2 * pipelinepdscommand.cpp
5 * Created by westcott on 10/5/10.
6 * Copyright 2010 Schloss Lab. All rights reserved.
10 #include "pipelinepdscommand.h"
11 #include "sffinfocommand.h"
12 #include "commandoptionparser.hpp"
14 //**********************************************************************************************************************
15 vector<string> PipelineCommand::getValidParameters(){
17 string Array[] = {"sff","oligos","align","chimera","classify","taxonomy","pipeline","processors","outputdir","inputdir"};
18 vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
22 m->errorOut(e, "PipelineCommand", "getValidParameters");
26 //**********************************************************************************************************************
27 vector<string> PipelineCommand::getRequiredParameters(){
29 vector<string> myArray;
33 m->errorOut(e, "PipelineCommand", "getRequiredParameters");
37 //**********************************************************************************************************************
38 vector<string> PipelineCommand::getRequiredFiles(){
40 vector<string> myArray;
44 m->errorOut(e, "PipelineCommand", "getRequiredFiles");
48 //**********************************************************************************************************************
49 PipelineCommand::PipelineCommand(string option) {
51 cFactory = CommandFactory::getInstance();
54 //allow user to run help
55 if(option == "help") { help(); abort = true; }
59 //valid paramters for this command
60 string AlignArray[] = {"sff","oligos","align","chimera","classify","taxonomy","pipeline","processors","outputdir","inputdir"};
61 vector<string> myArray (AlignArray, AlignArray+(sizeof(AlignArray)/sizeof(string)));
63 OptionParser parser(option);
64 map<string, string> parameters = parser.getParameters();
66 ValidParameters validParameter;
67 map<string, string>::iterator it;
69 //check to make sure all parameters are valid for command
70 for (it = parameters.begin(); it != parameters.end(); it++) {
71 if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; }
74 //if the user changes the input directory command factory will send this info to us in the output parameter
75 string inputDir = validParameter.validFile(parameters, "inputdir", false);
76 if (inputDir == "not found"){ inputDir = ""; }
79 it = parameters.find("sff");
80 //user has given a template file
81 if(it != parameters.end()){
82 path = m->hasPath(it->second);
83 //if the user has not given a path then, add inputdir. else leave path alone.
84 if (path == "") { parameters["sff"] = inputDir + it->second; }
87 it = parameters.find("oligos");
88 //user has given a template file
89 if(it != parameters.end()){
90 path = m->hasPath(it->second);
91 //if the user has not given a path then, add inputdir. else leave path alone.
92 if (path == "") { parameters["oligos"] = inputDir + it->second; }
95 it = parameters.find("align");
96 //user has given a template file
97 if(it != parameters.end()){
98 path = m->hasPath(it->second);
99 //if the user has not given a path then, add inputdir. else leave path alone.
100 if (path == "") { parameters["align"] = inputDir + it->second; }
103 it = parameters.find("chimera");
104 //user has given a template file
105 if(it != parameters.end()){
106 path = m->hasPath(it->second);
107 //if the user has not given a path then, add inputdir. else leave path alone.
108 if (path == "") { parameters["chimera"] = inputDir + it->second; }
111 it = parameters.find("classify");
112 //user has given a template file
113 if(it != parameters.end()){
114 path = m->hasPath(it->second);
115 //if the user has not given a path then, add inputdir. else leave path alone.
116 if (path == "") { parameters["classify"] = inputDir + it->second; }
119 it = parameters.find("taxonomy");
120 //user has given a template file
121 if(it != parameters.end()){
122 path = m->hasPath(it->second);
123 //if the user has not given a path then, add inputdir. else leave path alone.
124 if (path == "") { parameters["taxonomy"] = inputDir + it->second; }
127 it = parameters.find("pipeline");
128 //user has given a template file
129 if(it != parameters.end()){
130 path = m->hasPath(it->second);
131 //if the user has not given a path then, add inputdir. else leave path alone.
