def __init__(self,
k_list: List[int],
seq_file_list: List[str],
dissimilirary_list: List[str],
save_dir: str,
markov_list: List[int] = None):
self._k_list = k_list
self._seq_list = [
SequenceData(seq_file_list[i], i)
for i in range(len(seq_file_list))
]
self._dissimilarity = [
self._DIC_FUNC[name] for name in dissimilirary_list
]
self._markov_list = markov_list
self._dissimilarity_names = dissimilirary_list
self._result = Result(len(seq_file_list))
self._save_dir = save_dir
def get_Hao(seq_x: SequenceData, seq_y: SequenceData, k: int, result: Result, r: int = None) -> None:
if k < 2:
return
ktuple_1 = seq_x.get_ktuple(k)
total_1 = seq_x.get_total(k)
markov_1 = seq_x.get_markov(k, k - 2)
ktuple_2 = seq_y.get_ktuple(k)
total_2 = seq_y.get_total(k)
markov_2 = seq_y.get_markov(k, k - 2)
res = Dissimilarity._get_Hao(ktuple_1, ktuple_2, total_1, total_2, markov_1, markov_2)
key = 'Hao_k{}'.format(k)
result.add(key, seq_x.id, seq_y.id, res)
def get_D2S(seq_x: SequenceData, seq_y: SequenceData, k: int, result: Result, r_list: List[int]) -> None:
for r in r_list:
if k < r or k < 3:
continue
ktuple_1 = seq_x.get_ktuple(k)
total_1 = seq_x.get_total(k)
markov_1 = seq_x.get_markov(k, r)
ktuple_2 = seq_y.get_ktuple(k)
total_2 = seq_y.get_total(k)
markov_2 = seq_y.get_markov(k, r)
res = Dissimilarity._get_D2S(ktuple_1, ktuple_2, total_1, total_2, markov_1, markov_2)
key = 'D2S_k{}_M{}'.format(k, r)
result.add(key, seq_x.id, seq_y.id, res)
def get_Ma(seq_x: SequenceData, seq_y: SequenceData, k: int, result: Result, r: int = None) -> None:
ktuple_1 = seq_x.get_ktuple(k)
ktuple_2 = seq_y.get_ktuple(k)
res = Dissimilarity._get_Ma(ktuple_1, ktuple_2, seq_x.get_total(k), seq_y.get_total(k))
key = 'Ma_k{}'.format(k)
result.add(key, seq_x.id, seq_y.id, res)