X-Git-Url: https://git.donarmstrong.com/?p=mothur.git;a=blobdiff_plain;f=cooccurrencecommand.cpp;h=48fba8c9727b4df62b7a37cbb629a55c7c082d74;hp=85379d1a286f6a822a3a4a5fdb9525a9b7b5f2ca;hb=050a3ff02473a3d4c0980964e1a9ebe52e55d6b8;hpb=3116a941ad720952df651d84aab8c3a9bd6a7c78 diff --git a/cooccurrencecommand.cpp b/cooccurrencecommand.cpp index 85379d1..48fba8c 100644 --- a/cooccurrencecommand.cpp +++ b/cooccurrencecommand.cpp @@ -12,14 +12,14 @@ //********************************************************************************************************************** vector CooccurrenceCommand::setParameters() { try { - CommandParameter pshared("shared", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(pshared); - CommandParameter pmetric("metric", "Multiple", "cscore-checker-combo-vratio", "cscore", "", "", "",false,false); parameters.push_back(pmetric); - CommandParameter pmatrix("matrixmodel", "Multiple", "sim1-sim2-sim3-sim4-sim5-sim6-sim7-sim8-sim9", "sim2", "", "", "",false,false); parameters.push_back(pmatrix); - CommandParameter pruns("iters", "Number", "", "1000", "", "", "",false,false); parameters.push_back(pruns); - CommandParameter pinputdir("inputdir", "String", "", "", "", "", "",false,false); parameters.push_back(pinputdir); - CommandParameter poutputdir("outputdir", "String", "", "", "", "", "",false,false); parameters.push_back(poutputdir); - CommandParameter plabel("label", "String", "", "", "", "", "",false,false); parameters.push_back(plabel); - CommandParameter pgroups("groups", "String", "", "", "", "", "",false,false); parameters.push_back(pgroups); + CommandParameter pshared("shared", "InputTypes", "", "", "none", "none", "none","summary",false,true,true); parameters.push_back(pshared); + CommandParameter pmetric("metric", "Multiple", "cscore-checker-combo-vratio", "cscore", "", "", "","",false,false); parameters.push_back(pmetric); + CommandParameter pmatrix("matrixmodel", "Multiple", "sim1-sim2-sim3-sim4-sim5-sim6-sim7-sim8-sim9", "sim2", "", "", "","",false,false); parameters.push_back(pmatrix); + CommandParameter pruns("iters", "Number", "", "1000", "", "", "","",false,false); parameters.push_back(pruns); + CommandParameter pinputdir("inputdir", "String", "", "", "", "", "","",false,false); parameters.push_back(pinputdir); + CommandParameter poutputdir("outputdir", "String", "", "", "", "", "","",false,false); parameters.push_back(poutputdir); + CommandParameter plabel("label", "String", "", "", "", "", "","",false,false); parameters.push_back(plabel); + CommandParameter pgroups("groups", "String", "", "", "", "", "","",false,false); parameters.push_back(pgroups); vector myArray; for (int i = 0; i < parameters.size(); i++) { myArray.push_back(parameters[i].name); } @@ -51,6 +51,21 @@ string CooccurrenceCommand::getHelpString(){ } } //********************************************************************************************************************** +string CooccurrenceCommand::getOutputPattern(string type) { + try { + string pattern = ""; + + if (type == "summary") { pattern = "[filename],cooccurence.summary"; } + else { m->mothurOut("[ERROR]: No definition for type " + type + " output pattern.