int SequenceAlign(CpptrajState& State, ArgList& argIn) {
std::string blastfile = argIn.GetStringKey("blastfile");
if (blastfile.empty()) {
mprinterr("Error: 'blastfile' must be specified.\n");
return 1;
}
ReferenceFrame qref = State.DSL()->GetReferenceFrame(argIn);
if (qref.error() || qref.empty()) {
mprinterr("Error: Must specify reference structure for query.\n");
return 1;
}
std::string outfilename = argIn.GetStringKey("out");
if (outfilename.empty()) {
mprinterr("Error: Must specify output file.\n");
return 1;
}
TrajectoryFile::TrajFormatType fmt = TrajectoryFile::GetFormatFromArg(argIn);
if (fmt != TrajectoryFile::PDBFILE && fmt != TrajectoryFile::MOL2FILE)
fmt = TrajectoryFile::PDBFILE; // Default to PDB
int smaskoffset = argIn.getKeyInt("smaskoffset", 0) + 1;
int qmaskoffset = argIn.getKeyInt("qmaskoffset", 0) + 1;
// Load blast file
mprintf("\tReading BLAST alignment from '%s'\n", blastfile.c_str());
BufferedLine infile;
if (infile.OpenFileRead( blastfile )) return 1;
// Seek down to first Query line.
const char* ptr = infile.Line();
bool atFirstQuery = false;
while (ptr != 0) {
if (*ptr == 'Q') {
if ( strncmp(ptr, "Query", 5) == 0 ) {
atFirstQuery = true;
break;
}
}
ptr = infile.Line();
}
if (!atFirstQuery) {
mprinterr("Error: 'Query' not found.\n");
return 1;
}
// Read alignment. Replacing query with subject.
typedef std::vector<char> Carray;
typedef std::vector<int> Iarray;
Carray Query; // Query residues
Carray Sbjct; // Sbjct residues
Iarray Smap; // Smap[Sbjct index] = Query index
while (ptr != 0) {
const char* qline = ptr; // query line
const char* aline = infile.Line(); // alignment line
const char* sline = infile.Line(); // subject line
if (aline == 0 || sline == 0) {
mprinterr("Error: Missing alignment line or subject line after Query:\n");
mprinterr("Error: %s", qline);
return 1;
}
for (int idx = 12; qline[idx] != ' '; idx++) {
if (qline[idx] == '-') {
// Sbjct does not have corresponding res in Query
Smap.push_back(-1);
Sbjct.push_back( sline[idx] );
} else if (sline[idx] == '-') {
// Query does not have a corresponding res in Sbjct
Query.push_back( qline[idx] );
} else {
// Direct Query to Sbjct map
Smap.push_back( Query.size() );
Sbjct.push_back( sline[idx] );
Query.push_back( qline[idx] );
}
}
// Scan to next Query
ptr = infile.Line();
while (ptr != 0) {
if (*ptr == 'Q') {
if ( strncmp(ptr, "Query", 5) == 0 ) break;
}
ptr = infile.Line();
}
}
// DEBUG
std::string SmaskExp, QmaskExp;
if (State.Debug() > 0) mprintf(" Map of Sbjct to Query:\n");
for (int sres = 0; sres != (int)Sbjct.size(); sres++) {
if (State.Debug() > 0)
mprintf("%-i %3s %i", sres+smaskoffset, Residue::ConvertResName(Sbjct[sres]),
Smap[sres]+qmaskoffset);
const char* qres = "";
if (Smap[sres] != -1) {
qres = Residue::ConvertResName(Query[Smap[sres]]);
if (SmaskExp.empty())
SmaskExp.assign( integerToString(sres+smaskoffset) );
else
SmaskExp.append( "," + integerToString(sres+smaskoffset) );
if (QmaskExp.empty())
QmaskExp.assign( integerToString(Smap[sres]+qmaskoffset) );
else
QmaskExp.append( "," + integerToString(Smap[sres]+qmaskoffset) );
}
if (State.Debug() > 0) mprintf(" %3s\n", qres);
}
mprintf("Smask: %s\n", SmaskExp.c_str());
mprintf("Qmask: %s\n", QmaskExp.c_str());
// Check that query residues match reference.
for (unsigned int sres = 0; sres != Sbjct.size(); sres++) {
int qres = Smap[sres];
if (qres != -1) {
if (Query[qres] != qref.Parm().Res(qres).SingleCharName()) {
mprintf("Warning: Potential residue mismatch: Query %s reference %s\n",
Residue::ConvertResName(Query[qres]), qref.Parm().Res(qres).c_str());
}
}
}
// Build subject using coordinate from reference.
