/*
* Get the file name from the command line arguments.
* Show the help if required.
*/
bool GetOptions(int argc, char **argv, ConverterOptions &options)
{
CCmdLine cmdLine;
// parse argc,argv
// no switches were given on the command line, abort
if (cmdLine.SplitLine(argc, argv) < 1)
{
ShowHelp();
return false;
}
// test for the 'help' case
if (cmdLine.HasSwitch(HELP_ARG))
{
ShowHelp();
return false;
}
// get the required argument
try
{
string str;
str = cmdLine.GetArgument(INPUT_FILE_ARG, 0);
options.fileName = str;
str = cmdLine.GetArgument(VERSION_ARG, 0);
options.version = (CELFileVersionType)(atoi(str.c_str()));
}
catch (...)
{
// one of the required arguments was missing, abort
ShowHelp();
return false;
}
return true;
}
int main(int argc, char *argv[]){
Fgwas_params p;
CCmdLine cmdline;
if (cmdline.SplitLine(argc, argv) < 1){
printopts();
exit(1);
}
//get the input file
if (cmdline.HasSwitch("-i")) p.infile = cmdline.GetArgument("-i", 0).c_str();
else{
cerr << "ERROR: missing input file (-i)\n";
printopts();
exit(1);
}
//get the output file
if (cmdline.HasSwitch("-o")) p.outstem = cmdline.GetArgument("-o", 0);
if (cmdline.HasSwitch("-pcond")) printcond = true;
if (cmdline.HasSwitch("-v")) {
p.V.clear();
vector<string> strs;
string s = cmdline.GetArgument("-v", 0);
boost::split(strs, s ,boost::is_any_of(","));
for (int i = 0; i < strs.size(); i++) {
p.V.push_back( atof(strs[i].c_str()) );
}
}
//LD file
if (cmdline.HasSwitch("-ld")) {
p.overlap = true;
p.ldfile = cmdline.GetArgument("-ld", 0);
if (cmdline.HasSwitch("-nhap")) p.Nhap = atoi(cmdline.GetArgument("-nhap", 0).c_str());
else{
cerr << "ERROR: inputing LD matrix, -nhap flag\n";
printopts();
exit(1);
}
}
else if (cmdline.HasSwitch("-cor")){
//cerr << "WARNING: including correlation, did you mean to include an LD file?\n";
//printopts();
//exit(1);
}
if (cmdline.HasSwitch("-rev")) p.rev = true;
if (cmdline.HasSwitch("-numbered")) p.numberedseg = true;
//set K
if (cmdline.HasSwitch("-k")) p.K = atoi(cmdline.GetArgument("-k", 0).c_str());
if (cmdline.HasSwitch("-bed")) {
p.bedseg = true;
p.segment_bedfile = cmdline.GetArgument("-bed", 0);
}
if (cmdline.HasSwitch("-noprint")) p.print = false;
//names of the phenotypes, expecting header like NAME1_Z NAME1_V NAME2_Z NAME2_V
if (cmdline.HasSwitch("-phenos")){
p.pairwise = true;
p.pheno1 = cmdline.GetArgument("-phenos", 0);
p.pheno2 = cmdline.GetArgument("-phenos", 1);
}
else{
cerr << "ERROR: missing phenotypes (-pheno)\n";
printopts();
exit(1);
}
/*
if (cmdline.HasSwitch("-w")){
vector<string> strs;
string s = cmdline.GetArgument("-w", 0);
boost::split(strs, s ,boost::is_any_of("+"));
for (int i = 0; i < strs.size(); i++) {
p.wannot.push_back( strs[i] );
}
}
if (cmdline.HasSwitch("-dists")){
vector<string> strs;
string s = cmdline.GetArgument("-dists", 0);
boost::split(strs, s ,boost::is_any_of("+"));
for (int i = 0; i < strs.size(); i++) {
vector<string> strs2;
boost::split(strs2, strs[i], boost::is_any_of(":"));
p.dannot.push_back( strs2[0] );
p.distmodels.push_back(strs2[1]);
}
}
if (cmdline.HasSwitch("-drop")){
p.dropchr = true;
string s = cmdline.GetArgument("-drop", 0);
p.chrtodrop = s;
}
if (cmdline.HasSwitch("-dens")) {
p.segannot.push_back(cmdline.GetArgument("-dens", 0));
p.loquant = atof(cmdline.GetArgument("-dens", 1).c_str());
p.hiquant = atof(cmdline.GetArgument("-dens", 2).c_str());
}
*/
if (cmdline.HasSwitch("-fine")) p.finemap = true;
if (cmdline.HasSwitch("-mcmc")) p.MCMC = true;
if (cmdline.HasSwitch("-seed")){
p.seed = atoi(cmdline.GetArgument("-seed", 0).c_str());
}
else p.seed = unsigned( time(NULL));
