562946F0095C8C5 /* listotulabelscommand.cpp */,
A7FA10001302E096003860FE /* mantelcommand.h */,
A7FA10011302E096003860FE /* mantelcommand.cpp */,
A724D2B4153C8600000A826F /* makebiomcommand.h */,
A724D2B6153C8628000A826F /* makebiomcommand.cpp */,
+ A7A0671D1562AC230095C8C5 /* makecontigscommand.h */,
+ A7A0671E1562AC3E0095C8C5 /* makecontigscommand.cpp */,
A799F5B71309A3E000AEEFA0 /* makefastqcommand.h */,
A799F5B81309A3E000AEEFA0 /* makefastqcommand.cpp */,
A7E9B74412D37EC400DA6239 /* makegroupcommand.h */,
A724D2B7153C8628000A826F /* makebiomcommand.cpp in Sources */,
219C1DE01552C4BD004209F9 /* newcommandtemplate.cpp in Sources */,
219C1DE41559BCCF004209F9 /* getcoremicrobiomecommand.cpp in Sources */,
+ A7A0671A1562946F0095C8C5 /* listotulabelscommand.cpp in Sources */,
+ A7A0671F1562AC3E0095C8C5 /* makecontigscommand.cpp in Sources */,
);
runOnlyForDeploymentPostprocessing = 0;
};
<BuildableReference
BuildableIdentifier = "primary"
BlueprintIdentifier = "8DD76FA90486AB0100D96B5E"
- BuildableName = "Mothur"
+ BuildableName = "mothur"
BlueprintName = "Mothur"
ReferencedContainer = "container:Mothur.xcodeproj">
</BuildableReference>
<BuildableReference
BuildableIdentifier = "primary"
BlueprintIdentifier = "8DD76FA90486AB0100D96B5E"
- BuildableName = "Mothur"
+ BuildableName = "mothur"
BlueprintName = "Mothur"
ReferencedContainer = "container:Mothur.xcodeproj">
</BuildableReference>
<BuildableReference
BuildableIdentifier = "primary"
BlueprintIdentifier = "8DD76FA90486AB0100D96B5E"
- BuildableName = "Mothur"
+ BuildableName = "mothur"
BlueprintName = "Mothur"
ReferencedContainer = "container:Mothur.xcodeproj">
</BuildableReference>
<BuildableReference
BuildableIdentifier = "primary"
BlueprintIdentifier = "8DD76FA90486AB0100D96B5E"
- BuildableName = "Mothur"
+ BuildableName = "mothur"
BlueprintName = "Mothur"
ReferencedContainer = "container:Mothur.xcodeproj">
</BuildableReference>
/**************************************************************************************************/
-Alignment::Alignment() { /* do nothing */ }
+Alignment::Alignment() { m = MothurOut::getInstance(); /* do nothing */ }
/**************************************************************************************************/
}
}
+
+ //phylotree adds an extra unknown so we want to remove that
+ if (bestChild.name == "unknown") { bestChildSize--; }
//is this taxonomy above cutoff
int consensusConfidence = ceil((bestChildSize / (float) size) * 100);
cutoff = c;
aboveCutoff = cutoff + 10000.0;
m = MothurOut::getInstance();
+ if(method == "furthest") { tag = "fn"; }
+ else if (method == "average") { tag = "an"; }
+ else if (method == "weighted") { tag = "wn"; }
+ else if (method == "nearest") { tag = "nn"; }
}
catch(exception& e) {
m->errorOut(e, "ClusterClassic", "ClusterClassic");
-#ifndef CLUSTER_H
-#define CLUSTER_H
+#ifndef CLUSTERCLASSIC_H
+#define CLUSTERCLASSIC_H
-#include "mothur.h"
#include "mothurout.h"
#include "listvector.hpp"
#include "rabundvector.hpp"
int getNSeqs() { return nseqs; }
ListVector* getListVector() { return list; }
RAbundVector* getRAbundVector() { return rabund; }
- string getTag();
+ string getTag() { return tag; }
void setMapWanted(bool m);
map<string, int> getSeqtoBin() { return seq2Bin; }
bool mapWanted, sim;
double cutoff, aboveCutoff;
map<string, int> seq2Bin;
- string method;
+ string method, tag;
MothurOut* m;
};
#include "clustersplitcommand.h"
-
//**********************************************************************************************************************
vector<string> ClusterSplitCommand::setParameters(){
try {
CommandParameter pprecision("precision", "Number", "", "100", "", "", "",false,false); parameters.push_back(pprecision);
CommandParameter pmethod("method", "Multiple", "furthest-nearest-average-weighted", "average", "", "", "",false,false); parameters.push_back(pmethod);
CommandParameter phard("hard", "Boolean", "", "T", "", "", "",false,false); parameters.push_back(phard);
+ CommandParameter pclassic("classic", "Boolean", "", "F", "", "", "",false,false); parameters.push_back(pclassic);
CommandParameter pinputdir("inputdir", "String", "", "", "", "", "",false,false); parameters.push_back(pinputdir);
CommandParameter poutputdir("outputdir", "String", "", "", "", "", "",false,false); parameters.push_back(poutputdir);
helpString += "The taxonomy parameter allows you to enter the taxonomy file for your sequences, this is only valid if you are using splitmethod=classify. Be sure your taxonomy file does not include the probability scores. \n";
helpString += "The taxlevel parameter allows you to specify the taxonomy level you want to use to split the distance file, default=3, meaning use the first taxon in each list. \n";
helpString += "The large parameter allows you to indicate that your distance matrix is too large to fit in RAM. The default value is false.\n";
+ helpString += "The classic parameter allows you to indicate that you want to run your files with cluster.classic. It is only valid with splitmethod=fasta. Default=f.\n";
#ifdef USE_MPI
helpString += "When using MPI, the processors parameter is set to the number of MPI processes running. \n";
#endif
temp = validParameter.validFile(parameters, "large", false); if (temp == "not found") { temp = "F"; }
large = m->isTrue(temp);
-
+
temp = validParameter.validFile(parameters, "processors", false); if (temp == "not found"){ temp = m->getProcessors(); }
m->setProcessors(temp);
m->mothurConvert(temp, processors);
else { splitmethod = temp; }
}
+ temp = validParameter.validFile(parameters, "classic", false); if (temp == "not found") { temp = "F"; }
+ classic = m->isTrue(temp);
+
+ if ((splitmethod != "fasta") && classic) { m->mothurOut("splitmethod must be fasta to use cluster.classic.\n"); abort=true; }
+
temp = validParameter.validFile(parameters, "cutoff", false); if (temp == "not found") { temp = "0.25"; }
m->mothurConvert(temp, cutoff);
cutoff += (5 / (precision * 10.0));
SplitMatrix* split;
if (splitmethod == "distance") { split = new SplitMatrix(distfile, namefile, taxFile, cutoff, splitmethod, large); }
else if (splitmethod == "classify") { split = new SplitMatrix(distfile, namefile, taxFile, taxLevelCutoff, splitmethod, large); }
- else if (splitmethod == "fasta") { split = new SplitMatrix(fastafile, namefile, taxFile, taxLevelCutoff, cutoff, splitmethod, processors, outputDir); }
+ else if (splitmethod == "fasta") { split = new SplitMatrix(fastafile, namefile, taxFile, taxLevelCutoff, cutoff, splitmethod, processors, classic, outputDir); }
else { m->mothurOut("Not a valid splitting method. Valid splitting algorithms are distance, classify or fasta."); m->mothurOutEndLine(); return 0; }
split->split();
//cluster each distance file
for (int i = 0; i < distNames.size(); i++) {
- Cluster* cluster = NULL;
- SparseMatrix* matrix = NULL;
- ListVector* list = NULL;
- ListVector oldList;
- RAbundVector* rabund = NULL;
-
- if (m->control_pressed) { return listFileNames; }
-
string thisNamefile = distNames[i].begin()->second;
string thisDistFile = distNames[i].begin()->first;
-
- #ifdef USE_MPI
- int pid;
- MPI_Comm_rank(MPI_COMM_WORLD, &pid); //find out who we are
-
- //output your files too
- if (pid != 0) {
- cout << endl << "Reading " << thisDistFile << endl;
- }
- #endif
-
- m->mothurOutEndLine(); m->mothurOut("Reading " + thisDistFile); m->mothurOutEndLine();
