2 * chimeraseqscommand.cpp
5 * Created by Sarah Westcott on 6/29/09.
6 * Copyright 2009 Schloss Lab UMASS Amherst. All rights reserved.
10 #include "chimeraseqscommand.h"
11 #include "bellerophon.h"
14 #include "chimeracheckrdp.h"
17 //***************************************************************************************************************
19 ChimeraSeqsCommand::ChimeraSeqsCommand(string option){
23 //allow user to run help
24 if(option == "help") { help(); abort = true; }
27 //valid paramters for this command
28 string Array[] = {"fasta", "filter", "correction", "processors", "method", "window", "increment", "template", "conservation", "quantile", "mask", "numwanted", "ksize", "svg", "name" };
29 vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
31 OptionParser parser(option);
32 map<string,string> parameters = parser.getParameters();
34 ValidParameters validParameter;
36 //check to make sure all parameters are valid for command
37 for (map<string,string>::iterator it = parameters.begin(); it != parameters.end(); it++) {
38 if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; }
41 //check for required parameters
42 fastafile = validParameter.validFile(parameters, "fasta", true);
43 if (fastafile == "not open") { abort = true; }
44 else if (fastafile == "not found") { fastafile = ""; mothurOut("fasta is a required parameter for the chimera.seqs command."); mothurOutEndLine(); abort = true; }
46 templatefile = validParameter.validFile(parameters, "template", true);
47 if (templatefile == "not open") { abort = true; }
48 else if (templatefile == "not found") { templatefile = ""; }
50 consfile = validParameter.validFile(parameters, "conservation", true);
51 if (consfile == "not open") { abort = true; }
52 else if (consfile == "not found") { consfile = ""; }
54 quanfile = validParameter.validFile(parameters, "quantile", true);
55 if (quanfile == "not open") { abort = true; }
56 else if (quanfile == "not found") { quanfile = ""; }
58 namefile = validParameter.validFile(parameters, "name", true);
59 if (namefile == "not open") { abort = true; }
60 else if (namefile == "not found") { namefile = ""; }
62 maskfile = validParameter.validFile(parameters, "mask", false);
63 if (maskfile == "not found") { maskfile = ""; }
64 else if (maskfile != "default") {
66 int ableToOpen = openInputFile(maskfile, in);
67 if (ableToOpen == 1) { abort = true; }
71 method = validParameter.validFile(parameters, "method", false); if (method == "not found") { method = "pintail"; }
74 temp = validParameter.validFile(parameters, "filter", false); if (temp == "not found") { temp = "F"; }
75 filter = isTrue(temp);
77 temp = validParameter.validFile(parameters, "correction", false); if (temp == "not found") { temp = "T"; }
78 correction = isTrue(temp);
80 temp = validParameter.validFile(parameters, "processors", false); if (temp == "not found") { temp = "1"; }
81 convert(temp, processors);
83 temp = validParameter.validFile(parameters, "ksize", false); if (temp == "not found") { temp = "7"; }
86 temp = validParameter.validFile(parameters, "svg", false); if (temp == "not found") { temp = "F"; }
89 temp = validParameter.validFile(parameters, "window", false); if (temp == "not found") { temp = "0"; }
90 convert(temp, window);
92 temp = validParameter.validFile(parameters, "increment", false);
93 if ((temp == "not found") && (method == "chimeracheck")) { temp = "10"; }
94 else if (temp == "not found") { temp = "25"; }
95 convert(temp, increment);
97 temp = validParameter.validFile(parameters, "numwanted", false); if (temp == "not found") { temp = "20"; }
98 convert(temp, numwanted);
102 if (((method != "bellerophon")) && (templatefile == "")) { mothurOut("You must provide a template file with the pintail, ccode or chimeracheck methods."); mothurOutEndLine(); abort = true; }
107 catch(exception& e) {
108 errorOut(e, "ChimeraSeqsCommand", "ChimeraSeqsCommand");
112 //**********************************************************************************************************************
114 void ChimeraSeqsCommand::help(){
117 //"fasta", "filter", "correction", "processors", "method", "window", "increment", "template", "conservation", "quantile", "mask", "numwanted", "ksize", "svg", "name"
118 //mothurOut("chimera.seqs ASSUMES that your sequences are ALIGNED and if using a template that the template file sequences are the same length as the fasta file sequences.\n\n");
119 mothurOut("The chimera.seqs command reads a fastafile and creates list of potentially chimeric sequences.\n");
120 mothurOut("The chimera.seqs command parameters are fasta, filter, correction, processors, mask, method, window, increment, template, conservation, quantile, numwanted, ksize, svg, name.\n");
121 mothurOut("The fasta parameter is always required and template is required if using pintail, ccode or chimeracheck.\n");
122 mothurOut("The filter parameter allows you to specify if you would like to apply a vertical and 50% soft filter. \n");
