void compute_confusion_matrix(int32_t max_read_length, std::string bam_file, std::string fasta_file, std::string fasta_dir, bool skip_soft_clipped, std::ostream& out){
BamTools::BamReader bam_reader;
if (!bam_reader.Open(bam_file)) printErrorAndDie("Failed to open BAM file");
std::string ref_seq;
int32_t ref_id;
if (fasta_file.compare("N/A") == 0)
ref_id = -2;
else {
readFasta(fasta_file, fasta_dir, ref_seq);
ref_id = 0;
}
int32_t* matrix_counts = new int32_t [25*max_read_length]();
int32_t* total_counts = new int32_t [5*max_read_length]();
int32_t forward = 0, backward = 0;
process_reads(bam_reader, max_read_length, ref_id, ref_seq, fasta_dir, skip_soft_clipped, matrix_counts, total_counts, forward, backward);
out << forward << "\n"
<< backward << std::endl;
print_confusion_matrix(matrix_counts, total_counts, max_read_length, out);
delete [] matrix_counts;
delete [] total_counts;
}
int ListSeqsCommand::execute(){
try {
if (abort) { if (calledHelp) { return 0; } return 2; }
//read functions fill names vector
if (fastafile != "") { inputFileName = fastafile; readFasta(); }
else if (fastqfile != "") { inputFileName = fastqfile; readFastq(); }
else if (namefile != "") { inputFileName = namefile; readName(); }
else if (groupfile != "") { inputFileName = groupfile; readGroup(); }
else if (alignfile != "") { inputFileName = alignfile; readAlign(); }
else if (listfile != "") { inputFileName = listfile; readList(); }
else if (taxfile != "") { inputFileName = taxfile; readTax(); }
else if (countfile != "") { inputFileName = countfile; readCount(); }
if (m->getControl_pressed()) { outputTypes.clear(); return 0; }
//sort in alphabetical order
sort(names.begin(), names.end());
if (outputDir == "") { outputDir += util.hasPath(inputFileName); }
map<string, string> variables;
variables["[filename]"] = outputDir + util.getRootName(util.getSimpleName(inputFileName));
string outputFileName = getOutputFileName("accnos", variables);
util.printAccnos(outputFileName, names);
outputNames.push_back(outputFileName); outputTypes["accnos"].push_back(outputFileName);
if (m->getControl_pressed()) { outputTypes.clear(); util.mothurRemove(outputFileName); return 0; }
current->setAccnosFile(outputFileName);
m->mothurOut("\nOutput File Names: \n");
m->mothurOut(outputFileName); m->mothurOutEndLine();
m->mothurOutEndLine();
//set accnos file as new current accnosfile
string currentName = "";
itTypes = outputTypes.find("accnos");
if (itTypes != outputTypes.end()) {
if ((itTypes->second).size() != 0) { currentName = (itTypes->second)[0]; current->setAccnosFile(currentName); }
}
return 0;
}
catch(exception& e) {
m->errorOut(e, "ListSeqsCommand", "execute");
exit(1);
}
}
int main(int argc, char *argv[])
/* hash snpFasta, read through chrN_snpTmp, rewrite with extensions to individual chrom tables */
{
struct slName *chromList, *chromPtr;
char tableName[64];
if (argc != 2)
usage();
snpDb = argv[1];
hSetDb(snpDb);
chromList = hAllChromNamesDb(snpDb);
errorFileHandle = mustOpen("snpMoltype.errors", "w");
multiFastaHash = readFasta("chrMulti");
for (chromPtr = chromList; chromPtr != NULL; chromPtr = chromPtr->next)
{
safef(tableName, ArraySize(tableName), "%s_snpTmp", chromPtr->name);
if (!hTableExists(tableName)) continue;
verbose(1, "chrom = %s\n", chromPtr->name);
chromFastaHash = readFasta(chromPtr->name);
processSnps(chromPtr->name);
}
carefulClose(&errorFileHandle);
for (chromPtr = chromList; chromPtr != NULL; chromPtr = chromPtr->next)
{
safef(tableName, ArraySize(tableName), "%s_snpTmp", chromPtr->name);
if (!hTableExists(tableName)) continue;
