def test_mcc(self):
cg1 = ftmc.CoarseGrainRNA('test/forgi/threedee/data/1GID_A.cg')
cg2 = ftmc.CoarseGrainRNA('test/forgi/threedee/data/1GID_A_sampled.cg')
cm = ftme.confusion_matrix(cg1, cg2)
mcc = ftme.mcc(cm)
self.assertTrue(mcc < 1.0)
cm = ftme.confusion_matrix(cg2, cg2)
mcc = ftme.mcc(cm)
self.assertLess(abs(mcc - 1.0), 0.01)
pass
def main(args):
with fuc.hide_traceback():
cg1, cg2 = fuc.cgs_from_args(args, rna_type="3d", enable_logging=True)
if not (args.acc or args.rmsd or args.pdb_rmsd):
showall = True
else:
showall = False
if showall or args.acc:
if cg1.defines != cg2.defines:
if args.acc:
print(
"Cannot compare two 3d structures that do not correspond to the same RNA."
)
sys.exit(1)
else:
adj = ftms.AdjacencyCorrelation(cg1)
print("ACC:\t{:.3f}".format(ftms.mcc(adj.evaluate(cg2))))
if showall or args.rmsd:
print("RMSD:\t{:.3f}".format(ftms.cg_rmsd(cg1, cg2)))
if showall or args.pdb_rmsd:
if not pdb_rmsd(cg1, cg2):
# If --pdb-rmsd was not given, just don't print it.
# If it was given, we exit with non-zero exit status.
if args.pdb_rmsd:
print(
"Cannot calculate PDB-RMSD: The two files do not contain the same chains."
)
sys.exit(1)
def main():
usage = """
python calculate_mcc.py struct1.cg struct2.cg
"""
num_args= 0
parser = OptionParser(usage=usage)
#parser.add_option('-o', '--options', dest='some_option', default='yo', help="Place holder for a real option", type='str')
#parser.add_option('-u', '--useless', dest='uselesss', default=False, action='store_true', help='Another useless option')
(options, args) = parser.parse_args()
if len(args) < num_args:
parser.print_help()
sys.exit(1)
cg1 = ftmc.CoarseGrainRNA(args[0])
cg2 = ftmc.CoarseGrainRNA(args[1])
confusion_matrix = ftme.confusion_matrix(cg1, cg2)
print "confusion_matrix:", confusion_matrix
print "mcc:", ftme.mcc(confusion_matrix)
print "rmsd:", ftme.cg_rmsd(cg1, cg2)
def main(args):
with fuc.hide_traceback():
cg1, cg2 = fuc.cgs_from_args(
args, rna_type="3d", enable_logging=True)
if not (args.acc or args.rmsd or args.pdb_rmsd):
showall = True
else:
showall = False
if showall or args.acc:
if cg1.defines != cg2.defines:
if args.acc:
print(
"Cannot compare two 3d structures that do not correspond to the same RNA.")
sys.exit(1)
else:
adj = ftms.AdjacencyCorrelation(cg1)
print("ACC:\t{:.3f}".format(ftms.mcc(adj.evaluate(cg2))))
if showall or args.rmsd:
print("RMSD:\t{:.3f}".format(ftms.cg_rmsd(cg1, cg2)))
if showall or args.pdb_rmsd:
if not pdb_rmsd(cg1, cg2):
# If --pdb-rmsd was not given, just don't print it.
# If it was given, we exit with non-zero exit status.
if args.pdb_rmsd:
print(
"Cannot calculate PDB-RMSD: The two files do not contain the same chains.")