132 if (path == "") { parameters["pipeline"] = inputDir + it->second; }
136 outputDir = validParameter.validFile(parameters, "outputdir", false); if (outputDir == "not found"){ outputDir = ""; }
138 pipeFilename = validParameter.validFile(parameters, "pipeline", true);
139 if (pipeFilename == "not found") { pipeFilename = ""; }
140 else if (pipeFilename == "not open") { pipeFilename = ""; abort = true; }
142 string temp = validParameter.validFile(parameters, "processors", false); if (temp == "not found"){ temp = "1"; }
143 convert(temp, processors);
145 if (pipeFilename != "") {
146 abort = readUsersPipeline();
148 sffFile = validParameter.validFile(parameters, "sff", true);
149 if (sffFile == "not found") { m->mothurOut("sff is a required parameter for the pipeline command."); m->mothurOutEndLine(); abort = true; }
150 else if (sffFile == "not open") { sffFile = ""; abort = true; }
152 oligosFile = validParameter.validFile(parameters, "oligos", true);
153 if (oligosFile == "not found") { m->mothurOut("oligos is a required parameter for the pipeline command."); m->mothurOutEndLine(); abort = true; }
154 else if (oligosFile == "not open") { oligosFile = ""; abort = true; }
156 alignFile = validParameter.validFile(parameters, "align", true);
157 if (alignFile == "not found") { m->mothurOut("align is a required parameter for the pipeline command. Please provide the template to align with."); m->mothurOutEndLine(); abort = true; }
158 else if (alignFile == "not open") { alignFile = ""; abort = true; }
160 chimeraFile = validParameter.validFile(parameters, "chimera", true);
161 if (chimeraFile == "not found") { m->mothurOut("chimera is a required parameter for the pipeline command. Please provide the template to check for chimeras with."); m->mothurOutEndLine(); abort = true; }
162 else if (chimeraFile == "not open") { chimeraFile = ""; abort = true; }
164 classifyFile = validParameter.validFile(parameters, "classify", true);
165 if (classifyFile == "not found") { m->mothurOut("classify is a required parameter for the pipeline command. Please provide the template to use with the classifier."); m->mothurOutEndLine(); abort = true; }
166 else if (classifyFile == "not open") { classifyFile = ""; abort = true; }
168 taxonomyFile = validParameter.validFile(parameters, "taxonomy", true);
169 if (taxonomyFile == "not found") { m->mothurOut("taxonomy is a required parameter for the pipeline command."); m->mothurOutEndLine(); abort = true; }
170 else if (taxonomyFile == "not open") { taxonomyFile = ""; abort = true; }
175 catch(exception& e) {
176 m->errorOut(e, "PipelineCommand", "PipelineCommand");
180 //**********************************************************************************************************************
182 void PipelineCommand::help(){
184 m->mothurOut("The pipeline command is designed to guide you through your analysis using mothur.\n");
185 m->mothurOut("The pipeline command parameters are pipeline, sff, oligos, align, chimera, classify, taxonomy and processors.\n");
186 m->mothurOut("The sff parameter allows you to enter your sff file. It is required.\n");
187 m->mothurOut("The oligos parameter allows you to enter your oligos file. It is required.\n");
188 m->mothurOut("The align parameter allows you to enter a template to use with the aligner. It is required.\n");
189 m->mothurOut("The chimera parameter allows you to enter a template to use for chimera detection. It is required.\n");
190 m->mothurOut("The classify parameter allows you to enter a template to use for classification. It is required.\n");
191 m->mothurOut("The taxonomy parameter allows you to enter a taxonomy file for the classify template to use for classification. It is required.\n");
192 m->mothurOut("The processors parameter allows you to specify the number of processors to use. The default is 1.\n");
193 m->mothurOut("The pipeline parameter allows you to enter your own pipeline file. This file should look like a mothur batchfile, but where you would be using a mothur generated file, you can use mothurmade instead.\n");
