def _getSimlist(self): logger.info('Postprocessing new data') sims = simlist(glob(path.join(self.datapath, '*', '')), glob(path.join(self.inputpath, '*', '')), glob(path.join(self.inputpath, '*', ''))) if self.filter: sims = simfilter(sims, self.filteredpath, filtersel=self.filtersel) return sims
def setUpClass(self): from htmd.simlist import simlist, simfilter from glob import glob from htmd.projections.metric import Metric from moleculekit.projections.metricdistance import MetricDistance from moleculekit.projections.metricdihedral import MetricDihedral from moleculekit.util import tempname from htmd.home import home from os.path import join sims = simlist( glob(join(home(dataDir="adaptive"), "data", "*", "")), glob(join(home(dataDir="adaptive"), "input", "*")), ) fsims = simfilter(sims, tempname(), "not water") metr = Metric(fsims) metr.set( MetricDistance( "protein and resid 10 and name CA", "resname BEN and noh", periodic="selections", metric="contacts", groupsel1="residue", threshold=4, ) ) self.data1 = metr.project() metr.set(MetricDihedral()) self.data2 = metr.project()
def setUpClass(self): from htmd.simlist import simlist, simfilter from glob import glob from htmd.projections.metric import Metric from moleculekit.projections.metricdistance import MetricDistance from moleculekit.projections.metricdihedral import MetricDihedral from moleculekit.util import tempname from htmd.home import home from os.path import join sims = simlist(glob(join(home(dataDir='adaptive'), 'data', '*', '')), glob(join(home(dataDir='adaptive'), 'input', '*'))) fsims = simfilter(sims, tempname(), 'not water') metr = Metric(fsims) metr.set( MetricDistance('protein and resid 10 and name CA', 'resname BEN and noh', metric='contacts', groupsel1='residue', threshold=4)) self.data1 = metr.project() metr.set(MetricDihedral()) self.data2 = metr.project()
def _algorithm(self): logger.info('Postprocessing new data') sims = simlist(glob(path.join(self.datapath, '*', '')), glob(path.join(self.inputpath, '*', 'structure.pdb')), glob(path.join(self.inputpath, '*', ''))) if self.filter: sims = simfilter(sims, self.filteredpath, filtersel=self.filtersel) metr = Metric(sims, skip=self.skip) metr.set(self.projection) #if self.contactsym is not None: # contactSymmetry(data, self.contactsym) if self.ticadim > 0: # tica = TICA(metr, int(max(2, np.ceil(self.ticalag)))) # gianni: without project it was tooooo slow tica = TICA(metr.project(), int(max(2, np.ceil(self.ticalag)))) datadr = tica.project(self.ticadim) else: datadr = metr.project() datadr.dropTraj( ) # Preferably we should do this before any projections. Corrupted sims can affect TICA datadr.cluster( self.clustmethod(n_clusters=self._numClusters(datadr.numFrames))) self._model = Model(datadr) self._model.markovModel(self.lag, self._numMacrostates(datadr)) if self.save: self._model.save('adapt_model_e' + str(self._getEpoch()) + '.dat') relFrames = self._getSpawnFrames(self._model, datadr) self._writeInputs(datadr.rel2sim(np.concatenate(relFrames)))
def _getSimlist(self): logger.info("Postprocessing new data") sims = simlist( glob(path.join(self.datapath, "*", "")), glob(path.join(self.inputpath, "*", "")), glob(path.join(self.inputpath, "*", "")), ) if self.filter: sims = simfilter(sims, self.filteredpath, filtersel=self.filtersel) return sims
