try:
f = open(options.refpos, 'r')
ats_tmp = [line.rstrip('\n') for line in f]
f.close()
except:
print_("Error reading reference position file! Using default numbering 1 to number of positions")
ats_tmp = range(len(sequences[0]))
else:
print_("No reference position list provided. Using default numbering 1 to number of positions")
ats_tmp = range(len(sequences[0]))
sequences, ats = sca.makeATS(
sequences_full, ats_tmp, s_tmp[0], i_ref, options.truncate)
except:
sys.exit("Error!! Can't find reference sequence...")
else:
msa_num = sca.lett2num(sequences_full)
i_ref = sca.chooseRefSeq(sequences_full)
print_("No reference sequence given, chose as default ({:d}): {}".format(i_ref, headers_full[i_ref]))
sequences = sequences_full
ats = range(len(sequences[0]))
else:
print_("using provided reference index {:d}".format(i_ref))
print_(headers_full[i_ref])
s_tmp = sequences_ori[i_ref]
try:
if options.refpos is not None:
f = open(options.refpos, 'r')
ats_tmp = [line.rstrip('\n') for line in f]
# print ats_tmp
f.close()
else:
except:
print(
"Error reading reference position file! Using default numbering 1 to number of positions"
)
ats_tmp = range(len(sequences[0]))
else:
print(
"No reference position list provided. Using default numbering 1 to number of positions"
)
ats_tmp = range(len(sequences_full[0]))
sequences, ats = sca.makeATS(sequences_full, ats_tmp, s_tmp[0],
i_ref, options.truncate)
except:
sys.exit("Error!! Can't find reference sequence...")
else:
msa_num = sca.lett2num(sequences_full)
i_ref = sca.chooseRefSeq(sequences_full)
print("No reference sequence given, chose as default (%i): %s" %
(i_ref, headers_full[i_ref]))
sequences = sequences_full
ats = range(len(sequences[0]))
else:
print("using provided reference index %i" % (i_ref))
print(headers_full[i_ref])
s_tmp = sequences_ori[i_ref]
try:
if options.refpos is not None:
f = open(options.refpos, 'r')
ats_tmp = [line.rstrip('\n') for line in f]
f.close()
else:
alg1, iposkeep = sca.filterPos(alg0, seqw0, PARAMETERS[0])
ats = [ats[i] for i in iposkeep]
distance_matrix = pdb_distances[np.ix_(iposkeep, iposkeep)]
effseqsprelimit = int(seqw0.sum())
Nseqprelimit = len(alg1)
print(
"After filtering: alignment size is {} seqs, {} effective seqs, {} pos"
.format(len(alg1), effseqsprelimit, len(alg1[0])))
alg = alg1
hd = headers
# calculation of final MSA, sequence weights
seqw = sca.seqWeights(alg)
effseqs = seqw.sum()
msa_num = sca.lett2num(alg)
Nseq, Npos = msa_num.shape
structPos = [i for (i, k) in enumerate(ats) if k != '-']
print(
FINAL_MSG.format(Nseq, effseqs, Npos, len(ats), len(structPos),
len(distance_matrix), len(distance_matrix[0])))
path_list = os.path.split(options.alignment)
fn = path_list[-1]
fn_noext = fn.split(".")[0]
with open("Outputs/" + fn_noext + "processed" + ".fasta", "w") as f:
for i in range(len(alg)):
f.write(">%s\n" % (hd[i]))
f.write(alg[i] + "\n")