sys.exit(1)
def test_new_confusionmatrix_is_like_old(self):
cg1 = ftmc.CoarseGrainRNA('test/forgi/threedee/data/1GID_A.cg')
cg2 = ftmc.CoarseGrainRNA('test/forgi/threedee/data/1GID_A_sampled.cg')
cm = confusion_matrix(cg1, cg2)
mcc = ftme.mcc(cm)
cm_new = ftme.AdjacencyCorrelation(cg1) #previousely named ConfusionMatrix
mcc_n = ftme.mcc(cm_new.evaluate(cg2))
self.assertAlmostEqual(mcc, mcc_n)
self.assertAlmostEqual(mcc_n, 0.6756639246921762)
cm = confusion_matrix(cg1, cg1)
mcc = ftme.mcc(cm)
mcc_n = ftme.mcc(cm_new.evaluate(cg1))
self.assertAlmostEqual(mcc, mcc_n)
self.assertAlmostEqual(mcc_n, 1.0)
def test_mcc(self):
cg1 = ftmc.CoarseGrainRNA.from_bg_file(
'test/forgi/threedee/data/1GID_A.cg')
cg2 = ftmc.CoarseGrainRNA.from_bg_file(
'test/forgi/threedee/data/1GID_A_sampled.cg')
cm = confusion_matrix(cg1, cg2)
mcc = ftme.mcc(cm)
self.assertTrue(mcc < 1.0)
cm = confusion_matrix(cg2, cg2)
mcc = ftme.mcc(cm)
self.assertLess(abs(mcc - 1.0), 0.01)
pass
def test_new_confusionmatrix_is_like_old(self):
cg1 = ftmc.CoarseGrainRNA('test/forgi/threedee/data/1GID_A.cg')
cg2 = ftmc.CoarseGrainRNA('test/forgi/threedee/data/1GID_A_sampled.cg')
cm = ftme.confusion_matrix(cg1, cg2)
mcc = ftme.mcc(cm)
cm_new = ftme.AdjacencyCorrelation(
cg1) #previousely named ConfusionMatrix
mcc_n = ftme.mcc(cm_new.evaluate(cg2))
self.assertAlmostEqual(mcc, mcc_n)
self.assertLess(abs(mcc_n - 0.0761),
0.0001) #0.086 for distance=30, 0.0761 for 25
cm = ftme.confusion_matrix(cg1, cg1)
mcc = ftme.mcc(cm)
mcc_n = ftme.mcc(cm_new.evaluate(cg1))
self.assertAlmostEqual(mcc, mcc_n)
self.assertAlmostEqual(mcc_n, 1.0)
def update(self, sm, step):
try:
if self.silent:
return
else:
acc = ftme.mcc(self._cm_calc.evaluate(sm.bg))
self.history[0].append(acc)
return "{:5.3f}".format(acc)
except ZeroDivisionError:
return "{:5.3f}".format(float("nan"))
def test_new_confusionmatrix_is_like_old(self):
cg1 = ftmc.CoarseGrainRNA.from_bg_file(
'test/forgi/threedee/data/1GID_A.cg')
cg2 = ftmc.CoarseGrainRNA.from_bg_file(
'test/forgi/threedee/data/1GID_A_sampled.cg')
cm = confusion_matrix(cg1, cg2)
mcc = ftme.mcc(cm)
# previousely named ConfusionMatrix
cm_new = ftme.AdjacencyCorrelation(cg1)
mcc_n = ftme.mcc(cm_new.evaluate(cg2))
self.assertAlmostEqual(mcc, mcc_n)
self.assertAlmostEqual(mcc_n, 0.6756639246921762)
cm = confusion_matrix(cg1, cg1)
mcc = ftme.mcc(cm)
mcc_n = ftme.mcc(cm_new.evaluate(cg1))
self.assertAlmostEqual(mcc, mcc_n)
self.assertAlmostEqual(mcc_n, 1.0)
def update(self, sm, step):
try:
if self.silent:
return
else:
acc = ftme.mcc(self._cm_calc.evaluate(sm.bg))
self.history[0].append(acc)
return "{:5.3f}".format(acc)
except ZeroDivisionError:
self.history[0].append(float("nan"))
return "{:5.3f}".format(float("nan"))
def main(args):
if len(args.compareTo)==1:
cg1 = ftmc.CoarseGrainRNA(args.reference[0])
cg2 = ftmc.CoarseGrainRNA(args.compareTo[0])
print (ftms.cg_rmsd(cg1, cg2))
else:
print ("{:15}\t{:6}\t{:6}\t{:6}".format("filename","RMSD", "dRMSD", "ACC"))
ref_cg = ftmc.CoarseGrainRNA(args.reference[0])
reference = ref_cg.get_ordered_virtual_residue_poss()
acc_calc = ftms.AdjacencyCorrelation(ref_cg)
for filename in args.compareTo:
cg=ftmc.CoarseGrainRNA(filename)
curr_vress=cg.get_ordered_virtual_residue_poss()
rmsd = ftur.rmsd(reference, curr_vress)
drmsd = ftur.drmsd(reference, curr_vress)
acc = ftms.mcc(acc_calc.evaluate(cg))
print ("{:15}\t{:6.3f}\t{:6.3f}\t{:6.3f}".format(filename[-15:], rmsd, drmsd, acc))
def main(args):
if len(args.compareTo) == 1:
cg1 = ftmc.CoarseGrainRNA(args.reference[0])
