console.setLevel(logging.INFO)
logging.getLogger("").addHandler(console)
logging.info("SUPPORT : %d", support)
cutoff = 8.0
DS = 10 * np.load("../data/de_ds_mu.npy")
CM = DS < cutoff
Kr = [2, 52, 56, 60, 116, 258, 311, 460, 505, 507, 547, 595, 640, 642, 665, 683, 728, 767, 851, 1244, 1485, 1629, 1636]
CMr, Dr = CM[:, Kr], DS[:, Kr]
logging.info("FINAL Input Matrix: %s", Dr.shape)
logging.info("Reduction Rate: %7.4f", CMr.sum() / np.multiply(*CM.shape))
MFIS, low_fis = lat.maxminer(CMr, support)
dlat, Ik = lat.derived_lattice(MFIS, Dr, CMr)
logging.info("LATTICE,mfis,%d", len(MFIS))
logging.info("LATTICE,lfis,%d", len(low_fis))
logging.info("LATTICE,dlat,%d", len(dlat))
logging.info("LATTICE,iset,%d", len(Ik))
logging.info("LATTICE,edges,%d", sum([len(v) for v in Ik.values()]))
logging.info("SIZE,mfis,%d", sys.getsizeof(MFIS))
logging.info("SIZE,lfis,%d", sys.getsizeof(low_fis))
logging.info("SIZE,dlat,%d", sys.getsizeof(dlat))
logging.info("SIZE,iset,%d", sys.getsizeof(Ik))
logging.info("\n ALL DONE! Pickling Out")
outfile = open(home + "/work/latt_intrinsics/iset_%d.p" % support, "wb")
pickle.dump(Ik, outfile)
outfile.close()
logging.info("Iset written")
def bootstrap_lattice(catalog, num=10, build_new=False):
''' Bootstrap After TimeScape has run on source trajectory '''
home = os.getenv("HOME")
support = 1
cutoff = 8
start_coord = ['de2586_315', 'de531_20', 'de3765_63', 'de3305_668', 'de1732_139']
dcdfile = lambda x: home + '/work/data/{0}.dcd'.format(x)
outloc = lambda x: home+'/work/jc/denovouniform1/{0}/{0}'.format(x)
traj_list = {}
basin_list = catalog.lrange('basin:list', 0, -1)
if len(basin_list) == 134:
logging.info('Basin Data already loaded!')
rms_delta_list = [(i, np.sum(pickle.loads(catalog.get('basin:rmsdelta:'+b)))) for i, b in enumerate(basin_list)]
else:
logging.info('Loading all bootstrap data to initialize...')
basin_list = []
rms_delta_list = []
pdb_file = home+'/work/data/alpha.pdb'
topo = md.load(pdb_file)
ref_alpha = md.load(home+'/work/' + catalog.get('pdb:ref:0'))
ref_alpha.atom_slice(ref_alpha.top.select_atom_indices('alpha'), inplace=True)
res_rms_Kr = FEATURE_SET
for sc in start_coord:
dist_space = []
srcfile = outloc(sc) + '.dcd'
pdbfile = srcfile.replace('dcd', 'pdb')
logging.debug('LOADING TRAJ: %s', srcfile)
traj = md.load(srcfile, top = pdbfile)
traj_list[sc] = traj
alpha = traj.atom_slice(traj.top.select_atom_indices('alpha'))
logging.info('Grabbing TS data...')
