From: westcott Date: Tue, 11 May 2010 16:25:11 +0000 (+0000) Subject: added clearcut command X-Git-Url: https://git.donarmstrong.com/?p=mothur.git;a=commitdiff_plain;h=b1bcc272003b50a8c06dc9120754da1f5b744598 added clearcut command --- diff --git a/Mothur.xcodeproj/project.pbxproj b/Mothur.xcodeproj/project.pbxproj index f9fd39e..259ef9c 100644 --- a/Mothur.xcodeproj/project.pbxproj +++ b/Mothur.xcodeproj/project.pbxproj @@ -30,6 +30,8 @@ A7825503116519F70002E2DD /* chimerabellerophoncommand.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; path = chimerabellerophoncommand.cpp; sourceTree = ""; }; A78434881162224F00100BE0 /* chimeraccodecommand.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; path = chimeraccodecommand.h; sourceTree = ""; }; A78434891162224F00100BE0 /* chimeraccodecommand.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; path = chimeraccodecommand.cpp; sourceTree = ""; }; + A7D215C811996C6E00F13F13 /* clearcutcommand.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; path = clearcutcommand.h; sourceTree = ""; }; + A7D215C911996C6E00F13F13 /* clearcutcommand.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; path = clearcutcommand.cpp; sourceTree = ""; }; A7DA1FEC113FECD400BF472F /* ace.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; path = ace.cpp; sourceTree = ""; }; A7DA1FED113FECD400BF472F /* ace.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; path = ace.h; sourceTree = ""; }; A7DA1FEE113FECD400BF472F /* aligncommand.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; path = aligncommand.cpp; sourceTree = ""; }; @@ -660,6 +662,8 @@ A73953DB11987ED100B0B160 /* chopseqscommand.cpp */, A7DA201E113FECD400BF472F /* classifyseqscommand.h */, A7DA201D113FECD400BF472F /* classifyseqscommand.cpp */, + A7D215C811996C6E00F13F13 /* clearcutcommand.h */, + A7D215C911996C6E00F13F13 /* clearcutcommand.cpp */, A7DA2021113FECD400BF472F /* clustercommand.cpp */, A7DA2022113FECD400BF472F /* clustercommand.h */, A7DA2025113FECD400BF472F /* collectcommand.cpp */, diff --git a/clearcutcommand.cpp b/clearcutcommand.cpp new file mode 100644 index 0000000..fc028a2 --- /dev/null +++ b/clearcutcommand.cpp @@ -0,0 +1,235 @@ +/* + * clearcutcommand.cpp + * Mothur + * + * Created by westcott on 5/11/10. + * Copyright 2010 Schloss Lab. All rights reserved. + * + */ + +#include "clearcutcommand.h" +#include "globaldata.hpp" + +/**************************************************************************************/ +ClearcutCommand::ClearcutCommand(string option) { + try { + abort = false; + + //allow user to run help + if(option == "help") { help(); abort = true; } + + else { + //valid paramters for this command + string Array[] = {"fasta","phylip","version","verbose","quiet","seed","norandom","shuffle","neighbor","expblen", + "expdist","ntrees","matrixout","stdout","kimura","jukes","protein","DNA","stdin","outputdir","inputdir"}; + vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + + OptionParser parser(option); + map parameters = parser.getParameters(); + + ValidParameters validParameter; + map::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 { + string path; + it = parameters.find("fasta"); + //user has given a template file + if(it != parameters.end()){ + path = hasPath(it->second); + //if the user has not given a path then, add inputdir. else leave path alone. + if (path == "") { parameters["fasta"] = inputDir + it->second; } + } + + it = parameters.find("phylip"); + //user has given a template file + if(it != parameters.end()){ + path = hasPath(it->second); + //if the user has not given a path then, add inputdir. else leave path alone. + if (path == "") { parameters["phylip"] = inputDir + it->second; } + } + } + + //check for required parameters + fastafile = validParameter.validFile(parameters, "fasta", true); + if (fastafile == "not open") { fastafile = ""; abort = true; } + else if (fastafile == "not found") { fastafile = ""; } + else { inputFile = fastafile; } + + phylipfile = validParameter.validFile(parameters, "phylip", true); + if (phylipfile == "not open") { phylipfile = ""; abort = true; } + else if (phylipfile == "not found") { phylipfile = ""; } + else { inputFile = phylipfile; } + + if ((phylipfile == "") && (fastafile == "")) { m->mothurOut("You must provide either a phylip formatted distance matrix or an aligned fasta file."); m->mothurOutEndLine(); abort=true; } + if ((phylipfile != "") && (fastafile != "")) { m->mothurOut("You must provide either a phylip formatted distance matrix or an aligned fasta file, not BOTH."); 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 = ""; } + + string temp; + temp = validParameter.validFile(parameters, "version", false); if (temp == "not found"){ temp = "F"; } + version = isTrue(temp); + + temp = validParameter.validFile(parameters, "verbose", false); if (temp == "not found"){ temp = "F"; } + verbose = isTrue(temp); + + temp = validParameter.validFile(parameters, "quiet", false); if (temp == "not found"){ temp = "F"; } + quiet = isTrue(temp); + + seed = validParameter.validFile(parameters, "seed", false); if (seed == "not found"){ seed = "*"; } + + temp = validParameter.validFile(parameters, "norandom", false); if (temp == "not found"){ temp = "F"; } + norandom = isTrue(temp); + + temp = validParameter.validFile(parameters, "shuffle", false); if (temp == "not found"){ temp = "F"; } + shuffle = isTrue(temp); + + temp = validParameter.validFile(parameters, "neighbor", false); if (temp == "not found"){ temp = "F"; } + neighbor = isTrue(temp); + + temp = validParameter.validFile(parameters, "stdin", false); if (temp == "not found"){ temp = "F"; } + stdin = isTrue(temp); + + temp = validParameter.validFile(parameters, "DNA", false); if (temp == "not found"){ temp = "F"; } + DNA = isTrue(temp); + + temp = validParameter.validFile(parameters, "protein", false); if (temp == "not found"){ temp = "F"; } + protein = isTrue(temp); + + temp = validParameter.validFile(parameters, "jukes", false); if (temp == "not found"){ temp = "F"; } + jukes = isTrue(temp); + + temp = validParameter.validFile(parameters, "kimura", false); if (temp == "not found"){ temp = "F"; } + kimura = isTrue(temp); + + temp = validParameter.validFile(parameters, "stdout", false); if (temp == "not found"){ temp = "F"; } + stdout = isTrue(temp); + + matrixout = validParameter.validFile(parameters, "matrixout", false); if (matrixout == "not found"){ matrixout = ""; } + + ntrees = validParameter.validFile(parameters, "ntrees", false); if (ntrees == "not found"){ ntrees = "1"; } + + temp = validParameter.validFile(parameters, "expblen", false); if (temp == "not found"){ temp = "F"; } + expblen = isTrue(temp); + + temp = validParameter.validFile(parameters, "expdist", false); if (temp == "not found"){ temp = "F"; } + expdist = isTrue(temp); + + if ((fastafile != "") && ((!DNA) && (!protein))) { m->mothurOut("You must specify the type of sequences you are using: DNA or protein"); m->mothurOutEndLine(); abort=true; } + } + + } + catch(exception& e) { + m->errorOut(e, "ClearcutCommand", "ClearcutCommand"); + exit(1); + } +} +//********************************************************************************************************************** + +void ClearcutCommand::help(){ + try { + m->mothurOut("The clearcut command interfaces mothur with the clearcut program written by Initiative for Bioinformatics and Evolutionary Studies (IBEST) at the University of Idaho.