//AtomMask sMask; // Contain atoms that should be in sTop
Topology sTop;
Frame sFrame;
Iarray placeHolder; // Atom indices of placeholder residues.
for (unsigned int sres = 0; sres != Sbjct.size(); sres++) {
int qres = Smap[sres];
NameType SresName( Residue::ConvertResName(Sbjct[sres]) );
if (qres != -1) {
Residue const& QR = qref.Parm().Res(qres);
Residue SR(SresName, sres+1, ' ', QR.ChainID());
if (Query[qres] == Sbjct[sres]) { // Exact match. All non-H atoms.
for (int qat = QR.FirstAtom(); qat != QR.LastAtom(); qat++)
{
if (qref.Parm()[qat].Element() != Atom::HYDROGEN)
sTop.AddTopAtom( qref.Parm()[qat], SR );
sFrame.AddXYZ( qref.Coord().XYZ(qat) );
//sMask.AddAtom(qat);
}
} else { // Partial match. Copy only backbone and CB.
for (int qat = QR.FirstAtom(); qat != QR.LastAtom(); qat++)
{
if ( qref.Parm()[qat].Name().Match("N" ) ||
qref.Parm()[qat].Name().Match("CA") ||
qref.Parm()[qat].Name().Match("CB") ||
qref.Parm()[qat].Name().Match("C" ) ||
qref.Parm()[qat].Name().Match("O" ) )
{
sTop.AddTopAtom( qref.Parm()[qat], SR );
sFrame.AddXYZ( qref.Coord().XYZ(qat) );
}
}
}
} else {
// Residue in query does not exist for subject. Just put placeholder CA for now.
Vec3 Zero(0.0);
placeHolder.push_back( sTop.Natom() );
sTop.AddTopAtom( Atom("CA", "C "), Residue(SresName, sres+1, ' ', ' ') );
sFrame.AddXYZ( Zero.Dptr() );
}
}
//sTop.PrintAtomInfo("*");
mprintf("\tPlaceholder residue indices:");
for (Iarray::const_iterator p = placeHolder.begin(); p != placeHolder.end(); ++p)
mprintf(" %i", *p + 1);
mprintf("\n");
// Try to give placeholders more reasonable coordinates.
if (!placeHolder.empty()) {
Iarray current_indices;
unsigned int pidx = 0;
while (pidx < placeHolder.size()) {
if (current_indices.empty()) {
current_indices.push_back( placeHolder[pidx++] );
// Search for the end of this segment
for (; pidx != placeHolder.size(); pidx++) {
if (placeHolder[pidx] - current_indices.back() > 1) break;
current_indices.push_back( placeHolder[pidx] );
}
// DEBUG
mprintf("\tSegment:");
for (Iarray::const_iterator it = current_indices.begin();
it != current_indices.end(); ++it)
mprintf(" %i", *it + 1);
// Get coordinates of residues bordering segment.