recreateDatabaseTable(chromPtr->name);
verbose(1, "loading chrom = %s\n", chromPtr->name);
loadDatabase(chromPtr->name);
}
return 0;
}
int main(int argc, char **argv){
MultiFasta *fasta;
Parameters param;
param = readParams(argc, argv);
fasta = readFasta(param.fastaname);
multialign(fasta, param.kmersize, param.mindiagsize);
printFasta(fasta);
releaseFasta(fasta);
return EXIT_SUCCESS;
}
int do_file(char *fname, struct trie *root, int which){
FILE *fasta;
char *genome;
int glen;
int i;
char *window;
char *rcwindow;
int willInsert;
char dummy[SEQ_LENGTH];
int win = 0;
willInsert = 1;
fprintf(stderr, "\n\nInserting sequence from file %s\n", fname);
fasta = myfopen(fname, "r");
fgets(dummy, SEQ_LENGTH, fasta);
genome = readFasta(fasta, &glen);
window = (char *) mymalloc(sizeof(char) * WINDOW_SIZE+1);
rcwindow = (char *) mymalloc(sizeof(char) * WINDOW_SIZE+1);
i = 0;
while (i < glen - WINDOW_SIZE){
if (getWindow(genome, glen, &window, i) == 0 ){
i+=SLIDE_SIZE;
continue;
}
//while (getIndexWindow(fasta, &window, &willInsert) > 0){
//fprintf(stderr, "\rGetting windows from %s\t: %d%%", fname, ((int)(100.0*(float)(i+strlen(window))/(float)strlen(genome))));
if (VERBOSE)
printf("%s\n", window);
/* insert the window to the trie here */
if (willInsert){
// start location is i+1
// because i starts from 0 here; but
// we want the sequence index starting from 1
// STARTING POSITION FOR FORWARD
rcomp(window, rcwindow);
if (NOREV){
if (strcmp(window, rcwindow) < 0 )
insert(root, window, (i+1), fname, which);
else if (strcmp(window, rcwindow) > 0 )
insert(root, rcwindow, (-1*(i+1)), fname, which);
}
else{
insert(root, window, (i+1), fname, which);
insert(root, rcwindow, (-1*(i+1)), fname, which);
}
/*
insert(root, window, (i+1), fname, which);
if (!NOREV){
// reverse complement of this window is indexed by its negative
// value ENDING POSITION FOR REVERSE COMPLEMENT
rcomp(window, rcwindow);
if (strcmp(window, rcwindow))
insert(root, rcwindow, (-1*(i+1)), fname, which);
}*/
}
i+=SLIDE_SIZE;
if (i % 10000 == 0)
fprintf(stderr,"\r [%i] of [%d]", i, glen);
}
fprintf(stderr, "\n");
//free(genome);
fclose(fasta);
free(window);
free(rcwindow);
return 1;
}
void proteinInfer(){
readFasta();
proteinMap();
calcuPro();
proteinRela();
}
int GetSeqsCommand::execute(){
try {
if (abort == true) { if (calledHelp) { return 0; } return 2; }
//get names you want to keep
names = m->readAccnos(accnosfile);
if (m->control_pressed) { return 0; }
if (countfile != "") {
if ((fastafile != "") || (listfile != "") || (taxfile != "")) {
m->mothurOut("\n[NOTE]: The count file should contain only unique names, so mothur assumes your fasta, list and taxonomy files also contain only uniques.\n\n");
}
}
//read through the correct file and output lines you want to keep
if (namefile != "") { readName(); }
if (fastafile != "") { readFasta(); }
if (fastqfile != "") { readFastq(); }
if (groupfile != "") { readGroup(); }
if (countfile != "") { readCount(); }
if (alignfile != "") { readAlign(); }
if (listfile != "") { readList(); }
if (taxfile != "") { readTax(); }
if (qualfile != "") { readQual(); }
if (accnosfile2 != "") { compareAccnos(); }
if (m->debug) { runSanityCheck(); }
if (m->control_pressed) { outputTypes.clear(); for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; }
if (outputNames.size() != 0) {
m->mothurOutEndLine();
m->mothurOut("Output File Names: "); m->mothurOutEndLine();
for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); }
m->mothurOutEndLine();
//set fasta file as new current fastafile
string current = "";
