2 * secondarystructurecommand.cpp
5 * Created by westcott on 9/18/09.
6 * Copyright 2009 Schloss Lab. All rights reserved.
10 #include "secondarystructurecommand.h"
11 #include "sequence.hpp"
13 //**********************************************************************************************************************
14 vector<string> AlignCheckCommand::setParameters(){
16 CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(pfasta);
17 CommandParameter pmap("map", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(pmap);
18 CommandParameter pinputdir("inputdir", "String", "", "", "", "", "",false,false); parameters.push_back(pinputdir);
19 CommandParameter poutputdir("outputdir", "String", "", "", "", "", "",false,false); parameters.push_back(poutputdir);
21 vector<string> myArray;
22 for (int i = 0; i < parameters.size(); i++) { myArray.push_back(parameters[i].name); }
26 m->errorOut(e, "AlignCheckCommand", "setParameters");
30 //**********************************************************************************************************************
31 string AlignCheckCommand::getHelpString(){
33 string helpString = "";
34 helpString += "The align.check command reads a fasta file and map file.\n";
35 helpString += "It outputs a file containing the secondary structure matches in the .align.check file.\n";
36 helpString += "The align.check command parameters are fasta and map, both are required.\n";
37 helpString += "The align.check command should be in the following format: align.check(fasta=yourFasta, map=yourMap).\n";
38 helpString += "Example align.check(map=silva.ss.map, fasta=amazon.fasta).\n";
39 helpString += "Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n";
43 m->errorOut(e, "AlignCheckCommand", "getHelpString");
47 //**********************************************************************************************************************
48 AlignCheckCommand::AlignCheckCommand(){
50 abort = true; calledHelp = true;
52 vector<string> tempOutNames;
53 outputTypes["aligncheck"] = tempOutNames;
56 m->errorOut(e, "AlignCheckCommand", "AlignCheckCommand");
60 //**********************************************************************************************************************
62 AlignCheckCommand::AlignCheckCommand(string option) {
64 abort = false; calledHelp = false;
67 //allow user to run help
68 if(option == "help") { help(); abort = true; calledHelp = true; }
69 else if(option == "citation") { citation(); abort = true; calledHelp = true;}
72 vector<string> myArray = setParameters();
74 OptionParser parser(option);
75 map<string,string> parameters = parser.getParameters();
77 ValidParameters validParameter;
78 map<string,string>::iterator it;
80 //check to make sure all parameters are valid for command
81 for (it = parameters.begin(); it != parameters.end(); it++) {
82 if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; }
85 //initialize outputTypes
86 vector<string> tempOutNames;
87 outputTypes["aligncheck"] = tempOutNames;
89 //if the user changes the input directory command factory will send this info to us in the output parameter
90 string inputDir = validParameter.validFile(parameters, "inputdir", false);
91 if (inputDir == "not found"){ inputDir = ""; }
94 it = parameters.find("fasta");
95 //user has given a template file
96 if(it != parameters.end()){
97 path = m->hasPath(it->second);
98 //if the user has not given a path then, add inputdir. else leave path alone.
99 if (path == "") { parameters["fasta"] = inputDir + it->second; }
102 it = parameters.find("map");
103 //user has given a template file
104 if(it != parameters.end()){
105 path = m->hasPath(it->second);
106 //if the user has not given a path then, add inputdir. else leave path alone.
107 if (path == "") { parameters["map"] = inputDir + it->second; }
110 it = parameters.find("name");
111 //user has given a template file
112 if(it != parameters.end()){
113 path = m->hasPath(it->second);
114 //if the user has not given a path then, add inputdir. else leave path alone.
115 if (path == "") { parameters["name"] = inputDir + it->second; }
119 //check for required parameters
120 mapfile = validParameter.validFile(parameters, "map", true);
121 if (mapfile == "not open") { abort = true; }
122 else if (mapfile == "not found") { mapfile = ""; m->mothurOut("You must provide an map file."); m->mothurOutEndLine(); abort = true; }
124 fastafile = validParameter.validFile(parameters, "fasta", true);
125 if (fastafile == "not open") { abort = true; }
126 else if (fastafile == "not found") {
127 fastafile = m->getFastaFile();
128 if (fastafile != "") { m->mothurOut("Using " + fastafile + " as input file for the fasta parameter."); m->mothurOutEndLine(); }
129 else { m->mothurOut("You have no current fastafile and the fasta parameter is required."); m->mothurOutEndLine(); abort = true; }
130 }else { m->setFastaFile(fastafile); }
132 namefile = validParameter.validFile(parameters, "name", true);
133 if (namefile == "not open") { namefile = ""; abort = true; }
134 else if (namefile == "not found") { namefile = ""; }
135 else { m->setNameFile(namefile); }
137 //if the user changes the output directory command factory will send this info to us in the output parameter
138 outputDir = validParameter.validFile(parameters, "outputdir", false); if (outputDir == "not found"){
140 outputDir += m->hasPath(fastafile); //if user entered a file with a path then preserve it
146 catch(exception& e) {
147 m->errorOut(e, "AlignCheckCommand", "AlignCheckCommand");
151 //**********************************************************************************************************************
153 int AlignCheckCommand::execute(){
156 if (abort == true) { if (calledHelp) { return 0; } return 2; }
158 //get secondary structure info.