int prev_res = sTop[current_indices.front()].ResNum() - 1;
int next_res = sTop[current_indices.back() ].ResNum() + 1;
mprintf(" (prev_res=%i, next_res=%i)\n", prev_res+1, next_res+1);
Vec3 prev_crd(sFrame.XYZ(current_indices.front() - 1));
Vec3 next_crd(sFrame.XYZ(current_indices.back() + 1));
prev_crd.Print("prev_crd");
next_crd.Print("next_crd");
Vec3 crd_step = (next_crd - prev_crd) / (double)(current_indices.size()+1);
crd_step.Print("crd_step");
double* xyz = sFrame.xAddress() + (current_indices.front() * 3);
for (unsigned int i = 0; i != current_indices.size(); i++, xyz += 3) {
prev_crd += crd_step;
xyz[0] = prev_crd[0];
xyz[1] = prev_crd[1];
xyz[2] = prev_crd[2];
}
current_indices.clear();
}
}
}
//Topology* sTop = qref.Parm().partialModifyStateByMask( sMask );
//if (sTop == 0) return 1;
//Frame sFrame(qref.Coord(), sMask);
// Write output traj
Trajout_Single trajout;
if (trajout.PrepareTrajWrite(outfilename, argIn, &sTop, CoordinateInfo(), 1, fmt)) return 1;
if (trajout.WriteSingle(0, sFrame)) return 1;
trajout.EndTraj();
return 0;
}
int Cluster_DPeaks::ChoosePointsAutomatically() {
// Right now all density values are discrete. Try to choose outliers at each
// value for which there is density.;
/*
// For each point, calculate average distance (X,Y) to points in next and
// previous density values.
const double dens_cut = 3.0 * 3.0;
const double dist_cut = 1.32 * 1.32;
for (Carray::const_iterator point0 = Points_.begin(); point0 != Points_.end(); ++point0)
{
int Npts = 0;
for (Carray::const_iterator point1 = Points_.begin(); point1 != Points_.end(); ++point1)
{
if (point0 != point1) {
// Only do this for close densities
double dX = (double)(point0->PointsWithinEps() - point1->PointsWithinEps());
double dX2 = dX * dX;
double dY = (point0->Dist() - point1->Dist());
double dY2 = dY * dY;
if (dX2 < dens_cut && dY2 < dist_cut) {
Npts++;
}
}
}
mprintf("%i %i %i\n", point0->PointsWithinEps(), point0->Fnum()+1, Npts);
}
*/
/*
CpptrajFile tempOut;
tempOut.OpenWrite("temp.dat");
int currentDensity = -1;
double distAv = 0.0;
double distSD = 0.0;
double sumWts = 0.0;
int nValues = 0;
Carray::const_iterator lastPoint = Points_.end() + 1;
for (Carray::const_iterator point = Points_.begin(); point != lastPoint; ++point)
{
if (point == Points_.end() || point->PointsWithinEps() != currentDensity) {
if (nValues > 0) {
distAv = distAv / sumWts; //(double)nValues;
distSD = (distSD / sumWts) - (distAv * distAv);
if (distSD > 0.0)
distSD = sqrt(distSD);
else
distSD = 0.0;
//mprintf("Density %i: %i values Avg= %g SD= %g SumWts= %g\n", currentDensity,
// nValues, distAv, distSD, sumWts);
tempOut.Printf("%i %g\n", currentDensity, distAv);
}
if (point == Points_.end()) break;
currentDensity = point->PointsWithinEps();
distAv = 0.0;
distSD = 0.0;
sumWts = 0.0;
nValues = 0;
}
double wt = exp(point->Dist());
double dval = point->Dist() * wt;
sumWts += wt;
distAv += dval;
distSD += (dval * dval);
nValues++;
}
tempOut.CloseFile();
*/
// BEGIN CALCULATING WEIGHTED DISTANCE AVERAGE
CpptrajFile tempOut;
tempOut.OpenWrite("temp.dat");
DataSet_Mesh weightedAverage;
Carray::const_iterator cp = Points_.begin();
// Skip local density of 0.
//while (cp->PointsWithinEps() == 0 && cp != Points_.end()) ++cp;
while (cp != Points_.end())
{
int densityVal = cp->PointsWithinEps();
Carray densityArray;
// Add all points of current density.
while (cp->PointsWithinEps() == densityVal && cp != Points_.end())
densityArray.push_back( *(cp++) );
mprintf("Density value %i has %zu points.\n", densityVal, densityArray.size());
// Sort array by distance
std::sort(densityArray.begin(), densityArray.end(), Cpoint::dist_sort());
// Take the average of the points weighted by their position.