cg2 = ftmc.CoarseGrainRNA(args.compareTo[0])
print(ftms.cg_rmsd(cg1, cg2))
else:
print("{:15}\t{:6}\t{:6}\t{:6}".format("filename", "RMSD", "dRMSD",
"ACC"))
ref_cg = ftmc.CoarseGrainRNA(args.reference[0])
reference = ref_cg.get_ordered_virtual_residue_poss()
acc_calc = ftms.AdjacencyCorrelation(ref_cg)
for filename in args.compareTo:
cg = ftmc.CoarseGrainRNA(filename)
curr_vress = cg.get_ordered_virtual_residue_poss()
rmsd = ftur.rmsd(reference, curr_vress)
drmsd = ftur.drmsd(reference, curr_vress)
acc = ftms.mcc(acc_calc.evaluate(cg))
print("{:15}\t{:6.3f}\t{:6.3f}\t{:6.3f}".format(
filename[-15:], rmsd, drmsd, acc))
def main():
usage = """
python calculate_mcc.py struct1.cg struct2.cg
"""
num_args = 0
parser = OptionParser(usage=usage)
#parser.add_option('-o', '--options', dest='some_option', default='yo', help="Place holder for a real option", type='str')
#parser.add_option('-u', '--useless', dest='uselesss', default=False, action='store_true', help='Another useless option')
(options, args) = parser.parse_args()
if len(args) < num_args:
parser.print_help()
sys.exit(1)
cg1 = ftmc.CoarseGrainRNA(args[0])
cg2 = ftmc.CoarseGrainRNA(args[1])
confusion_matrix = ftme.confusion_matrix(cg1, cg2)
print "confusion_matrix:", confusion_matrix
print "mcc:", ftme.mcc(confusion_matrix)
print "rmsd:", ftme.cg_rmsd(cg1, cg2)
def main():
usage = """
python cg_to_fornac_html.py file1.cg file2.cg
Convert coarse grain files to html files using fornac
to display a 2D version of the structure.
"""
num_args = 1
parser = OptionParser(usage=usage)
parser.add_option(
'-d',
'--distance',
dest='distance',
default=25,
help=
"Draw links between elements that are within a certain distance from each other",
type='float')
parser.add_option(
'-b',
'--bp-distance',
dest='bp_distance',
default=16,
help=
"Draw links only between nucleotides which are so many nucleotides apart",
type='int')
parser.add_option('-s',
'--sort-by',
dest='sort_by',
default='mcc',
help="What to sort by (options: mcc, pca)",
type='string')
parser.add_option('-n',
'--names',
dest='names',
default=False,
action='store_true',
help='Add the name of the structure to the display')
(options, args) = parser.parse_args()
if len(args) < num_args:
parser.print_help()
sys.exit(1)
structs = []
pair_bitmaps = []
cgs = []
all_links = []
mccs = []
cm = None
for filename in args:
cg = ftmc.CoarseGrainRNA(filename)
cgs += [cg]
if not cm:
cm = ftme.AdjacencyCorrelation(cg)
(links, pair_bitmap) = extract_extra_links(
cg,
options.distance,
options.bp_distance,
correct_links=None if len(all_links) == 0 else all_links[0])
all_links += [links]
pair_bitmaps += [pair_bitmap]
mcc = ftme.mcc(cm.evaluate(cg))
rmsd = ftme.cg_rmsd(cgs[0], cg)
seq_struct = {
"sequence": cg.seq,
"structure": cg.to_dotbracket_string(),
"extraLinks": links
}
fud.pv('options.names')
fud.pv('mcc, rmsd')
if options.names:
seq_struct['name'] = op.basename(
filename) + " ({:.2f},{:.1f})".format(mcc, rmsd)
else:
seq_struct['name'] = ''
structs += [seq_struct]
mccs += [mcc]
if options.sort_by == 'pca':
print("Sorting by pca", file=sys.stderr)
ix = reorder_structs(pair_bitmaps)
else:
print("Sorting by mcc", file=sys.stderr)
ix = np.argsort(-np.array(mccs))
new_array = [0 for i in range(len(ix))]
for i, x in enumerate(ix):
new_array[i] = structs[x]
print(output_template.format(json.dumps(new_array)))
def update_statistics(self, energy_function, sm, prev_energy, tracking_energies = None, tracked_energies=None):
'''
Add a newly sampled structure to the set of statistics.