\n"); m->control_pressed = true; } + + return pattern; + } + catch(exception& e) { + m->errorOut(e, "CooccurrenceCommand", "getOutputPattern"); + exit(1); + } +} +//********************************************************************************************************************** CooccurrenceCommand::CooccurrenceCommand(){ try { abort = true; calledHelp = true; @@ -176,11 +191,13 @@ int CooccurrenceCommand::execute(){ set userLabels = labels; ofstream out; - string outputFileName = outputDir + m->getRootName(m->getSimpleName(sharedfile)) + "cooccurence.summary"; + map variables; + variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(sharedfile)); + string outputFileName = getOutputFileName("summary", variables); m->openOutputFile(outputFileName, out); outputNames.push_back(outputFileName); outputTypes["summary"].push_back(outputFileName); out.setf(ios::fixed, ios::floatfield); out.setf(ios::showpoint); - out << "metric\tlabel\tScore\tpValue\n"; + out << "metric\tlabel\tScore\tzScore\tstandardDeviation\tnp_Pvalue\n"; //as long as you are not at the end of the file or done wih the lines you want while((lookup[0] != NULL) && ((allLines == 1) || (userLabels.size() != 0))) { @@ -270,27 +287,30 @@ int CooccurrenceCommand::execute(){ //********************************************************************************************************************** int CooccurrenceCommand::getCooccurrence(vector& thisLookUp, ofstream& out){ - try { + try { int numOTUS = thisLookUp[0]->getNumBins(); - vector< vector > initmatrix; initmatrix.resize(thisLookUp.size()); + + if(numOTUS < 2) { + m->mothurOut("Not enough OTUs for co-occurrence analysis, skipping"); m->mothurOutEndLine(); + return 0; + } + vector< vector > co_matrix; co_matrix.resize(thisLookUp[0]->getNumBins()); for (int i = 0; i < thisLookUp[0]->getNumBins(); i++) { co_matrix[i].resize((thisLookUp.size()), 0); } - for (int i = 0; i < thisLookUp.size(); i++) { initmatrix[i].resize((thisLookUp[i]->getNumBins()), 0); } vector columntotal; columntotal.resize(thisLookUp.size(), 0); vector rowtotal; rowtotal.resize(numOTUS, 0); - for (int i = 0; i < thisLookUp.size(); i++) { - for (int j = 0; j < thisLookUp[i]->getNumBins(); j++) { - if (m->control_pressed) { return 0; } - int abund = thisLookUp[i]->getAbundance(j); - - if(abund > 0) { - initmatrix[i][j] = 1; + for (int i = 0; i < thisLookUp.size(); i++) { //nrows in the shared file + for (int j = 0; j < thisLookUp[i]->getNumBins(); j++) { //cols of original shared file + if (m->control_pressed) { return 0; } + int abund = thisLookUp[i]->getAbundance(j); + + if(abund > 0) { co_matrix[j][i] = 1; rowtotal[j]++; columntotal[i]++; - } - } + } + } } //nrows is ncols of inital matrix. All the functions need this value. They assume the transposition has already taken place and nrows and ncols refer to that matrix. @@ -298,124 +318,263 @@ int CooccurrenceCommand::getCooccurrence(vector& thisLookUp int nrows = numOTUS;//rows of inital matrix int ncols = thisLookUp.size();//groups double initscore = 0.0; - - vector initcolumntotal; initcolumntotal.resize(ncols, 0); - vector initrowtotal; initrowtotal.resize(nrows, 0); + vector stats; - + vector probabilityMatrix; probabilityMatrix.resize(ncols * nrows, 0); + vector > nullmatrix(nrows, vector(ncols, 0)); + TrialSwap2 trial; - initcolumntotal = rowtotal; - initrowtotal = columntotal; - trial.update_row_col_totals(co_matrix, rowtotal, columntotal); + int n = accumulate( columntotal.begin(), columntotal.end(), 0 ); - if (metric == "cscore") { initscore = trial.calc_c_score(co_matrix, rowtotal); } - else if (metric == "checker") { initscore = trial.calc_checker(co_matrix, rowtotal); } - else if (metric == "vratio") { initscore = trial.calc_vratio(rowtotal, columntotal); } - else if (metric == "combo") { initscore = trial.calc_combo(co_matrix); } - else { m->mothurOut("[ERROR]: No metric selected!