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 //***************************************************************************************************************
16 ChimeraSeqsCommand::ChimeraSeqsCommand(string option){
20 //allow user to run help
21 if(option == "help") { help(); abort = true; }
24 //valid paramters for this command
25 string Array[] = {"fasta", "filter", "correction", "processors", "method", "window", "increment", "template", "conservation", "quantile", "mask" };
26 vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
28 OptionParser parser(option);
29 map<string,string> parameters = parser.getParameters();
31 ValidParameters validParameter;
33 //check to make sure all parameters are valid for command
34 for (map<string,string>::iterator it = parameters.begin(); it != parameters.end(); it++) {
35 if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; }
38 //check for required parameters
39 fastafile = validParameter.validFile(parameters, "fasta", true);
40 if (fastafile == "not open") { abort = true; }
41 else if (fastafile == "not found") { fastafile = ""; mothurOut("fasta is a required parameter for the chimera.seqs command."); mothurOutEndLine(); abort = true; }
43 templatefile = validParameter.validFile(parameters, "template", true);
44 if (templatefile == "not open") { abort = true; }
45 else if (templatefile == "not found") { templatefile = ""; }
47 consfile = validParameter.validFile(parameters, "conservation", true);
48 if (consfile == "not open") { abort = true; }
49 else if (consfile == "not found") { consfile = ""; }
51 quanfile = validParameter.validFile(parameters, "quantile", true);
52 if (quanfile == "not open") { abort = true; }
53 else if (quanfile == "not found") { quanfile = ""; }
55 maskfile = validParameter.validFile(parameters, "mask", false);
56 if (maskfile == "not found") { maskfile = ""; }
57 else if (maskfile != "default") {
59 int ableToOpen = openInputFile(maskfile, in);
60 if (ableToOpen == 1) { abort = true; }
68 temp = validParameter.validFile(parameters, "filter", false); if (temp == "not found") { temp = "F"; }
69 filter = isTrue(temp);
71 temp = validParameter.validFile(parameters, "correction", false); if (temp == "not found") { temp = "T"; }
72 correction = isTrue(temp);
74 temp = validParameter.validFile(parameters, "processors", false); if (temp == "not found") { temp = "1"; }
75 convert(temp, processors);
77 temp = validParameter.validFile(parameters, "window", false); if (temp == "not found") { temp = "0"; }
78 convert(temp, window);
80 temp = validParameter.validFile(parameters, "increment", false); if (temp == "not found") { temp = "25"; }
81 convert(temp, increment);
83 method = validParameter.validFile(parameters, "method", false); if (method == "not found") { method = "pintail"; }
85 if ((method == "pintail") && (templatefile == "")) { mothurOut("You must provide a template file with the pintail method."); mothurOutEndLine(); abort = true; }
91 errorOut(e, "ChimeraSeqsCommand", "ChimeraSeqsCommand");
95 //**********************************************************************************************************************
97 void ChimeraSeqsCommand::help(){
99 mothurOut("chimera.seqs ASSUMES that your sequences are ALIGNED.\n");
100 mothurOut("The chimera.seqs command reads a fastafile and creates a sorted priority score list of potentially chimeric sequences (ideally, the sequences should already be aligned).\n");
101 mothurOut("The chimera.seqs command parameters are fasta, filter, correction, processors, mask, method, window, increment, template, conservation and quantile.\n");
102 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");
103 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");
104 mothurOut("The processors parameter allows you to specify how many processors you would like to use. The default is 1. \n");
105 mothurOut("The method parameter allows you to specify the method for finding chimeric sequences. The default is pintail. Options include..... \n");
106 mothurOut("The mask parameter allows you to specify a file containing one sequence you wish to use as a mask for the pintail and mallard method. The default is no mask. If you enter mask=default, then the mask is 236627 EU009184.1 Shigella dysenteriae str. FBD013. \n");
107 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");
108 mothurOut("The increment parameter allows you to specify how far you move each window while finding chimeric sequences. The default is 25.\n");
109 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");
110 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");
111 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");
112 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.");
113 mothurOut("The chimera.seqs command should be in the following format: \n");
114 mothurOut("chimera.seqs(fasta=yourFastaFile, filter=yourFilter, correction=yourCorrection, processors=yourProcessors, method=bellerophon) \n");
115 mothurOut("Example: chimera.seqs(fasta=AD.align, filter=True, correction=true, processors=2, method=yourMethod) \n");
116 mothurOut("Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFastaFile).\n\n");
118 catch(exception& e) {
119 errorOut(e, "ChimeraSeqsCommand", "help");
124 //***************************************************************************************************************
126 ChimeraSeqsCommand::~ChimeraSeqsCommand(){ /* do nothing */ }
128 //***************************************************************************************************************
130 int ChimeraSeqsCommand::execute(){
133 if (abort == true) { return 0; }
135 if (method == "bellerophon") { chimera = new Bellerophon(fastafile); }
136 else if (method == "pintail") { chimera = new Pintail(fastafile, templatefile);
137 //saves time to avoid generating it
138 if (consfile != "") { chimera->setCons(consfile); }
139 else { chimera->setCons(""); }
141 //saves time to avoid generating it
142 if (quanfile != "") { chimera->setQuantiles(quanfile); }
143 else { chimera->setQuantiles(""); }
145 if (maskfile == "default") { mothurOut("I am using the default 236627 EU009184.1 Shigella dysenteriae str. FBD013."); mothurOutEndLine(); }
146 chimera->setMask(maskfile);
148 }else { mothurOut("Not a valid method."); mothurOutEndLine(); return 0; }
151 chimera->setFilter(filter);
152 chimera->setCorrection(correction);
153 chimera->setProcessors(processors);
154 chimera->setWindow(window);
155 chimera->setIncrement(increment);
158 chimera->getChimeras();
160 string outputFileName = getRootName(fastafile) + method + maskfile + ".chimeras";
162 openOutputFile(outputFileName, out);
174 catch(exception& e) {
175 errorOut(e, "ChimeraSeqsCommand", "execute");
179 /**************************************************************************************************/