class Autocompleter():
"""Autocomplete System.
Maintains a trie with keys from a given corpus of words.
Gives autocompletion suggestions by retrieving all keys for a give prefix.
"""
def __init__(self, words):
"""Initialize a autocompleter with a given set of words."""
self.trie = CharTrie((word, True) for word in words)
def suggest(self, prefix):
"""Return all words in the corpus starting with a given prefix."""
try:
return self.trie.keys(prefix=prefix)
except KeyError:
return []
def tile_stats(orfs, tiles):
"""compute tile stats
orfs and tiles are name->seq dicts
NOTE: for prefix trie stats (e.g., num of tiles per orf), it is assumed the
orf name is a prefix to the name of a tile from that orf
"""
import numpy as np
tile_lens = np.asarray([len(t) for t in tiles.values()])
orf_lens = np.asarray([len(o) for o in orfs.values()])
tile_size = int(round(np.median(tile_lens)).tolist())
# compute tile counts for each orf
orf_prefixes = CharTrie()
for name in orfs:
orf_prefixes[name] = True
# ensure that no ORF name is a prefix for a different valid ORF
for name in orfs:
if len(orf_prefixes.keys(name)) != 1:
print(orf_prefixes.keys(name))
raise ValueError(
"some ORF name is a prefix for a different valid ORF")
tile_prefixes = CharTrie()
for name in tiles:
tile_prefixes[name] = True
# compute orf coverages
orf_coverages = {}
for (orf, seq) in orfs.items():
orf_residues = len(seq)
tile_residues = 0.0
if tile_prefixes.has_subtrie(orf) or (orf in tile_prefixes):
for tile in tile_prefixes.keys(orf):
tile_residues += len(tiles[tile])
orf_coverages[orf] = tile_residues / orf_residues
stats = {}
stats["tile_size"] = tile_size
stats["num_tiles"] = len(tiles)
stats["total_tile_residues"] = tile_lens.sum().tolist()
stats["avg_orf_coverage"] = tile_lens.sum().tolist() / orf_lens.sum(
).tolist()
stats["num_orfs_smaller_than_tile_size"] = (orf_lens <
tile_size).sum().tolist()
stats["approx_num_tiles_naive_1x_tiling"] = (np.ceil(
orf_lens / tile_size).sum().tolist())
stats["avg_orf_coverage"] = sum(
orf_coverages.values()) / len(orf_coverages)
stats["max_tiles_per_len_normed_orf"] = max(orf_coverages.values())
stats["tile_len_hist"] = compute_int_hist(tile_lens)
# what is the tile coverage of each ORF (tot tile residues / orf residues)
# tiles are assigned to ORFs if they share a name
stats["orf_coverage_hist"] = compute_float_hist(
list(orf_coverages.values()))
stats["top_5_orf_cov"] = list(
map(
list,
sorted(orf_coverages.items(), key=lambda tup: tup[1],
reverse=True)[:5],
))
stats["bot_5_orf_cov"] = list(
map(list,
sorted(orf_coverages.items(), key=lambda tup: tup[1])[:5]))
return stats
