def compute_correction_terms(alignment_file, binary_raw_file):
#initialise ccmpred object
ccm = CCMpred()
# specify possible file paths
ccm.set_alignment_file(alignment_file)
ccm.set_initraw_file(binary_raw_file)
# read alignment and remove gapped sequences and positions
ccm.read_alignment("psicov", 50, 75)
# compute sequence weights (in order to reduce sampling bias)
ccm.compute_sequence_weights("simple", 0.8)
# compute amino acid counts and frequencies adding pseudo counts for non-observed amino acids
ccm.compute_frequencies("uniform_pseudocounts", 1, 1)
#read in binary raw file
ccm.intialise_potentials()
#compute apc
ccm.recenter_potentials()
cmat = contactmatrix.frobenius_score(ccm.x_pair)
mean = np.mean(cmat, axis=0)
apc_mat = mean[:, np.newaxis] * mean[np.newaxis, :] / np.mean(cmat)
#compute entropy correction
single_freq = ccm.pseudocounts.freqs[0]
nr_states = 20
log = np.log2
scaling_factor, mat_corrected = contactmatrix.compute_local_correction(
single_freq,
ccm.x_pair,
ccm.neff,
1,
squared=False,
entropy=True,
nr_states=nr_states,
log=log)
entropy_correction_mat = cmat - mat_corrected
return apc_mat, entropy_correction_mat
def main():
parser = argparse.ArgumentParser(description='Plotting a contact map.')
group_append = parser.add_mutually_exclusive_group(required=True)
group_append.add_argument('-m', '--mat-file', dest='mat_file', type=str, help='path to mat file')
group_append.add_argument('-b', '--braw-file', dest='braw_file', type=str,help='path to binary raw coupling file')
parser.add_argument('-o', '--plot-out', dest='plot_out', type=str, help='Output directory for plot')
parser.add_argument('--seq-sep', dest='seqsep', type=int, default=6, help='Minimal sequence separation')
parser.add_argument('--contact-threshold', dest='contact_threshold', type=int, default=8, help='Contact definition as maximal C_beta distance between residue pairs.')
parser.add_argument('--pdb-file', dest='pdb_file', type=str, help='Optional PDB file (renumbered starting from 1) for distance matrix.')
parser.add_argument('--alignment-file', dest='alignment_file', type=str, help='Optional alignment file for gap percentage and entropy subplot.')
parser.add_argument("--aln-format", dest="aln_format", default="psicov", help="File format for MSAs [default: \"%(default)s\"]")
parser.add_argument("--apc", action="store_true", default=False, help="Apply average product correction")
parser.add_argument("--entropy-correction", dest='entropy_correction', action="store_true", default=False, help="Apply entropy correction")
args = parser.parse_args()
if args.mat_file is None and args.braw_file is None:
print("Either mat_file or braw_file need to be set.")
mat_file = args.mat_file
braw_file = args.braw_file
alignment_file = args.alignment_file
aln_format = args.aln_format
pdb_file = args.pdb_file
plot_out = args.plot_out
seqsep = args.seqsep
contact_threshold = args.contact_threshold
apc = args.apc
entropy_correction = args.entropy_correction
alignment=None
if alignment_file is not None:
alignment = read_msa(alignment_file, aln_format)
#compute sequence weights
weighting = SequenceWeights(False, 0.8)
weights = weighting.weights_simple(alignment)
#compute frequencies
pseudocounts = PseudoCounts(alignment, weights)
pseudocounts.calculate_frequencies(
'uniform_pseudocounts', 1, 1, remove_gaps=False
)
if braw_file is not None:
braw = raw.parse_msgpack(braw_file)
meta_info = braw.meta
#compute frobenius score from couplings
mat = io.frobenius_score(braw.x_pair)
if entropy_correction:
if alignment is None:
print("Alignment file is necessary to compute entropy correction!")
else:
scaling_factor_eta, mat = io.compute_local_correction(
pseudocounts.freqs[0],
braw.x_pair,
meta_info['workflow'][0]['msafile']['neff'],
meta_info['workflow'][0]['regularization']['lambda_pair'],
mat,
squared=False, entropy=True
)
elif apc:
mat = io.apc(mat)
if mat_file is not None:
mat, meta_info = io.read_matrix(mat_file)
if entropy_correction:
print("Binary Raw file is necessary to compute entropy correction!")
elif apc:
mat = io.apc(mat)
plot_file = plot_out + "/contact_map_seqsep{0}_contacthr{1}.html".format(seqsep, contact_threshold)
plot_contact_map(mat, seqsep, contact_threshold, plot_file, "", alignment=alignment, pdb_file=pdb_file)
def plot_contact_map(alignment_file, aln_format, braw_file, mat_file, pdb_file, plot_file,
entropy_correction, apc, seqsep, contact_threshold):
pseudocounts = None
mat = None
gaps_percentage_plot = None
protein = None
if entropy_correction and (alignment_file is None or braw_file is None):
print("Entropy correction requires specification of alignment file and binary raw couplign file!")
sys.exit(1)
if alignment_file is not None:
protein = os.path.basename(alignment_file).split(".")[0]
alignment = io.read_msa(alignment_file, aln_format)
# compute sequence weights
weights = ccmpred.weighting.weights_simple(alignment, 0.8)
# compute frequencies
pseudocounts = PseudoCounts(alignment, weights)
pseudocounts.calculate_frequencies(
'uniform_pseudocounts', 1, 1, remove_gaps=False
)
gaps_percentage_plot = plot.plot_percentage_gaps_per_position(pseudocounts.counts[0], plot_file=None)
if braw_file is not None:
protein = os.path.basename(braw_file).split(".")[0]
braw = raw.parse_msgpack(braw_file)
meta_info = braw.meta
# compute frobenius score from couplings
mat = io_cm.frobenius_score(braw.x_pair)
if entropy_correction:
scaling_factor_eta, mat = io_cm.compute_local_correction(
pseudocounts.freqs[0],
braw.x_pair,
meta_info['workflow'][0]['msafile']['neff'],
meta_info['workflow'][0]['regularization']['lambda_pair'],
mat,
entropy=True
)
elif apc:
mat = io_cm.apc(mat)
if mat_file is not None:
protein = os.path.basename(mat_file).split(".")[0]
mat, meta_info = io_cm.read_matrix(mat_file)
if apc:
mat = io_cm.apc(mat)
L = len(mat)
indices_upper_tri_i, indices_upper_tri_j = np.triu_indices(L, seqsep)
plot_matrix = pd.DataFrame()
plot_matrix['residue_i'] = indices_upper_tri_i + 1
plot_matrix['residue_j'] = indices_upper_tri_j + 1
plot_matrix['confidence'] = mat[indices_upper_tri_i, indices_upper_tri_j]
if pdb_file is not None:
# compute distance map from pdb file
observed_distances = io.distance_map(pdb_file, L)
plot_matrix['distance'] = observed_distances[indices_upper_tri_i, indices_upper_tri_j]
plot_matrix['contact'] = ((plot_matrix.distance < contact_threshold) * 1).tolist()
plot_title="Contact Map for protein {0}".format(protein)
# Plot Contact Map
plot.plot_contact_map_someScore_plotly(plot_matrix, plot_title, seqsep, gaps_percentage_plot, plot_file)