itTypes = outputTypes.find("fasta");
if (itTypes != outputTypes.end()) {
if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setFastaFile(current); }
}
itTypes = outputTypes.find("name");
if (itTypes != outputTypes.end()) {
if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setNameFile(current); }
}
itTypes = outputTypes.find("group");
if (itTypes != outputTypes.end()) {
if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setGroupFile(current); }
}
itTypes = outputTypes.find("list");
if (itTypes != outputTypes.end()) {
if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setListFile(current); }
}
itTypes = outputTypes.find("taxonomy");
if (itTypes != outputTypes.end()) {
if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setTaxonomyFile(current); }
}
itTypes = outputTypes.find("qfile");
if (itTypes != outputTypes.end()) {
if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setQualFile(current); }
}
itTypes = outputTypes.find("count");
if (itTypes != outputTypes.end()) {
if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setCountTableFile(current); }
}
}
return 0;
}
catch(exception& e) {
m->errorOut(e, "GetSeqsCommand", "execute");
exit(1);
}
}
int RemoveGroupsCommand::execute(){
try {
if (abort == true) { if (calledHelp) { return 0; } return 2; }
//get groups you want to remove
if (accnosfile != "") { m->readAccnos(accnosfile, Groups); m->setGroups(Groups); }
if (groupfile != "") {
groupMap = new GroupMap(groupfile);
groupMap->readMap();
//make sure groups are valid
//takes care of user setting groupNames that are invalid or setting groups=all
vector<string> namesGroups = groupMap->getNamesOfGroups();
vector<string> checkedGroups;
for (int i = 0; i < Groups.size(); i++) {
if (m->inUsersGroups(Groups[i], namesGroups)) { checkedGroups.push_back(Groups[i]); }
else { m->mothurOut("[WARNING]: " + Groups[i] + " is not a valid group in your groupfile, ignoring.\n"); }
}
if (checkedGroups.size() == 0) { m->mothurOut("[ERROR]: no valid groups, aborting.\n"); delete groupMap; return 0; }
else {
Groups = checkedGroups;
m->setGroups(Groups);
}
//fill names with names of sequences that are from the groups we want to remove
fillNames();
delete groupMap;
}else if (countfile != ""){
if ((fastafile != "") || (listfile != "") || (taxfile != "")) {
m->mothurOut("\n[NOTE]: The count file should contain only unique names, so mothur assumes your fasta, list and taxonomy files also contain only uniques.\n\n");
}
CountTable ct;
ct.readTable(countfile, true, false);
if (!ct.hasGroupInfo()) { m->mothurOut("[ERROR]: your count file does not contain group info, aborting.\n"); return 0; }
vector<string> gNamesOfGroups = ct.getNamesOfGroups();
SharedUtil util;
util.setGroups(Groups, gNamesOfGroups);
vector<string> namesOfSeqs = ct.getNamesOfSeqs();
sort(Groups.begin(), Groups.end());
for (int i = 0; i < namesOfSeqs.size(); i++) {
vector<string> thisSeqsGroups = ct.getGroups(namesOfSeqs[i]);
if (m->isSubset(Groups, thisSeqsGroups)) { //you only have seqs from these groups so remove you
names.insert(namesOfSeqs[i]);
}
}
}
if (m->control_pressed) { return 0; }
//read through the correct file and output lines you want to keep
if (namefile != "") { readName(); }
if (fastafile != "") { readFasta(); }
if (groupfile != "") { readGroup(); }
if (countfile != "") { readCount(); }
if (listfile != "") { readList(); }
if (taxfile != "") { readTax(); }
if (sharedfile != "") { readShared(); }
if (designfile != "") { readDesign(); }
if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; }
if (outputNames.size() != 0) {