if (cmdline.HasSwitch("-nburn")){
p.burnin = atoi(cmdline.GetArgument("-nburn", 0).c_str());
}
if (cmdline.HasSwitch("-nsamp")){
p.nsamp = atoi(cmdline.GetArgument("-nsamp", 0).c_str());
}
if (cmdline.HasSwitch("-jumpsd")){
p.MCMC_gauss_SD = atof(cmdline.GetArgument("-jumpsd", 0).c_str());
}
if (cmdline.HasSwitch("-cor")){
p.cor = atof(cmdline.GetArgument("-cor", 0).c_str());
//p.overlap = true;
}
if (cmdline.HasSwitch("-prior")){
if (cmdline.GetArgumentCount("-prior") != 5) {
cerr << "ERROR: -prior needs 5 entries, "<< cmdline.GetArgumentCount("-prior") << " given\n";
exit(1);
}
p.alpha_prior[0] = atof(cmdline.GetArgument("-prior", 0).c_str());
p.alpha_prior[1] = atof(cmdline.GetArgument("-prior", 1).c_str());
p.alpha_prior[2] = atof(cmdline.GetArgument("-prior", 2).c_str());
p.alpha_prior[3] = atof(cmdline.GetArgument("-prior", 3).c_str());
p.alpha_prior[4] = atof(cmdline.GetArgument("-prior", 4).c_str());
}
//random number generator
const gsl_rng_type * T;
gsl_rng * r;
gsl_rng_env_setup();
T = gsl_rng_ranlxs2;
r = gsl_rng_alloc(T);
int seed = (int) time(0);
gsl_rng_set(r, p.seed);
SNPs_PW s(&p);
if (printcond) s.get_all_condZ();
s.GSL_optim();
vector<double> ml;
for (int i = 0; i < 5; i++)ml.push_back(s.pi[i]);
vector<pair<pair<int, int>, pair<double, double> > > cis = s.get_cis();
string outML = p.outstem+".MLE";
ofstream outr(outML.c_str());
int sti = 0;
if (p.finemap) sti = 1;
for (int i = sti; i < 5; i++){
outr << "pi_"<< i <<" "<< cis.at(i-sti).second.first << " "<< ml[i]<< " "<< cis.at(i-sti).second.second << "\n";
}
outr.close();
if (p.MCMC) s.MCMC(r);
if (p.print) s.print(p.outstem+".bfs.gz", p.outstem+".segbfs.gz");
//if (p.finemap) return 0;
return 0;
}
/*! The main entrance to the program. */
int main(int argc, char * argv[])
{
try
{
// Parse the command line arguments.
CCmdLine cmdLine;
if (cmdLine.SplitLine(argc, argv) < 1)
{
show_help();
exit(-1);
}
string execId = cmdLine.GetArgument("-execid", 0);
string celFile = cmdLine.GetSafeArgument("-cel", 0, "");
string inFile = cmdLine.GetArgument("-in", 0);
string outFile = cmdLine.GetArgument("-out", 0);
string arrayType = cmdLine.GetArgument("-arrayType", 0);
string algName = cmdLine.GetArgument("-algName", 0);
string algVersion = cmdLine.GetArgument("-algVersion", 0);
string programName = cmdLine.GetArgument("-programName", 0);
string programVersion = cmdLine.GetArgument("-programVersion", 0);
string programCompany = cmdLine.GetArgument("-programCompany", 0);
vector<string> paramNames;
int n = cmdLine.GetArgumentCount("-paramNames");
for (int i=0; i<n; i++)
paramNames.push_back(cmdLine.GetArgument("-paramNames", i));
vector<string> paramValues;
n = cmdLine.GetArgumentCount("-paramValues");
for (int i=0; i<n; i++)
paramValues.push_back(cmdLine.GetArgument("-paramValues", i));
vector<string> sumNames;
n = cmdLine.GetArgumentCount("-sumNames");
for (int i=0; i<n; i++)
sumNames.push_back(cmdLine.GetArgument("-sumNames", i));
vector<string> sumValues;
n = cmdLine.GetArgumentCount("-sumValues");
for (int i=0; i<n; i++)
sumValues.push_back(cmdLine.GetArgument("-sumValues", i));
// Read the TSV input file
list<string> names;
list<float> quantifications;
ReadData(inFile, names, quantifications);
// Create the CHP file.
CreateFileWithHeader(execId, celFile, outFile, names, algName, algVersion, arrayType,
programName, programVersion, programCompany, paramNames, paramValues, sumNames, sumValues);
UpdateQuantifications(outFile, quantifications);
}
catch (string s)
{
cout << s << endl;
show_help();
}
catch (int e)
{
cout << "Invalid argument" << endl;
show_help();
}
catch (...)