194 m->mothurOut("First column contains the command name, and the second column contains the parameter options or 'defaults', meaning use defaults. You may leave out file options.\n");
195 m->mothurOut("Example: trim.seqs(processors=8, allfiles=T, maxambig=0, maxhomop=8, flip=T, bdiffs=1, pdiffs=2, qwindowaverage=35, qwindowsize=50, fasta=may1.v13.fasta, oligos=may1.v13.oligos, qfile=may1.v13.qual)\n");
196 m->mothurOut("then, you could enter unique.seqs(fasta=mothurmade), and mothur would use the .trim.fasta file from the trim.seqs command. \n");
197 m->mothurOut("then you could enter align.seqs(candidate=mothurmade, template=silva.v13.align, processors=8). , and mothur would use the .trim.unique.fasta file from the unique.seqs command. \n");
198 m->mothurOut("If no pipeline file is given then mothur will use Pat's pipeline. \n\n");
199 m->mothurOut("Here is a list of the commands used in Pat's pipeline.\n");
200 m->mothurOut("All paralellized commands will use the processors you entered.\n");
201 m->mothurOut("The sffinfo command takes your sff file and extracts the fasta and quality files.\n");
202 m->mothurOut("The trim.seqs command uses your oligos file and the quality and fasta files generated by sffinfo.\n");
203 m->mothurOut("The trim.seqs command sets the following parameters: allfiles=T, maxambig=0, maxhomop=8, flip=T, bdiffs=1, pdiffs=2, qwindowaverage=35, qwindowsize=50.\n");
204 m->mothurOut("The unique.seqs command uses the trimmed fasta file and removes redundant sequences, don't worry the names file generated by unique.seqs will be used in the pipeline to make sure they are included.\n");
205 m->mothurOut("The align.seqs command aligns the unique sequences using the aligners default options. \n");
206 m->mothurOut("The screen.seqs command screens the sequences using optimize=end-minlength. \n");
207 m->mothurOut("The pipeline uses chimera.slayer to detect chimeras using the default options. \n");
208 m->mothurOut("The pipeline removes all sequences determined to be chimeric by chimera.slayer. \n");
209 m->mothurOut("The filter.seqs command filters the sequences using vertical=T, trump=. \n");
210 m->mothurOut("The unique.seqs command uses the filtered fasta file and name file to remove sequences that have become redundant after filtering.\n");
211 m->mothurOut("The pre.cluster command clusters sequences that have no more than 2 differences.\n");
212 m->mothurOut("The dist.seqs command is used to generate a column and phylip formatted distance matrix using cutoff=0.20 for column.\n");
213 m->mothurOut("The pipeline uses cluster with method=average, hard=T. \n");
214 m->mothurOut("The classify.seqs command is used to classify the sequences using the bayesian method with a cutoff of 80.\n");
215 m->mothurOut("The phylotype command is used to cluster the sequences based on their classification.\n");
216 m->mothurOut("The clearcut command is used to generate a tree using neighbor=T. \n");
217 m->mothurOut("The summary.single and summary.shared commands are run on the otu files from cluster and phylotype commands. \n");
218 m->mothurOut("The summary.shared command uses calc=sharednseqs-sharedsobs-sharedchao-sharedace-anderberg-jclass-jest-kulczynski-kulczynskicody-lennon-ochiai-sorclass-sorest-whittaker-braycurtis-jabund-morisitahorn-sorabund-thetan-thetayc. \n");
219 m->mothurOut("The summary.single command uses calc=nseqs-sobs-coverage-bergerparker-chao-ace-jack-bootstrap-boneh-efron-shen-solow-shannon-npshannon-invsimpson-qstat-simpsoneven-shannoneven-heip-smithwilson. \n");
220 m->mothurOut("The classify.otu command is used to get the concensus taxonomy for otu files from cluster and phylotype commands. \n");
221 m->mothurOut("The phylo.diversity command run on the tree generated by clearcut with rarefy=T, iters=100. \n");
222 m->mothurOut("The unifrac commands are also run on the tree generated by clearcut with random=F, distance=T. \n");
223 m->mothurOut("\n\n");