\n"); + m->mothurOut("For more information about clearcut refer to http://bioinformatics.hungry.com/clearcut/ \n"); + m->mothurOut("The clearcut command parameters are phylip, fasta, version, verbose, quiet, seed, norandom, shuffle, neighbor, expblen, expdist, ntrees, matrixout, stdout, kimura, jukes, protein, DNA, stdin. \n"); + m->mothurOut("The phylip parameter allows you to enter your phylip formatted distance matrix. \n"); + m->mothurOut("The fasta parameter allows you to enter your aligned fasta file, if you enter a fastafile you specify if the sequences are DNA or protein using the DNA or protein parameters. \n"); + + m->mothurOut("The version parameter prints out the version of clearcut you are using, default=F. \n"); + m->mothurOut("The verbose parameter prints out more output from clearcut, default=F. \n"); + m->mothurOut("The quiet parameter turns on silent operation mode, default=F. \n"); + m->mothurOut("The seed parameter allows you to explicitly set the PRNG seed to a specific value. \n"); + m->mothurOut("The norandom parameter allows you to attempt joins deterministically, default=F. \n"); + m->mothurOut("The shuffle parameter allows you to randomly shuffle the distance matrix, default=F. \n"); + m->mothurOut("The neighbor parameter allows you to use traditional Neighbor-Joining algorithm, default=F. \n"); + + m->mothurOut("The stdin parameter reads input from STDIN, default=F. \n"); + m->mothurOut("The DNA parameter allows you to indicate your fasta file contains DNA sequences, default=F. \n"); + m->mothurOut("The protein parameter allows you to indicate your fasta file contains protein sequences, default=F. \n"); + + m->mothurOut("The stdout parameter outputs your tree to STDOUT, default=F. \n"); + m->mothurOut("The matrixout parameter allows you to specify a filename to output a distance matrix to. \n"); + m->mothurOut("The ntrees parameter allows you to specify the number of output trees, default=1. \n"); + m->mothurOut("The expblen parameter allows you to use exponential notation for branch lengths, default=F. \n"); + m->mothurOut("The expdist parameter allows you to use exponential notation for distance outputs, default=F. \n"); + + m->mothurOut("The clearcut command should be in the following format: \n"); + m->mothurOut("clearcut(phylip=yourDistanceFile) \n"); + m->mothurOut("Example: clearcut(phylip=abrecovery.phylip.dist) \n"); + } + catch(exception& e) { + m->errorOut(e, "ClearcutCommand", "help"); + exit(1); + } +} + +/**************************************************************************************/ +int ClearcutCommand::execute() { + try { + + if (abort == true) { return 0; } + + //prepare filename + string outputName = outputDir + getRootName(getSimpleName(inputFile)) + "tre"; + + //get location of clearcut + GlobalData* globaldata = GlobalData::getInstance(); + string path = globaldata->argv; + path = path.substr(0, (path.find_last_of('m'))); + + string clearcutCommand = path + "clearcut/clearcut "; + + //you gave us a distance matrix + if (phylipfile != "") { clearcutCommand += "--distance "; } + + //you gave us a fastafile + if (fastafile != "") { clearcutCommand += "--alignment "; } + + if (version) { clearcutCommand += "--version "; } + if (verbose) { clearcutCommand += "--verbose "; } + if (quiet) { clearcutCommand += "--quiet "; } + if (seed != "*") { clearcutCommand += "--seed=" + seed + " "; } + if (norandom) { clearcutCommand += "--norandom "; } + if (shuffle) { clearcutCommand += "--shuffle "; } + if (neighbor) { clearcutCommand += "--neighbor "; } + + if (stdin) { clearcutCommand += "--stdin "; } + else { clearcutCommand += "--in=" + inputFile + " "; } + if (stdout) { clearcutCommand += "--stdout "; } + else { clearcutCommand += "--out=" + outputName + " "; } + + if (DNA) { clearcutCommand += "--DNA "; } + if (protein) { clearcutCommand += "--protein "; } + if (jukes) { clearcutCommand += "--jukes "; } + if (kimura) { clearcutCommand += "--kimura "; } + if (matrixout != "") { clearcutCommand += "--matrixout=" + matrixout + " "; } + if (ntrees != "1") { clearcutCommand += "--ntrees=" + ntrees + " "; } + if (expblen) { clearcutCommand += "--expblen "; } + if (expdist) { clearcutCommand += "--expdist "; } + + //run clearcut + system(clearcutCommand.c_str()); + + if (!stdout) { + m->mothurOutEndLine(); + m->mothurOut("Output File Names: "); m->mothurOutEndLine(); + m->mothurOut(outputName); m->mothurOutEndLine(); + m->mothurOutEndLine(); + } + + return 0; + } + catch(exception& e) { + m->errorOut(e, "ClearcutCommand", "execute"); + exit(1); + } +} +/**************************************************************************************/ diff --git a/clearcutcommand.h b/clearcutcommand.h new file mode 100644 index 0000000..b3ac28e --- /dev/null +++ b/clearcutcommand.h @@ -0,0 +1,41 @@ +#ifndef CLEARCUTCOMMAND_H +#define CLEARCUTCOMMAND_H + +/* + * clearcutcommand.h + * Mothur + * + * Created by westcott on 5/11/10. + * Copyright 2010 Schloss Lab. All rights reserved. + * + */ + +#include "command.hpp" + + +/* + Evans, J., L. Sheneman, and J.A. Foster (2006) Relaxed Neighbor-Joining: + A Fast Distance-Based Phylogenetic Tree Construction Method, + J. Mol. Evol., 62, 785-792 + */ + +/****************************************************************************/ + +class ClearcutCommand : public Command { + +public: + ClearcutCommand(string); + ~ClearcutCommand() {}; + int execute(); + void help(); + +private: + string outputDir, phylipfile, fastafile, matrixout, inputFile, seed, ntrees; + bool version, verbose, quiet, norandom, shuffle, neighbor, expblen, expdist, stdout, kimura, jukes, protein, DNA, stdin; + bool abort; +}; + +/****************************************************************************/ + +#endif + diff --git a/commandfactory.cpp b/commandfactory.cpp index 2ac61e3..9917b3c 100644 --- a/commandfactory.cpp +++ b/commandfactory.cpp @@ -75,6 +75,7 @@ #include "phylodiversitycommand.h" #include "makegroupcommand.h" #include "chopseqscommand.h" +#include "clearcutcommand.h" /*******************************************************/ @@ -157,6 +158,7 @@ CommandFactory::CommandFactory(){ commands["phylo.diversity"] = "phylo.diversity"; commands["make.group"] = "make.group"; commands["chop.seqs"] = "chop.seqs"; + commands["clearcut"] = "clearcut"; commands["classify.seqs"] = "MPIEnabled"; commands["dist.seqs"] = "MPIEnabled"; commands["filter.seqs"] = "MPIEnabled"; @@ -276,6 +278,7 @@ Command* CommandFactory::getCommand(string commandName, string optionString){ else if(commandName == "phylo.diversity") { command = new PhyloDiversityCommand(optionString); } else if(commandName == "make.group") { command = new MakeGroupCommand(optionString); } else if(commandName == "chop.seqs") { command = new ChopSeqsCommand(optionString); } + else if(commandName == "clearcut") { command = new ClearcutCommand(optionString); } else { command = new NoCommand(optionString); } return command; diff --git a/makefile b/makefile index ecdbcf0..7c21475 100644 --- a/makefile +++ b/makefile @@ -147,7 +147,8 @@ mothur : \ ./groupmap.o\ ./helpcommand.o\ ./makegroupcommand.o\ - ./chopseqscommand.o\ + ./chopseqscommand.o\ + ./clearcutcommand.o\ ./inputdata.o\ ./jackknife.o\ ./kmer.o\ @@ -350,7 +351,8 @@ mothur : \ ./groupmap.o\ ./helpcommand.o\ ./makegroupcommand.o\ - ./chopseqscommand.o\ + ./chopseqscommand.o\ + ./clearcutcommand.o\ ./inputdata.o\ ./jackknife.o\ ./kmer.o\ @@ -556,7 +558,8 @@ clean : ./groupmap.o\ ./helpcommand.o\ ./makegroupcommand.o\ - ./chopseqscommand.o\ + ./chopseqscommand.o\ + ./clearcutcommand.o\ ./inputdata.o\ ./jackknife.o\ ./kmer.o\ @@ -1661,6 +1664,10 @@ install : mothur # Item # 202 -- chopseqscommand -- ./chopseqscommand.o : chopseqscommand.cpp - $(CC) $(CC_OPTIONS) chopseqscommand.cpp -c $(INCLUDE) -o ./chopseqscommand.o + $(CC) $(CC_OPTIONS) chopseqscommand.cpp -c $(INCLUDE) -o ./chopseqscommand.o + +# Item # 203 -- clearcutcommand -- +./clearcutcommand.o : clearcutcommand.cpp + $(CC) $(CC_OPTIONS) clearcutcommand.cpp -c $(INCLUDE) -o ./clearcutcommand.o ##### END RUN ####