-
- ReadMatrix* read = new ReadColumnMatrix(thisDistFile);
- read->setCutoff(cutoff);
-
- NameAssignment* nameMap = new NameAssignment(thisNamefile);
- nameMap->readMap();
- read->read(nameMap);
-
- if (m->control_pressed) { delete read; delete nameMap; return listFileNames; }
-
- list = read->getListVector();
- oldList = *list;
- matrix = read->getMatrix();
-
- delete read; read = NULL;
- delete nameMap; nameMap = NULL;
-
-
- #ifdef USE_MPI
- //output your files too
- if (pid != 0) {
- cout << endl << "Clustering " << thisDistFile << endl;
- }
- #endif
- m->mothurOutEndLine(); m->mothurOut("Clustering " + thisDistFile); m->mothurOutEndLine();
-
- rabund = new RAbundVector(list->getRAbundVector());
-
- //create cluster
- if (method == "furthest") { cluster = new CompleteLinkage(rabund, list, matrix, cutoff, method); }
- else if(method == "nearest"){ cluster = new SingleLinkage(rabund, list, matrix, cutoff, method); }
- else if(method == "average"){ cluster = new AverageLinkage(rabund, list, matrix, cutoff, method); }
- tag = cluster->getTag();
-
- if (outputDir == "") { outputDir += m->hasPath(thisDistFile); }
- fileroot = outputDir + m->getRootName(m->getSimpleName(thisDistFile));
-
- ofstream listFile;
- m->openOutputFile(fileroot+ tag + ".list", listFile);
-
- listFileNames.push_back(fileroot+ tag + ".list");
-
- float previousDist = 0.00000;
- float rndPreviousDist = 0.00000;
-
- oldList = *list;
-
- print_start = true;
- start = time(NULL);
- double saveCutoff = cutoff;
-
- while (matrix->getSmallDist() < cutoff && matrix->getNNodes() > 0){
-
- if (m->control_pressed) { //clean up
- delete matrix; delete list; delete cluster; delete rabund;
- listFile.close();
- for (int i = 0; i < listFileNames.size(); i++) { m->mothurRemove(listFileNames[i]); }
- listFileNames.clear(); return listFileNames;
- }
-
- cluster->update(saveCutoff);
-
- float dist = matrix->getSmallDist();
- float rndDist;
- if (hard) {
- rndDist = m->ceilDist(dist, precision);
- }else{
- rndDist = m->roundDist(dist, precision);
- }
-
- if(previousDist <= 0.0000 && dist != previousDist){
- oldList.setLabel("unique");
- oldList.print(listFile);
- if (labels.count("unique") == 0) { labels.insert("unique"); }
- }
- else if(rndDist != rndPreviousDist){
- oldList.setLabel(toString(rndPreviousDist, length-1));
- oldList.print(listFile);
- if (labels.count(toString(rndPreviousDist, length-1)) == 0) { labels.insert(toString(rndPreviousDist, length-1)); }
- }
-
- previousDist = dist;
- rndPreviousDist = rndDist;
- oldList = *list;
- }
+ string listFileName = "";
+ if (classic) { listFileName = clusterClassicFile(thisDistFile, thisNamefile, labels, smallestCutoff); }
+ else { listFileName = clusterFile(thisDistFile, thisNamefile, labels, smallestCutoff); }
-
- if(previousDist <= 0.0000){
- oldList.setLabel("unique");
- oldList.print(listFile);
- if (labels.count("unique") == 0) { labels.insert("unique"); }
- }
- else if(rndPreviousDist<cutoff){
- oldList.setLabel(toString(rndPreviousDist, length-1));
- oldList.print(listFile);
- if (labels.count(toString(rndPreviousDist, length-1)) == 0) { labels.insert(toString(rndPreviousDist, length-1)); }
- }
-
- delete matrix; delete list; delete cluster; delete rabund;
- matrix = NULL; list = NULL; cluster = NULL; rabund = NULL;
- listFile.close();
-
if (m->control_pressed) { //clean up
for (int i = 0; i < listFileNames.size(); i++) { m->mothurRemove(listFileNames[i]); }
listFileNames.clear(); return listFileNames;
}
-
- m->mothurRemove(thisDistFile);
- m->mothurRemove(thisNamefile);
-
- if (saveCutoff != cutoff) {
- if (hard) { saveCutoff = m->ceilDist(saveCutoff, precision); }
- else { saveCutoff = m->roundDist(saveCutoff, precision); }
-
- m->mothurOut("Cutoff was " + toString(cutoff) + " changed cutoff to " + toString(saveCutoff)); m->mothurOutEndLine();
- }
-
- if (saveCutoff < smallestCutoff) { smallestCutoff = saveCutoff; }
- }
+
+ listFileNames.push_back(listFileName);
+ }
cutoff = smallestCutoff;
}
//**********************************************************************************************************************
+string ClusterSplitCommand::clusterClassicFile(string thisDistFile, string thisNamefile, set<string>& labels, double& smallestCutoff){
+ try {
+ string listFileName = "";
+
+ ListVector* list = NULL;
+ ListVector oldList;
+ RAbundVector* rabund = NULL;
+
+#ifdef USE_MPI
+ int pid;
+ MPI_Comm_rank(MPI_COMM_WORLD, &pid); //find out who we are
+
+ //output your files too
+ if (pid != 0) {
+ cout << endl << "Reading " << thisDistFile << endl;
+ }
+#endif
+
+ m->mothurOutEndLine(); m->mothurOut("Reading " + thisDistFile); m->mothurOutEndLine();
+
+ NameAssignment* nameMap = new NameAssignment(thisNamefile);
+ nameMap->readMap();
+
+ //reads phylip file storing data in 2D vector, also fills list and rabund
+ bool sim = false;
+ ClusterClassic* cluster = new ClusterClassic(cutoff, method, sim);
+ cluster->readPhylipFile(thisDistFile, nameMap);
+ tag = cluster->getTag();
+
+ if (m->control_pressed) { delete cluster; return 0; }
+
+ list = cluster->getListVector();
+ rabund = cluster->getRAbundVector();
+
+ if (outputDir == "") { outputDir += m->hasPath(thisDistFile); }
+ fileroot = outputDir + m->getRootName(m->getSimpleName(thisDistFile));
+ listFileName = fileroot+ tag + ".list";
+
+ ofstream listFile;
+ m->openOutputFile(fileroot+ tag + ".list", listFile);
+
+ float previousDist = 0.00000;
+ float rndPreviousDist = 0.00000;
+ oldList = *list;
+
+#ifdef USE_MPI
+ //output your files too
+ if (pid != 0) {
+ cout << endl << "Clustering " << thisDistFile << endl;
+ }
+#endif
+
+ m->mothurOutEndLine(); m->mothurOut("Clustering " + thisDistFile); m->mothurOutEndLine();
+
+ while ((cluster->getSmallDist() < cutoff) && (cluster->getNSeqs() > 1)){
+ if (m->control_pressed) { delete cluster; delete list; delete rabund; listFile.close(); return listFileName; }
+
+ cluster->update(cutoff);
+
+ float dist = cluster->getSmallDist();
+ float rndDist;
+ if (hard) {
+ rndDist = m->ceilDist(dist, precision);
+ }else{
+ rndDist = m->roundDist(dist, precision);
+ }
+
+ if(previousDist <= 0.0000 && dist != previousDist){
+ oldList.setLabel("unique");
+ oldList.print(listFile);
+ if (labels.count("unique") == 0) { labels.insert("unique"); }
+ }
+ else if(rndDist != rndPreviousDist){
+ oldList.setLabel(toString(rndPreviousDist, length-1));
+ oldList.print(listFile);
+ if (labels.count(toString(rndPreviousDist, length-1)) == 0) { labels.insert(toString(rndPreviousDist, length-1)); }
+ }
+
+
+ previousDist = dist;
+ rndPreviousDist = rndDist;
+ oldList = *list;
+ }
+
+ if(previousDist <= 0.0000){
+ oldList.setLabel("unique");
+ oldList.print(listFile);
+ if (labels.count("unique") == 0) { labels.insert("unique"); }
+ }
+ else if(rndPreviousDist<cutoff){
+ oldList.setLabel(toString(rndPreviousDist, length-1));
+ oldList.print(listFile);
+ if (labels.count(toString(rndPreviousDist, length-1)) == 0) { labels.insert(toString(rndPreviousDist, length-1)); }
+ }
+
+
+ listFile.close();
+
+ delete cluster; delete nameMap; delete list; delete rabund;
+
+
+ return listFileName;
+
+ }
+ catch(exception& e) {
+ m->errorOut(e, "ClusterSplitCommand", "clusterClassicFile");
+ exit(1);
+ }
+}
+
+//**********************************************************************************************************************