225 catch(exception& e) {
226 m->errorOut(e, "PipelineCommand", "help");
231 //**********************************************************************************************************************
233 PipelineCommand::~PipelineCommand(){}
235 //**********************************************************************************************************************
237 int PipelineCommand::execute(){
239 if (abort == true) { return 0; }
241 int start = time(NULL);
243 if (pipeFilename == "") {
244 createPatsPipeline();
247 for (int i = 0; i < commands.size(); i++) {
248 m->mothurOutEndLine(); m->mothurOut("mothur > " + commands[i]); m->mothurOutEndLine();
250 if (m->control_pressed) { return 0; }
252 CommandOptionParser parser(commands[i]);
253 string commandName = parser.getCommandString();
254 string options = parser.getOptionString();
258 MPI_Comm_rank(MPI_COMM_WORLD, &pid);
260 if ((cFactory->MPIEnabled(commandName)) || (pid == 0)) {
263 //executes valid command
264 Command* command = cFactory->getCommand(commandName, options, "pipe");
267 //add output files to list
268 map<string, vector<string> > thisCommandsFile = command->getOutputFiles();
269 map<string, vector<string> >::iterator itMade;
270 for (itMade = thisCommandsFile.begin(); itMade != thisCommandsFile.end(); itMade++) {
271 vector<string> temp = itMade->second;
272 for (int j = 0; j < temp.size(); j++) { outputNames.push_back(temp[j]); }
280 }else { runUsersPipeline(); }
282 if (m->control_pressed) { return 0; }
284 m->mothurOut("It took " + toString(time(NULL) - start) + " secs to run the pipeline analysis."); m->mothurOutEndLine(); m->mothurOutEndLine();
286 m->mothurOutEndLine();
287 m->mothurOut("Output File Names: "); m->mothurOutEndLine();
288 for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); }
289 m->mothurOutEndLine();
293 catch(exception& e) {
294 m->errorOut(e, "PipelineCommand", "execute");
298 //**********************************************************************************************************************
300 bool PipelineCommand::readUsersPipeline(){
304 m->openInputFile(pipeFilename, in);
306 string nextCommand = "";
308 map<string, vector<string> > mothurMadeFiles;
311 nextCommand = m->getline(in); m->gobble(in);
313 if (nextCommand[0] != '#') {
316 string commandName, options;
317 error = parseCommand(nextCommand, commandName, options);
319 if (error) { in.close(); return error; }
320 if (commandName == "pipeline.pds") { m->mothurOut("Cannot run the pipeline.pds command from inside the pipeline.pds command."); m->mothurOutEndLine(); in.close(); return true; }
322 error = checkForValidAndRequiredParameters(commandName, options, mothurMadeFiles);
324 if (error) { in.close(); return error; }
332 catch(exception& e) {
333 m->errorOut(e, "PipelineCommand", "readUsersPipeline");
337 //**********************************************************************************************************************
339 bool PipelineCommand::parseCommand(string nextCommand, string& name, string& options){
341 CommandOptionParser parser(nextCommand);
342 name = parser.getCommandString();
343 options = parser.getOptionString();
345 if (name == "") { return true; } //name == "" if () are not right
349 catch(exception& e) {
350 m->errorOut(e, "PipelineCommand", "parseCommand");
354 //**********************************************************************************************************************
356 bool PipelineCommand::checkForValidAndRequiredParameters(string name, string options, map<string, vector<string> >& mothurMadeFiles){
359 if (name == "system") { return false; }
361 //get shell of the command so we can check to make sure its valid without running it
362 Command* command = cFactory->getCommand(name);
364 //check to make sure all parameters are valid for command
365 vector<string> validParameters = command->getValidParameters();
367 OptionParser parser(options);
368 map<string, string> parameters = parser.getParameters();
370 ValidParameters validParameter;
