//**********************************************************************************************************************
vector<string> 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<string> myArray;
for (int i = 0; i < parameters.size(); i++) { myArray.push_back(parameters[i].name); }
}
}
//**********************************************************************************************************************
+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;
set<string> userLabels = labels;
ofstream out;
- string outputFileName = outputDir + m->getRootName(m->getSimpleName(sharedfile)) + "cooccurence.summary";
+ map<string, string> 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))) {
int CooccurrenceCommand::getCooccurrence(vector<SharedRAbundVector*>& thisLookUp, ofstream& out){
try {
int numOTUS = thisLookUp[0]->getNumBins();
+
+ if(numOTUS < 2) {
+ m->mothurOut("Not enough OTUs for co-occurrence analysis, skipping"); m->mothurOutEndLine();
+ return 0;
+ }
+
vector< vector<int> > co_matrix; co_matrix.resize(thisLookUp[0]->getNumBins());
for (int i = 0; i < thisLookUp[0]->getNumBins(); i++) { co_matrix[i].resize((thisLookUp.size()), 0); }
vector<int> columntotal; columntotal.resize(thisLookUp.size(), 0);
int nrows = numOTUS;//rows of inital matrix
int ncols = thisLookUp.size();//groups
double initscore = 0.0;
-
+
vector<double> stats;
- double probabilityMatrix[ncols * nrows];
+ vector<double> probabilityMatrix; probabilityMatrix.resize(ncols * nrows, 0);
vector<vector<int> > nullmatrix(nrows, vector<int>(ncols, 0));
-
+
TrialSwap2 trial;
int n = accumulate( columntotal.begin(), columntotal.end(), 0 );
}
}
}
- else if (matrix == "sim2") {
- for(int i=0;i<nrows;i++) {
- start = 0.0;
- for(int j=0;j<ncols;j++) {
- probabilityMatrix[ncols * i + j] = start + 1/double(ncols);
- start = start + 1/double(ncols);
- }
- }
- }
+ //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;i<nrows;i++) {
+// start = 0.0;
+// for(int j=0;j<ncols;j++) {
+// probabilityMatrix[ncols * i + j] = start + 1/double(ncols);
+// start = start + 1/double(ncols);
+// }
+// }
+// }
else if (matrix == "sim3") {
for(int j=0;j<ncols;j++) {
}
}
}
- else if (matrix == "sim9") { }
+ else if (matrix == "sim9" || matrix == "sim2") { }
else {
m->mothurOut("[ERROR]: No model selected! \n");
m->control_pressed = true;
double current;
double randnum;
int count;
-
- //burn-in
- for(int i=0;i<10000;i++){
- nullmatrix.clear();
- //zero-fill the null matrix
- nullmatrix.assign(nrows, vector<int>(ncols, 0));
-
- if(matrix == "sim1" || matrix == "sim6" || matrix == "sim8" || matrix == "sim7") {
- count = 0;
- while(count < n) {
- nextnum:
- previous = 0.0;
- randnum = rand() / double(RAND_MAX);
- for(int i=0;i<nrows;i++) {
- for(int j=0;j<ncols;j++) {
- current = probabilityMatrix[ncols * i + j];
- if(randnum <= current && randnum > previous) {
- nullmatrix[i][j] = 1;
- count++;
- if (count > n) break;
- else
- goto nextnum;
- }
- previous = current;
- }
- }
- }
- }
-
- else if(matrix == "sim2" || matrix == "sim4") {
- for(int i=0;i<nrows;i++) {
- previous = 0.0;
- count = 0;
- while(count < rowtotal[i]) {
- randnum = rand() / double(RAND_MAX);
- for(int j=0;j<ncols;j++) {
- current = probabilityMatrix[ncols * i + j];
- if(randnum <= current && randnum > 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;j<ncols;j++) {
- count = 0;
- while(count < columntotal[j]) {
- randnum = rand() / double(RAND_MAX);
- for(int i=0;i<nrows;i++) {
- current = probabilityMatrix[ncols * i + j];
- if(randnum <= current && randnum > previous && nullmatrix[i][j] != 1) {
- nullmatrix[i][j] = 1;
- count++;
- previous = 0.0;
- break;
- }
- previous = current;
- }
- }
- }
- }
-
+
+ //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 i=0;i<runs;i++){
+ for(int k=0;k<runs;k++){
nullmatrix.clear();
//zero-fill the null matrix
nullmatrix.assign(nrows, vector<int>(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);
}
}
- else if(matrix == "sim2" || matrix == "sim4") {
+ else if (matrix == "sim2") {
+ for(int i=0;i<nrows;i++) {
+ random_shuffle( co_matrix[i].begin(), co_matrix[i].end() );
+ }
+ //do this for the scoring since those all have nullmatrix as a parameter
+ //nullmatrix gets cleared at the begining of each run
+ nullmatrix = co_matrix;
+ }
+
+ else if(matrix == "sim4") {
for(int i=0;i<nrows;i++) {
- previous = 0.0;
count = 0;
while(count < rowtotal[i]) {
+ previous = 0.0;
+ if (m->control_pressed) { return 0; }
randnum = rand() / double(RAND_MAX);
for(int j=0;j<ncols;j++) {
current = probabilityMatrix[ncols * i + j];
for(int j=0;j<ncols;j++) {
count = 0;
while(count < columntotal[j]) {
+ if (m->control_pressed) { return 0; }
randnum = rand() / double(RAND_MAX);
for(int i=0;i<nrows;i++) {
current = probabilityMatrix[ncols * i + j];
//swap_checkerboards takes the original matrix and swaps checkerboards
else if(matrix == "sim9") {
- trial.swap_checkerboards (co_matrix, rowtotal, columntotal, ncols, nrows);
+ trial.swap_checkerboards (co_matrix, ncols, nrows);
+ nullmatrix = co_matrix;
}
else {
m->mothurOut("[ERROR]: No null model selected!\n\n"); m->control_pressed = true;
m->mothurOutEndLine(); 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); }
+
+ 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;
}