Extracting pdb structures

[GSINGH006]

Hi, is there a method in Deeptime similar to Pyemma's " pyemma.coordinates.save_traj" which can be used to extract pdb structures representing macrostates after coarse-graining using PCCA+

[clonker]

There is no direct MD dependency in deeptime so in that sense, no, but you can use deeptime to estimate your models and extract the indices, put these into pyemma :)

[GSINGH006]

Hi @clonker I am using the following code for the same

dtrajs = []
for projected_trajectory in tics:
dtrajs.append(clustering.transform(projected_trajectory))
**msm = MaximumLikelihoodMSM(lagtime=50).fit_fetch(dtrajs)
nstates = 3
cg = msm.pcca(nstates)
pcca_dist1=cg.metastable_distributions
indices = dt.markov.sample.compute_index_states(dtrajs)
ind=dt.markov.sample.indices_by_distribution(indices,distributions=pcca_dist1,nsample=1)
pyemma.coordinates.save_traj(traj_list, ind[0],'/home/lab/samples_pcca1.xtc' , top=topfile)
Is this the correct way to extract the indices and use them for getting the representative structures?
what does nsamples in this function exactly represent?
Thank you

[GSINGH006]

Hi, Moritz @clonker is this the right way to get the representative structures ?