{
cout << "Unknown error" << endl;
show_help();
}
return 0;
}
int main( int argc, char** argv )
{
#ifdef USE_CVCAM
bool cvcam=true;
#else
bool cvcam=false;
#endif
if (cmdLine.SplitLine(argc, argv) < 1)
{
// no switches were given on the command line, abort
//ShowHelp();
//exit(-1);
}
std::string infile="../../../stip_online/video/walk-complex.avi";
std::string tmp;
int cam=-1;
try
{
if( cmdLine.HasSwitch("-h") ||
cmdLine.HasSwitch("-help") ||
cmdLine.HasSwitch("--help"))
{
ShowHelp();
exit(0);
}
if( cmdLine.HasSwitch("-f") && cmdLine.HasSwitch("-cam") )
{
std::cout<<"You can't specify both file and camera as input!"<<std::endl;
ShowHelp();
exit(-1);
}
if( !(cmdLine.HasSwitch("-f") || cmdLine.HasSwitch("-cam") ))
{
std::cout<<"no input..."<<std::endl;
ShowHelp();
exit(-1);
}
//*** input/output options
if(cmdLine.GetArgumentCount("-f")>0)
infile = cmdLine.GetArgument("-f", 0);
if(cmdLine.GetArgumentCount("-o")>0)
outfile = cmdLine.GetArgument("-o", 0);
if(cmdLine.HasSwitch("-cam"))
if(cmdLine.GetArgumentCount("-cam")>0)
cam = atoi(cmdLine.GetArgument("-cam", 0).c_str());
else
cam = -1;
if(cmdLine.GetArgumentCount("-res")>0) resid = atoi(cmdLine.GetArgument( "-res", 0 ).c_str());
if(resid<0 || resid>4) resid=1;
if(cmdLine.GetArgumentCount("-vis")>0) show = cmdLine.GetArgument("-vis", 0)=="yes"?true:false;
//*** descriptor options
if(cmdLine.GetArgumentCount("-dscr")>0) mshb.descriptortype = cmdLine.GetArgument("-dscr", 0);
if(cmdLine.GetArgumentCount("-szf")>0) mshb.patchsizefactor = atof(cmdLine.GetArgument("-szf", 0).c_str());
//*** detection options
if(cmdLine.GetArgumentCount("-nplev")>0) mshb.nxplev=atoi(cmdLine.GetArgument("-nplev", 0).c_str());
if(cmdLine.GetArgumentCount("-plev0")>0) mshb.initpyrlevel=atoi(cmdLine.GetArgument("-plev0", 0).c_str());
//if(cmdLine.GetArgumentCount("-sigma")>0) hb.sig2 = atof(cmdLine.GetArgument( "-sigma", 0 ).c_str());
//if(cmdLine.GetArgumentCount("-tau")>0) hb.tau2 = atof(cmdLine.GetArgument( "-tau", 0 ).c_str());
if(cmdLine.GetArgumentCount("-kparam")>0) mshb.kparam = atof(cmdLine.GetArgument( "-kparam", 0 ).c_str());
if(cmdLine.GetArgumentCount("-thresh")>0) mshb.SignificantPointThresh = atof(cmdLine.GetArgument( "-thresh", 0 ).c_str());
if(cmdLine.GetArgumentCount("-border")>0) mshb.Border = atoi(cmdLine.GetArgument( "-border", 0 ).c_str());
//*** video capture options
mshb.framemax = 100000000;
if(cmdLine.GetArgumentCount("-framemax")>0) mshb.framemax = atoi(cmdLine.GetArgument( "-framemax", 0 ).c_str());
if(cmdLine.GetArgumentCount("-ff")>0) frame_begin = atoi(cmdLine.GetArgument( "-ff", 0 ).c_str());
if(cmdLine.GetArgumentCount("-lf")>0) frame_end = atoi(cmdLine.GetArgument( "-lf", 0 ).c_str());
}
catch (...)
{
ShowHelp();
exit(-1);
}
if(infile=="") //prb:both can handle cam and file
{
if(!InitCVCAM(cam))
return -2;
// initialize source name string
sourcename="CameraStream";
} else {
cvcam=false;
if(!InitCapture(infile.c_str()))
return -2;
// initialize source name string
sourcename=infile;
std::cout<<"Options summary: "<<std::endl;
std::cout<<" video input: "<<sourcename<<std::endl;
std::cout<<" frame interval: "<<frame_begin<<"-"<<frame_end<<std::endl;
std::cout<<" output file: "<<outfile<<std::endl;
std::cout<<" #pyr.levels: "<<mshb.nxplev<<std::endl;
std::cout<<" init.pyr.level: "<<mshb.initpyrlevel<<std::endl;
std::cout<<" patch size fct.: "<<mshb.patchsizefactor<<std::endl;
std::cout<<" descriptor type: "<<mshb.descriptortype<<std::endl;
}
if(show)
{
//cvNamedWindow( win1, CV_WINDOW_AUTOSIZE );
cvNamedWindow( win2, 0 );
}
//cvNamedWindow("Original");
if(capture)
{
int fn=0;
for(;;)
{
if (fn>=mshb.framemax) break;
if (fn>=frame_end-frame_begin) break;
fn++;
frame = cvQueryFrame( capture );
if( !frame )
break;
//CVUtil::DrawCircleFeature(frame,cvPoint(10,10),4.0);
//CapProperties(capture);
//cvShowImage("Original",frame);
dostuff(frame);
if(show)
{
dovisstuff();
//cvWaitKey();
cvWaitKey(10);
//if(cvWaitKey(10) >= 0 )
// break;
}
}
}
std::cout<<"-> detected "<<TotalIPs<<" points"<<std::endl;
#ifdef USE_CVCAM
if(cvcam)
{
cvWaitKey(0);
cvcamExit();
}
#endif
if(capture)
cvReleaseCapture( &capture );
if(show)
{
cvDestroyWindow(win1);
}
if(gray) cvReleaseImage(&gray);
if(vis) cvReleaseImage(&vis);
if(vis2) cvReleaseImage(&vis2);
if(vis3) cvReleaseImage(&vis3);
if(camimg) cvReleaseImage(&camimg);
return 0;
}
int main(int argc, char* argv[]){
CCmdLine cmdLine;
cmdLine.SplitLine(argc, argv);
if ( !(cmdLine.HasSwitch("-i") && cmdLine.HasSwitch("-o") && (cmdLine.HasSwitch("-pos") || cmdLine.HasSwitch("-f") || cmdLine.HasSwitch("-pbOnly"))) ){
fprintf(stderr, "usage: %s -i <image> -o <output-directory> < -pos <x> <y> | -f <fixation-points-file> > [ -pb <probabilistic-boundary-prefix ] [ -flow <optical-flow-file> ] [ -sobel ]\n",argv[0]);
fprintf(stderr, "OR \t %s -pbOnly -i <image> -o <output-probabilistic-boundary-prefix>\n",argv[0]);
exit(1);
}
class segLayer frame1;
char tmp[80];
strcpy (tmp, cmdLine.GetArgument("-i", 0).c_str());
int64 tic1,tic2,tic3,tic4;
double ticFrequency = cvGetTickFrequency()*1000000;
tic1=cvGetTickCount();
IplImage *im=cvLoadImage(tmp), *im2;
#ifdef CUDA_SUPPORT
int maxWidth=640;
#else
int maxWidth=640;
#endif
bool resized=false;
float scale=1;
if(cvGetSize(im).width>maxWidth){
scale=maxWidth/(double)(cvGetSize(im).width);
printf("Image too big, resizing it for the segmentation...\n");
int newHeight=(int)(cvGetSize(im).height*scale);
im2=cvCreateImage( cvSize(maxWidth,newHeight), IPL_DEPTH_8U, 3 );
cvResize(im,im2);
resized=true;
}else{
im2=im;
}
frame1.setImage(im2);
if (cmdLine.HasSwitch("-pb")){
strcpy (tmp, cmdLine.GetArgument("-pb", 0).c_str());
frame1.readPbBoundary(tmp);
}else{
// Edge detection!