W = TS.TimeScape.windows(outloc(sc) + '_transitions.log')
ts_traj = TS.TimeScapeParser(pdbfile, outloc(sc), sc, dcd=srcfile, traj=traj)
basins = ts_traj.load_basins()
logging.info("Processing distance space and residue RMS")
dsa = DR.distance_space(alpha)
resrmsd = 10*np.array([LA.norm(i-ref_alpha.xyz[0], axis=1) for i in alpha.xyz])
basin_res_rms = np.zeros(shape=(len(ts_traj.basins), alpha.n_atoms))
for i, (a,b) in enumerate(W):
dist_space.append(dsa[a:b].mean(0))
basin_res_rms[i] = np.median(resrmsd[a:b], axis=0)
basin_res_rms_delta = np.array([rms_delta(i) for i in basin_res_rms.T]).T
logging.debug('RMS LEN CHECK: %d =?= %d -- Updating RMS Delta',len(basins), len(basin_res_rms_delta))
for i, basin in enumerate(basins):
pipe = catalog.pipeline()
bid = basin.id
# Store on Disk and in redis
jc_filename = os.path.join(settings.datadir, 'basin_%s.pdb' % bid)
logging.info('MIN for %s: Idx# %d to %s', bid, basin.mindex, jc_filename)
minima_frame = traj.slice(basin.mindex) #md.load_frame(src_traj, basin.mindex, top=src_traj.replace('dcd', 'pdb'))
minima_frame.save_pdb(jc_filename)
basin_hash = basin.kv()
basin_hash['pdbfile'] = jc_filename
logging.info(' Basin: %(id)s %(start)d - %(end)d Minima: %(mindex)d size=%(len)d' % basin_hash)
pipe.rpush('basin:list', bid)
pipe.hmset('basin:%s'%bid, basin_hash)
pipe.set('basin:dmu:'+bid, pickle.dumps(dist_space[i]))
pipe.set('minima:%s'%bid, pickle.dumps(minima_frame))
# FOR RESIDUE RMSD
resrms_d = np.sum(basin_res_rms_delta[i][res_rms_Kr])
basin_hash['resrms_delta'] = resrms_d
rms_delta_list.append((len(basin_list), resrms_d))
basin_list.append(basin_hash)
pipe.set('basin:rmsdelta:'+bid, pickle.dumps(basin_res_rms_delta[i]))
pipe.execute()
# FOR RESIDUE RMSD
# FOR SEED SAMPLING USING RMS_DELTA
# Note: skip the first basin
# Re-Construct the Lattice from
if build_new:
dist_space = 10*np.array(dist_space)
cm = ds<cutoff
fs = lat.reduced_feature_set(cm,.115); len(fs)
dr, cr = ds[:,fs], cm[:,fs]
mfis,lfis = lat.maxminer(cr, 1)
dlat, ik = lat.derived_lattice(mfis, dr, cr)
pickle.dump(mfis, open(home + '/work/data/denovo_mfis.p', 'wb'))
pickle.dump(lfis, open(home + '/work/data/denovo_lfis.p', 'wb'))
pickle.dump(ik, open(home + '/work/data/denovo_iset.p', 'wb'))
pickle.dump(dlat, open(home + '/work/data/denovo_dlat.p', 'wb'))
else:
logging.info('Loading Pre-Constructed Lattice Data')
dlat = pickle.load(open(home + '/work/data/denovo_dlat.p', 'rb'))
mfis = pickle.load(open(home + '/work/data/denovo_mfis.p', 'rb'))
lfis = pickle.load(open(home + '/work/data/denovo_lfis.p', 'rb'))
ik = pickle.load(open(home + '/work/data/denovo_iset.p', 'rb'))
with catalog.pipeline() as pipe:
pipe.set('lattice:max_fis', pickle.dumps(mfis))
pipe.set('lattice:low_fis', pickle.dumps(lfis))
pipe.set('lattice:dlat', pickle.dumps(dlat))
pipe.set('lattice:iset', pickle.dumps(ik))
pipe.execute()
# logging.info('Building Existing lattice object')
# lattice=lat.Lattice(ds, fs, cutoff, support)
# lattice.set_fis(max_fis, low_fis)
# lattice.set_dlat(dlat, Ik)
# sampler = LatticeSampler(lattice)
# Sample -- FOR USING LATTICE TO BOOTSTRAP
# cl,sc,el = lat.clusterlattice(dlat, cr, dr, ik, num_k=8, invert=True)
# cl_list = sorted(el, key=lambda x: len(x))
# TODO: Check if fan out > single item clusters
# start_indices = [clu[0][0] for clu in cl_list[:num]]
rms_delta_ranked = [x[0] for x in sorted(rms_delta_list, key=lambda i: i[1], reverse=True)]