def _algorithm(self): logger.info('Postprocessing new data') sims = simlist(glob(path.join(self.datapath, '*', '')), glob(path.join(self.inputpath, '*', 'structure.pdb')), glob(path.join(self.inputpath, '*', ''))) if self.filter: sims = simfilter(sims, self.filteredpath, filtersel=self.filtersel) metr = Metric(sims, skip=self.skip) metr.set(self.projection) # if self.contactsym is not None: # contactSymmetry(data, self.contactsym) if self.ticadim > 0: # tica = TICA(metr, int(max(2, np.ceil(self.ticalag)))) # gianni: without project it was tooooo slow tica = TICA(metr.project(), int(max(2, np.ceil(self.ticalag)))) datadr = tica.project(self.ticadim) else: datadr = metr.project() datadr.dropTraj( ) # Preferably we should do this before any projections. Corrupted sims can affect TICA datadr.cluster( self.clustmethod(n_clusters=self._numClusters(datadr.numFrames))) model = Model(datadr) self._model = model self._model.markovModel(self.lag, self._numMacrostates(datadr)) if self.save: self._model.save('adapt_model_e' + str(self._getEpoch()) + '.dat') # Undirected component uc = -model.data.N # Lower counts should give higher score hence the - if self.statetype == 'micro': uc = uc[model.cluster_ofmicro] if self.statetype == 'macro': uc = macroAccumulate(model, uc[model.cluster_ofmicro]) # Calculating the directed component dc = self._calculateDirectedComponent(sims, model.data.St, model.data.N) if self.statetype == 'micro': dc = dc[model.cluster_ofmicro] if self.statetype == 'macro': dc = macroAccumulate(model, dc[model.cluster_ofmicro]) uc = self._featScale(uc) dc = self._featScale(dc) reward = dc + self.ucscale * uc relFrames = self._getSpawnFrames(reward, self._model, datadr) self._writeInputs(datadr.rel2sim(np.concatenate(relFrames)))
def _algorithm(self): logger.info('Postprocessing new data') datalist = simlist(glob(path.join(self.datapath, '*', '')), glob(path.join(self.inputpath, '*', 'structure.pdb')), glob(path.join(self.inputpath, '*', ''))) filtlist = simfilter(datalist, self.filteredpath, filtersel=self.filtersel) if hasattr(self, 'metricsel2') and self.metricsel2 is not None: proj = MetricDistance(self.metricsel1, self.metricsel2, metric=self.metrictype) else: proj = MetricSelfDistance(self.metricsel1, metric=self.metrictype) metr = Metric(filtlist, skip=self.skip) metr.projection(proj) data = metr.project() #if self.contactsym is not None: # contactSymmetry(data, self.contactsym) data.dropTraj() if self.ticadim > 0: tica = TICA(data, int(max(2, np.ceil(20/self.skip)))) datadr = tica.project(self.ticadim) else: datadr = data K = int(max(np.round(0.6 * np.log10(datadr.numFrames/1000)*1000+50), 100)) # heuristic if K > datadr.numFrames / 3: # Freaking ugly patches ... K = int(datadr.numFrames / 3) datadr.cluster(self.clustmethod(n_clusters=K), mergesmall=5) replacement = False if datadr.K < 10: datadr.cluster(self.clustmethod(n_clusters=K)) replacement = True model = Model(datadr) macronum = self.macronum if datadr.K < macronum: macronum = np.ceil(datadr.K / 2) logger.warning('Using less macrostates than requested due to lack of microstates. macronum = ' + str(macronum)) from pyemma.msm import timescales_msm timesc = timescales_msm(datadr.St.tolist(), lags=self.lag, nits=macronum).get_timescales() macronum = min(self.macronum, max(np.sum(timesc > self.lag), 2)) model.markovModel(self.lag, macronum) p_i = self._criteria(model, self.method) (spawncounts, prob) = self._spawn(p_i, self.nmax-self.running) logger.debug('spawncounts {}'.format(spawncounts)) stateIdx = np.where(spawncounts > 0)[0] _, relFrames = model.sampleStates(stateIdx, spawncounts[stateIdx], statetype='micro', replacement=replacement) logger.debug('relFrames {}'.format(relFrames)) self._writeInputs(datadr.rel2sim(np.concatenate(relFrames)))
