def __init__(self,
common_positions,
numbering_schemes,
segments,
difference_matrix,
protein_set,
cutoff=40):
self.cutoff = cutoff
self.common_gn = common_positions
self.schemes = numbering_schemes
self.segments = segments
self.diff_matrix = difference_matrix
self.signature_matrix_filtered = OrderedDict()
self.signature_consensus = OrderedDict()
self.protein_set = protein_set
self.relevant_gn = OrderedDict([(x[0], OrderedDict())
for x in self.schemes])
self.relevant_segments = OrderedDict()
self.scored_proteins = []
self.protein_report = OrderedDict()
self.protein_signatures = OrderedDict()
self.find_relevant_gns()
self.residue_to_feat = dict([(x, set()) for x in AMINO_ACIDS.keys()])
for fidx, feat in enumerate(AMINO_ACID_GROUPS.items()):
for res in feat[1].split(','):
self.residue_to_feat[res].add(fidx)
def prepare_aa_group_preference():
pref_dict = {}
lengths = {}
for row, group in enumerate(AMINO_ACID_GROUPS.items()):
tmp_len = len(group[1])
try:
lengths[tmp_len].append(row)
except KeyError:
lengths[tmp_len] = [
row,
]
l_heap = sorted(lengths.keys())
while l_heap:
tmp = l_heap.pop()
for feat_row in lengths[tmp]:
pref_dict[feat_row] = []
for pref_feat in l_heap:
pref_dict[feat_row].extend(lengths[pref_feat])
return pref_dict