if (cmdLine.HasSwitch("-sobel"))
frame1.edgeSobel();
else{
#ifdef CUDA_SUPPORT
if(!get_lock()){
fprintf(stderr,"Impossible to get the lock...\n");
exit(1);
}
frame1.edgeGPU(false);
if(!release_lock()){
fprintf(stderr,"Impossible to release the lock...\n");
exit(1);
}
#else
frame1.edgeCGTG();
#endif
}
tic2=cvGetTickCount();
if (cmdLine.HasSwitch("-flow")){
strcpy (tmp, cmdLine.GetArgument("-flow", 0).c_str());
IplImage *flow=cvLoadImage(tmp);
IplImage *flow32 = cvCreateImage(cvGetSize(flow), IPL_DEPTH_32F,3);
IplImage *flowU = cvCreateImage(cvGetSize(flow), IPL_DEPTH_32F,1);
IplImage *flowV = cvCreateImage(cvGetSize(flow), IPL_DEPTH_32F,1);
cvConvertScale(flow, flow32, 40/255.,-20);
cvSplit(flow32,flowU,NULL,NULL,NULL);
cvSplit(flow32,NULL,flowV,NULL,NULL);
frame1.setU(flowU);
frame1.setV(flowV);
cvReleaseImage(&flow);
cvReleaseImage(&flow32);
}
frame1.generatePbBoundary();
}
if (cmdLine.HasSwitch("-pbOnly")){
strcpy (tmp, cmdLine.GetArgument("-o", 0).c_str());
frame1.savePbBoundary(tmp);
}else{
frame1.allocateMemForContours();// Don't forget to allocate memory to store the region contours.
//select fixation point!
if(cmdLine.HasSwitch("-pos")){
float x,y;
sscanf(cmdLine.GetArgument("-pos", 0).c_str(),"%f",&x);
sscanf(cmdLine.GetArgument("-pos", 1).c_str(),"%f",&y);
frame1.assignFixPt((int)(x*scale), (int)(y*scale));
}else{
strcpy (tmp, cmdLine.GetArgument("-f", 0).c_str());
frame1.readFixPts(tmp,scale);
}
//segment
frame1.segmentAllFixs();
tic3=cvGetTickCount();
//display!
//frame1.displayCurrSegs(-1);
strcpy (tmp, cmdLine.GetArgument("-o", 0).c_str());
//sprintf(tmp,"%s/",tmp);
if(resized)
frame1.saveResizedRegions(tmp,cvGetSize(im).width,cvGetSize(im).height);
else
frame1.saveRegions(tmp);
//release memory!
frame1.deallocateMemForContours();
}
tic4=cvGetTickCount();
printf("\n\nTotal time = %f\n",(tic4-tic1)/ticFrequency);
if(!cmdLine.HasSwitch("-pb"))
printf("\t edges detection = %f\n",(tic2-tic1)/ticFrequency);
if(!cmdLine.HasSwitch("-pbOnly"))
printf("\t segmentation = %f\n",(tic3-tic2)/ticFrequency);
return 0;
}
/*! The main entrance to the program. */
int main(int argc, char * argv[])
{
try
{
// Parse the command line arguments.
CCmdLine cmdLine;
if (cmdLine.SplitLine(argc, argv) < 1)
{
show_help();
exit(-1);
}
string execId = cmdLine.GetArgument("-execid", 0);
string celFile = cmdLine.GetSafeArgument("-cel", 0, "");
string inFile = cmdLine.GetArgument("-in", 0);
string outFile = cmdLine.GetArgument("-out", 0);
string arrayType = cmdLine.GetArgument("-arrayType", 0);
string algName = cmdLine.GetArgument("-algName", 0);
string algVersion = cmdLine.GetArgument("-algVersion", 0);
string programName = cmdLine.GetArgument("-programName", 0);
string programVersion = cmdLine.GetArgument("-programVersion", 0);
string programCompany = cmdLine.GetArgument("-programCompany", 0);
vector<string> colNames;
int n = cmdLine.GetArgumentCount("-colNames");
for (int i=0; i<n; i++)
colNames.push_back(cmdLine.GetArgument("-colNames", i));
vector<string> colTypes;
n = cmdLine.GetArgumentCount("-colTypes");
for (int i=0; i<n; i++)
colTypes.push_back(cmdLine.GetArgument("-colTypes", i));
vector<string> paramNames;
n = cmdLine.GetArgumentCount("-paramNames");
for (int i=0; i<n; i++)
paramNames.push_back(cmdLine.GetArgument("-paramNames", i));
vector<string> paramValues;
n = cmdLine.GetArgumentCount("-paramValues");
for (int i=0; i<n; i++)
paramValues.push_back(cmdLine.GetArgument("-paramValues", i));
vector<string> sumNames;
n = cmdLine.GetArgumentCount("-sumNames");
for (int i=0; i<n; i++)
sumNames.push_back(cmdLine.GetArgument("-sumNames", i));
vector<string> sumValues;
n = cmdLine.GetArgumentCount("-sumValues");
for (int i=0; i<n; i++)
sumValues.push_back(cmdLine.GetArgument("-sumValues", i));
vector<string> extraNames;
n = cmdLine.GetArgumentCount("-extraNames");
for (int i=0; i<n; i++)
extraNames.push_back(cmdLine.GetArgument("-extraNames", i));
vector<string> extraValues;
n = cmdLine.GetArgumentCount("-extraValues");
for (int i=0; i<n; i++)
extraValues.push_back(cmdLine.GetArgument("-extraValues", i));
// Read the TSV input file
int maxProbeSetNameLength = 0;
// data collection is no longer used, so we have ReadData return the row count so that we can pass it into
// CreateFileWithHeader call
unsigned long rowCount = ReadData(inFile, maxProbeSetNameLength);
// Create the CHP file.