\n"); m->control_pressed = true; return 1; } + //============================================================ - m->mothurOut("Initial c score: " + toString(initscore)); m->mothurOutEndLine(); + //generate a probability matrix. Only do this once. + float start = 0.0; - //nullmatrix burn in - for(int i=0;i<10000;i++) { - if (m->control_pressed) { return 0; } - if (matrix == "sim1") { - trial.sim1(co_matrix); - }else if (matrix == "sim2") { - trial.sim2(co_matrix); - }else if (matrix == "sim3") { - trial.sim3(initmatrix); - co_matrix = initmatrix; - }else if (matrix == "sim4") { - trial.sim4(columntotal, rowtotal, co_matrix); - }else if (matrix == "sim5") { - trial.sim5(initcolumntotal, initrowtotal, initmatrix); - trial.transpose_matrix(initmatrix,co_matrix); - }else if (matrix == "sim6") { - trial.sim6(columntotal, co_matrix); - }else if (matrix == "sim7") { - trial.sim7(initcolumntotal, initmatrix); - co_matrix = initmatrix; - }else if (matrix == "sim8") { - trial.sim8(columntotal, rowtotal, co_matrix); - }else if (matrix == "sim9") { - trial.swap_checkerboards (co_matrix); - }else{ - m->mothurOut("[ERROR]: No model selected! \n"); - m->control_pressed = true; + if (matrix == "sim1") { + for(int i=0;icontrol_pressed) { return 0; } - //calc metric of nullmatrix - if (matrix == "sim1") { - trial.sim1(co_matrix); - }else if (matrix == "sim2") { - trial.sim2(co_matrix); - }else if (matrix == "sim3") { - trial.sim3(initmatrix); - co_matrix = initmatrix; - }else if (matrix == "sim4") { - trial.sim4(columntotal, rowtotal, co_matrix); - }else if (matrix == "sim5") { - trial.sim5(initcolumntotal, initrowtotal, initmatrix); - trial.transpose_matrix(initmatrix,co_matrix); - }else if (matrix == "sim6") { - trial.sim6(columntotal, co_matrix); - }else if (matrix == "sim7") { - trial.sim7(initcolumntotal, initmatrix); - co_matrix = initmatrix; - }else if (matrix == "sim8") { - trial.sim8(columntotal, rowtotal, co_matrix); - }else if (matrix == "sim9") { - trial.swap_checkerboards (co_matrix); - }else{ - m->mothurOut("[ERROR]: No model selected! \n"); - m->control_pressed = true; + //don't need a prob matrix because we just shuffle the rows, may use this in the future + else if (matrix == "sim2") { } +// for(int i=0;imothurOut("[ERROR]: No model selected! \n"); + m->control_pressed = true; + } + + + //co_matrix is the transposed shared file, initmatrix is the original shared file + if (metric == "cscore") { initscore = trial.calc_c_score(co_matrix, rowtotal, ncols, nrows); } + else if (metric == "checker") { initscore = trial.calc_checker(co_matrix, rowtotal, ncols, nrows); } + else if (metric == "vratio") { initscore = trial.calc_vratio(nrows, ncols, rowtotal, columntotal); } + else if (metric == "combo") { initscore = trial.calc_combo(nrows, ncols, co_matrix); } + else { m->mothurOut("[ERROR]: No metric selected!\n"); m->control_pressed = true; return 1; } + + m->mothurOut("Initial c score: " + toString(initscore)); m->mothurOutEndLine(); + + double previous; + double current; + double randnum; + int count; + + //burn-in for sim9 + if(matrix == "sim9") { + for(int i=0;i<10000;i++) trial.swap_checkerboards (co_matrix, ncols, nrows); + } + + //populate null matrix from probability matrix, do this a lot. + for(int k=0;k(ncols, 0)); + + if(matrix == "sim1" || matrix == "sim6" || matrix == "sim8" || matrix == "sim7") { + count = 0; + while(count < n) { + if (m->control_pressed) { return 0; } + nextnum2: + previous = 0.0; + randnum = rand() / double(RAND_MAX); + for(int i=0;i previous) { + nullmatrix[i][j] = 1; + count++; + if (count > n) break; + else + goto nextnum2; + } + previous = current; + } + } + } + } + + else if (matrix == "sim2") { + for(int i=0;icontrol_pressed) { return 0; } + randnum = rand() / double(RAND_MAX); + for(int j=0;j