start_indices = rms_delta_ranked[:num]
seedlist = [catalog.lindex('basin:list', i) for i in start_indices]
sim_init = {key: catalog.get(key) for key in settings.sim_params.keys()}
global_params = getSimParameters(sim_init, 'seed')
global_params['psf'] = home+'/work/jc/serial2/de0_0/de0_0.psf'
for seed in seedlist:
logging.debug('\nSeeding Job: %s ', seed)
basin = catalog.hgetall('basin:%s'%seed)
catalog.rpush('executed', seed)
# Generate new set of params/coords
jcID, config = generateFromBasin(basin)
# Update Additional JC Params and Decision History, as needed
config.update(global_params)
# Push to catalog
logging.info("New Simulation Job Created: %s", jcID)
for k, v in config.items():
logging.debug(" %s: %s", k, str(v))
catalog.rpush('jcqueue', jcID)
catalog.hmset(wrapKey('jc', jcID), config)
CM = DS<cutoff
CMr, Dr = CM[:,Kr], DS[:,Kr]
CMm, Dm = CM[:,Km], DS[:,Km]
delabel = np.load(home+'/work/results/DE_label_full.npy')
DW = []
for i in range(42):
for a,b in TS.TimeScape.windows(home+'/work/timescape/desh_%02d_transitions.log'%i):
DW.append((a+i*100000, b+i*100000))
dL = [delabel[a:b] for a,b in DW]
DE_LABEL = [LABEL10(i,.9) for i in dL]
SPT = [i[0] for i in db.runquery('select distinct support from latt order by support')]
NC = [i[0] for i in db.runquery('select distinct numclu from latt order by numclu')]
mf, lf = {}, {}
dl, ik = {}, {}
key, clu, cent, var, Gm = {}, {}, {}, {}, {}
s=support
mf[s], lf[s] = lat.maxminer(CMr, s)
dl[s], ik[s] = lat.derived_lattice(mf[s], Dr, CMr)
pickle.dump(dl[s], open(home + '/work/latt_intrinsics/dlat2_%d.p' % support, 'wb'))
for num_clu in NC:
key[s], clu[s], cent[s], var[s], Gm[s] = lat.cluster_harch(dl[s], CMr, Dr, theta=.5, num_k=num_clu, dL=None, verbose=False)
w, t = lat.score_clusters(clu[s], Dr, cent[s], var[s], Gm[s], sigma, DE_LABEL)
for k in TBIN10:
logging.info('SCORE,W,%d,%d,%s,%.5f', support, num_clu, k, w[k])
for k in TBIN10:
logging.info('SCORE,T,%d,%d,%s,%.5f', support, num_clu, k, t[k])
console.setLevel(logging.INFO)
logging.getLogger('').addHandler(console)
logging.info("SUPPORT : %d", support)
cutoff = 8.
DS = 10*np.load('../data/de_ds_mu.npy')
CM = (DS<cutoff)
Kr = [2, 52, 56, 60, 116, 258, 311, 460, 505, 507, 547, 595, 640, 642, 665, 683, 728, 767, 851, 1244, 1485, 1629, 1636]
CMr, Dr = CM[:,Kr], DS[:,Kr]
logging.info('FINAL Input Matrix: %s', Dr.shape)
logging.info('Reduction Rate: %7.4f', CMr.sum()/np.multiply(*CM.shape))
MFIS, low_fis = lat.maxminer(CMr, support)
dlat, Ik = lat.derived_lattice(MFIS, Dr, CMr)
logging.info('LATTICE,mfis,%d', len(MFIS))
logging.info('LATTICE,lfis,%d', len(low_fis))
logging.info('LATTICE,dlat,%d', len(dlat))
logging.info('LATTICE,iset,%d', len(Ik))
logging.info('LATTICE,edges,%d', sum([len(v) for v in Ik.values()]))
logging.info('SIZE,mfis,%d', sys.getsizeof(MFIS))
logging.info('SIZE,lfis,%d', sys.getsizeof(low_fis))
logging.info('SIZE,dlat,%d', sys.getsizeof(dlat))
logging.info('SIZE,iset,%d', sys.getsizeof(Ik))
logging.info('\n ALL DONE! Pickling Out')