+string ClusterSplitCommand::clusterFile(string thisDistFile, string thisNamefile, set<string>& labels, double& smallestCutoff){
+ try {
+ string listFileName = "";
+
+ Cluster* cluster = NULL;
+ SparseMatrix* matrix = NULL;
+ ListVector* list = NULL;
+ ListVector oldList;
+ RAbundVector* rabund = NULL;
+
+ if (m->control_pressed) { return listFileName; }
+
+#ifdef USE_MPI
+ int pid;
+ MPI_Comm_rank(MPI_COMM_WORLD, &pid); //find out who we are
+
+ //output your files too
+ if (pid != 0) {
+ cout << endl << "Reading " << thisDistFile << endl;
+ }
+#endif
+
+ m->mothurOutEndLine(); m->mothurOut("Reading " + thisDistFile); m->mothurOutEndLine();
+
+ ReadMatrix* read = new ReadColumnMatrix(thisDistFile);
+ read->setCutoff(cutoff);
+
+ NameAssignment* nameMap = new NameAssignment(thisNamefile);
+ nameMap->readMap();
+ read->read(nameMap);
+
+ if (m->control_pressed) { delete read; delete nameMap; return listFileName; }
+
+ list = read->getListVector();
+ oldList = *list;
+ matrix = read->getMatrix();
+
+ delete read; read = NULL;
+ delete nameMap; nameMap = NULL;
+
+
+#ifdef USE_MPI
+ //output your files too
+ if (pid != 0) {
+ cout << endl << "Clustering " << thisDistFile << endl;
+ }
+#endif
+
+ m->mothurOutEndLine(); m->mothurOut("Clustering " + thisDistFile); m->mothurOutEndLine();
+
+ rabund = new RAbundVector(list->getRAbundVector());
+
+ //create cluster
+ if (method == "furthest") { cluster = new CompleteLinkage(rabund, list, matrix, cutoff, method); }
+ else if(method == "nearest"){ cluster = new SingleLinkage(rabund, list, matrix, cutoff, method); }
+ else if(method == "average"){ cluster = new AverageLinkage(rabund, list, matrix, cutoff, method); }
+ tag = cluster->getTag();
+
+ if (outputDir == "") { outputDir += m->hasPath(thisDistFile); }
+ fileroot = outputDir + m->getRootName(m->getSimpleName(thisDistFile));
+
+ ofstream listFile;
+ m->openOutputFile(fileroot+ tag + ".list", listFile);
+
+ listFileName = fileroot+ tag + ".list";
+
+ float previousDist = 0.00000;
+ float rndPreviousDist = 0.00000;
+
+ oldList = *list;
+
+ print_start = true;
+ start = time(NULL);
+ double saveCutoff = cutoff;
+
+ while (matrix->getSmallDist() < cutoff && matrix->getNNodes() > 0){
+
+ if (m->control_pressed) { //clean up
+ delete matrix; delete list; delete cluster; delete rabund;
+ listFile.close();
+ m->mothurRemove(listFileName);
+ return listFileName;
+ }
+
+ cluster->update(saveCutoff);
+
+ float dist = matrix->getSmallDist();
+ float rndDist;
+ if (hard) {
+ rndDist = m->ceilDist(dist, precision);
+ }else{
+ rndDist = m->roundDist(dist, precision);
+ }
+
+ if(previousDist <= 0.0000 && dist != previousDist){
+ oldList.setLabel("unique");
+ oldList.print(listFile);
+ if (labels.count("unique") == 0) { labels.insert("unique"); }
+ }
+ else if(rndDist != rndPreviousDist){
+ oldList.setLabel(toString(rndPreviousDist, length-1));
+ oldList.print(listFile);
+ if (labels.count(toString(rndPreviousDist, length-1)) == 0) { labels.insert(toString(rndPreviousDist, length-1)); }
+ }
+
+ previousDist = dist;
+ rndPreviousDist = rndDist;
+ oldList = *list;
+ }
+
+
+ if(previousDist <= 0.0000){
+ oldList.setLabel("unique");
+ oldList.print(listFile);
+ if (labels.count("unique") == 0) { labels.insert("unique"); }
+ }
+ else if(rndPreviousDist<cutoff){
+ oldList.setLabel(toString(rndPreviousDist, length-1));
+ oldList.print(listFile);
+ if (labels.count(toString(rndPreviousDist, length-1)) == 0) { labels.insert(toString(rndPreviousDist, length-1)); }
+ }
+
+ delete matrix; delete list; delete cluster; delete rabund;
+ matrix = NULL; list = NULL; cluster = NULL; rabund = NULL;
+ listFile.close();
+
+ if (m->control_pressed) { //clean up
+ m->mothurRemove(listFileName);
+ return listFileName;
+ }
+
+ m->mothurRemove(thisDistFile);
+ m->mothurRemove(thisNamefile);
+
+ if (saveCutoff != cutoff) {
+ if (hard) { saveCutoff = m->ceilDist(saveCutoff, precision); }
+ else { saveCutoff = m->roundDist(saveCutoff, precision); }
+
+ m->mothurOut("Cutoff was " + toString(cutoff) + " changed cutoff to " + toString(saveCutoff)); m->mothurOutEndLine();
+ }
+
+ if (saveCutoff < smallestCutoff) { smallestCutoff = saveCutoff; }
+
+ return listFileName;
+
+ }
+ catch(exception& e) {
+ m->errorOut(e, "ClusterSplitCommand", "clusterFile");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
int ClusterSplitCommand::createMergedDistanceFile(vector< map<string, string> > distNames) {
try{
#include "readmatrix.hpp"
#include "inputdata.h"
#include "clustercommand.h"
+#include "clusterclassic.h"
class ClusterSplitCommand : public Command {
string method, fileroot, tag, outputDir, phylipfile, columnfile, namefile, distfile, format, showabund, timing, splitmethod, taxFile, fastafile;
double cutoff, splitcutoff;
int precision, length, processors, taxLevelCutoff;
- bool print_start, abort, hard, large;
+ bool print_start, abort, hard, large, classic;
time_t start;
ofstream outList, outRabund, outSabund;
void printData(ListVector*);
vector<string> createProcesses(vector< map<string, string> >, set<string>&);
vector<string> cluster(vector< map<string, string> >, set<string>&);
+ string clusterFile(string, string, set<string>&, double&);
+ string clusterClassicFile(string, string, set<string>&, double&);
int mergeLists(vector<string>, map<float, int>, ListVector*);
map<float, int> completeListFile(vector<string>, string, set<string>&, ListVector*&);
int createMergedDistanceFile(vector< map<string, string> >);
#include "createdatabasecommand.h"
#include "makebiomcommand.h"
#include "getcoremicrobiomecommand.h"
+#include "listotulabelscommand.h"
/*******************************************************/
commands["pcr.seqs"] = "pcr.seqs";
commands["create.database"] = "create.database";
commands["make.biom"] = "make.biom";
- commands["get.coremicrobiome"] = "get.coremicrobiome";
+ commands["get.coremicrobiome"] = "get.coremicrobiome";
+ commands["list.otulabels"] = "list.otulabels";
commands["quit"] = "MPIEnabled";
}
else if(commandName == "create.database") { command = new CreateDatabaseCommand(optionString); }
else if(commandName == "make.biom") { command = new MakeBiomCommand(optionString); }
else if(commandName == "get.coremicrobiome") { command = new GetCoreMicroBiomeCommand(optionString); }
+ else if(commandName == "list.otulabels") { command = new ListOtuLabelsCommand(optionString); }
else { command = new NoCommand(optionString); }
return command;
else if(commandName == "create.database") { pipecommand = new CreateDatabaseCommand(optionString); }
else if(commandName == "make.biom") { pipecommand = new MakeBiomCommand(optionString); }
else if(commandName == "get.coremicrobiome") { pipecommand = new GetCoreMicroBiomeCommand(optionString); }
+ else if(commandName == "list.otulabels") { pipecommand = new ListOtuLabelsCommand(optionString); }
else { pipecommand = new NoCommand(optionString); }
return pipecommand;
else if(commandName == "create.database") { shellcommand = new CreateDatabaseCommand(); }
else if(commandName == "make.biom") { shellcommand = new MakeBiomCommand(); }
else if(commandName == "get.coremicrobiome") { shellcommand = new GetCoreMicroBiomeCommand(); }
+ else if(commandName == "list.otulabels") { shellcommand = new ListOtuLabelsCommand(); }
else { shellcommand = new NoCommand(); }
return shellcommand;
--- /dev/null
+//
+// listotucommand.cpp
+// Mothur
+//
+// Created by Sarah Westcott on 5/15/12.