161 if (namefile != "") { nameMap = m->readNames(namefile); }
163 if (m->control_pressed) { return 0; }
166 m->openInputFile(fastafile, in);
169 string outfile = outputDir + m->getRootName(m->getSimpleName(fastafile)) + "align.check";
170 m->openOutputFile(outfile, out);
173 out << "name" << '\t' << "pound" << '\t' << "dash" << '\t' << "plus" << '\t' << "equal" << '\t';
174 out << "loop" << '\t' << "tilde" << '\t' << "total" << '\t' << "numseqs" << endl;
186 if (m->control_pressed) { in.close(); out.close(); remove(outfile.c_str()); return 0; }
188 Sequence seq(in); m->gobble(in);
189 if (seq.getName() != "") {
190 statData data = getStats(seq.getAligned());
192 if (haderror == 1) { m->control_pressed = true; break; }
195 if (namefile != "") {
196 //make sure this sequence is in the namefile, else error
197 map<string, int>::iterator it = nameMap.find(seq.getName());
199 if (it == nameMap.end()) { m->mothurOut("[ERROR]: " + seq.getName() + " is not in your namefile, please correct."); m->mothurOutEndLine(); m->control_pressed = true; }
200 else { num = it->second; }
203 //for each sequence this sequence represents
204 for (int i = 0; i < num; i++) {
205 pound.push_back(data.pound);
206 dash.push_back(data.dash);
207 plus.push_back(data.plus);
208 equal.push_back(data.equal);
209 loop.push_back(data.loop);
210 tilde.push_back(data.tilde);
211 total.push_back(data.total);
215 out << seq.getName() << '\t' << data.pound << '\t' << data.dash << '\t' << data.plus << '\t' << data.equal << '\t';
216 out << data.loop << '\t' << data.tilde << '\t' << data.total << '\t' << num << endl;
223 if (m->control_pressed) { remove(outfile.c_str()); return 0; }
225 sort(pound.begin(), pound.end());
226 sort(dash.begin(), dash.end());
227 sort(plus.begin(), plus.end());
228 sort(equal.begin(), equal.end());
229 sort(loop.begin(), loop.end());
230 sort(tilde.begin(), tilde.end());
231 sort(total.begin(), total.end());
232 int size = pound.size();
234 int ptile0_25 = int(size * 0.025);
235 int ptile25 = int(size * 0.250);
236 int ptile50 = int(size * 0.500);
237 int ptile75 = int(size * 0.750);
238 int ptile97_5 = int(size * 0.975);
239 int ptile100 = size - 1;
241 if (m->control_pressed) { remove(outfile.c_str()); return 0; }
243 m->mothurOutEndLine();
244 m->mothurOut("\t\tPound\tDash\tPlus\tEqual\tLoop\tTilde\tTotal"); m->mothurOutEndLine();
245 m->mothurOut("Minimum:\t" + toString(pound[0]) + "\t" + toString(dash[0]) + "\t" + toString(plus[0]) + "\t" + toString(equal[0]) + "\t" + toString(loop[0]) + "\t" + toString(tilde[0]) + "\t" + toString(total[0])); m->mothurOutEndLine();
246 m->mothurOut("2.5%-tile:\t" + toString(pound[ptile0_25]) + "\t" + toString(dash[ptile0_25]) + "\t" + toString(plus[ptile0_25]) + "\t" + toString(equal[ptile0_25]) + "\t"+ toString(loop[ptile0_25]) + "\t"+ toString(tilde[ptile0_25]) + "\t"+ toString(total[ptile0_25])); m->mothurOutEndLine();
247 m->mothurOut("25%-tile:\t" + toString(pound[ptile25]) + "\t" + toString(dash[ptile25]) + "\t" + toString(plus[ptile25]) + "\t" + toString(equal[ptile25]) + "\t" + toString(loop[ptile25]) + "\t" + toString(tilde[ptile25]) + "\t" + toString(total[ptile25])); m->mothurOutEndLine();
248 m->mothurOut("Median: \t" + toString(pound[ptile50]) + "\t" + toString(dash[ptile50]) + "\t" + toString(plus[ptile50]) + "\t" + toString(equal[ptile50]) + "\t" + toString(loop[ptile50]) + "\t" + toString(tilde[ptile50]) + "\t" + toString(total[ptile50])); m->mothurOutEndLine();
249 m->mothurOut("75%-tile:\t" + toString(pound[ptile75]) + "\t" + toString(dash[ptile75]) + "\t" + toString(plus[ptile75]) + "\t" + toString(equal[ptile75]) + "\t" + toString(loop[ptile75]) + "\t" + toString(tilde[ptile75]) + "\t" + toString(total[ptile75])); m->mothurOutEndLine();
250 m->mothurOut("97.5%-tile:\t" + toString(pound[ptile97_5]) + "\t" + toString(dash[ptile97_5]) + "\t" + toString(plus[ptile97_5]) + "\t" + toString(equal[ptile97_5]) + "\t" + toString(loop[ptile97_5]) + "\t" + toString(tilde[ptile97_5]) + "\t" + toString(total[ptile97_5])); m->mothurOutEndLine();