double wtDistAv = 0.0;
double sumWts = 0.0;
//std::vector<double> weights;
//weights.reserve( densityArray.size() );
int maxPt = (int)densityArray.size() - 1;
for (int ip = 0; ip != (int)densityArray.size(); ++ip)
{
double wt = exp( (double)(ip - maxPt) );
//mprintf("\t%10i %10u %10u %10g\n", densityVal, ip, maxPt, wt);
wtDistAv += (densityArray[ip].Dist() * wt);
sumWts += wt;
//weights.push_back( wt );
}
wtDistAv /= sumWts;
// Calculate the weighted sample variance
//double distSD = 0.0;
//for (unsigned int ip = 0; ip != densityArray.size(); ++ip) {
// double diff = densityArray[ip].Dist() - wtDistAv;
// distSD += weights[ip] * (diff * diff);
//}
//distSD /= sumWts;
weightedAverage.AddXY(densityVal, wtDistAv);
//tempOut.Printf("%i %g %g %g\n", densityVal, wtDistAv, sqrt(distSD), sumWts);
tempOut.Printf("%i %g %g\n", densityVal, wtDistAv, sumWts);
/*
// Find the median.
double median, Q1, Q3;
if (densityArray.size() == 1) {
median = densityArray[0].Dist();
Q1 = median;
Q3 = median;
} else {
unsigned int q3_beg;
unsigned int med_idx = densityArray.size() / 2; // Always 0 <= Q1 < med_idx
if ((densityArray.size() % 2) == 0) {
median = (densityArray[med_idx].Dist() + densityArray[med_idx-1].Dist()) / 2.0;
q3_beg = med_idx;
} else {
median = densityArray[med_idx].Dist();
q3_beg = med_idx + 1;
}
if (densityArray.size() == 2) {
Q1 = densityArray[0].Dist();
Q3 = densityArray[1].Dist();
} else {
// Find lower quartile
unsigned int q1_idx = med_idx / 2;
if ((med_idx % 2) == 0)
Q1 = (densityArray[q1_idx].Dist() + densityArray[q1_idx-1].Dist()) / 2.0;
else
Q1 = densityArray[q1_idx].Dist();
// Find upper quartile
unsigned int q3_size = densityArray.size() - q3_beg;
unsigned int q3_idx = (q3_size / 2) + q3_beg;
if ((q3_size %2) == 0)
Q3 = (densityArray[q3_idx].Dist() + densityArray[q3_idx-1].Dist()) / 2.0;
else
Q3 = densityArray[q3_idx].Dist();
}
}
mprintf("\tMedian dist value is %g. Q1= %g Q3= %g\n", median, Q1, Q3);
*/
}
tempOut.CloseFile();
// END CALCULATING WEIGHTED DISTANCE AVERAGE
/*
// TEST
tempOut.OpenWrite("temp2.dat");
std::vector<double> Hist( Points_.back().PointsWithinEps()+1, 0.0 );
int gWidth = 3;
double cval = 3.0;
double two_c_squared = 2.0 * cval * cval;
mprintf("DBG: cval= %g, Gaussian denominator is %g\n", cval, two_c_squared);
for (int wtIdx = 0; wtIdx != (int)weightedAverage.Size(); wtIdx++)
{
int bval = weightedAverage.X(wtIdx);
for (int xval = std::max(bval - gWidth, 0);
xval != std::min(bval + gWidth + 1, (int)Hist.size()); xval++)
{
// a: height (weighted average)
// b: center (density value)
// c: width
// x: density value in histogram
//int xval = weightedAverage.X(idx);
//double bval = weightedAverage.X(wtIdx);
//double bval = (double)wtIdx;
double diff = (double)(xval - bval);
//Hist[xval] += (weightedAverage.Y(wtIdx) * exp( -( (diff * diff) / two_c_squared ) ));
Hist[xval] = std::max(Hist[xval],
weightedAverage.Y(wtIdx) * exp( -( (diff * diff) / two_c_squared ) ));
}
}
for (unsigned int idx = 0; idx != Hist.size(); idx++)
tempOut.Printf("%u %g\n", idx, Hist[idx]);
tempOut.CloseFile();
// END TEST
*/
/*
// TEST
// Construct best-fit line segments
tempOut.OpenWrite("temp2.dat");
double slope, intercept, correl;
int segment_length = 3;
DataSet_Mesh Segment;
Segment.Allocate1D( segment_length );
for (int wtIdx = 0; wtIdx != (int)weightedAverage.Size(); wtIdx++)
{
Segment.Clear();
for (int idx = std::max(wtIdx - 1, 0); // TODO: use segment_length
idx != std::min(wtIdx + 2, (int)weightedAverage.Size()); idx++)
Segment.AddXY(weightedAverage.X(idx), weightedAverage.Y(idx));
Segment.LinearRegression(slope, intercept, correl, true);
for (int idx = std::max(wtIdx - 1, 0); // TODO: use segment_length
idx != std::min(wtIdx + 2, (int)weightedAverage.Size()); idx++)
{
double x = weightedAverage.X(idx);
double y = slope * x + intercept;
tempOut.Printf("%g %g %i\n", x, y, weightedAverage.X(wtIdx));
}
}
tempOut.CloseFile();
// END TEST
*/
// BEGIN WEIGHTED RUNNING AVG/SD OF DISTANCES
// For each point, determine if it is greater than the average of the
// weighted average distances of the previous, current, and next densities.