+// Copyright (c) 2012 Schloss Lab. All rights reserved.
+//
+
+#include "listotulabelscommand.h"
+#include "inputdata.h"
+
+//**********************************************************************************************************************
+vector<string> ListOtuLabelsCommand::setParameters(){
+ try {
+ CommandParameter pshared("shared", "InputTypes", "", "", "SharedRel", "SharedRel", "none",false,false); parameters.push_back(pshared);
+ CommandParameter prelabund("relabund", "InputTypes", "", "", "SharedRel", "SharedRel", "none",false,false); parameters.push_back(prelabund);
+ CommandParameter pgroups("groups", "String", "", "", "", "", "",false,false); parameters.push_back(pgroups);
+ CommandParameter plabel("label", "String", "", "", "", "", "",false,false); parameters.push_back(plabel);
+ //every command must have inputdir and outputdir. This allows mothur users to redirect input and output files.
+ CommandParameter pinputdir("inputdir", "String", "", "", "", "", "",false,false); parameters.push_back(pinputdir);
+ CommandParameter poutputdir("outputdir", "String", "", "", "", "", "",false,false); parameters.push_back(poutputdir);
+
+ vector<string> myArray;
+ for (int i = 0; i < parameters.size(); i++) { myArray.push_back(parameters[i].name); }
+ return myArray;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "ListOtuLabelsCommand", "setParameters");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+string ListOtuLabelsCommand::getHelpString(){
+ try {
+ string helpString = "";
+ helpString += "The list.labels lists otu labels from shared or relabund file. The results can be used by the get.labels to select specific otus with the output from classify.otu, otu.association, or corr.axes.\n";
+ helpString += "The list.labels parameters are: shared, relabund, label and groups.\n";
+ helpString += "The label parameter is used to analyze specific labels in your input.\n";
+ helpString += "The groups parameter allows you to specify which of the groups you would like analyzed.\n";
+ helpString += "The list.labels commmand should be in the following format: \n";
+ helpString += "list.otulabels(shared=yourSharedFile, groups=yourGroup1-yourGroup2)\n";
+ return helpString;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "ListOtuLabelsCommand", "getHelpString");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+ListOtuLabelsCommand::ListOtuLabelsCommand(){
+ try {
+ abort = true; calledHelp = true;
+ setParameters();
+ vector<string> tempOutNames;
+ outputTypes["otulabels"] = tempOutNames;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "ListOtuLabelsCommand", "ListOtuLabelsCommand");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+ListOtuLabelsCommand::ListOtuLabelsCommand(string option) {
+ try {
+ abort = false; calledHelp = false;
+ allLines = 1;
+
+ //allow user to run help
+ if(option == "help") { help(); abort = true; calledHelp = true; }
+ else if(option == "citation") { citation(); abort = true; calledHelp = true;}
+
+ else {
+ //valid paramters for this command
+ vector<string> myArray = setParameters();
+
+ OptionParser parser(option);
+ map<string,string> parameters = parser.getParameters();
+
+ ValidParameters validParameter;
+ map<string,string>::iterator it;
+ //check to make sure all parameters are valid for command
+ for (it = parameters.begin(); it != parameters.end(); it++) {
+ if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; }
+ }
+
+
+ //if the user changes the input directory command factory will send this info to us in the output parameter
+ string inputDir = validParameter.validFile(parameters, "inputdir", false);
+ if (inputDir == "not found"){ inputDir = ""; }
+ else {
+
+ //edit file types below to include only the types you added as parameters
+
+ string path;
+ it = parameters.find("relabund");
+ //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["relabund"] = inputDir + it->second; }
+ }
+
+ it = parameters.find("shared");
+ //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["shared"] = inputDir + it->second; }
+ }
+ }
+
+ vector<string> tempOutNames;
+ outputTypes["otulabels"] = tempOutNames;
+
+ //check for parameters
+ sharedfile = validParameter.validFile(parameters, "shared", true);
+ if (sharedfile == "not open") { abort = true; }
+ else if (sharedfile == "not found") { sharedfile = ""; }
+ else { inputFileName = sharedfile; format = "sharedfile"; m->setSharedFile(sharedfile); }
+
+ relabundfile = validParameter.validFile(parameters, "relabund", true);
+ if (relabundfile == "not open") { abort = true; }
+ else if (relabundfile == "not found") { relabundfile = ""; }
+ else { inputFileName = relabundfile; format = "relabund"; m->setRelAbundFile(relabundfile); }
+
+ if ((relabundfile == "") && (sharedfile == "")) {
+ //is there are current file available for either of these?
