def group_clone_VJ_cdr3(dico_same_VJ, dicoSeq, Clone_threshold):
VJ_ID_diff_CDR3 = {}
dicoclone_vj_cdr3 = {}
for VJ_ID in dico_same_VJ.keys():
sub_sub_group = 0
#print (VJ_ID,"VJ_ID,VJ_ID")
VJ_ID_diff_CDR3[VJ_ID] = {}
for seq in dico_same_VJ[VJ_ID]:
sub_gourp_dist = {}
CDR3_seq = dicoSeq[seq.rstrip()][2]
print(VJ_ID_diff_CDR3[VJ_ID].keys())
if len(VJ_ID_diff_CDR3[VJ_ID].keys()) != 0:
Sub_gourp = VJ_ID_diff_CDR3[VJ_ID].keys()
for g in Sub_gourp:
print(g, dicoSeq[seq.rstrip()][2])
print(
"aaaaa",
1 - hamming_distance(dicoSeq[seq.rstrip()][2], g) /
float(len(g)))
if len(dicoSeq[seq.rstrip()][2]) == len(g):
if 1 - (hamming_distance(dicoSeq[seq.rstrip()][2], g) /
float(len(g))) >= Clone_threshold:
print("here!")
sub_gourp_dist[g] = ('+', 1 - (hamming_distance(
dicoSeq[seq.rstrip()][2], g) / float(len(g))))
elif dicoSeq[seq.rstrip()][1].split("*")[0][-1] == "6":
length = max(len(dicoSeq[seq.rstrip()][2]), len(g))
if 1 - (levenshtein_distance(dicoSeq[seq.rstrip(
)][2], g) / float(length)) >= Clone_threshold:
sub_gourp_dist[g] = (
'+', 1 -
(levenshtein_distance(dicoSeq[seq.rstrip()][2],
g) / float(length)))
if sub_gourp_dist == {}:
VJ_ID_diff_CDR3[VJ_ID][CDR3_seq] = [seq]
else:
dist_loc = {}
for key in sub_gourp_dist.keys():
seqs = [
skbio.Protein(CDR3_seq,
metadata={'id': "CDR3_seq"}),
skbio.Protein(key, metadata={'id': "key"})
]
#print (seqs[0],seqs[1])
msa = skbio.alignment.global_pairwise_align_protein(
seqs[0], seqs[1], 25)
dist_loc[key] = float(msa[1])
print(dist_loc, "dist_loc")
best_coressp = (max(dist_loc.items(),
key=operator.itemgetter(1))[0])
VJ_ID_diff_CDR3[VJ_ID][best_coressp].append(seq)
else:
VJ_ID_diff_CDR3[VJ_ID][CDR3_seq] = [seq]
print(sub_gourp_dist)
#print (VJ_ID_diff_CDR3)
return VJ_ID_diff_CDR3
def trim(OGid):
# 0 Load MSA
try:
msa1 = read_fasta(f'../align_fastas1/out/{OGid}.mfa')
except FileNotFoundError:
msa1 = read_fasta(f'../align_fastas2-2/out/{OGid}.mfa')
# 1 Calculate shared variables
gaps_array = np.full((len(msa1), len(msa1[0][1])), False)
for i, (_, seq) in enumerate(msa1):
for j, sym in enumerate(seq):
if sym == '-':
gaps_array[i, j] = True
scores = gaps_array.sum(axis=0)
msa1 = skbio.TabularMSA([skbio.Protein(seq, metadata={'description': header}) for header, seq in msa1])
# 2 Get trims (segments and columns)
syms_list1 = trim_conserved(msa1, scores, gaps_array,
tp['con_frac'], tp['con_window'], tp['con_minlen'], tp['con_rate'], tp['con_minsig'])
syms_list2, trims = trim_insertions(msa1, scores, gaps_array,
tp['gap_num'], tp['gap_rate'], tp['gap_minsig'],
tp['nongap_frac'], tp['nongap_minlen'],
tp['gp_sigma'], tp['gd_window'], tp['indel1_rate'], tp['indel2_rate'],
tp['weights'], tp['threshold'],
matrix)
# 3 Combine trims (segments and columns) to yield final alignment
msa2 = []
for seq, syms1, syms2 in zip(msa1, syms_list1, syms_list2):
syms = ['-' if sym1 != sym2 else sym1 for sym1, sym2 in zip(syms1, syms2)] # Will only differ if one is converted to gap
msa2.append((seq.metadata['description'], syms))
# 4 Restore gap only columns
gaps_array = np.full((len(msa2), len(msa2[0][1])), False)
for i, (_, seq) in enumerate(msa2):
for j, sym in enumerate(seq):
if sym == '-':
gaps_array[i, j] = True
scores = gaps_array.sum(axis=0)
rf = ['x' for _ in range(len(msa2[0][1]))] # Metadata for marking consensus columns in profile HMM
for region, in ndimage.find_objects(ndimage.label(scores == len(msa2))[0]):
rf[region] = (region.stop - region.start) * ['.']
for i in range(len(msa2)):
syms = msa2[i][1]
syms[region] = list(str(msa1[i, region]))
# 5 Write to file
msa2 = skbio.TabularMSA([skbio.Protein(''.join(syms), metadata={'description': header}) for header, syms in msa2],
positional_metadata={'RF': rf})
msa2.write(f'out/{OGid}.sto', 'stockholm')
def _series_to_fasta_format(ff, data, sequence_type="DNA"):
with ff.open() as f:
for id_, seq in data.iteritems():
if sequence_type == "protein":
sequence = skbio.Protein(seq, metadata={'id': id_})
elif sequence_type == "DNA":
sequence = skbio.DNA(seq, metadata={'id': id_})
elif sequence_type == "RNA":
sequence = skbio.RNA(seq, metadata={'id': id_})
else:
raise NotImplementedError(
"pd.Series can only be converted to DNA or "
"protein FASTA format.")
skbio.io.write(sequence, format='fasta', into=f)
rows = []
for OGid in OGids:
try:
msa = read_fasta(f'../align_fastas1/out/{OGid}.mfa')
except FileNotFoundError:
msa = read_fasta(f'../align_fastas2-2/out/{OGid}.mfa')
gaps_array = np.full((len(msa), len(msa[0][1])), False)
for i, (_, seq) in enumerate(msa):
for j, sym in enumerate(seq):
if sym == '-':
gaps_array[i, j] = True
scores = gaps_array.sum(axis=0)
msa = skbio.TabularMSA([
skbio.Protein(seq, metadata={'description': header})
for header, seq in msa
])
mask = ndimage.label(len(msa) - scores <= tp['gap_num'])[0]
regions = [region for region, in ndimage.find_objects(mask)]
for region in regions:
for segment in get_segments(msa, region, matrix):
row = {
'OGid': OGid,
'start': segment['region'].start,
'stop': segment['region'].stop,
'index': segment['index'],
'length': sum([s.stop - s.start for s in segment['slices']])
}
rows.append(row)