// Creates the header
CreateFileWithHeader(execId, celFile, outFile, colNames, colTypes, rowCount, maxProbeSetNameLength,
algName, algVersion, arrayType, programName, programVersion, programCompany, paramNames, paramValues,
sumNames, sumValues, extraNames, extraValues);
// add the body (data)
AddFileBody(inFile,outFile, maxProbeSetNameLength, colTypes);
}
catch (string s)
{
cout << s << endl;
show_help();
}
catch (int e)
{
cout << "Invalid argument" << endl;
show_help();
}
catch (...)
{
cout << "Unknown error" << endl;
show_help();
}
return 0;
}
int main(int argc, char* argv[])
{
// Read in parameters from command line.
CCmdLine cmdLine;
if(cmdLine.SplitLine(argc, argv) < 3)
{
cerr << "Usage: ./gittar -m consensus_motif -e log_ratio_file -s promoter_sequence" << endl;
cerr << "Additional parameters:" << endl;
cerr << "[-mis] mismatches to consensus motif(Default=1)" << endl;
cerr << "[-a] annotation file" << endl;
cerr << "[-o] output(gene_and_other_info PSFM)" << endl;
cerr << "[-v] verbose mode" << endl;
cerr << "[-h] hyperprio parameters(hyper_samples=50 mu=2.0 sigma^2=1.0 flanking_length=7" << endl;
cerr << "[-n] DO NOT use prio information(overide hyperprio parameters)" << endl;
cerr << "[-g] Gibbs sampler parameters(starting_point=10 burn-in=100 window=100)" << endl;
cerr << "[-misc] Miscellaneous parameters(stds_of_intial_target=4 skip_core_region=0 random_background=0 threshold_for_target=0.5 stds_enfore=1)" << endl;
return 1;
}
string m, e, s;
try
{
m = cmdLine.GetArgument("-m", 0);
e = cmdLine.GetArgument("-e", 0);
s = cmdLine.GetArgument("-s", 0);
}
catch(int)
{
cerr << "Wrong arguments!" << endl;
return 1;
}
string mis = cmdLine.GetSafeArgument("-mis", 0, "1"); // mismatches.
unsigned misallow = atoi(mis.data());
string a = cmdLine.GetSafeArgument("-a", 0, ""); // gene annotation file.
string o1 = cmdLine.GetSafeArgument("-o", 0, ""); // output gene and other information.
string o2 = cmdLine.GetSafeArgument("-o", 1, ""); // output PSFM.
// Hyper-prio parameters.
HypePrio hypePrio;
string v = cmdLine.GetSafeArgument("-h", 0, "50");
hypePrio.V = atoi(v.data());
string mu = cmdLine.GetSafeArgument("-h", 1, "2.0");
hypePrio.MU = atof(mu.data());
string sigma2 = cmdLine.GetSafeArgument("-h", 2, "1.0");
hypePrio.SIGMA_2 = atof(sigma2.data());
string flanking = cmdLine.GetSafeArgument("-h", 3, "7");
hypePrio.FLANKING = atoi(flanking.data());
// DO NOT use prior information?
if(cmdLine.HasSwitch("-n"))
hypePrio.V = 1;
// Gibbs-sampler parameters.
string sta_pnt = cmdLine.GetSafeArgument("-g", 0, "10");
STA_PNT = atoi(sta_pnt.data());
string burn_in = cmdLine.GetSafeArgument("-g", 1, "100");
BURN_IN = atoi(burn_in.data());
string window = cmdLine.GetSafeArgument("-g", 2, "100");
WINDOW = atoi(window.data());
// Miscellaneous parameters.
string iniv = cmdLine.GetSafeArgument("-misc", 0, "4");
INIV = atoi(iniv.data());
string skipcore = cmdLine.GetSafeArgument("-misc", 1, "0");
SKIPCORE = atoi(skipcore.data());
string randbg = cmdLine.GetSafeArgument("-misc", 2, "0");
RANDBG = atoi(randbg.data());
VERBOSE = cmdLine.HasSwitch("-v"); // verbose mode switch.
// Load data into memory.
string motifSeq; // string of motif sequence.
Expr expr; // hash table of expression values.
Seq seq; // hash table of sequences.
GeneAnno geneAnno; // hash table of gene annotation info.
if(VERBOSE)
cout << "Loading...motif...expression...sequence..." << endl;
if(load_data(m, e, s, a, motifSeq, expr, seq, geneAnno)) // load data.