+ //give priority to shared, then relabund
+ sharedfile = m->getSharedFile();
+ if (sharedfile != "") { inputFileName = sharedfile; format="sharedfile"; m->mothurOut("Using " + sharedfile + " as input file for the shared parameter."); m->mothurOutEndLine(); }
+ else {
+ relabundfile = m->getRelAbundFile();
+ if (relabundfile != "") { inputFileName = relabundfile; format="relabund"; m->mothurOut("Using " + relabundfile + " as input file for the relabund parameter."); m->mothurOutEndLine(); }
+ else {
+ m->mothurOut("No valid current files. You must provide a shared or relabund."); 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"){
+ outputDir = m->hasPath(inputFileName); //if user entered a file with a path then preserve it
+ }
+
+ string groups = validParameter.validFile(parameters, "groups", false);
+ if (groups == "not found") { groups = ""; }
+ else { m->splitAtDash(groups, Groups); }
+ m->setGroups(Groups);
+
+ string label = validParameter.validFile(parameters, "label", false);
+ if (label == "not found") { label = ""; }
+ else {
+ if(label != "all") { m->splitAtDash(label, labels); allLines = 0; }
+ else { allLines = 1; }
+ }
+ }
+
+ }
+ catch(exception& e) {
+ m->errorOut(e, "ListOtuLabelsCommand", "ListOtuLabelsCommand");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+
+int ListOtuLabelsCommand::execute(){
+ try {
+
+ if (abort == true) { if (calledHelp) { return 0; } return 2; }
+
+ InputData input(inputFileName, format);
+
+ if (format == "relabund") {
+ vector<SharedRAbundFloatVector*> lookup = input.getSharedRAbundFloatVectors();
+ string lastLabel = lookup[0]->getLabel();
+
+ //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;
+
+ //as long as you are not at the end of the file or done wih the lines you want
+ while((lookup[0] != NULL) && ((allLines == 1) || (userLabels.size() != 0))) {
+
+ if (m->control_pressed) { for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; } for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; }
+
+ if(allLines == 1 || labels.count(lookup[0]->getLabel()) == 1){
+
+ m->mothurOut(lookup[0]->getLabel()); m->mothurOutEndLine();
+
+ createList(lookup);
+
+ processedLabels.insert(lookup[0]->getLabel());
+ userLabels.erase(lookup[0]->getLabel());
+ }
+
+ if ((m->anyLabelsToProcess(lookup[0]->getLabel(), userLabels, "") == true) && (processedLabels.count(lastLabel) != 1)) {
+ string saveLabel = lookup[0]->getLabel();
+
+ for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; }
+ lookup = input.getSharedRAbundFloatVectors(lastLabel);
+ m->mothurOut(lookup[0]->getLabel()); m->mothurOutEndLine();
+
+ createList(lookup);
+
+ processedLabels.insert(lookup[0]->getLabel());
+ userLabels.erase(lookup[0]->getLabel());
+
+ //restore real lastlabel to save below
+ lookup[0]->setLabel(saveLabel);
+ }
+
+ lastLabel = lookup[0]->getLabel();
+ //prevent memory leak
+ for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; lookup[i] = NULL; }
+
+ if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; }
+
+ //get next line to process
+ lookup = input.getSharedRAbundFloatVectors();
+ }
+
+ if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; }
+
+ //output error messages about any remaining user labels
+ set<string>::iterator it;
+ bool needToRun = false;
+ for (it = userLabels.begin(); it != userLabels.end(); it++) {
+ m->mothurOut("Your file does not include the label " + *it);
+ if (processedLabels.count(lastLabel) != 1) {
+ m->mothurOut(". I will use " + lastLabel + "."); m->mothurOutEndLine();
+ needToRun = true;
+ }else {
+ m->mothurOut(". Please refer to " + lastLabel + "."); m->mothurOutEndLine();
+ }
+ }
+
+ //run last label if you need to
+ if (needToRun == true) {
+ for (int i = 0; i < lookup.size(); i++) { if (lookup[i] != NULL) { delete lookup[i]; } }
+ lookup = input.getSharedRAbundFloatVectors(lastLabel);
+
+ m->mothurOut(lookup[0]->getLabel()); m->mothurOutEndLine();
+
+ createList(lookup);
+
+ for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; }
+ }
+ }else {
+
+ vector<SharedRAbundVector*> lookup = input.getSharedRAbundVectors();
+ string lastLabel = lookup[0]->getLabel();
+
+ //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;
+
+ //as long as you are not at the end of the file or done wih the lines you want
+ while((lookup[0] != NULL) && ((allLines == 1) || (userLabels.size() != 0))) {
+
+ if (m->control_pressed) { for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; } for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; }
+
+ if(allLines == 1 || labels.count(lookup[0]->getLabel()) == 1){
+
+ m->mothurOut(lookup[0]->getLabel()); m->mothurOutEndLine();
+
+ createList(lookup);
+
+ processedLabels.insert(lookup[0]->getLabel());
+ userLabels.erase(lookup[0]->getLabel());
+ }
+
+ if ((m->anyLabelsToProcess(lookup[0]->getLabel(), userLabels, "") == true) && (processedLabels.count(lastLabel) != 1)) {
+ string saveLabel = lookup[0]->getLabel();
+
+ for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; }
+ lookup = input.getSharedRAbundVectors(lastLabel);
+ m->mothurOut(lookup[0]->getLabel()); m->mothurOutEndLine();
+
+ createList(lookup);
+
+ processedLabels.insert(lookup[0]->getLabel());
+ userLabels.erase(lookup[0]->getLabel());
+
+ //restore real lastlabel to save below
+ lookup[0]->setLabel(saveLabel);
+ }
+
+ lastLabel = lookup[0]->getLabel();
+ //prevent memory leak
+ for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; lookup[i] = NULL; }
+
+ if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; }
+
+ //get next line to process
+ lookup = input.getSharedRAbundVectors();
+ }
+
+ if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; }
+
+ //output error messages about any remaining user labels
+ set<string>::iterator it;
+ bool needToRun = false;
+ for (it = userLabels.begin(); it != userLabels.end(); it++) {
+ m->mothurOut("Your file does not include the label " + *it);
+ if (processedLabels.count(lastLabel) != 1) {
+ m->mothurOut(". I will use " + lastLabel + "."); m->mothurOutEndLine();
+ needToRun = true;
+ }else {
+ m->mothurOut(". Please refer to " + lastLabel + "."); m->mothurOutEndLine();
+ }
+ }
+
+ //run last label if you need to
+ if (needToRun == true) {
+ for (int i = 0; i < lookup.size(); i++) { if (lookup[i] != NULL) { delete lookup[i]; } }
+ lookup = input.getSharedRAbundVectors(lastLabel);
+
+ m->mothurOut(lookup[0]->getLabel()); m->mothurOutEndLine();
+
+ createList(lookup);
+
+ for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; }
+ }
+ }
+
+ if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; }
+
+ //output files created by command
+ m->mothurOutEndLine();
+ m->mothurOut("Output File Names: "); m->mothurOutEndLine();
+ for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); }
+ m->mothurOutEndLine();
+ return 0;
+
+ }
+ catch(exception& e) {
+ m->errorOut(e, "ListOtuLabelsCommand", "execute");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+
+int ListOtuLabelsCommand::createList(vector<SharedRAbundVector*>& lookup){
+ try {
+
+ string outputFileName = outputDir + m->getRootName(m->getSimpleName(inputFileName)) + lookup[0]->getLabel() + ".otu.labels";
+ outputNames.push_back(outputFileName); outputTypes["otulabels"].push_back(outputFileName);
+ ofstream out;
+ m->openOutputFile(outputFileName, out);
+
+ for (int i = 0; i < m->currentBinLabels.size(); i++) { out << m->currentBinLabels[i] << endl; }
+
+ out.close();
+
+ return 0;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "ListOtuLabelsCommand", "createTable");
+ exit(1);
+ }
+}
+
+//**********************************************************************************************************************
+
+int ListOtuLabelsCommand::createList(vector<SharedRAbundFloatVector*>& lookup){
+ try {
+
+ string outputFileName = outputDir + m->getRootName(m->getSimpleName(inputFileName)) + lookup[0]->getLabel() + ".otu.labels";
+ outputNames.push_back(outputFileName); outputTypes["accnos"].push_back(outputFileName);
+ ofstream out;
+ m->openOutputFile(outputFileName, out);
+
+ for (int i = 0; i < m->currentBinLabels.size(); i++) { out << m->currentBinLabels[i] << endl; }
+
+ out.close();
+
+ return 0;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "ListOtuLabelsCommand", "createTable");
+ exit(1);
+ }
+}
+
+//**********************************************************************************************************************
+
--- /dev/null
+#ifndef Mothur_listotucommand_h
+#define Mothur_listotucommand_h
+
+//
+// listotucommand.h
+// Mothur
+//
+// Created by Sarah Westcott on 5/15/12.
+// Copyright (c) 2012 Schloss Lab. All rights reserved.
+//
+
+
+#include "command.hpp"
+#include "sharedrabundvector.h"
+
+/**************************************************************************************************/
+
+class ListOtuLabelsCommand : public Command {
+public:
+ ListOtuLabelsCommand(string);
+ ListOtuLabelsCommand();
+ ~ListOtuLabelsCommand(){}
+
+ vector<string> setParameters();
+ string getCommandName() { return "list.otulabels"; }
+ string getCommandCategory() { return "OTU-Based Approaches"; }
+ //commmand category choices: Sequence Processing, OTU-Based Approaches, Hypothesis Testing, Phylotype Analysis, General, Clustering and Hidden
+ string getHelpString();
+ string getCitation() { return "http://www.mothur.org/wiki/List.otulabels"; }
+ string getDescription() { return "lists otu labels from shared or relabund file. Can be used with output from classify.otu, otu.association, or corr.axes to select specific otus."; }
+
+ int execute();
+ void help() { m->mothurOut(getHelpString()); }
+
+private:
+ bool abort, allLines;
+ string outputDir, sharedfile, relabundfile, label, inputFileName, format;
+ vector<string> outputNames;
+ vector<string> Groups;
+ set<string> labels;
+
+ int createList(vector<SharedRAbundFloatVector*>&);
+ int createList(vector<SharedRAbundVector*>&);
+
+};
+
+/**************************************************************************************************/
+
+
+
+
+
+
+#endif
--- /dev/null
+//
+// makecontigscommand.cpp
+// Mothur
+//
+// Created by Sarah Westcott on 5/15/12.