m->mothurOutEndLine();
m->mothurOut("Output File names: "); m->mothurOutEndLine();
for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); }
m->mothurOutEndLine();
//set fasta file as new current fastafile
string current = "";
itTypes = outputTypes.find("fasta");
if (itTypes != outputTypes.end()) {
if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setFastaFile(current); }
}
itTypes = outputTypes.find("name");
if (itTypes != outputTypes.end()) {
if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setNameFile(current); }
}
itTypes = outputTypes.find("group");
if (itTypes != outputTypes.end()) {
if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setGroupFile(current); }
}
itTypes = outputTypes.find("list");
if (itTypes != outputTypes.end()) {
if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setListFile(current); }
}
itTypes = outputTypes.find("taxonomy");
if (itTypes != outputTypes.end()) {
if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setTaxonomyFile(current); }
}
itTypes = outputTypes.find("shared");
if (itTypes != outputTypes.end()) {
if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setSharedFile(current); }
}
itTypes = outputTypes.find("design");
if (itTypes != outputTypes.end()) {
if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setDesignFile(current); }
}
itTypes = outputTypes.find("count");
if (itTypes != outputTypes.end()) {
if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setCountTableFile(current); }
}
}
return 0;
}
catch(exception& e) {
m->errorOut(e, "RemoveGroupsCommand", "execute");
exit(1);
}
}
int main(int argc, char **argv){
char str[1000];
FILE *fasta;
FILE *hor;
FILE *log;
FILE *aligned;
int i,j;
int count;
int nseq, nhor;
int *freqs;
int swapfreq;
int mismatch;
int trim;
/* pattern match stuff */
FILE *clusterFile;
char cfbase[100];
struct cluster *allclusters;
struct cluster *prevcluster;
struct cluster *current;
struct cmember *cm;
struct wgsread *allreads;
struct wgsread *wgs1, *wgs2;
struct asatseq *asat;
struct asatseq *patternasat;
char *wgsname;
int wgsstart, wgsend;
int iflag;
int isInserted;
int cluster_id;
int pattern_id;
int occurance;
int isFINALHOR;
/* pattern match stuff ends here */
if (argc != 3 && argc!=4){
fprintf(stderr, "Aligns sequences to the given center star given a two fasta-centroid files.\nThen dumps the alignments\n");
fprintf(stderr, "%s [fasta file][hor fasta] <-trim>\n", argv[0]);
exit(0);
}
trim = 0;
fasta = fopen(argv[1], "r");
hor = fopen(argv[2], "r");
if (argc == 4 && !strcmp(argv[3], "-trim"))
trim = 1;
if (fasta == NULL || hor == NULL)
return 0;
strcpy(str, argv[1]);
for (i=strlen(str)-1;i>=0;i--)
if (str[i]=='.'){
str[i] = 0;
break;
}
if (trim)
fprintf(stdout, "Will trim.\n");
makevectors();
strcat(str, ".log");
log = fopen(str, "w");
sprintf(str, "center-%s", argv[1]);
aligned = fopen(str, "w");
readFasta(fasta, hor, &nseq, &nhor);
fprintf(stderr, "%d monomers, and the center are read into memory.\n", nseq);
for (i=0;i<nseq;i++){
align(seqs[i], horseqs[0]);
/* aligned seq is in Sp, aligned center is in Tp */
fprintf(aligned, ">%s\n", names[i]);
fprintf(log, "%s\t%s\n%s\t%s\n", names[i], Sp, hornames[0], Tp);
for (j=strlen(Sp)-1;j>=0;j--){
if (!trim)
fprintf(aligned, "%c", Sp[j]);
else if (Tp[j]!='-')
fprintf(aligned, "%c", Sp[j]);
if ((strlen(Sp)-j)%60 == 0 && j!=strlen(Sp)-1)
fprintf(aligned, "\n");
}
fprintf(aligned, "\n");
if (strchr(Tp, '-')!=NULL)
fprintf(log, "%s\n", names[i]);
fprintf(stderr, "\r%d\tof\t%d", (i+1), nseq);
}
fprintf(stderr, "\n");
fclose(log);
fclose(aligned);
return 1;
}