{
cerr << "Error occurs during data loading!" << endl;
return 1;
}
if(VERBOSE)
cout << "Data load complete!" << endl;
// Normalize expression levels.
double bkm = mean(expr);
double bkstd = stnd(expr, bkm);
if(VERBOSE)
cout << "All gene mean: " << bkm << ", standard deviation: " << bkstd << endl;
// Find all genes containing the motif with mismatch.
VGene vGene;
motifgene(motifSeq, hypePrio.FLANKING, expr, seq, misallow, vGene);
if(VERBOSE)
cout << "Total genes identified: " << vGene.size() << endl;
// Calculate pseudo-count for DNA bases among all sequences.
double dnaPor[4];
sudocnt(seq, dnaPor);
if(VERBOSE)
{
cout << "DNA bases portion in all sequences." << endl;
cout << "A: " << dnaPor[0] << endl;
cout << "C: " << dnaPor[1] << endl;
cout << "G: " << dnaPor[2] << endl;
cout << "T: " << dnaPor[3] << endl;
}
// Gibbs sampler starts from here...
double tPSFM[4][40], nPSFM[4][40]; // target and non-target PSFM.
double mTarget, s2Target;
SST eLen = motifSeq.length() + 2*hypePrio.FLANKING;
setzero(tPSFM, 4, (unsigned)eLen);
setzero(nPSFM, 4, (unsigned)eLen);
mTarget = s2Target = 0.0;
for(unsigned i = 0; i < STA_PNT; i++)
{
// Generate candidate genes' initial labels.
genlbl(vGene, bkm, bkstd);
// Use Gibbs Sampler to calculate the estimated labels.
if(VERBOSE)
cout << "Gibbs sampler starting..." << endl;
double mTarget_, s2Target_;
double tPSFM_[4][40], nPSFM_[4][40];
/*
Here go the parameters information:
vGene: Information about all genes that contain motif.
dnaPor: DNA pseudo-count.
seq: Promoter sequences for all genes.
mVal: background expression mean.
sVal: background expression std.
*/
int iter;
iter = gsamp(vGene, mTarget_, s2Target_, tPSFM_, nPSFM_, misallow, dnaPor, motifSeq, seq, bkm, bkstd, hypePrio);
if(VERBOSE)
cout << "Gibbs sampler stops with " << iter << " iterations." << endl;
mTarget += mTarget_;
s2Target += s2Target_;
add2mat(tPSFM, tPSFM, tPSFM_, (unsigned)eLen);
add2mat(nPSFM, nPSFM, nPSFM_, (unsigned)eLen);
if(VERBOSE)
{
cout << "Target genes in last iteration: " << ntar(vGene) << endl;
cout << "Non-target genes in last iteration: " << nnon(vGene) << endl;
}
sum_iter(i, vGene);
}
// Summarize the results from different starting points.
avg_iter(vGene);
unsigned nTar = ntar(vGene, true);
unsigned nNon = nnon(vGene, true);
mTarget /= STA_PNT;
s2Target /= STA_PNT;
normat(tPSFM, (unsigned)eLen, STA_PNT);
normat(nPSFM, (unsigned)eLen, STA_PNT);
// Write results into files.
if(VERBOSE)
cout << "Writing results into files..." << endl;
time_t time_tag = time(NULL);
if(o2 == "")
{
ostringstream logstream;
logstream << time_tag << "_" << motifSeq << "_mis" << misallow << ".log";
o2 = logstream.str();
}
// PSFMs and profile ratios.
if(write_log(o2, (unsigned)eLen, tPSFM, nPSFM) != 0)
cerr << "Writing matrices information failed!" << endl;
else if(VERBOSE)
cout << "PSFMs and profile ratios write complete!" << endl;
// Re-calculate binding site according to the averaged PSFM.
map<string, string> mbindloc; // A map to store all binding sites of each gene.
for(unsigned i = 0; i < vGene.size(); i++)
mbindloc[vGene[i].name] = bindsite(vGene[i], vGene[i].target, seq[vGene[i].name], tPSFM, nPSFM, hypePrio.FLANKING);
// Write genes information.
// Sort genes according to their probabilities and expression values.