previous && nullmatrix[i][j] != 1) { + nullmatrix[i][j] = 1; + count++; + previous = 0.0; + break; + } + previous = current; + } + } + } + } + + else if(matrix == "sim3" || matrix == "sim5") { + //columns + for(int j=0;jcontrol_pressed) { return 0; } + randnum = rand() / double(RAND_MAX); + for(int i=0;i previous && nullmatrix[i][j] != 1) { + nullmatrix[i][j] = 1; + count++; + previous = 0.0; + break; + } + previous = current; + } + } + } + } + + //swap_checkerboards takes the original matrix and swaps checkerboards + else if(matrix == "sim9") { + trial.swap_checkerboards (co_matrix, ncols, nrows); + nullmatrix = co_matrix; + } + else { + m->mothurOut("[ERROR]: No null model selected!\n\n"); m->control_pressed = true; + return 1; } - // - // - //trial.update_row_col_totals(co_matrix, rowtotal, columntotal); - if (metric == "cscore") { - stats.push_back(trial.calc_c_score(co_matrix, rowtotal)); - }else if (metric == "checker") { - stats.push_back(trial.calc_checker(co_matrix, rowtotal)); - }else if (metric == "vratio") { - stats.push_back(trial.calc_vratio(rowtotal, columntotal)); - }else if (metric == "combo") { - stats.push_back(trial.calc_combo(co_matrix)); - }else { - m->mothurOut("[ERROR]: No metric selected!\n"); - m->control_pressed = true; + //run metric on null matrix and add score to the stats vector + if (metric == "cscore"){ + stats.push_back(trial.calc_c_score(nullmatrix, rowtotal, ncols, nrows)); + } + else if (metric == "checker") { + stats.push_back(trial.calc_checker(nullmatrix, rowtotal, ncols, nrows)); + } + else if (metric == "vratio") { + stats.push_back(trial.calc_vratio(nrows, ncols, rowtotal, columntotal)); + } + else if (metric == "combo") { + stats.push_back(trial.calc_combo(nrows, ncols, nullmatrix)); + } + else { + m->mothurOut("[ERROR]: No metric selected!\n\n"); m->control_pressed = true; return 1; } } - + + + double total = 0.0; - for (int i=0; imothurOutEndLine(); m->mothurOut("average metric score: " + toString(nullMean)); m->mothurOutEndLine(); + //calc_p_value is not a statistical p-value, it's just the average that are either > or < the initscore. + //All it does is show what is expected in a competitively structured community + //zscore is output so p-value can be looked up in a ztable double pvalue = 0.0; - if (metric == "cscore" || metric == "checker") { pvalue = trial.calc_pvalue_greaterthan (stats, initscore); } - else{ pvalue = trial.calc_pvalue_lessthan (stats, initscore); } + if (metric == "cscore" || metric == "checker") { pvalue = trial.calc_pvalue_greaterthan (stats, initscore); } + else{ pvalue = trial.calc_pvalue_lessthan (stats, initscore); } + + double sd = trial.getSD(runs, stats, nullMean); + + double zscore = trial.get_zscore(sd, nullMean, initscore); - m->mothurOut("pvalue: " + toString(pvalue)); m->mothurOutEndLine(); - out << metric << '\t' << thisLookUp[0]->getLabel() << '\t' << nullMean << '\t' << pvalue << endl; + m->mothurOut("zscore: " + toString(zscore)); m->mothurOutEndLine(); + m->mothurOut("standard deviation: " + toString(sd)); m->mothurOutEndLine(); + m->mothurOut("non-parametric p-value: " + toString(pvalue)); m->mothurOutEndLine(); + out << metric << '\t' << thisLookUp[0]->getLabel() << '\t' << nullMean << '\t' << zscore << '\t' << sd << '\t' << pvalue << endl; return 0; - } - catch(exception& e) { - m->errorOut(e, "CooccurrenceCommand", "Cooccurrence"); - exit(1); - } + } + catch(exception& e) { + m->errorOut(e, "CooccurrenceCommand", "Cooccurrence"); + exit(1); + } } //**********************************************************************************************************************