371 map<string, string>::iterator it;
372 map<string, vector<string> >::iterator itMade;
374 for (it = parameters.begin(); it != parameters.end(); it++) {
376 if (validParameter.isValidParameter(it->first, validParameters, it->second) != true) { return true; } // not valid
377 if (it->second == "mothurmade") {
378 itMade = mothurMadeFiles.find(it->first);
380 if (itMade == mothurMadeFiles.end()) {
381 if ((name == "align.seqs") && (it->first == "candidate")) {} //do nothing about candidate
383 m->mothurOut("You have the " + it->first + " listed as a mothurmade file for the " + name + " command, but it seems mothur will not make that file in your current pipeline, please correct."); m->mothurOutEndLine();
390 //is the command missing any required
391 vector<string> requiredParameters = command->getRequiredParameters();
396 if (requiredParameters.size() > 2) {
397 if (requiredParameters[(requiredParameters.size()-1)] == "or") { hasOr = true; }
400 for (int i = 0; i < requiredParameters.size(); i++) {
401 it = parameters.find(requiredParameters[i]);
403 if (it != parameters.end()) { numFound++; }
405 if (!hasOr) { m->mothurOut(name + " requires the " + requiredParameters[i] + " parameter, please correct."); m->mothurOutEndLine(); }
409 // if all are needed and not all are found
410 if ((!hasOr) && (numFound != requiredParameters.size())) { return true; }
411 //if one is needed and none are found
412 else if ((hasOr) && (numFound == 0)) { return true; }
415 map<string, vector<string> > thisCommandsFile = command->getOutputFiles();
416 for (itMade = thisCommandsFile.begin(); itMade != thisCommandsFile.end(); itMade++) {
417 mothurMadeFiles[itMade->first] = itMade->second; //adds any new types
422 catch(exception& e) {
423 m->errorOut(e, "PipelineCommand", "checkForValidAndRequiredParameters");
427 //**********************************************************************************************************************
428 int PipelineCommand::runUsersPipeline(){
431 m->openInputFile(pipeFilename, in);
433 string nextCommand = "";
435 map<string, vector<string> > mothurMadeFiles;
438 nextCommand = m->getline(in); m->gobble(in);
440 if (nextCommand[0] != '#') {
441 CommandOptionParser parser(nextCommand);
442 string commandName = parser.getCommandString();
443 string options = parser.getOptionString();
445 if ((options != "") && (commandName != "system")) {
446 bool error = fillInMothurMade(options, mothurMadeFiles);
447 if (error) { in.close(); return 0; }
450 m->mothurOutEndLine(); m->mothurOut("mothur > " + commandName + "(" + options + ")"); m->mothurOutEndLine();
452 if (m->control_pressed) { return 0; }
456 MPI_Comm_rank(MPI_COMM_WORLD, &pid);
458 if ((cFactory->MPIEnabled(commandName)) || (pid == 0)) {
461 //executes valid command
462 Command* command = cFactory->getCommand(commandName, options, "pipe");
465 //add output files to list
466 map<string, vector<string> > thisCommandsFile = command->getOutputFiles();
467 map<string, vector<string> >::iterator itMade;
468 map<string, vector<string> >::iterator it;
469 for (itMade = thisCommandsFile.begin(); itMade != thisCommandsFile.end(); itMade++) {
471 vector<string> temp = itMade->second;
472 for (int k = 0; k < temp.size(); k++) { outputNames.push_back(temp[k]); } //
474 //update Mothur Made for each file
475 it = mothurMadeFiles.find(itMade->first);
477 if (it == mothurMadeFiles.end()) { //new type
479 mothurMadeFiles[itMade->first] = temp;
481 }else{ //update existing type
482 vector<string> oldFileNames = it->second;
483 //look at new files, see if an old version of the file exists, if so update, else just add.
484 //for example you may have abrecovery.fasta and amazon.fasta as old files and you created a new amazon.trim.fasta.
486 for (int k = 0; k < temp.size(); k++) {
489 string root = m->getSimpleName(temp[k]);
490 string individual = "";
491 for(int i=0;i<root.length();i++){
496 individual += root[i];
500 //look for that base name in oldfiles