sort(vGene.begin(), vGene.end(), cmp);
if(o1 == "")
{
ostringstream infostream;
infostream << time_tag << "_" << motifSeq << "_mis" << misallow << ".info";
o1 = infostream.str();
}
if(write_info(o1, vGene, geneAnno, mTarget, sqrt(s2Target), bkm, bkstd,
(unsigned)seq.size(), nTar, nNon, hypePrio, motifSeq, mbindloc) != 0)
cerr << "Writing genes information failed!" << endl;
else if(VERBOSE)
{
cout << "Genes information write complete!" << endl;
cout << "Finished!" << endl;
}
return 0;
}
int
P300ClassifierMain( int argc, char **argv, QApplication& app )
{
ConfigDialog dialog;
CCmdLine cmdLine;
QString arg_TrainingDataFiles;
QString arg_TestingDataFiles;
QString arg_inicfg;
QStringList arg_TrainingDataFilesList;
QStringList arg_TestingDataFilesList;
bool barg_TrainingDataFiles;
bool barg_TestingDataFiles;
bool barg_inicfg;
cmdLine.SplitLine(argc, argv);
barg_TrainingDataFiles =cmdLine.HasSwitch("-TrainingDataFiles");
barg_TestingDataFiles =cmdLine.HasSwitch("-TestingDataFiles");
barg_inicfg =cmdLine.HasSwitch("-inicfg");
//int co = cmdLine.GetArgumentCount("-TrainingDataFiles");
if (barg_TrainingDataFiles)
{
for (int i=0; i<cmdLine.GetArgumentCount("-TrainingDataFiles"); i++)
{
arg_TrainingDataFiles = arg_TrainingDataFiles.fromStdString(cmdLine.GetArgument("-TrainingDataFiles",i));
arg_TrainingDataFilesList.insert(i, arg_TrainingDataFiles);
}
}
else
{
arg_TrainingDataFiles = "";
}
if (barg_TestingDataFiles)
{
for (int i=0; i<cmdLine.GetArgumentCount("-TestingDataFiles"); i++)
{
arg_TestingDataFiles = arg_TestingDataFiles.fromStdString(cmdLine.GetArgument("-TestingDataFiles",i));
arg_TestingDataFilesList.insert(i, arg_TestingDataFiles);
}
}
else
{
arg_TestingDataFiles = "";
}
if (barg_inicfg)
{
arg_inicfg = arg_inicfg.fromStdString(cmdLine.GetArgument("-inicfg",0));
}
else
{
arg_inicfg = "";
}
QString classifierOutputFile = cmdLine.GetSafeArgument( "-ClassifierOutputFile", 0, "" ).c_str();
dialog.SetFiles(arg_TrainingDataFilesList, arg_TestingDataFilesList, arg_inicfg, classifierOutputFile);
return dialog.exec();
}
int MainEntry(HINSTANCE hInstance,
HINSTANCE hPrevInstance,
LPSTR lpCmdLine,
int nCmdShow)
{
MSG msg;
ULONG_PTR gdiplusToken;
GdiplusStartupInput gdiplusStartupInput;
BOOL bConsoleAttached = FALSE;
// Set locale
char *locale = setlocale(LC_ALL, ".936");
// Startup GDI+
Status status = GdiplusStartup(&gdiplusToken, &gdiplusStartupInput, NULL);
if (status != Ok)
return FALSE;
// set options by command line
CCmdLine cmdline;
if (cmdline.SplitLine(__argc, __argv) > 0)
{
if (cmdline.HasSwitch("-width"))
g_nScreenWidth = atoi(cmdline.GetArgument("-width", 0).c_str());
if (cmdline.HasSwitch("-height"))
g_nScreenHeight = atoi(cmdline.GetArgument("-height", 0).c_str());
if (cmdline.HasSwitch("-d"))
{
if (AttachConsole(ATTACH_PARENT_PROCESS))
{
bConsoleAttached = TRUE;
freopen("CONIN$", "r", stdin);
freopen("CONOUT$", "w", stdout);
freopen("CONOUT$", "w", stderr);
}
}
if (cmdline.HasSwitch("-appid"))
{
xsStrCpyN(g_szAppId, cmdline.GetArgument("-appid", 0).c_str(), sizeof(g_szAppId));
}
}
xsTcsCpy((xsTChar *)g_szTitle, xsT("XSKit"));
xsTcsCpy((xsTChar *)g_szWindowClass, xsT("XSKitMainWnd"));
RegisterWndClass(hInstance);
if (!InitInstance (hInstance, nCmdShow))
{
if (bConsoleAttached)
FreeConsole();
return FALSE;
}
while (GetMessage(&msg, NULL, 0, 0))
{
TranslateMessage(&msg);
DispatchMessage(&msg);
}
xsPalGuiUninit();
if (bConsoleAttached)
FreeConsole();
// Shutdown GDI+
GdiplusShutdown(gdiplusToken);
return msg.wParam;
}
int main(int argc, char* argv[])
{
// Read parameters from console.
CCmdLine cmdLine;
if(cmdLine.SplitLine(argc, argv) < 5)
{
cerr << "Usage: ./bbnet -s score_file -n node -b bkg -f func_depth -o output" << endl;
cerr << endl << "Additional parameter:" << endl;
cerr << "-k\tPenalty parameter(logK, Default = 5.0)" << endl;
cerr << "-c\tnumber of candidate motifs (Default=50)" << endl;
cerr << "-d\tpositive negative (for prediction using BN)" << endl;
cerr << "-l\toutput of all training samples' information." << endl;
cerr << "-t\ttranslational(transcriptional) start sites.(Default = right end)" << endl;
cerr << "-rb\tbit-string to determine which rules to include.(Default = 111110)" << endl;
cerr << "-i\tUse mutual information instead of Bayesian score" << endl;
cerr << endl << "Contact: \"Li Shen\"<*****@*****.**>" << endl;
return 1;
}
string s, n, b, f, o;
try
{
s = cmdLine.GetArgument("-s", 0); // score file.
n = cmdLine.GetArgument("-n", 0); // node gene list file.
b = cmdLine.GetArgument("-b", 0); // bkg gene list file.
f = cmdLine.GetArgument("-f", 0); // func depth folder.
o = cmdLine.GetArgument("-o", 0); // results output file.
}
catch(int)
{
cerr << "Wrong arguments!" << endl;
return 1;
}
if(cmdLine.HasSwitch("-i"))
itag = true;
//itag = true;
//string s = "../gbnet/data/Beer/scor_test.list";
//string n = "../gbnet/data/Beer/node.list";
//string b = "../gbnet/data/Beer/bkg.list";
//string f = "../gbnet/data/Beer/func";
//string k = "0.015";
//logK = atof(k.data());
//string o = "../gbnet/data/Beer/bb_res_test2.txt";
string k; // Penalty parameter; logK value.
if(!itag)
k = cmdLine.GetSafeArgument("-k", 0, "5.0");
else
k = cmdLine.GetSafeArgument("-k", 0, "0.015");
logK = atof(k.data());
string c = cmdLine.GetSafeArgument("-c", 0, "50"); // number of candidate motifs. default = 50.
motifcand = atoi(c.data());
// Use prior counts for some motifs if specified.
string p = cmdLine.GetSafeArgument("-p", 0, "0"); // prior counts.
pricnt = atoi(p.data());
if(pricnt > 0) // read preferred motifs list from file.
