string MakeBiomCommand::getHelpString(){
try {
string helpString = "";
- helpString += "The make.biom command parameters are shared, groups, matrixtype and label. shared is required, unless you have a valid current file.\n";
+ helpString += "The make.biom command parameters are shared, contaxonomy, groups, matrixtype and label. shared is required, unless you have a valid current file.\n";
helpString += "The groups parameter allows you to specify which of the groups in your groupfile you would like included. The group names are separated by dashes.\n";
helpString += "The label parameter allows you to select what distance levels you would like, and are also separated by dashes.\n";
helpString += "The matrixtype parameter allows you to select what type you would like to make. Choices are sparse and dense, default is sparse.\n";
+ helpString += "The contaxonomy file is the taxonomy file outputted by classify.otu(list=yourListfile, taxonomy=yourTaxonomyFile). Be SURE that the you are the constaxonomy file distance matches the shared file distance. ie, for *.0.03.cons.taxonomy set label=0.03. Mothur is smart enough to handle shared files that have been subsampled.\n";
helpString += "The make.biom command should be in the following format: make.biom(shared=yourShared, groups=yourGroups, label=yourLabels).\n";
- helpString += "The contaxonomy file is the taxonomy file outputted by classify.otu(list=yourListfile, taxonomy=yourTaxonomyFile). Be SURE that the you are the constaxonomy file distance matches the shared file distance. ie, for *.0.03.cons.taxonomy set label=0.03. Mothur is smart enough to handle shared files that have been subsampled after the classify.otu command was run on the list and taxonomy file.\n";
helpString += "Example make.biom(shared=abrecovery.an.shared, groups=A-B-C).\n";
helpString += "The default value for groups is all the groups in your groupfile, and all labels in your inputfile will be used.\n";
helpString += "The make.biom command outputs a .biom file.\n";
//initialize outputTypes
vector<string> tempOutNames;
- outputTypes["relabund"] = tempOutNames;
+ outputTypes["biom"] = tempOutNames;
//if the user changes the input directory command factory will send this info to us in the output parameter
string inputDir = validParameter.validFile(parameters, "inputdir", false);
if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; }
+ //set sabund file as new current sabundfile
+ string current = "";
+ itTypes = outputTypes.find("biom");
+ if (itTypes != outputTypes.end()) {
+ if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setBiomFile(current); }
+ }
+
+
m->mothurOutEndLine();
m->mothurOut("Output File Names: "); m->mothurOutEndLine();
for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); }
//convert list file bin labels to shared file bin labels
//parse tax strings
//save in map
- map<string, vector<string> > labelTaxMap;
+ map<string, string> labelTaxMap;
string snumBins = toString(otuLabels.size());
for (int i = 0; i < otuLabels.size(); i++) {
}
binLabel += sbinNumber;
- vector<string> taxString;
- m->splitAtChar(taxs[i], taxString, ';');
- taxString.pop_back(); //adds blank string because taxonomies end in ;
-
- labelTaxMap[binLabel] = taxString;
+ labelTaxMap[binLabel] = taxs[i];
}
//traverse the binLabels forming the metadata strings and saving them
//make sure to sanity check
- map<string, vector<string> >::iterator it;
+ map<string, string>::iterator it;
for (int i = 0; i < m->currentBinLabels.size(); i++) {
if (m->control_pressed) { return metadata; }
if (it == labelTaxMap.end()) { m->mothurOut("[ERROR]: can't find taxonomy information for " + m->currentBinLabels[i] + ".\n"); m->control_pressed = true; }
else {
+ vector<string> bootstrapValues;
string data = "{\"taxonomy\":[";
- for (int j = 0; j < (it->second).size()-1; j ++) {
-
- string taxon = (it->second)[j];
-
- //strip "" if they are there
- int pos = taxon.find("\"");
- if (pos != string::npos) {
- string newTax = "";
- for (int k = 0; k < taxon.length(); k++) {
- if (taxon[k] != '\"') { newTax += taxon[k]; }
- }
- taxon = newTax;
- }
-
- data += "\"" + taxon + "\", ";
- }
+
+ vector<string> scores;
+ vector<string> taxonomies = parseTax(it->second, scores);
- string taxon = (it->second)[(it->second).size()-1];
+ for (int j = 0; j < taxonomies.size()-1; j ++) { data += "\"" + taxonomies[j] + "\", "; }
+ data += "\"" + taxonomies[taxonomies.size()-1] + "\"]";
- //strip "" if they are there
- int pos = taxon.find("\"");
- if (pos != string::npos) {
- string newTax = "";
- for (int k = 0; k < taxon.length(); k++) {
- if (taxon[k] != '\"') { newTax += taxon[k]; }
- }
- taxon = newTax;
+ //add bootstrap values if available
+ if (scores[0] != "null") {
+ data += ", \"bootstrap\":[";
+
+ for (int j = 0; j < scores.size()-1; j ++) { data += scores[j] + ", "; }
+ data += scores[scores.size()-1] + "]";
+
}
-
- data += "\"" + taxon + "\"]} ";
+ data += "}";
metadata.push_back(data);
}
exit(1);
}
-}
+}
+/**************************************************************************************************/
+//returns {Bacteria, Bacteroidetes, ..} and scores is filled with {100, 98, ...} or {null, null, null}
+vector<string> MakeBiomCommand::parseTax(string tax, vector<string>& scores) {
+ try {
+
+ string taxon;
+ vector<string> taxs;
+
+ while (tax.find_first_of(';') != -1) {
+
+ if (m->control_pressed) { return taxs; }
+
+ //get taxon
+ taxon = tax.substr(0,tax.find_first_of(';'));
+
+ int pos = taxon.find_last_of('(');
+ if (pos != -1) {
+ //is it a number?
+ int pos2 = taxon.find_last_of(')');
+ if (pos2 != -1) {
+ string confidenceScore = taxon.substr(pos+1, (pos2-(pos+1)));
+ if (m->isNumeric1(confidenceScore)) {
+ taxon = taxon.substr(0, pos); //rip off confidence
+ scores.push_back(confidenceScore);
+ }else{ scores.push_back("null"); }
+ }
+ }
+
+ //strip "" if they are there
+ pos = taxon.find("\"");
+ if (pos != string::npos) {
+ string newTax = "";
+ for (int k = 0; k < taxon.length(); k++) {
+ if (taxon[k] != '\"') { newTax += taxon[k]; }
+ }
+ taxon = newTax;
+ }
+
+ //look for bootstrap value
+ taxs.push_back(taxon);
+ tax = tax.substr(tax.find_first_of(';')+1, tax.length());
+ }
+
+ return taxs;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "MakeBiomCommand", "parseTax");
+ exit(1);
+ }
+}
+
//**********************************************************************************************************************