123 mothurOut("The correction parameter allows you to put more emphasis on the distance between highly similar sequences and less emphasis on the differences between remote homologs.\n");
124 mothurOut("The processors parameter allows you to specify how many processors you would like to use. The default is 1. \n");
125 mothurOut("The method parameter allows you to specify the method for finding chimeric sequences. The default is pintail. Options include bellerophon, ccode and chimeracheck \n");
126 mothurOut("The mask parameter allows you to specify a file containing one sequence you wish to use as a mask for the your sequences. \n");
127 mothurOut("The window parameter allows you to specify the window size for searching for chimeras. \n");
128 mothurOut("The increment parameter allows you to specify how far you move each window while finding chimeric sequences.\n");
129 mothurOut("The template parameter allows you to enter a template file containing known non-chimeric sequences. \n");
130 mothurOut("The conservation parameter allows you to enter a frequency file containing the highest bases frequency at each place in the alignment.\n");
131 mothurOut("The quantile parameter allows you to enter a file containing quantiles for a template files sequences.\n");
132 mothurOut("The numwanted parameter allows you to specify how many sequences you would each query sequence compared with.\n");
133 mothurOut("The ksize parameter allows you to input kmersize. \n");
134 mothurOut("The svg parameter allows you to specify whether or not you would like a svg file outputted for each query sequence.\n");
135 mothurOut("The name parameter allows you to enter a file containing names of sequences you would like .svg files for.\n");
136 mothurOut("NOT ALL PARAMETERS ARE USED BY ALL METHODS. Please look below for method specifics.\n\n");
137 mothurOut("Details for each method: \n");
138 mothurOut("\tpintail: \n");
139 mothurOut("\t\tparameters: fasta=required, template=required, filter=F, mask=no mask, processors=1, window=300, increment=25, conservation=not required, but will improve speed, quantile=not required, but will greatly improve speed. \n");
140 mothurOut("\t\tIf you have run chimera.seqs using pintail a .quan and .freq file will be created for your template, if you have not provided them for use in future command executions.\n");
141 mothurOut("\tbellerophon: \n");
142 mothurOut("\t\tparameters: fasta=required, filter=F, processors=1, window=1/4 length of seq, increment=25, correction=T. \n");
143 mothurOut("\tccode: \n");
144 mothurOut("\t\tparameters: fasta=required, template=required, filter=F, mask=no mask, processors=1, window=10% of length, numwanted=20\n");
145 mothurOut("\tchimeracheck: \n");
146 mothurOut("\t\tparameters: fasta=required, template=required, processors=1, increment=10, ksize=7, svg=F, name=none\n\n");
147 mothurOut("The chimera.seqs command should be in the following format: \n");
148 mothurOut("chimera.seqs(fasta=yourFastaFile, filter=yourFilter, correction=yourCorrection, processors=yourProcessors, method=bellerophon) \n");
149 mothurOut("Example: chimera.seqs(fasta=AD.align, filter=True, correction=true, method=bellerophon, window=200) \n");
150 mothurOut("Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFastaFile).\n\n");
152 catch(exception& e) {
153 errorOut(e, "ChimeraSeqsCommand", "help");
158 //***************************************************************************************************************
160 ChimeraSeqsCommand::~ChimeraSeqsCommand(){ /* do nothing */ }
162 //***************************************************************************************************************
164 int ChimeraSeqsCommand::execute(){
167 if (abort == true) { return 0; }
169 if (method == "bellerophon") { chimera = new Bellerophon(fastafile); }
170 else if (method == "pintail") { chimera = new Pintail(fastafile, templatefile); }
171 else if (method == "ccode") { chimera = new Ccode(fastafile, templatefile); }
172 else if (method == "chimeracheck") { chimera = new ChimeraCheckRDP(fastafile, templatefile); }
173 else { mothurOut("Not a valid method."); mothurOutEndLine(); return 0; }
176 if (maskfile == "default") { mothurOut("I am using the default 236627 EU009184.1 Shigella dysenteriae str. FBD013."); mothurOutEndLine(); }
178 //saves time to avoid generating it
179 chimera->setCons(consfile);
181 //saves time to avoid generating it
182 chimera->setQuantiles(quanfile);
184 chimera->setMask(maskfile);
185 chimera->setFilter(filter);
186 chimera->setCorrection(correction);
187 chimera->setProcessors(processors);
188 chimera->setWindow(window);
189 chimera->setIncrement(increment);
190 chimera->setNumWanted(numwanted);
191 chimera->setKmerSize(ksize);
192 chimera->setSVG(svg);
193 chimera->setName(namefile);
196 chimera->getChimeras();
198 string outputFileName = getRootName(fastafile) + method + maskfile + ".chimeras";
200 openOutputFile(outputFileName, out);
212 catch(exception& e) {
213 errorOut(e, "ChimeraSeqsCommand", "execute");
217 /**************************************************************************************************/