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"
15 //***************************************************************************************************************
17 ChimeraSeqsCommand::ChimeraSeqsCommand(string option){
21 //allow user to run help
22 if(option == "help") { help(); abort = true; }
25 //valid paramters for this command
26 string Array[] = {"fasta", "filter", "correction", "processors", "method", "window", "increment", "template", "conservation", "quantile", "mask" };
27 vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
29 OptionParser parser(option);
30 map<string,string> parameters = parser.getParameters();
32 ValidParameters validParameter;
34 //check to make sure all parameters are valid for command
35 for (map<string,string>::iterator it = parameters.begin(); it != parameters.end(); it++) {
36 if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; }
39 //check for required parameters
40 fastafile = validParameter.validFile(parameters, "fasta", true);
41 if (fastafile == "not open") { abort = true; }
42 else if (fastafile == "not found") { fastafile = ""; mothurOut("fasta is a required parameter for the chimera.seqs command."); mothurOutEndLine(); abort = true; }
44 templatefile = validParameter.validFile(parameters, "template", true);
45 if (templatefile == "not open") { abort = true; }
46 else if (templatefile == "not found") { templatefile = ""; }
48 consfile = validParameter.validFile(parameters, "conservation", true);
49 if (consfile == "not open") { abort = true; }
50 else if (consfile == "not found") { consfile = ""; }
52 quanfile = validParameter.validFile(parameters, "quantile", true);
53 if (quanfile == "not open") { abort = true; }
54 else if (quanfile == "not found") { quanfile = ""; }
56 maskfile = validParameter.validFile(parameters, "mask", false);
57 if (maskfile == "not found") { maskfile = ""; }
58 else if (maskfile != "default") {
60 int ableToOpen = openInputFile(maskfile, in);
61 if (ableToOpen == 1) { abort = true; }
69 temp = validParameter.validFile(parameters, "filter", false); if (temp == "not found") { temp = "F"; }
70 filter = isTrue(temp);
72 temp = validParameter.validFile(parameters, "correction", false); if (temp == "not found") { temp = "T"; }
73 correction = isTrue(temp);
75 temp = validParameter.validFile(parameters, "processors", false); if (temp == "not found") { temp = "1"; }
76 convert(temp, processors);
78 temp = validParameter.validFile(parameters, "window", false); if (temp == "not found") { temp = "0"; }
79 convert(temp, window);
81 temp = validParameter.validFile(parameters, "increment", false); if (temp == "not found") { temp = "25"; }
82 convert(temp, increment);
84 method = validParameter.validFile(parameters, "method", false); if (method == "not found") { method = "pintail"; }
86 if ((method == "pintail") && (templatefile == "")) { mothurOut("You must provide a template file with the pintail method."); mothurOutEndLine(); abort = true; }
92 errorOut(e, "ChimeraSeqsCommand", "ChimeraSeqsCommand");
96 //**********************************************************************************************************************
98 void ChimeraSeqsCommand::help(){
100 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");
101 mothurOut("The chimera.seqs command reads a fastafile and creates list of potentially chimeric sequences.\n");
102 mothurOut("The chimera.seqs command parameters are fasta, filter, correction, processors, mask, method, window, increment, template, conservation and quantile.\n");
103 mothurOut("The fasta parameter is always required and template is required if using pintail.\n");
104 mothurOut("The filter parameter allows you to specify if you would like to apply a 50% soft filter this only applies when the method is bellerphon. The default is false. \n");
105 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. The default is true. This only applies when the method is bellerphon.\n");
106 mothurOut("The processors parameter allows you to specify how many processors you would like to use. The default is 1. \n");
107 mothurOut("The method parameter allows you to specify the method for finding chimeric sequences. The default is pintail. Options include..... \n");
108 mothurOut("The mask parameter allows you to specify a file containing one sequence you wish to use as a mask for the pintail. The default is no mask. If you enter mask=default, then the mask is 236627 EU009184.1 Shigella dysenteriae str. FBD013. \n");
109 mothurOut("The window parameter allows you to specify the window size for searching for chimeras. The default is 300 is method is pintail unless the sequence length is less than 300, and 1/4 sequence length for bellerphon.\n");
110 mothurOut("The increment parameter allows you to specify how far you move each window while finding chimeric sequences. The default is 25.\n");
111 mothurOut("The template parameter allows you to enter a template file containing known non-chimeric sequences for use by the pintail algorythm. It is a required parameter if using pintail.\n");
112 mothurOut("The conservation parameter allows you to enter a frequency file containing the highest bases frequency at each place in the alignment for use by the pintail algorythm. It is not required, but will speed up the pintail method.\n");
113 mothurOut("The quantile parameter allows you to enter a file containing quantiles for a template files sequences for use by the pintail algorythm. It is not required, but will speed up the pintail method.\n");
114 mothurOut("If you have run chimera.seqs using pintail a .quan and .freq file will be created if you have not provided them for use in future command executions.");
115 mothurOut("The chimera.seqs command should be in the following format: \n");
116 mothurOut("chimera.seqs(fasta=yourFastaFile, filter=yourFilter, correction=yourCorrection, processors=yourProcessors, method=bellerophon) \n");
117 mothurOut("Example: chimera.seqs(fasta=AD.align, filter=True, correction=true, processors=2, method=yourMethod) \n");
118 mothurOut("Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFastaFile).\n\n");
120 catch(exception& e) {
121 errorOut(e, "ChimeraSeqsCommand", "help");
126 //***************************************************************************************************************
128 ChimeraSeqsCommand::~ChimeraSeqsCommand(){ /* do nothing */ }
130 //***************************************************************************************************************
132 int ChimeraSeqsCommand::execute(){
135 if (abort == true) { return 0; }
137 if (method == "bellerophon") { chimera = new Bellerophon(fastafile); }
138 else if (method == "pintail") { chimera = new Pintail(fastafile, templatefile); }
139 else { mothurOut("Not a valid method."); mothurOutEndLine(); return 0; }
142 if (maskfile == "default") { mothurOut("I am using the default 236627 EU009184.1 Shigella dysenteriae str. FBD013."); mothurOutEndLine(); }
144 //saves time to avoid generating it
145 if (consfile != "") { chimera->setCons(consfile); }
146 else { chimera->setCons(""); }
148 //saves time to avoid generating it
149 if (quanfile != "") { chimera->setQuantiles(quanfile); }
150 else { chimera->setQuantiles(""); }
152 chimera->setMask(maskfile);
153 chimera->setFilter(filter);
154 chimera->setCorrection(correction);
155 chimera->setProcessors(processors);
156 chimera->setWindow(window);
157 chimera->setIncrement(increment);
160 chimera->getChimeras();
162 string outputFileName = getRootName(fastafile) + method + maskfile + ".chimeras";
164 openOutputFile(outputFileName, out);
176 catch(exception& e) {
177 errorOut(e, "ChimeraSeqsCommand", "execute");
181 /**************************************************************************************************/