def load_image_data(pdb,load_all=False):
g = utils.load_GREMLIN_dataset(pdb)
fasta,seq = utils.load_seq(pdb)
NATIVE = utils.load_contact_map(pdb)
# Sanity checks
assert(len(seq) == g.shape[0])
assert(len(seq) == NATIVE.shape[0])
# APC corrections and whiten
g = APC_L2(g)
N = g.shape[0]
IDX = generate_matrix_IDX(N,kernel_window)
idx_true_pos = set()
idx_true_neg = set()
# Load the set of TP and TN
for i,j in IDX:
if NATIVE[i,j]:
idx_true_pos.add((i,j))
else:
idx_true_neg.add((i,j))
# Shuffle the contacts
idx_true_neg = list(idx_true_neg)
np.random.shuffle(idx_true_neg)
# If we are only loading a subset of TN, truncate here
if load_all:
FP_choosen = len(idx_true_neg)
else:
FP_choosen = int(ratio_TP_to_TN*len(idx_true_pos))
ratio = float(len(idx_true_neg))/ len(idx_true_pos)
status_str = "{} {:5d} {:5d} {:0.4f}"
print status_str.format(pdb, len(idx_true_pos), FP_choosen, ratio)
idx_true_neg = idx_true_neg[:FP_choosen]
X0 = generate_feature_vectors(g,seq,idx_true_pos,kernel_window)
Y0 = [1,]*len(X0)
X1 = generate_feature_vectors(g,seq,idx_true_neg,kernel_window)
Y1 = [0,]*len(X1)
# Concatenate the two samples and make them a numpy array
X = np.array(X0+X1)
Y = np.array(Y0+Y1)
return X,Y
def compute_predictions(pdb, clf):
# Load the GREMLIN data
g = utils.load_GREMLIN_dataset(pdb)
fasta, seq = utils.load_seq(pdb)
# Sanity checks
assert len(seq) == g.shape[0]
# APC corrections and whiten
g = APC_L2(g)
N = g.shape[0]
IDX = generate_matrix_IDX(N, kernel_window)
# Load the native contacts
# NATIVE_MATRIX = utils.load_contact_map(pdb)
# native = [NATIVE_MATRIX[idx] for idx in IDX]
#################################################################
X = generate_feature_vectors(g, seq, IDX, kernel_window)
Yp = clf.predict_proba(X)[:, 1]
g2 = np.zeros(g.shape)
for (i, j), y in zip(IDX, Yp):
g2[i, j] = g2[j, i] = y
"""
# Reorder based off of ranking
order = np.argsort(Yp)[::-1]
IDX0 = np.array(map(list,IDX))
IDX0 = IDX0[order]
W = np.array([G[i,j] for i,j in IDX])
order = np.argsort(W)[::-1]
IDX1 = np.array(map(list,IDX))
IDX1 = IDX1[order]
"""
return g2
def build_constraint_text(pdb, f_prediction):
IDX = np.loadtxt(f_prediction).astype(int)
fasta,_ = utils.load_seq(pdb)
constraint_text = []
for i,j in IDX:
atom_i = fasta[i]
atom_j = fasta[j]
fade = {"res1":i+index_offset,
"res2":j+index_offset,
"score":FADE_strength}
fade["atom1"] = choose_atom(atom_i)
fade["atom2"] = choose_atom(atom_j)
line = FADE_line.format(**fade)
constraint_text.append(line)
constraint_text = '\n'.join(constraint_text)
return constraint_text