502 for (int l = 0; l < oldFileNames.size(); l++) {
503 int pos = oldFileNames[l].find(root);
504 if (pos != string::npos) {
510 //if you found it update it, else add it
512 mothurMadeFiles[it->first][spot] = temp[k];
514 mothurMadeFiles[it->first].push_back(temp[k]);
528 catch(exception& e) {
529 m->errorOut(e, "PipelineCommand", "runUsersPipeline");
533 //**********************************************************************************************************************
534 bool PipelineCommand::fillInMothurMade(string& options, map<string, vector<string> >& mothurMadeFiles){
537 OptionParser parser(options);
538 map<string, string> parameters = parser.getParameters();
539 map<string, string>::iterator it;
540 map<string, vector<string> >::iterator itMade;
544 //fill in mothurmade filenames
545 for (it = parameters.begin(); it != parameters.end(); it++) {
546 string paraType = it->first;
547 string tempOption = it->second;
549 if (tempOption == "mothurmade") {
551 if (it->first == "candidate") { paraType = "fasta"; }
553 itMade = mothurMadeFiles.find(paraType);
555 if (itMade == mothurMadeFiles.end()) {
556 m->mothurOut("Looking for a mothurmade " + paraType + " file, but it seems mothur has not made that file type in your current pipeline, please correct."); m->mothurOutEndLine();
559 vector<string> temp = itMade->second;
561 if (temp.size() > 1) {
562 //ask user which file to use
563 m->mothurOut("More than one file has been created for the " + paraType + " parameter. "); m->mothurOutEndLine();
564 for (int i = 0; i < temp.size(); i++) {
565 m->mothurOut(toString(i) + " - " + temp[i]); m->mothurOutEndLine();
568 m->mothurOut("Please select the number of the file you would like to use: ");
571 m->mothurOutJustToLog(toString(num)); m->mothurOutEndLine();
573 if ((num < 0) || (num > (temp.size()-1))) { m->mothurOut("Not a valid response, quitting."); m->mothurOutEndLine(); return true; }
575 tempOption = temp[num];
578 //clears buffer so next command doesn't have error
582 vector<string> newTemp;
583 for (int i = 0; i < temp.size(); i++) {
584 if (i == num) { newTemp.push_back(temp[i]); }
586 m->mothurOut("Would you like to remove " + temp[i] + " as an option for " + paraType + ", (y/n): "); m->mothurOutEndLine();
589 m->mothurOutJustToLog(response); m->mothurOutEndLine();
591 if (response == "n") { newTemp.push_back(temp[i]); }
593 //clears buffer so next command doesn't have error
599 mothurMadeFiles[paraType] = newTemp;
602 }else if (temp.size() == 0){
603 m->mothurOut("Sorry, we seem to think you created a " + paraType + " file, but it seems mothur doesn't have a filename."); m->mothurOutEndLine();
606 tempOption = temp[0];
611 options += it->first + "=" + tempOption + ", ";
614 //rip off extra comma
615 options = options.substr(0, (options.length()-2));
619 catch(exception& e) {
620 m->errorOut(e, "PipelineCommand", "fillInMothurMade");
625 //**********************************************************************************************************************
626 void PipelineCommand::createPatsPipeline(){
630 string thisCommand = "sffinfo(sff=" + sffFile + ")";
631 commands.push_back(thisCommand);
634 string fastaFile = m->getRootName(m->getSimpleName(sffFile)) + "fasta";
635 string qualFile = m->getRootName(m->getSimpleName(sffFile)) + "qual";
636 thisCommand = "trim.seqs(processors=" + toString(processors) + ", fasta=" + fastaFile + ", allfiles=T, maxambig=0, maxhomop=8, flip=T, bdiffs=1, pdiffs=2, qwindowaverage=35, qwindowsize=50, oligos=" + oligosFile + ", qfile=" + qualFile + ")";
637 commands.push_back(thisCommand);
640 string groupFile = m->getRootName(m->getSimpleName(fastaFile)) + "groups";
641 qualFile = m->getRootName(m->getSimpleName(fastaFile)) + "trim.qual";
642 fastaFile = m->getRootName(m->getSimpleName(fastaFile)) + "trim.fasta";
643 thisCommand = "unique.seqs(fasta=" + fastaFile + ")";
644 commands.push_back(thisCommand);
647 string nameFile = m->getRootName(m->getSimpleName(fastaFile)) + "names";