+// Copyright (c) 2012 Schloss Lab. All rights reserved.
+//
+
+#include "makecontigscommand.h"
+
+//**********************************************************************************************************************
+vector<string> MakeContigsCommand::setParameters(){
+ try {
+ CommandParameter pfasta("ffastq", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(pfasta);
+ CommandParameter prfasta("rfastq", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(prfasta);
+ CommandParameter palign("align", "Multiple", "needleman-gotoh-blast-noalign", "needleman", "", "", "",false,false); parameters.push_back(palign);
+ CommandParameter pmatch("match", "Number", "", "1.0", "", "", "",false,false); parameters.push_back(pmatch);
+ CommandParameter pmismatch("mismatch", "Number", "", "-1.0", "", "", "",false,false); parameters.push_back(pmismatch);
+ CommandParameter pgapopen("gapopen", "Number", "", "-2.0", "", "", "",false,false); parameters.push_back(pgapopen);
+ CommandParameter pgapextend("gapextend", "Number", "", "-1.0", "", "", "",false,false); parameters.push_back(pgapextend);
+ CommandParameter pprocessors("processors", "Number", "", "1", "", "", "",false,false); parameters.push_back(pprocessors);
+ CommandParameter pinputdir("inputdir", "String", "", "", "", "", "",false,false); parameters.push_back(pinputdir);
+ CommandParameter poutputdir("outputdir", "String", "", "", "", "", "",false,false); parameters.push_back(poutputdir);
+
+ vector<string> myArray;
+ for (int i = 0; i < parameters.size(); i++) { myArray.push_back(parameters[i].name); }
+ return myArray;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "MakeContigsCommand", "setParameters");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+string MakeContigsCommand::getHelpString(){
+ try {
+ string helpString = "";
+ helpString += "The make.contigs command reads a forward fastq file and a reverse fastq file and outputs new fasta and quality files.\n";
+ helpString += "The make.contigs command parameters are ffastq, rfastq, align, match, mismatch, gapopen, gapextend and processors.\n";
+ helpString += "The ffastq and rfastq parameter is required.\n";
+ helpString += "The align parameter allows you to specify the alignment method to use. Your options are: gotoh, needleman, blast and noalign. The default is needleman.\n";
+ helpString += "The match parameter allows you to specify the bonus for having the same base. The default is 1.0.\n";
+ helpString += "The mistmatch parameter allows you to specify the penalty for having different bases. The default is -1.0.\n";
+ helpString += "The gapopen parameter allows you to specify the penalty for opening a gap in an alignment. The default is -2.0.\n";
+ helpString += "The gapextend parameter allows you to specify the penalty for extending a gap in an alignment. The default is -1.0.\n";
+ helpString += "The processors parameter allows you to specify how many processors you would like to use. The default is 1. \n";
+ helpString += "The make.contigs command should be in the following format: \n";
+ helpString += "make.contigs(ffastq=yourForwardFastqFile, rfastq=yourReverseFastqFile, align=yourAlignmentMethod) \n";
+ helpString += "Note: No spaces between parameter labels (i.e. ffastq), '=' and parameters (i.e.yourForwardFastqFile).\n";
+ return helpString;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "MakeContigsCommand", "getHelpString");
+ exit(1);
+ }
+}
+
+//**********************************************************************************************************************
+MakeContigsCommand::MakeContigsCommand(){
+ try {
+ abort = true; calledHelp = true;
+ setParameters();
+ vector<string> tempOutNames;
+ outputTypes["fasta"] = tempOutNames;
+ outputTypes["qfile"] = tempOutNames;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "MakeContigsCommand", "MakeContigsCommand");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+MakeContigsCommand::MakeContigsCommand(string option) {
+ try {
+ abort = false; calledHelp = false;
+
+ //allow user to run help
+ if(option == "help") { help(); abort = true; calledHelp = true; }
+ else if(option == "citation") { citation(); abort = true; calledHelp = true;}
+
+ else {
+ vector<string> myArray = setParameters();
+
+ OptionParser parser(option);
+ map<string, string> parameters = parser.getParameters();
+
+ ValidParameters validParameter("pairwise.seqs");
+ map<string, string>::iterator it;
+
+ //check to make sure all parameters are valid for command
+ for (it = parameters.begin(); it != parameters.end(); it++) {
+ if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; }
+ }
+
+ //initialize outputTypes
+ vector<string> tempOutNames;
+ outputTypes["fasta"] = tempOutNames;
+ outputTypes["qfile"] = tempOutNames;
+
+
+ //if the user changes the input directory command factory will send this info to us in the output parameter
+ string inputDir = validParameter.validFile(parameters, "inputdir", false);
+ if (inputDir == "not found"){ inputDir = ""; }
+ else {
+ string path;
+ it = parameters.find("ffastq");
+ //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["ffastq"] = inputDir + it->second; }
+ }
+
+ it = parameters.find("rfastq");
+ //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["rfastq"] = inputDir + it->second; }
+ }
+ }
+
+ ffastqfile = validParameter.validFile(parameters, "ffastq", true);
+ if (ffastqfile == "not open") { ffastqfile = ""; abort = true; }
+ else if (ffastqfile == "not found") { ffastqfile = ""; abort=true; m->mothurOut("The ffastq parameter is required.\n"); }
+
+ rfastqfile = validParameter.validFile(parameters, "rfastq", true);
+ if (rfastqfile == "not open") { rfastqfile = ""; abort = true; }
+ else if (rfastqfile == "not found") { rfastqfile = ""; abort=true; m->mothurOut("The rfastq parameter is required.\n"); }
+
+ //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 = m->hasPath(ffastqfile); }
+
+
+ //check for optional parameter and set defaults
+ // ...at some point should added some additional type checking...
+ string temp;
+ temp = validParameter.validFile(parameters, "match", false); if (temp == "not found"){ temp = "1.0"; }
+ m->mothurConvert(temp, match);
+
+ temp = validParameter.validFile(parameters, "mismatch", false); if (temp == "not found"){ temp = "-1.0"; }
+ m->mothurConvert(temp, misMatch);
+ if (misMatch > 0) { m->mothurOut("[ERROR]: mismatch must be negative.\n"); abort=true; }
+
+ temp = validParameter.validFile(parameters, "gapopen", false); if (temp == "not found"){ temp = "-2.0"; }
+ m->mothurConvert(temp, gapOpen);
+ if (gapOpen > 0) { m->mothurOut("[ERROR]: gapopen must be negative.\n"); abort=true; }
+
+ temp = validParameter.validFile(parameters, "gapextend", false); if (temp == "not found"){ temp = "-1.0"; }
+ m->mothurConvert(temp, gapExtend);
+ if (gapExtend > 0) { m->mothurOut("[ERROR]: gapextend must be negative.\n"); abort=true; }
+
+ temp = validParameter.validFile(parameters, "processors", false); if (temp == "not found"){ temp = m->getProcessors(); }
+ m->setProcessors(temp);
+ m->mothurConvert(temp, processors);
+
+ align = validParameter.validFile(parameters, "align", false); if (align == "not found"){ align = "needleman"; }
+ if ((align != "needleman") && (align != "blast") && (align != "gotoh") && (align != "noalign")) { m->mothurOut(align + " is not a valid alignment method. Options are needleman, blast, gotoh and noalign. I will use needleman."); m->mothurOutEndLine(); align = "needleman"; }
+ }
+
+ }
+ catch(exception& e) {
+ m->errorOut(e, "MakeContigsCommand", "MakeContigsCommand");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+int MakeContigsCommand::execute(){
+ try {
+ if (abort == true) { if (calledHelp) { return 0; } return 2; }
+
+ //read ffastq and rfastq files creating fasta and qual files.