:param energy_function: The energy_function used to evaluate the structure.
:param sm: The spatial model that was sampled.
:param prev_energy: The evaluated (accepted) energy of the current step
:tracking_energyis: The energy_functions which are calculated for statistics, but not used for sampling.
:tracked_energies: The energy values of the tracking_energies.
'''
self.counter += 1
if self.energy_orig is None:
self.energy_orig = 0.
try:
self.sm_orig.bg.add_all_virtual_residues()
self.energy_orig = energy_function.eval_energy(self.sm_orig)
except KeyError:
# most likely no native structure was provided
pass
energy = prev_energy
#energy = energy_function.eval_energy(sm, background=True)
if energy_function.uses_background():
energy_nobg = energy_function.eval_energy(sm, background=False)
else:
energy_nobg=energy
mcc = None
if self.centers_orig is not None:
r = 0.
if not self.no_rmsd:
centers_new = ftug.bg_virtual_residues(sm.bg)
r = cbr.centered_rmsd(self.centers_orig, centers_new)
#r = cbr.drmsd(self.centers_orig, centers_new)
cm = self.confusion_matrix_calculator.evaluate(sm.bg)
mcc = ftme.mcc(cm)
else:
# no original coordinates provided so we can't calculate rmsds
r = 0.
dist = None
dist2 = None
cg = sm.bg
dists = []
for (self.dist1, self.dist2) in self.dists:
node1 = cg.get_node_from_residue_num(self.dist1)
node2 = cg.get_node_from_residue_num(self.dist2)
pos1, len1 = cg.get_position_in_element(self.dist1)
pos2, len2 = cg.get_position_in_element(self.dist2)
#fud.pv('node1, node2, pos1, pos2')
vec1 = cg.coords[node1][1] - cg.coords[node1][0]
vec2 = cg.coords[node2][1] - cg.coords[node2][0]
#mid1 = (cg.coords[node1][0] + cg.coords[node1][1]) / 2
#mid2 = (cg.coords[node2][0] + cg.coords[node2][1]) / 2
mid1 = cg.coords[node1][0] + pos1 * (vec1 / len1)
mid2 = cg.coords[node2][0] + pos2 * (vec2 / len2)
#fud.pv('mid1, mid2')
dists += [ftuv.vec_distance(mid1, mid2)]
#self.energy_rmsd_structs += [(energy, r, sm.bg)]
self.energy_rmsd_structs += [(energy_nobg, r, copy.deepcopy(sm.bg))]
#self.energy_rmsd_structs += [(energy, r, sm.bg.copy())]
sorted_energies = sorted(self.energy_rmsd_structs, key=lambda x: x[0])
self.energy_rmsd_structs = sorted_energies[:self.save_n_best]
if r > self.highest_rmsd:
self.highest_rmsd = r
if r < self.lowest_rmsd:
self.lowest_rmsd = r
lowest_energy = sorted_energies[0][0]
lowest_rmsd = sorted_energies[0][1]
'''
if energy == lowest_energy:
for key in sm.angle_defs:
print >>sys.stderr, key, str(sm.angle_defs[key])
'''
if not self.silent:
if self.verbose:
'''
for energy_func in energy_function.energies:
print energy_func.__class__.__name__, energy_func.eval_energy(sm)
'''
_, rog=fbe.length_and_rog(sm.bg)
#output_str = u"native_energy [{:s} {:d}]: {:3d} {:5.03g} {:5.3f} ROG: {:5.3f} | min:
output_str = u"native_energy [%s %d]: %3d %5.03g %5.3f ROG: %5.3f | min: %5.2f (%5.2f) %5.2f | extreme_rmsds: %5.2f %5.2f (%.2f)" % ( sm.bg.name, sm.bg.seq_length, self.counter, energy, r , rog, lowest_energy, self.energy_orig, lowest_rmsd, self.lowest_rmsd, self.highest_rmsd, energy_nobg)
output_str += " |"
# assume that the energy function is a combined energy
if isinstance(self.energy_function, fbe.CombinedEnergy):
for e in self.energy_function.iterate_energies():
if isinstance(e,fbe.DistanceExponentialEnergy):
output_str += " [clamp {},{}: {:.1f}]".format(e.from_elem,
e.to_elem,
e.get_distance(sm))
if tracked_energies and tracking_energies:
output_str += " | [tracked Energies]"
for i,e in enumerate(tracking_energies):
sn=e.shortname()
if len(sn)>12:
sn=sn[:9]+"..."