648 fastaFile = m->getRootName(m->getSimpleName(fastaFile)) + "unique" + m->getExtension(fastaFile);
649 thisCommand = "align.seqs(processors=" + toString(processors) + ", candidate=" + fastaFile + ", template=" + alignFile + ")";
650 commands.push_back(thisCommand);
653 fastaFile = m->getRootName(m->getSimpleName(fastaFile)) + "align";
654 thisCommand = "screen.seqs(processors=" + toString(processors) + ", fasta=" + fastaFile + ", name=" + nameFile + ", group=" + groupFile + ", optimize=end-minlength)";
655 commands.push_back(thisCommand);
658 fastaFile = m->getRootName(m->getSimpleName(fastaFile)) + "good" + m->getExtension(fastaFile);
659 nameFile = m->getRootName(m->getSimpleName(nameFile)) + "good" + m->getExtension(nameFile);
660 groupFile = m->getRootName(m->getSimpleName(groupFile)) + "good" + m->getExtension(groupFile);
661 thisCommand = "chimera.slayer(processors=" + toString(processors) + ", fasta=" + fastaFile + ", template=" + chimeraFile + ")";
662 commands.push_back(thisCommand);
665 string accnosFile = m->getRootName(m->getSimpleName(fastaFile)) + "slayer.accnos";
666 thisCommand = "remove.seqs(fasta=" + fastaFile + ", name=" + nameFile + ", group=" + groupFile + ", accnos=" + accnosFile + ", dups=T)";
667 commands.push_back(thisCommand);
670 nameFile = m->getRootName(m->getSimpleName(nameFile)) + "pick" + m->getExtension(nameFile);
671 groupFile = m->getRootName(m->getSimpleName(groupFile)) + "pick" + m->getExtension(groupFile);
672 fastaFile = m->getRootName(m->getSimpleName(fastaFile)) + "pick" + m->getExtension(fastaFile);
673 thisCommand = "filter.seqs(processors=" + toString(processors) + ", fasta=" + fastaFile + ", vertical=T, trump=.)";
674 commands.push_back(thisCommand);
677 fastaFile = m->getRootName(m->getSimpleName(fastaFile)) + "filter.fasta";
678 thisCommand = "unique.seqs(fasta=" + fastaFile + ", name=" + nameFile + ")";
679 commands.push_back(thisCommand);
682 nameFile = m->getRootName(m->getSimpleName(fastaFile)) + "names";
683 fastaFile = m->getRootName(m->getSimpleName(fastaFile)) + "unique" + m->getExtension(fastaFile);
684 thisCommand = "pre.cluster(fasta=" + fastaFile + ", name=" + nameFile + ", diffs=2)";
685 commands.push_back(thisCommand);
688 nameFile = m->getRootName(m->getSimpleName(fastaFile)) + "precluster.names";
689 fastaFile = m->getRootName(m->getSimpleName(fastaFile)) + "precluster" + m->getExtension(fastaFile);
690 thisCommand = "dist.seqs(processors=" + toString(processors) + ", fasta=" + fastaFile + ", cutoff=0.20)";
691 commands.push_back(thisCommand);
694 string columnFile = m->getRootName(m->getSimpleName(fastaFile)) + "dist";
695 thisCommand = "dist.seqs(processors=" + toString(processors) + ", fasta=" + fastaFile + ", output=lt)";
696 commands.push_back(thisCommand);
699 string phylipFile = m->getRootName(m->getSimpleName(fastaFile)) + "phylip.dist";
700 thisCommand = "read.dist(column=" + columnFile + ", name=" + nameFile + ")";
701 commands.push_back(thisCommand);
704 thisCommand = "cluster(method=average, hard=T)";
705 commands.push_back(thisCommand);
707 string listFile = m->getRootName(m->getSimpleName(columnFile)) + "an.list";
708 string rabundFile = m->getRootName(m->getSimpleName(columnFile)) + "an.rabund";
711 thisCommand = "degap.seqs(fasta=" + fastaFile + ")";
712 commands.push_back(thisCommand);
715 fastaFile = m->getRootName(m->getSimpleName(fastaFile)) + "ng.fasta";
716 thisCommand = "classify.seqs(processors=" + toString(processors) + ", fasta=" + fastaFile + ", name=" + nameFile + ", template=" + classifyFile + ", taxonomy=" + taxonomyFile + ", cutoff=80)";
717 commands.push_back(thisCommand);
719 string RippedTaxName = m->getRootName(m->getSimpleName(taxonomyFile));
720 RippedTaxName = m->getExtension(RippedTaxName.substr(0, RippedTaxName.length()-1));
721 if (RippedTaxName[0] == '.') { RippedTaxName = RippedTaxName.substr(1, RippedTaxName.length()); }
722 RippedTaxName += ".";
724 string fastaTaxFile = m->getRootName(m->getSimpleName(fastaFile)) + RippedTaxName + "taxonomy";