outfile = open(home + '/work/latt_intrinsics/iset_%d.p'%support, 'wb')
pickle.dump(Ik, outfile)
outfile.close()
logging.info('Iset written')
SPT = [
i[0]
for i in db.runquery('select distinct support from latt order by support')
]
NC = [
i[0]
for i in db.runquery('select distinct numclu from latt order by numclu')
]
mf, lf = {}, {}
dl, ik = {}, {}
key, clu, cent, var, Gm = {}, {}, {}, {}, {}
s = support
mf[s], lf[s] = lat.maxminer(CMr, s)
dl[s], ik[s] = lat.derived_lattice(mf[s], Dr, CMr)
pickle.dump(dl[s],
open(home + '/work/latt_intrinsics/dlat2_%d.p' % support, 'wb'))
for num_clu in NC:
key[s], clu[s], cent[s], var[s], Gm[s] = lat.cluster_harch(dl[s],
CMr,
Dr,
theta=.5,
num_k=num_clu,
dL=None,
verbose=False)
w, t = lat.score_clusters(clu[s], Dr, cent[s], var[s], Gm[s], sigma,
DE_LABEL)
for k in TBIN10:
logging.info('SCORE,W,%d,%d,%s,%.5f', support, num_clu, k, w[k])
for k in TBIN10:
def bootstrap_lattice(catalog, num=10, build_new=False):
''' Bootstrap After TimeScape has run on source trajectory '''
home = os.getenv("HOME")
support = 1
cutoff = 8
start_coord = [
'de2586_315', 'de531_20', 'de3765_63', 'de3305_668', 'de1732_139'
]
dcdfile = lambda x: home + '/work/data/{0}.dcd'.format(x)
outloc = lambda x: home + '/work/jc/denovouniform1/{0}/{0}'.format(x)
traj_list = {}
basin_list = catalog.lrange('basin:list', 0, -1)
if len(basin_list) == 134:
logging.info('Basin Data already loaded!')
rms_delta_list = [
(i, np.sum(pickle.loads(catalog.get('basin:rmsdelta:' + b))))
for i, b in enumerate(basin_list)
]
else:
logging.info('Loading all bootstrap data to initialize...')
basin_list = []
rms_delta_list = []
pdb_file = home + '/work/data/alpha.pdb'
topo = md.load(pdb_file)
ref_alpha = md.load(home + '/work/' + catalog.get('pdb:ref:0'))
ref_alpha.atom_slice(ref_alpha.top.select_atom_indices('alpha'),
inplace=True)
res_rms_Kr = FEATURE_SET
for sc in start_coord:
dist_space = []
srcfile = outloc(sc) + '.dcd'
pdbfile = srcfile.replace('dcd', 'pdb')
logging.debug('LOADING TRAJ: %s', srcfile)
traj = md.load(srcfile, top=pdbfile)
traj_list[sc] = traj
alpha = traj.atom_slice(traj.top.select_atom_indices('alpha'))
logging.info('Grabbing TS data...')
W = TS.TimeScape.windows(outloc(sc) + '_transitions.log')
ts_traj = TS.TimeScapeParser(pdbfile,
outloc(sc),
sc,
dcd=srcfile,
traj=traj)
basins = ts_traj.load_basins()
logging.info("Processing distance space and residue RMS")
dsa = DR.distance_space(alpha)
resrmsd = 10 * np.array(
[LA.norm(i - ref_alpha.xyz[0], axis=1) for i in alpha.xyz])
basin_res_rms = np.zeros(shape=(len(ts_traj.basins),
alpha.n_atoms))
for i, (a, b) in enumerate(W):
dist_space.append(dsa[a:b].mean(0))
basin_res_rms[i] = np.median(resrmsd[a:b], axis=0)
basin_res_rms_delta = np.array(
[rms_delta(i) for i in basin_res_rms.T]).T
logging.debug('RMS LEN CHECK: %d =?= %d -- Updating RMS Delta',
len(basins), len(basin_res_rms_delta))
for i, basin in enumerate(basins):
pipe = catalog.pipeline()
bid = basin.id
# Store on Disk and in redis
jc_filename = os.path.join(settings.datadir,
'basin_%s.pdb' % bid)
logging.info('MIN for %s: Idx# %d to %s', bid, basin.mindex,
jc_filename)
minima_frame = traj.slice(
basin.mindex
) #md.load_frame(src_traj, basin.mindex, top=src_traj.replace('dcd', 'pdb'))