int width = 2;
int currentDensity = 0;
int wtIdx = 0;
double currentAvg = 0.0;
double deltaSD = 0.0;
double deltaAv = 0.0;
int Ndelta = 0;
CpptrajFile raOut;
if (!rafile_.empty()) raOut.OpenWrite(rafile_);
CpptrajFile raDelta;
if (!radelta_.empty()) raDelta.OpenWrite(radelta_);
std::vector<unsigned int> candidateIdxs;
std::vector<double> candidateDeltas;
cp = Points_.begin();
// Skip over points with zero density
while (cp != Points_.end() && cp->PointsWithinEps() == 0) ++cp;
while (weightedAverage.X(wtIdx) != cp->PointsWithinEps() && wtIdx < (int)Points_.size())
++wtIdx;
for (Carray::const_iterator point = cp; point != Points_.end(); ++point)
{
if (point->PointsWithinEps() != currentDensity) {
//currentAvg = weightedAverage.Y(wtIdx);
// New density value. Determine average.
currentAvg = 0.0;
// unsigned int Npt = 0;
double currentWt = 0.0;
for (int idx = std::max(wtIdx - width, 0);
idx != std::min(wtIdx + width + 1, (int)weightedAverage.Size()); idx++)
{
//currentAvg += weightedAverage.Y(idx);
//Npt++;
double wt = weightedAverage.Y(idx);
currentAvg += (weightedAverage.Y(idx) * wt);
currentWt += wt;
}
//currentAvg /= (double)Npt;
currentAvg /= currentWt;
//smoothAv += currentAvg;
//smoothSD += (currentAvg * currentAvg);
//Nsmooth++;
currentDensity = point->PointsWithinEps();
if (raOut.IsOpen())
raOut.Printf("%i %g %g\n", currentDensity, currentAvg, weightedAverage.Y(wtIdx));
wtIdx++;
}
double delta = (point->Dist() - currentAvg);
if (delta > 0.0) {
//delta *= log((double)currentDensity);
if (raDelta.IsOpen())
raDelta.Printf("%8i %8.3f %8i %8.3f %8.3f\n",
currentDensity, delta, point->Fnum()+1, point->Dist(), currentAvg);
candidateIdxs.push_back( point - Points_.begin() );
candidateDeltas.push_back( delta );
deltaAv += delta;
deltaSD += (delta * delta);
Ndelta++;
}
}
raOut.CloseFile();
deltaAv /= (double)Ndelta;
deltaSD = (deltaSD / (double)Ndelta) - (deltaAv * deltaAv);
if (deltaSD > 0.0)
deltaSD = sqrt(deltaSD);
else
deltaSD = 0.0;
if (raDelta.IsOpen())
raDelta.Printf("#DeltaAvg= %g DeltaSD= %g\n", deltaAv, deltaSD);
raDelta.CloseFile();
int cnum = 0;
for (unsigned int i = 0; i != candidateIdxs.size(); i++) {
if (candidateDeltas[i] > (deltaSD)) {
Points_[candidateIdxs[i]].SetCluster( cnum++ );
mprintf("\tPoint %u (frame %i, density %i) selected as candidate for cluster %i\n",
candidateIdxs[i], Points_[candidateIdxs[i]].Fnum()+1,
Points_[candidateIdxs[i]].PointsWithinEps(), cnum-1);
}
}
// END WEIGHTED AVG/SD OF DISTANCES
/*
// Currently doing this by calculating the running average of density vs
// distance, then choosing points with distance > twice the SD of the
// running average.