725 string taxSummaryFile = m->getRootName(m->getSimpleName(fastaFile)) + RippedTaxName + "tax.summary";
728 thisCommand = "phylotype(taxonomy=" + fastaTaxFile + ", name=" + nameFile + ")";
729 commands.push_back(thisCommand);
731 string phyloListFile = m->getRootName(m->getSimpleName(fastaTaxFile)) + "tx.list";
732 string phyloRabundFile = m->getRootName(m->getSimpleName(fastaTaxFile)) + "tx.rabund";
735 thisCommand = "clearcut(phylip=" + phylipFile + ", neighbor=T)";
736 commands.push_back(thisCommand);
738 string treeFile = m->getRootName(m->getSimpleName(phylipFile)) + "tre";
741 thisCommand = "read.otu(list=" + listFile + ", group=" + groupFile + ", label=0.03)";
742 commands.push_back(thisCommand);
744 string sharedFile = m->getRootName(m->getSimpleName(listFile)) + "shared";
747 thisCommand = "read.otu(list=" + phyloListFile + ", group=" + groupFile + ", label=1)";
748 commands.push_back(thisCommand);
750 string phyloSharedFile = m->getRootName(m->getSimpleName(phyloListFile)) + "shared";
753 thisCommand = "read.otu(shared=" + sharedFile + ")";
754 commands.push_back(thisCommand);
757 thisCommand = "summary.single(calc=nseqs-sobs-coverage-bergerparker-chao-ace-jack-bootstrap-boneh-efron-shen-solow-shannon-npshannon-invsimpson-qstat-simpsoneven-shannoneven-heip-smithwilson, size=5000)";
758 commands.push_back(thisCommand);
761 thisCommand = "summary.shared(calc=sharednseqs-sharedsobs-sharedchao-sharedace-anderberg-jclass-jest-kulczynski-kulczynskicody-lennon-ochiai-sorclass-sorest-whittaker-braycurtis-jabund-morisitahorn-sorabund-thetan-thetayc)";
762 commands.push_back(thisCommand);
765 thisCommand = "read.otu(rabund=" + rabundFile + ", label=0.03)";
766 commands.push_back(thisCommand);
769 thisCommand = "summary.single(calc=nseqs-sobs-coverage-bergerparker-chao-ace-jack-bootstrap-boneh-efron-shen-solow-shannon-npshannon-invsimpson-qstat-simpsoneven-shannoneven-heip-smithwilson, size=5000)";
770 commands.push_back(thisCommand);
773 thisCommand = "read.otu(shared=" + phyloSharedFile + ")";
774 commands.push_back(thisCommand);
777 thisCommand = "summary.single(calc=nseqs-sobs-coverage-bergerparker-chao-ace-jack-bootstrap-boneh-efron-shen-solow-shannon-npshannon-invsimpson-qstat-simpsoneven-shannoneven-heip-smithwilson, size=5000)";
778 commands.push_back(thisCommand);
781 thisCommand = "summary.shared(calc=sharednseqs-sharedsobs-sharedchao-sharedace-anderberg-jclass-jest-kulczynski-kulczynskicody-lennon-ochiai-sorclass-sorest-whittaker-braycurtis-jabund-morisitahorn-sorabund-thetan-thetayc)";
782 commands.push_back(thisCommand);
785 thisCommand = "read.otu(rabund=" + phyloRabundFile + ", label=1)";
786 commands.push_back(thisCommand);
789 thisCommand = "summary.single(calc=nseqs-sobs-coverage-bergerparker-chao-ace-jack-bootstrap-boneh-efron-shen-solow-shannon-npshannon-invsimpson-qstat-simpsoneven-shannoneven-heip-smithwilson, size=5000)";
790 commands.push_back(thisCommand);
793 thisCommand = "classify.otu(taxonomy=" + fastaTaxFile + ", name=" + nameFile + ", list=" + listFile + ", cutoff=51, label=0.03)";
794 commands.push_back(thisCommand);
797 thisCommand = "classify.otu(taxonomy=" + fastaTaxFile + ", name=" + nameFile + ", list=" + phyloListFile + ", cutoff=51, label=1)";
798 commands.push_back(thisCommand);
801 thisCommand = "read.tree(tree=" + treeFile + ", name=" + nameFile + ", group=" + groupFile + ")";
802 commands.push_back(thisCommand);
805 thisCommand = "phylo.diversity(iters=100,rarefy=T)";
806 commands.push_back(thisCommand);
809 thisCommand = "unifrac.weighted(random=false, distance=true, groups=all, processors=" + toString(processors) + ")";
810 commands.push_back(thisCommand);
813 thisCommand = "unifrac.unweighted(random=false, distance=true, processors=" + toString(processors) + ")";
814 commands.push_back(thisCommand);
818 catch(exception& e) {
819 m->errorOut(e, "PipelineCommand", "createPatsPipeline");
824 //**********************************************************************************************************************