minima_frame.save_pdb(jc_filename)
basin_hash = basin.kv()
basin_hash['pdbfile'] = jc_filename
logging.info(
' Basin: %(id)s %(start)d - %(end)d Minima: %(mindex)d size=%(len)d'
% basin_hash)
pipe.rpush('basin:list', bid)
pipe.hmset('basin:%s' % bid, basin_hash)
pipe.set('basin:dmu:' + bid, pickle.dumps(dist_space[i]))
pipe.set('minima:%s' % bid, pickle.dumps(minima_frame))
# FOR RESIDUE RMSD
resrms_d = np.sum(basin_res_rms_delta[i][res_rms_Kr])
basin_hash['resrms_delta'] = resrms_d
rms_delta_list.append((len(basin_list), resrms_d))
basin_list.append(basin_hash)
pipe.set('basin:rmsdelta:' + bid,
pickle.dumps(basin_res_rms_delta[i]))
pipe.execute()
# FOR RESIDUE RMSD
# FOR SEED SAMPLING USING RMS_DELTA
# Note: skip the first basin
# Re-Construct the Lattice from
if build_new:
dist_space = 10 * np.array(dist_space)
cm = ds < cutoff
fs = lat.reduced_feature_set(cm, .115)
len(fs)
dr, cr = ds[:, fs], cm[:, fs]
mfis, lfis = lat.maxminer(cr, 1)
dlat, ik = lat.derived_lattice(mfis, dr, cr)
pickle.dump(mfis, open(home + '/work/data/denovo_mfis.p', 'wb'))
pickle.dump(lfis, open(home + '/work/data/denovo_lfis.p', 'wb'))
pickle.dump(ik, open(home + '/work/data/denovo_iset.p', 'wb'))
pickle.dump(dlat, open(home + '/work/data/denovo_dlat.p', 'wb'))
else:
logging.info('Loading Pre-Constructed Lattice Data')
dlat = pickle.load(open(home + '/work/data/denovo_dlat.p', 'rb'))
mfis = pickle.load(open(home + '/work/data/denovo_mfis.p', 'rb'))
lfis = pickle.load(open(home + '/work/data/denovo_lfis.p', 'rb'))
ik = pickle.load(open(home + '/work/data/denovo_iset.p', 'rb'))
with catalog.pipeline() as pipe:
pipe.set('lattice:max_fis', pickle.dumps(mfis))
pipe.set('lattice:low_fis', pickle.dumps(lfis))
pipe.set('lattice:dlat', pickle.dumps(dlat))
pipe.set('lattice:iset', pickle.dumps(ik))
pipe.execute()
# logging.info('Building Existing lattice object')
# lattice=lat.Lattice(ds, fs, cutoff, support)
# lattice.set_fis(max_fis, low_fis)
# lattice.set_dlat(dlat, Ik)
# sampler = LatticeSampler(lattice)
# Sample -- FOR USING LATTICE TO BOOTSTRAP
# cl,sc,el = lat.clusterlattice(dlat, cr, dr, ik, num_k=8, invert=True)
# cl_list = sorted(el, key=lambda x: len(x))
# TODO: Check if fan out > single item clusters
# start_indices = [clu[0][0] for clu in cl_list[:num]]
rms_delta_ranked = [
x[0] for x in sorted(rms_delta_list, key=lambda i: i[1], reverse=True)
]
start_indices = rms_delta_ranked[:num]
seedlist = [catalog.lindex('basin:list', i) for i in start_indices]
sim_init = {key: catalog.get(key) for key in settings.sim_params.keys()}
global_params = getSimParameters(sim_init, 'seed')
global_params['psf'] = home + '/work/jc/serial2/de0_0/de0_0.psf'
for seed in seedlist:
logging.debug('\nSeeding Job: %s ', seed)
basin = catalog.hgetall('basin:%s' % seed)
catalog.rpush('executed', seed)
# Generate new set of params/coords
jcID, config = generateFromBasin(basin)
# Update Additional JC Params and Decision History, as needed
config.update(global_params)
# Push to catalog
logging.info("New Simulation Job Created: %s", jcID)
for k, v in config.items():
logging.debug(" %s: %s", k, str(v))
catalog.rpush('jcqueue', jcID)
catalog.hmset(wrapKey('jc', jcID), config)