// NOTE: Store in a mesh data set for now in case we want to spline etc later.
if (avg_factor_ < 1) avg_factor_ = 10;
unsigned int window_size = Points_.size() / (unsigned int)avg_factor_;
mprintf("\tRunning avg window size is %u\n", window_size);
// FIXME: Handle case where window_size < frames
DataSet_Mesh runavg;
unsigned int ra_size = Points_.size() - window_size + 1;
runavg.Allocate1D( ra_size );
double dwindow = (double)window_size;
double sumx = 0.0;
double sumy = 0.0;
for (unsigned int i = 0; i < window_size; i++) {
sumx += (double)Points_[i].PointsWithinEps();
sumy += Points_[i].Dist();
}
runavg.AddXY( sumx / dwindow, sumy / dwindow );
for (unsigned int i = 1; i < ra_size; i++) {
unsigned int nextwin = i + window_size - 1;
unsigned int prevwin = i - 1;
sumx = (double)Points_[nextwin].PointsWithinEps() -
(double)Points_[prevwin].PointsWithinEps() + sumx;
sumy = Points_[nextwin].Dist() -
Points_[prevwin].Dist() + sumy;
runavg.AddXY( sumx / dwindow, sumy / dwindow );
}
// Write running average
if (!rafile_.empty()) {
CpptrajFile raOut;
if (raOut.OpenWrite(rafile_))
mprinterr("Error: Could not open running avg file '%s' for write.\n", rafile_.c_str());
else {
for (unsigned int i = 0; i != runavg.Size(); i++)
raOut.Printf("%g %g\n", runavg.X(i), runavg.Y(i));
raOut.CloseFile();
}
}
double ra_sd;
double ra_avg = runavg.Avg( ra_sd );
// Double stdev to use as cutoff for findning anomalously high peaks.
ra_sd *= 2.0;
mprintf("\tAvg of running avg set is %g, SD*2.0 (delta cutoff) is %g\n", ra_avg, ra_sd);
// For each point in density vs distance plot, determine which running
// average point is closest. If the difference between the point and the
// running average point is > 2.0 the SD of the running average data,
// consider it a 'peak'.
CpptrajFile raDelta;
if (!radelta_.empty())
raDelta.OpenWrite("radelta.dat");
if (raDelta.IsOpen())
raDelta.Printf("%-10s %10s %10s\n", "#Frame", "RnAvgPos", "Delta");
unsigned int ra_position = 0; // Position in the runavg DataSet
unsigned int ra_end = runavg.Size() - 1;
int cnum = 0;
for (Carray::iterator point = Points_.begin();
point != Points_.end(); ++point)
{
if (ra_position != ra_end) {
// Is the next running avgd point closer to this point?
while (ra_position != ra_end) {
double dens = (double)point->PointsWithinEps();
double diff0 = fabs( dens - runavg.X(ra_position ) );
double diff1 = fabs( dens - runavg.X(ra_position+1) );
if (diff1 < diff0)
++ra_position; // Next running avg position is closer for this point.
else
break; // This position is closer.
}
}
double delta = point->Dist() - runavg.Y(ra_position);
if (raDelta.IsOpen())
raDelta.Printf("%-10i %10u %10g", point->Fnum()+1, ra_position, delta);
if (delta > ra_sd) {
if (raDelta.IsOpen())
raDelta.Printf(" POTENTIAL CLUSTER %i", cnum);
point->SetCluster(cnum++);
}
if (raDelta.IsOpen()) raDelta.Printf("\n");
}
raDelta.CloseFile();
*/
return cnum;
}