+ //this function will create a forward and reverse, fasta and qual files for each processor.
+ //files has an entry for each processor. files[i][0] = forwardFasta, files[i][1] = forwardQual, files[i][2] = reverseFasta, files[i][3] = reverseQual
+ int numReads = 0;
+ m->mothurOut("Reading fastq data..."); cout.flush();
+ vector< vector<string> > files = readFastqFiles(numReads);
+ m->mothurOut("Done.\n");
+
+
+
+
+ string currentFasta = "";
+ itTypes = outputTypes.find("fasta");
+ if (itTypes != outputTypes.end()) {
+ if ((itTypes->second).size() != 0) { currentFasta = (itTypes->second)[0]; m->setFastaFile(currentFasta); }
+ }
+
+ string currentQual = "";
+ itTypes = outputTypes.find("qfile");
+ if (itTypes != outputTypes.end()) {
+ if ((itTypes->second).size() != 0) { currentQual = (itTypes->second)[0]; m->setQualFile(currentQual); }
+ }
+
+ //output files created by command
+ m->mothurOutEndLine();
+ m->mothurOut("Output File Names: "); m->mothurOutEndLine();
+ for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); }
+ m->mothurOutEndLine();
+
+
+ return 0;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "MakeContigsCommand", "execute");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+vector< vector<string> > MakeContigsCommand::readFastqFiles(int& count){
+ try {
+ vector< vector<string> > files;
+
+ //maps processors number to file pointer
+ map<int, vector<ofstream*> > tempfiles; //tempfiles[0] = forwardFasta, [1] = forwardQual, [2] = reverseFasta, [3] = reverseQual
+ map<int, vector<ofstream*> >::iterator it;
+
+ //create files to write to
+ for (int i = 0; i < processors; i++) {
+ vector<ofstream*> temp;
+ ofstream* outFF = new ofstream; temp.push_back(outFF);
+ ofstream* outFQ = new ofstream; temp.push_back(outFQ);
+ ofstream* outRF = new ofstream; temp.push_back(outRF);
+ ofstream* outRQ = new ofstream; temp.push_back(outRQ);
+ tempfiles[i] = temp;
+
+ vector<string> names;
+ string ffastafilename = outputDir + m->getRootName(m->getSimpleName(ffastqfile)) + toString(i) + "ffasta.temp";
+ string rfastafilename = outputDir + m->getRootName(m->getSimpleName(rfastqfile)) + toString(i) + "rfasta.temp";
+ string fqualfilename = outputDir + m->getRootName(m->getSimpleName(ffastqfile)) + toString(i) + "fqual.temp";
+ string rqualfilename = outputDir + m->getRootName(m->getSimpleName(rfastqfile)) + toString(i) + "rqual.temp";
+ names.push_back(ffastafilename); names.push_back(fqualfilename);
+ names.push_back(rfastafilename); names.push_back(rqualfilename);
+ files.push_back(names);
+
+ m->openOutputFile(ffastafilename, *outFF);
+ m->openOutputFile(rfastafilename, *outRF);
+ m->openOutputFile(fqualfilename, *outFQ);
+ m->openOutputFile(rqualfilename, *outRQ);
+ }
+
+ if (m->control_pressed) {
+ //close files, delete ofstreams
+ for (it = tempfiles.begin(); it!=tempfiles.end(); it++) { for (int i = 0; i < (it->second).size(); i++) { (*(it->second)[i]).close(); delete (it->second)[i]; } }
+ //remove files
+ for (int i = 0; i < files.size(); i++) {
+ for(int j = 0; j < files[i].size(); j++) { m->mothurRemove(files[i][j]); }
+ }
+ }
+
+ ifstream inForward;
+ m->openInputFile(ffastqfile, inForward);
+
+ ifstream inReverse;
+ m->openInputFile(rfastqfile, inReverse);
+
+ count = 0;
+ while ((!inForward.eof()) && (!inReverse.eof())) {
+
+ if (m->control_pressed) { for (it = tempfiles.begin(); it!=tempfiles.end(); it++) { for (int i = 0; i < (it->second).size(); i++) { (*(it->second)[i]).close(); delete (it->second)[i]; } } for (int i = 0; i < files.size(); i++) { for(int j = 0; j < files[i].size(); j++) { m->mothurRemove(files[i][j]); } } inForward.close(); inReverse.close(); return files; }
+
+ //get a read from forward and reverse fastq files
+ fastqRead fread = readFastq(inForward);
+ fastqRead rread = readFastq(inReverse);
+ checkReads(fread, rread);
+
+ if (m->control_pressed) { for (it = tempfiles.begin(); it!=tempfiles.end(); it++) { for (int i = 0; i < (it->second).size(); i++) { (*(it->second)[i]).close(); delete (it->second)[i]; } } for (int i = 0; i < files.size(); i++) { for(int j = 0; j < files[i].size(); j++) { m->mothurRemove(files[i][j]); } } inForward.close(); inReverse.close(); return files; }
+
+ //if the reads are okay write to output files
+ int process = count % processors;
+
+ *(tempfiles[process][0]) << ">" << fread.name << endl << fread.sequence << endl;
+ *(tempfiles[process][1]) << ">" << fread.name << endl;
+ for (int i = 0; i < fread.scores.size(); i++) { *(tempfiles[process][1]) << fread.scores[i] << " "; }
+ *(tempfiles[process][1]) << endl;
+ *(tempfiles[process][2]) << ">" << rread.name << endl << rread.sequence << endl;
+ *(tempfiles[process][3]) << ">" << rread.name << endl;
+ for (int i = 0; i < rread.scores.size(); i++) { *(tempfiles[process][3]) << rread.scores[i] << " "; }
+ *(tempfiles[process][3]) << endl;
+
+ count++;
+
+ //report progress
+ if((count) % 10000 == 0){ m->mothurOut(toString(count)); m->mothurOutEndLine(); }
+
+ }
+ //report progress
+ if((count) % 10000 != 0){ m->mothurOut(toString(count)); m->mothurOutEndLine(); }
+
+
+
+ //close files, delete ofstreams
+ for (it = tempfiles.begin(); it!=tempfiles.end(); it++) { for (int i = 0; i < (it->second).size(); i++) { (*(it->second)[i]).close(); delete (it->second)[i]; } }
+ inForward.close();
+ inReverse.close();
+
+ //adjust for really large processors or really small files
+ if (count < processors) {
+ for (int i = count; i < processors; i++) { for(int j = 0; j < files[i].size(); j++) { m->mothurRemove(files[i][j]); } files[i].clear(); }
+ files.resize(count);
+ processors = count;
+ }
+
+ return files;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "MakeContigsCommand", "readFastqFiles");
+ exit(1);
+ }
+}
+
+//**********************************************************************************************************************
+fastqRead MakeContigsCommand::readFastq(ifstream& in){
+ try {
+ fastqRead read;
+
+ //read sequence name
+ string name = m->getline(in); m->gobble(in);
+ if (name == "") { m->mothurOut("[ERROR]: Blank fasta name."); m->mothurOutEndLine(); m->control_pressed = true; return read; }
+ else if (name[0] != '@') { m->mothurOut("[ERROR]: reading " + name + " expected a name with @ as a leading character."); m->mothurOutEndLine(); m->control_pressed = true; return read; }
+ else { name = name.substr(1); }
+
+ //read sequence
+ string sequence = m->getline(in); m->gobble(in);
+ if (sequence == "") { m->mothurOut("[ERROR]: missing sequence for " + name); m->mothurOutEndLine(); m->control_pressed = true; return read; }
+
+ //read sequence name
+ string name2 = m->getline(in); m->gobble(in);
+ if (name2 == "") { m->mothurOut("[ERROR]: Blank quality name."); m->mothurOutEndLine(); m->control_pressed = true; return read; }
+ else if (name2[0] != '+') { m->mothurOut("[ERROR]: reading " + name2 + " expected a name with + as a leading character."); m->mothurOutEndLine(); m->control_pressed = true; return read; }
+ else { name2 = name2.substr(1); }
+
+ //read quality scores
+ string quality = m->getline(in); m->gobble(in);
+ if (quality == "") { m->mothurOut("[ERROR]: missing quality for " + name2); m->mothurOutEndLine(); m->control_pressed = true; return read; }
