sys.exit(
"Error!! Can't find reference sequence...")
else:
try:
print(
"Finding reference sequence using global MSAsearch..."
)
i_ref = sca.MSAsearch(headers_full, sequences_full,
seq_pdb)
options.i_ref = i_ref
print("reference sequence index is: %i" % (i_ref))
print(headers_full[i_ref])
print(sequences_full[i_ref])
except:
sys.exit("Error!! Can't find reference sequence...")
sequences, ats = sca.makeATS(sequences_full, ats_pdb, seq_pdb,
i_ref, options.truncate)
dist_new = np.zeros((len(ats), len(ats)))
for (j, pos1) in enumerate(ats):
for (k, pos2) in enumerate(ats):
if k != j:
if (pos1 == '-') or (pos2 == '-'):
dist_new[j, k] == 1000
else:
ix_j = ats_pdb.index(pos1)
ix_k = ats_pdb.index(pos2)
dist_new[j, k] = dist_pdb[ix_j, ix_k]
dist_pdb = dist_new
except:
sys.exit("Error!!! Something wrong with PDBid or path...")
elif options.refseq is not None:
print("Finding reference sequence using provided sequence file...")
# Create the ATS
i_ref = options.i_ref
print "Reference sequence %i:" % (i_ref)
print headers_full[i_ref]
s_tmp = sequences_full[i_ref]
try:
f = open(options.refpos,'r')
ats_tmp = [line.rstrip('\n') for line in f]
print ats_tmp
f.close()
except:
sys.exit("Error!! Unable to read reference positions!")
try:
sequences, ats = sca.makeATS(sequences_full, ats_tmp, s_tmp, i_ref)
except:
sys.exit("Error!! Unable to make ATS!")
print "Final alignment parameters:"
print "Number of positions: L = %i" % (len(s_tmp))
print "Size of ats: %i" % len(ats)
# saving the important stuff. Everything is stored in a file called [MSAname]_sequence.db.
path_list = options.alignment.split(os.sep)
fn = path_list[-1]
fn_noext = fn.split(".")[0]
D = {}
D['alg'] = sequences_full
D['hd'] = headers_full
print_("reference sequence index is: {:d}".format(i_ref))
print_(headers_full[i_ref])
print_(sequences_full[i_ref])
except:
sys.exit("Error!! Can't find reference sequence...")
else:
try:
print_("Finding reference sequence using global MSAsearch...")
i_ref = sca.MSAsearch(headers_full, sequences_full, seq_pdb)
options.i_ref = i_ref
print_("reference sequence index is: {:d}".format(i_ref))
print_(headers_full[i_ref])
print_(sequences_full[i_ref])
except:
sys.exit("Error!! Can't find reference sequence...")
sequences, ats = sca.makeATS(sequences_full, ats_pdb, seq_pdb, i_ref, options.truncate)
dist_new = np.zeros((len(ats), len(ats)))
for (j, pos1) in enumerate(ats):
for (k, pos2) in enumerate(ats):
if k != j:
if (pos1 == '-') or (pos2 == '-'):
dist_new[j, k] == 1000
else:
ix_j = ats_pdb.index(pos1)
ix_k = ats_pdb.index(pos2)
dist_new[j, k] = dist_pdb[ix_j, ix_k]
dist_pdb = dist_new
except:
sys.exit("Error!!! Something wrong with PDBid or path...")
elif options.refseq is not None:
print_("Finding reference sequence using provided sequence file...")
print('Collecting residue data from PDB')
pdb_residues = get_pdb_residues(options.pdbid, options.chainID, QUIET=True)
print('Parsing sequence and pdb_ats')
pdb_sequence, pdb_ats = get_pdb_sequence(pdb_residues)
print('Calculating distances')
pdb_distances = get_pdb_distances(pdb_residues)
print("Finding reference sequence using Bio.pairwise2.align.globalxx")
reference_index = locate_reference(position_filtered_sequences,
pdb_sequence)
print("Index of reference sequence: {}".format(reference_index))
sequences, ats = sca.makeATS(position_filtered_sequences, pdb_ats,
pdb_sequence, reference_index,
options.truncate)
# filtering sequences and positions, calculations of effective number of seqs
print(
"Conducting sequence and position filtering: alignment size is {} seqs, {} pos"
.format(len(sequences), len(sequences[0])))
print(f'ATS size: {len(ats)}')
print(
f'Dim Distance Matrix: {len(pdb_distances)} x {len(pdb_distances[0])}')
alg0, seqw0, seqkeep = sca.filterSeq(sequences,
reference_index,
max_fracgaps=PARAMETERS[1],
min_seqid=PARAMETERS[2],
max_seqid=PARAMETERS[3])