{
prior = 1;
string fPrim = cmdLine.GetSafeArgument("-p", 1, "primot.txt");
vector<string> primv;
if(get1stcol(fPrim, primv) < 0)
return 1;
for(size_t i = 0; i < primv.size(); i++)
primo.insert(primv[i]);
}
// File names for positive, negative and left-out testing lists.
string pos = cmdLine.GetSafeArgument("-d", 0, ""); // positive testing cases.
string neg = cmdLine.GetSafeArgument("-d", 1, ""); // negative testing cases.
string res = cmdLine.GetSafeArgument("-d", 2, ""); // left-out testing cases.
vector<string> plst, nlst, rlst; // positive, negative and left-out lists.
if(pos != "" && neg != "")
{
if(get1stcol(pos, plst) < 0)
return 1;
if(get1stcol(neg, nlst) < 0)
return 1;
}
if(res != "")
{
if(get1stcol(res, rlst) < 0)
return 1;
}
// File for output of all training samples' information.
string finfo = cmdLine.GetSafeArgument("-l", 0, "");
// File to store all genes' translational/transcriptional start sites.
string ftss = cmdLine.GetSafeArgument("-t", 0, "");
if(ftss != "")
loadtss(ftss, mtss);
// A bit-string to determine which rules to include.
rb = cmdLine.GetSafeArgument("-rb", 0, "111110");
string bp = cmdLine.GetSafeArgument("-bp", 0, ""); // Output each gene's probability like in Beer's prediction.
// Load motif Bayesian score file.
if(loadscor(mscor, s) != 0)
{
cerr << "Load motif scores eror!" << endl;
return 1;
}
else
{
#ifdef VERBOSE
cout << "Display candidate motifs that are loaded:" << endl;
dispscor(mscor);
#endif
}
vector<MotifScore> oscor = mscor; // Save an original copy of motif scores.
// Load gene list.
vector<Case> tlst, blst, genlst;
set<string> genset;
if(loadgene(tlst, blst, n, b) != 0)
{
cerr << "Load gene lists error!" << endl;
return 1;
}
else
{
genlst.insert(genlst.end(), tlst.begin(), tlst.end());
genlst.insert(genlst.end(), blst.begin(), blst.end());
#ifdef VERBOSE
cout << "Load gene list completed!" << endl;
#endif
// All training and testing gene names are put into genmap.
for(size_t i = 0; i < genlst.size(); i++)
genset.insert(genlst[i].name);
for(size_t i = 0; i < plst.size(); i++)
genset.insert(plst[i]);
for(size_t i = 0; i < nlst.size(); i++)
genset.insert(nlst[i]);
for(size_t i = 0; i < rlst.size(); i++)
genset.insert(rlst[i]);
}
// Load motif binding information of genes in genmap.
if(loadbind(allbind, mscor, genset, f) != 0)
{
cerr << "Load binding information error!" << endl;
return 1;
}
else
{
#ifdef VERBOSE
cout << "Load binding information completed!" << endl;
#endif
}
// File for output.
ofstream hOut(o.data());
if(!hOut)
{
cerr << "Can't open " << o << endl;
return 1;
}
hOut << "Number of genes in category 1: " << tlst.size() << endl;
hOut << "Number of genes in category 0: " << blst.size() << endl << endl;
#ifdef VERBOSE
cout << endl << "Running on original data." << endl;
#endif
vector<Constraint> cons;
vector<CPTRow> cpt;
clock_t start = clock();
double scor = bbnet(cons, cpt, genlst);
clock_t finish = clock();
if(outbayes(hOut, scor, cons, cpt, oscor, tlst.size(), blst.size()) != 0)
{
cerr << "Output Bayesian network results error!" << endl;
return 1;
}
if(finfo != "")
{
if(outgene(finfo, tlst, blst, cons) != 0)
cerr << "Output training samples' information error!" << endl;
return 1;
}
if(pos != "" && neg != "")
{
Pred d = predict(cons, cpt, plst, nlst);
outpred(hOut, d, n, b, pos, neg);
if(bp != "") // output each gene's probability being in this cluster if output file is specified.
{
ofstream hbp(bp.data());
if(!hbp)
{
cerr << "Can't open " << bp << endl;
return 1;
}
vector<BPred> trnbp = predict(cons, cpt, genlst, 0); // probabilities for training genes.
outpred(hbp, trnbp);
vector<string> tstlst; // probabilities for testing genes.
tstlst.insert(tstlst.end(), plst.begin(), plst.end()); // positive testings.
tstlst.insert(tstlst.end(), nlst.begin(), nlst.end()); // negative testings.
vector<BPred> tstbp = predict(cons, cpt, tstlst, 1);
outpred(hbp, tstbp);
if(res != "") // probabilities for left-out genes if the left-out file is specified.
{
vector<BPred> lefbp = predict(cons, cpt, rlst, -1);
outpred(hbp, lefbp);
}
hbp.close();
}
}
hOut << endl << "Bayesian network occupied CPU " << (double)(finish-start)/CLOCKS_PER_SEC << " seconds." << endl;
hOut.close();
return 0;
}