251 m->mothurOut("Maximum:\t" + toString(pound[ptile100]) + "\t" + toString(dash[ptile100]) + "\t" + toString(plus[ptile100]) + "\t" + toString(equal[ptile100]) + "\t" + toString(loop[ptile100]) + "\t" + toString(tilde[ptile100]) + "\t" + toString(total[ptile100])); m->mothurOutEndLine();
252 if (namefile == "") { m->mothurOut("# of Seqs:\t" + toString(count)); m->mothurOutEndLine(); }
253 else { m->mothurOut("# of unique seqs:\t" + toString(count)); m->mothurOutEndLine(); m->mothurOut("total # of seqs:\t" + toString(size)); m->mothurOutEndLine(); }
256 m->mothurOutEndLine();
257 m->mothurOut("Output File Name: "); m->mothurOutEndLine();
258 m->mothurOut(outfile); m->mothurOutEndLine(); outputNames.push_back(outfile); outputTypes["aligncheck"].push_back(outfile);
259 m->mothurOutEndLine();
264 catch(exception& e) {
265 m->errorOut(e, "AlignCheckCommand", "execute");
269 //**********************************************************************************************************************
270 void AlignCheckCommand::readMap(){
273 structMap.resize(1, 0);
276 m->openInputFile(mapfile, in);
281 structMap.push_back(position);
286 seqLength = structMap.size();
289 //check you make sure is structMap[10] = 380 then structMap[380] = 10.
290 for(int i=0;i<seqLength;i++){
291 if(structMap[i] != 0){
292 if(structMap[structMap[i]] != i){
293 m->mothurOut("Your map file contains an error: line " + toString(i) + " does not match line " + toString(structMap[i]) + "."); m->mothurOutEndLine();
300 catch(exception& e) {
301 m->errorOut(e, "AlignCheckCommand", "readMap");
305 /**************************************************************************************************/
307 statData AlignCheckCommand::getStats(string sequence){
311 sequence = "*" + sequence; // need to pad the sequence so we can index it by 1
313 int length = sequence.length();
315 if (length != seqLength) { m->mothurOut("your sequences are " + toString(length) + " long, but your map file only contains " + toString(seqLength) + " entries. please correct."); m->mothurOutEndLine(); haderror = 1; return data; }
317 for(int i=1;i<length;i++){
318 if(structMap[i] != 0){
319 if(sequence[i] == 'A'){
320 if(sequence[structMap[i]] == 'T') { data.tilde++; }
321 else if(sequence[structMap[i]] == 'A') { data.pound++; }
322 else if(sequence[structMap[i]] == 'G') { data.equal++; }
323 else if(sequence[structMap[i]] == 'C') { data.pound++; }
324 else if(sequence[structMap[i]] == '-') { data.pound++; }
327 else if(sequence[i] == 'T'){
328 if(sequence[structMap[i]] == 'T') { data.plus++; }
329 else if(sequence[structMap[i]] == 'A') { data.tilde++; }
330 else if(sequence[structMap[i]] == 'G') { data.dash++; }
331 else if(sequence[structMap[i]] == 'C') { data.pound++; }
332 else if(sequence[structMap[i]] == '-') { data.pound++; }
335 else if(sequence[i] == 'G'){
336 if(sequence[structMap[i]] == 'T') { data.dash++; }
337 else if(sequence[structMap[i]] == 'A') { data.equal++; }
338 else if(sequence[structMap[i]] == 'G') { data.pound++; }
339 else if(sequence[structMap[i]] == 'C') { data.tilde++; }
340 else if(sequence[structMap[i]] == '-') { data.pound++; }
343 else if(sequence[i] == 'C'){
344 if(sequence[structMap[i]] == 'T') { data.pound++; }
345 else if(sequence[structMap[i]] == 'A') { data.pound++; }
346 else if(sequence[structMap[i]] == 'G') { data.tilde++; }
347 else if(sequence[structMap[i]] == 'C') { data.pound++; }
348 else if(sequence[structMap[i]] == '-') { data.pound++; }
351 else if(sequence[i] == '-'){
352 if(sequence[structMap[i]] == 'T') { data.pound++; data.total++; }
353 else if(sequence[structMap[i]] == 'A') { data.pound++; data.total++; }
354 else if(sequence[structMap[i]] == 'G') { data.pound++; data.total++; }
355 else if(sequence[structMap[i]] == 'C') { data.pound++; data.total++; }
356 else if(sequence[structMap[i]] == '-') { /*donothing*/ }
359 else if(isalnum(sequence[i])){
367 catch(exception& e) {
368 m->errorOut(e, "AlignCheckCommand", "getStats");
372 //**********************************************************************************************************************