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; }
71 vector<string> myArray = setParameters();
73 OptionParser parser(option);
74 map<string,string> parameters = parser.getParameters();
76 ValidParameters validParameter;
77 map<string,string>::iterator it;
79 //check to make sure all parameters are valid for command
80 for (it = parameters.begin(); it != parameters.end(); it++) {
81 if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; }
84 //initialize outputTypes
85 vector<string> tempOutNames;
86 outputTypes["aligncheck"] = tempOutNames;
88 //if the user changes the input directory command factory will send this info to us in the output parameter
89 string inputDir = validParameter.validFile(parameters, "inputdir", false);
90 if (inputDir == "not found"){ inputDir = ""; }
93 it = parameters.find("fasta");
94 //user has given a template file
95 if(it != parameters.end()){
96 path = m->hasPath(it->second);
97 //if the user has not given a path then, add inputdir. else leave path alone.
98 if (path == "") { parameters["fasta"] = inputDir + it->second; }
101 it = parameters.find("map");
102 //user has given a template file
103 if(it != parameters.end()){
104 path = m->hasPath(it->second);
105 //if the user has not given a path then, add inputdir. else leave path alone.
106 if (path == "") { parameters["map"] = inputDir + it->second; }
109 it = parameters.find("name");
110 //user has given a template file
111 if(it != parameters.end()){
112 path = m->hasPath(it->second);
113 //if the user has not given a path then, add inputdir. else leave path alone.
114 if (path == "") { parameters["name"] = inputDir + it->second; }
118 //check for required parameters
119 mapfile = validParameter.validFile(parameters, "map", true);
120 if (mapfile == "not open") { abort = true; }
121 else if (mapfile == "not found") { mapfile = ""; m->mothurOut("You must provide an map file."); m->mothurOutEndLine(); abort = true; }
123 fastafile = validParameter.validFile(parameters, "fasta", true);
124 if (fastafile == "not open") { abort = true; }
125 else if (fastafile == "not found") {
126 fastafile = m->getFastaFile();
127 if (fastafile != "") { m->mothurOut("Using " + fastafile + " as input file for the fasta parameter."); m->mothurOutEndLine(); }
128 else { m->mothurOut("You have no current fastafile and the fasta parameter is required."); m->mothurOutEndLine(); abort = true; }
131 namefile = validParameter.validFile(parameters, "name", true);
132 if (namefile == "not open") { namefile = ""; abort = true; }
133 else if (namefile == "not found") { namefile = ""; }
135 //if the user changes the output directory command factory will send this info to us in the output parameter
136 outputDir = validParameter.validFile(parameters, "outputdir", false); if (outputDir == "not found"){
138 outputDir += m->hasPath(fastafile); //if user entered a file with a path then preserve it
144 catch(exception& e) {
145 m->errorOut(e, "AlignCheckCommand", "AlignCheckCommand");
149 //**********************************************************************************************************************
151 int AlignCheckCommand::execute(){
154 if (abort == true) { if (calledHelp) { return 0; } return 2; }
156 //get secondary structure info.
159 if (namefile != "") { nameMap = m->readNames(namefile); }
161 if (m->control_pressed) { return 0; }
164 m->openInputFile(fastafile, in);
167 string outfile = outputDir + m->getRootName(m->getSimpleName(fastafile)) + "align.check";
168 m->openOutputFile(outfile, out);
171 out << "name" << '\t' << "pound" << '\t' << "dash" << '\t' << "plus" << '\t' << "equal" << '\t';
172 out << "loop" << '\t' << "tilde" << '\t' << "total" << '\t' << "numseqs" << endl;
184 if (m->control_pressed) { in.close(); out.close(); remove(outfile.c_str()); return 0; }
186 Sequence seq(in); m->gobble(in);
187 if (seq.getName() != "") {
188 statData data = getStats(seq.getAligned());
190 if (haderror == 1) { m->control_pressed = true; break; }
193 if (namefile != "") {
194 //make sure this sequence is in the namefile, else error
195 map<string, int>::iterator it = nameMap.find(seq.getName());
197 if (it == nameMap.end()) { m->mothurOut("[ERROR]: " + seq.getName() + " is not in your namefile, please correct."); m->mothurOutEndLine(); m->control_pressed = true; }
198 else { num = it->second; }
201 //for each sequence this sequence represents
202 for (int i = 0; i < num; i++) {
203 pound.push_back(data.pound);
204 dash.push_back(data.dash);
205 plus.push_back(data.plus);
206 equal.push_back(data.equal);
207 loop.push_back(data.loop);
208 tilde.push_back(data.tilde);
209 total.push_back(data.total);
213 out << seq.getName() << '\t' << data.pound << '\t' << data.dash << '\t' << data.plus << '\t' << data.equal << '\t';
214 out << data.loop << '\t' << data.tilde << '\t' << data.total << '\t' << num << endl;
