def compute_cmap(f_rank):
base = os.path.basename(f_rank)
model_name = os.path.dirname(f_rank)
pdb = base.split('.')[0]
func = {
"G2" : utils.load_improved_GREMLIN_dataset,
"APC": utils.load_GREMLIN_dataset,
}
G = func[model_name](pdb)
NATIVE_MATRIX = utils.load_contact_map(pdb)
N = G.shape[0]
IDX = list(generate_matrix_IDX(N,kernel_window))
# Load the native contacts
native = np.array([NATIVE_MATRIX[idx] for idx in IDX])
g = np.array([G[idx] for idx in IDX])
data = {}
CUT_IDX = np.linspace(1,5*N,cut_iterations)
for cut_idx in CUT_IDX:
contacts = fixedL_cut(g,native,cut_idx,index_only=True)
C = build_cmap_from_index(N, IDX,contacts)
data[cut_idx/N] = C
return CUT_IDX,data,NATIVE_MATRIX
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
PDB = [os.path.basename(f).split('.')[0] for f in known_models]
kernel_window = 2
print "Found {} known models to predict.".format(len(PDB))
os.system('mkdir -p predictions')
def score_ordering(IDX, A):
a = np.array([A[idx] for idx in IDX])
order = np.argsort(a)[::-1]
return np.array(map(list,IDX))[order]
for pdb in PDB:
G1 = utils.load_GREMLIN_dataset(pdb)
G2 = utils.load_improved_GREMLIN_dataset(pdb)
NATIVE = utils.load_contact_map(pdb)
N = NATIVE.shape[0]
IDX = utils.generate_matrix_IDX(N,kernel_window)
sidx1 = score_ordering(IDX, G1)
sidx2 = score_ordering(IDX, G2)
args = {"model" : "GREMLIN", "pdb": pdb}
f_save = "predictions/{pdb}_{model}_{L:0.2f}.txt"
for L in L_SET:
args["L"] = L
cut_idx = int(N*args["L"])
contacts = sidx1[:cut_idx]