output_str += " [{}]: ".format(sn)
output_str += "%5.03g" % (tracked_energies[i])
elif tracking_energies:
output_str += " | [tracked Energies]"
for e in tracking_energies:
sn=e.shortname()
if len(sn)>12:
sn=sn[:9]+"..."
output_str += " [{}]: ".format(sn)
output_str += "%5.03g" % (e.eval_energy(sm))
if dist:
output_str += " | dist %.2f" % (dist)
for dist2 in dists:
if dist2 is not None:
output_str += " | [dist2: %.2f]" % (dist2)
if mcc is not None:
output_str += " | [mcc: %.3f]" % (mcc)
output_str += " [time: %.1f]" % (time.time() - self.creation_time)
#Print to both STDOUT and the log file.
if self.output_file != sys.stdout:
print (output_str.strip())
if self.output_file != None:
print(output_str, file=self.output_file)
self.output_file.flush()
self.update_plots(energy, r)
'''
if self.counter % 1000 == 0:
import pdb; pdb.set_trace()
'''
if self.counter % 10 == 0:
if not self.silent:
self.save_top(self.save_n_best, counter=self.counter)
if self.step_save > 0 and self.counter % self.step_save == 0:
#If a projection match energy was used, save the optimal projection direction to the file.
if isinstance(self.energy_function, fbe.CombinedEnergy):
for e in self.energy_function.iterate_energies():
if hasattr(e, "accepted_projDir"):
sm.bg.project_from=e.accepted_projDir
sm.bg.to_cg_file(os.path.join(cbc.Configuration.sampling_output_dir, 'step%06d.coord' % (self.counter)))
def main():
usage = """
python cg_to_fornac_html.py file1.cg file2.cg
Convert coarse grain files to html files using fornac
to display a 2D version of the structure.
"""
num_args= 1
parser = OptionParser(usage=usage)
parser.add_option('-d', '--distance', dest='distance', default=25, help="Draw links between elements that are within a certain distance from each other", type='float')
parser.add_option('-b', '--bp-distance', dest='bp_distance', default=16, help="Draw links only between nucleotides which are so many nucleotides apart", type='int')
parser.add_option('-s', '--sort-by', dest='sort_by', default='mcc', help="What to sort by (options: mcc, pca)", type='string')
parser.add_option('-n', '--names', dest='names', default=False, action='store_true', help='Add the name of the structure to the display')
(options, args) = parser.parse_args()
if len(args) < num_args:
parser.print_help()
sys.exit(1)
structs = []
pair_bitmaps = []
cgs = []
all_links = []
mccs = []
cm=None
for filename in args:
cg = ftmc.CoarseGrainRNA(filename)
cgs += [cg]
if not cm:
cm=ftme.AdjacencyCorrelation(cg)
(links, pair_bitmap) = extract_extra_links(cg, options.distance, options.bp_distance,
correct_links = None if len(all_links) == 0 else all_links[0])
all_links += [links]
pair_bitmaps += [pair_bitmap]
mcc = ftme.mcc(cm.evaluate(cg))
rmsd = ftme.cg_rmsd(cgs[0], cg)
seq_struct = {"sequence": cg.seq,
"structure": cg.to_dotbracket_string(),
"extraLinks": links}
fud.pv('options.names')
fud.pv('mcc, rmsd')
if options.names:
seq_struct['name'] = op.basename(filename) + " ({:.2f},{:.1f})".format(mcc, rmsd)
else:
seq_struct['name'] = ''
structs += [seq_struct]
mccs += [mcc]
if options.sort_by == 'pca':
print >>sys.stderr, "Sorting by pca"
ix = reorder_structs(pair_bitmaps)
else:
print >>sys.stderr, "Sorting by mcc"
ix = np.argsort(-np.array(mccs))
new_array = [0 for i in range(len(ix))]
for i,x in enumerate(ix):
new_array[i] = structs[x]
print output_template.format(json.dumps(new_array))