if __name__ == '__main__': from htmd.simlist import simlist, simfilter from glob import glob from htmd.projections.metric import Metric from htmd.projections.metricdistance import MetricDistance from htmd.projections.metricdihedral import MetricDihedral from htmd.util import tempname from htmd.home import home from os.path import join testfolder = home(dataDir='adaptive') sims = simlist(glob(join(testfolder, 'data', '*', '')), glob(join(testfolder, 'input', '*', 'structure.pdb'))) fsims = simfilter(sims, tempname(), 'not water') metr = Metric(fsims) metr.set( MetricDistance('protein and resid 10 and name CA', 'resname BEN and noh', metric='contacts', groupsel1='residue', threshold=4)) data1 = metr.project() metr.set(MetricDihedral()) data2 = metr.project() # Testing combining of metrics data1.combine(data2) # Testing dimensions
def _algorithm(self): logger.info('Postprocessing new data') datalist = simlist( glob(path.join(self.datapath, '*', '')), glob(path.join(self.inputpath, '*', 'structure.pdb')), glob(path.join(self.inputpath, '*', ''))) filtlist = simfilter(datalist, self.filteredpath, filtersel=self.filtersel) if hasattr(self, 'metricsel2') and self.metricsel2 is not None: proj = MetricDistance(self.metricsel1, self.metricsel2, metric=self.metrictype) else: proj = MetricSelfDistance(self.metricsel1, metric=self.metrictype) metr = Metric(filtlist, skip=self.skip) metr.projection(proj) data = metr.project() #if self.contactsym is not None: # contactSymmetry(data, self.contactsym) data.dropTraj() if self.ticadim > 0: tica = TICA(data, int(max(2, np.ceil(20 / self.skip)))) datadr = tica.project(self.ticadim) else: datadr = data K = int( max(np.round(0.6 * np.log10(datadr.numFrames / 1000) * 1000 + 50), 100)) # heuristic if K > datadr.numFrames / 3: # Freaking ugly patches ... K = int(datadr.numFrames / 3) datadr.cluster(self.clustmethod(n_clusters=K), mergesmall=5) replacement = False if datadr.K < 10: datadr.cluster(self.clustmethod(n_clusters=K)) replacement = True model = Model(datadr) macronum = self.macronum if datadr.K < macronum: macronum = np.ceil(datadr.K / 2) logger.warning( 'Using less macrostates than requested due to lack of microstates. macronum = ' + str(macronum)) from pyemma.msm import timescales_msm timesc = timescales_msm(datadr.St.tolist(), lags=self.lag, nits=macronum).get_timescales() macronum = min(self.macronum, max(np.sum(timesc > self.lag), 2)) model.markovModel(self.lag, macronum) p_i = self._criteria(model, self.method) (spawncounts, prob) = self._spawn(p_i, self.nmax - self.running) logger.debug('spawncounts {}'.format(spawncounts)) stateIdx = np.where(spawncounts > 0)[0] _, relFrames = model.sampleStates(stateIdx, spawncounts[stateIdx], statetype='micro', replacement=replacement) logger.debug('relFrames {}'.format(relFrames)) self._writeInputs(datadr.rel2sim(np.concatenate(relFrames)))
if __name__ == '__main__': from htmd.simlist import simlist, simfilter from glob import glob from htmd.projections.metric import Metric from htmd.projections.metricdistance import MetricDistance from htmd.projections.metricdihedral import MetricDihedral from htmd.util import tempname from htmd.home import home from os.path import join testfolder = home(dataDir='adaptive') sims = simlist(glob(join(testfolder, 'data', '*', '')), glob(join(testfolder, 'input', '*', 'structure.pdb'))) fsims = simfilter(sims, tempname(), 'not water') metr = Metric(fsims) metr.set(MetricDistance('protein and resid 10 and name CA', 'resname BEN and noh', metric='contacts', groupsel1='residue', threshold=4)) data1 = metr.project() metr.set(MetricDihedral()) data2 = metr.project() # Testing combining of metrics data1.combine(data2) # Testing dimensions assert np.array_equal(data1.description.shape, (897, 3)), 'combine not working correct' assert np.array_equal(data1.trajectories[0].projection.shape, (6, 897)), 'combine not working correct' assert np.array_equal(np.where(data1.description.type == 'contact')[0], [0, 1, 2, 3, 4, 5, 6, 7, 8]), 'combine not working correct'