+
+ //sanity check sequence length and number of quality scores match
+ if (name2 != "") { if (name != name2) { m->mothurOut("[ERROR]: names do not match. read " + name + " for fasta and " + name2 + " for quality."); m->mothurOutEndLine(); m->control_pressed = true; return read; } }
+ if (quality.length() != sequence.length()) { m->mothurOut("[ERROR]: Lengths do not match for sequence " + name + ". Read " + toString(sequence.length()) + " characters for fasta and " + toString(quality.length()) + " characters for quality scores."); m->mothurOutEndLine(); m->control_pressed = true; return read; }
+
+ vector<int> qualScores;
+ int controlChar = int('@');
+ for (int i = 0; i < quality.length(); i++) {
+ int temp = int(quality[i]);
+ temp -= controlChar;
+
+ qualScores.push_back(temp);
+ }
+
+ read.name = name;
+ read.sequence = sequence;
+ read.scores = qualScores;
+
+ return read;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "MakeContigsCommand", "readFastq");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+bool MakeContigsCommand::checkReads(fastqRead& forward, fastqRead& reverse){
+ try {
+ bool good = true;
+
+ //fix names
+ if ((forward.name.length() > 2) && (reverse.name.length() > 2)) {
+ forward.name = forward.name.substr(0, forward.name.length()-2);
+ reverse.name = reverse.name.substr(0, reverse.name.length()-2);
+ }else { good = false; m->control_pressed = true; }
+
+ //do names match
+ if (forward.name != reverse.name) {
+ m->mothurOut("[ERROR]: read " + forward.name + " from " + ffastqfile + ", but read " + reverse.name + " from " + rfastqfile + ".\n");
+ good = false; m->control_pressed = true;
+ }
+
+ //do sequence lengths match
+ if (forward.sequence.length() != reverse.sequence.length()) {
+ m->mothurOut("[ERROR]: For sequence " + forward.name + " I read a sequence of length " + toString(forward.sequence.length()) + " from " + ffastqfile + ", but read a sequence of length " + toString(reverse.sequence.length()) + " from " + rfastqfile + ".\n");
+ good = false; m->control_pressed = true;
+ }
+
+ //do number of qual scores match
+ if (forward.scores.size() != reverse.scores.size()) {
+ m->mothurOut("[ERROR]: For sequence " + forward.name + " I read " + toString(forward.scores.size()) + " quality scores from " + ffastqfile + ", but read " + toString(reverse.scores.size()) + " quality scores from " + rfastqfile + ".\n");
+ good = false; m->control_pressed = true;
+ }
+
+ return good;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "MakeContigsCommand", "readFastq");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+
+
+
+
--- /dev/null
+#ifndef Mothur_makecontigscommand_h
+#define Mothur_makecontigscommand_h
+
+//
+// makecontigscommand.h
+// Mothur
+//
+// Created by Sarah Westcott on 5/15/12.
+// Copyright (c) 2012 Schloss Lab. All rights reserved.
+//
+
+#include "command.hpp"
+
+struct fastqRead {
+ vector<int> scores;
+ string name;
+ string sequence;
+
+ fastqRead() { name = ""; sequence = ""; scores.clear(); };
+ fastqRead(string n, string s, vector<int> sc) : name(n), sequence(s), scores(sc) {};
+ ~fastqRead() {};
+};
+
+/**************************************************************************************************/
+
+class MakeContigsCommand : public Command {
+public:
+ MakeContigsCommand(string);
+ MakeContigsCommand();
+ ~MakeContigsCommand(){}
+
+ vector<string> setParameters();
+ string getCommandName() { return "make.contigs"; }
+ string getCommandCategory() { return "Sequence Processing"; }
+ //commmand category choices: Sequence Processing, OTU-Based Approaches, Hypothesis Testing, Phylotype Analysis, General, Clustering and Hidden
+ string getHelpString();
+ string getCitation() { return "http://www.mothur.org/wiki/Make.contigs"; }
+ string getDescription() { return "description"; }
+
+ int execute();
+ void help() { m->mothurOut(getHelpString()); }
+
+private:
+ bool abort;
+ string outputDir, ffastqfile, rfastqfile, align;
+ float match, misMatch, gapOpen, gapExtend;
+ int processors, longestBase;
+ vector<string> outputNames;
+
+ fastqRead readFastq(ifstream&);
+ vector< vector<string> > readFastqFiles(int&);
+ bool checkReads(fastqRead&, fastqRead&);
+};
+
+/**************************************************************************************************/
+
+
+
+
+
+
+
+#endif
try {
string qualScores;
- int controlChar = int('!');
+ int controlChar = int('@');
for (int i = 0; i < qual.size(); i++) {
int temp = qual[i] + controlChar;
try {
vector<int> qualScores;
- int controlChar = int('!');
+ int controlChar = int('@');
for (int i = 0; i < qual.length(); i++) {
int temp = int(qual[i]);
}
/***********************************************************************/
-SplitMatrix::SplitMatrix(string ffile, string name, string tax, float c, float cu, string t, int p, string output){
+SplitMatrix::SplitMatrix(string ffile, string name, string tax, float c, float cu, string t, int p, bool cl, string output){
m = MothurOut::getInstance();
fastafile = ffile;
namefile = name;
distCutoff = cu; //for fasta method if you are creating distance matrix you need a cutoff for that
method = t;
processors = p;
+ classic = cl;
outputDir = output;
}
//process each distance file
for (int i = 0; i < numGroups; i++) {
- string options = "fasta=" + (fastafile + "." + toString(i) + ".temp") + ", processors=" + toString(processors) + ", cutoff=" + toString(distCutoff);
+ string options = "";
+ if (classic) { options = "fasta=" + (fastafile + "." + toString(i) + ".temp") + ", processors=" + toString(processors) + ", output=lt"; }
+ else { options = "fasta=" + (fastafile + "." + toString(i) + ".temp") + ", processors=" + toString(processors) + ", cutoff=" + toString(distCutoff); }
if (outputDir != "") { options += ", outputdir=" + outputDir; }
Command* command = new DistanceCommand(options);
for(int i=0;i<numGroups;i++){
string tempNameFile = namefile + "." + toString(i) + ".temp";
if (outputDir == "") { outputDir = m->hasPath(fastafile); }
- string tempDistFile = outputDir + m->getRootName(m->getSimpleName((fastafile + "." + toString(i) + ".temp"))) + "dist";
+ string tempDistFile = "";
+ if (classic) { tempDistFile = outputDir + m->getRootName(m->getSimpleName((fastafile + "." + toString(i) + ".temp"))) + "phylip.dist";}
+ else { tempDistFile = outputDir + m->getRootName(m->getSimpleName((fastafile + "." + toString(i) + ".temp"))) + "dist"; }
//if there are valid distances
ifstream fileHandle;
public:
SplitMatrix(string, string, string, float, string, bool); //column formatted distance file, namesfile, cutoff, method, large
- SplitMatrix(string, string, string, float, float, string, int, string); //fastafile, namefile, taxFile, taxcutoff, cutoff, method, processors, outputDir
+ SplitMatrix(string, string, string, float, float, string, int, bool, string); //fastafile, namefile, taxFile, taxcutoff, cutoff, method, processors, classic, outputDir
~SplitMatrix();
int split();
string distFile, namefile, singleton, method, taxFile, fastafile, outputDir;
vector< map< string, string> > dists;
float cutoff, distCutoff;
- bool large;
+ bool large, classic;
int processors;
int splitDistance();
projects / mothur.git / commitdiff