221 if (m->control_pressed) { remove(outfile.c_str()); return 0; }
223 sort(pound.begin(), pound.end());
224 sort(dash.begin(), dash.end());
225 sort(plus.begin(), plus.end());
226 sort(equal.begin(), equal.end());
227 sort(loop.begin(), loop.end());
228 sort(tilde.begin(), tilde.end());
229 sort(total.begin(), total.end());
230 int size = pound.size();
232 int ptile0_25 = int(size * 0.025);
233 int ptile25 = int(size * 0.250);
234 int ptile50 = int(size * 0.500);
235 int ptile75 = int(size * 0.750);
236 int ptile97_5 = int(size * 0.975);
237 int ptile100 = size - 1;
239 if (m->control_pressed) { remove(outfile.c_str()); return 0; }
241 m->mothurOutEndLine();
242 m->mothurOut("\t\tPound\tDash\tPlus\tEqual\tLoop\tTilde\tTotal"); m->mothurOutEndLine();
243 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();
244 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();
245 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();
246 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();
247 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();
248 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();
249 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();
250 if (namefile == "") { m->mothurOut("# of Seqs:\t" + toString(count)); m->mothurOutEndLine(); }
251 else { m->mothurOut("# of unique seqs:\t" + toString(count)); m->mothurOutEndLine(); m->mothurOut("total # of seqs:\t" + toString(size)); m->mothurOutEndLine(); }
254 m->mothurOutEndLine();
255 m->mothurOut("Output File Name: "); m->mothurOutEndLine();
256 m->mothurOut(outfile); m->mothurOutEndLine(); outputNames.push_back(outfile); outputTypes["aligncheck"].push_back(outfile);
257 m->mothurOutEndLine();
262 catch(exception& e) {
263 m->errorOut(e, "AlignCheckCommand", "execute");
267 //**********************************************************************************************************************
268 void AlignCheckCommand::readMap(){
271 structMap.resize(1, 0);
274 m->openInputFile(mapfile, in);
279 structMap.push_back(position);
284 seqLength = structMap.size();
287 //check you make sure is structMap[10] = 380 then structMap[380] = 10.
288 for(int i=0;i<seqLength;i++){
289 if(structMap[i] != 0){
290 if(structMap[structMap[i]] != i){
291 m->mothurOut("Your map file contains an error: line " + toString(i) + " does not match line " + toString(structMap[i]) + "."); m->mothurOutEndLine();
298 catch(exception& e) {
299 m->errorOut(e, "AlignCheckCommand", "readMap");
303 /**************************************************************************************************/
305 statData AlignCheckCommand::getStats(string sequence){
309 sequence = "*" + sequence; // need to pad the sequence so we can index it by 1
311 int length = sequence.length();
313 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; }
315 for(int i=1;i<length;i++){
316 if(structMap[i] != 0){
317 if(sequence[i] == 'A'){
318 if(sequence[structMap[i]] == 'T') { data.tilde++; }
319 else if(sequence[structMap[i]] == 'A') { data.pound++; }
320 else if(sequence[structMap[i]] == 'G') { data.equal++; }
321 else if(sequence[structMap[i]] == 'C') { data.pound++; }
322 else if(sequence[structMap[i]] == '-') { data.pound++; }
325 else if(sequence[i] == 'T'){
326 if(sequence[structMap[i]] == 'T') { data.plus++; }
327 else if(sequence[structMap[i]] == 'A') { data.tilde++; }
328 else if(sequence[structMap[i]] == 'G') { data.dash++; }
329 else if(sequence[structMap[i]] == 'C') { data.pound++; }
330 else if(sequence[structMap[i]] == '-') { data.pound++; }
333 else if(sequence[i] == 'G'){
334 if(sequence[structMap[i]] == 'T') { data.dash++; }
335 else if(sequence[structMap[i]] == 'A') { data.equal++; }
336 else if(sequence[structMap[i]] == 'G') { data.pound++; }
337 else if(sequence[structMap[i]] == 'C') { data.tilde++; }
338 else if(sequence[structMap[i]] == '-') { data.pound++; }
341 else if(sequence[i] == 'C'){
342 if(sequence[structMap[i]] == 'T') { data.pound++; }
343 else if(sequence[structMap[i]] == 'A') { data.pound++; }
344 else if(sequence[structMap[i]] == 'G') { data.tilde++; }
345 else if(sequence[structMap[i]] == 'C') { data.pound++; }
346 else if(sequence[structMap[i]] == '-') { data.pound++; }
349 else if(sequence[i] == '-'){
350 if(sequence[structMap[i]] == 'T') { data.pound++; data.total++; }
351 else if(sequence[structMap[i]] == 'A') { data.pound++; data.total++; }
352 else if(sequence[structMap[i]] == 'G') { data.pound++; data.total++; }
353 else if(sequence[structMap[i]] == 'C') { data.pound++; data.total++; }
354 else if(sequence[structMap[i]] == '-') { /*donothing*/ }
357 else if(isalnum(sequence[i])){
365 catch(exception& e) {
366 m->errorOut(e, "AlignCheckCommand", "getStats");
370 //**********************************************************************************************************************