def __init__(self, path, list_path, aa_batchsize=800):
# self.input_path = './data/nr40/KNN'
# self.target_path = './data/nr40/tor'
self.input_path = path['knn_75_batch']
if list_path == None:
self.file_list = os.listdir(path)
else:
with open(file_list, 'r') as f:
self.file_list = f.read().splitlines()
length = {}
with open('./data/nr40/len.txt') as f:
lines = f.read().split('\n')
for line in lines[:-1]:
filename, l_ = line.split(':')
length[filename] = int(l_)
len_sep_files = [[] for _ in range(2000)]
lengths = []
for filename in self.file_list:
lengths.append(length[filename])
len_sep_files[length[filename]].append(filename)
self.batchs = rep_utils.group_files(len_sep_files, lengths,
aa_batchsize)
def __init__(self, path, length_file, seq_file, aa_batchsize=1250):
self.input_path = path
self.file_list = os.listdir(path)
length = {}
with open(length_file) as f:
lines = f.read().split('\n')
for line in lines[:-1]:
filename, l = line.split(':')
length[filename] = int(l)
len_seq_files = [[] for _ in range(2000)]
lengths = []
for filename in self.file_list:
filename = filename.split('.')[0]
lengths.append(length[filename])
len_seq_files[length[filename]].append(filename)
# len_seq_files为按seq_length从小到大分类的文件名
self.batchs = rep_utils.group_files(len_seq_files, lengths,
aa_batchsize)
self.seq_dict = rep_utils.read_fasta(seq_file)
def __init__(self, file_list, aa_batchsize=800):
# self.input_path = './data/nr40/comp_image_pept_r128'
self.input_path = './data/nr40/comp_image_ca_rescon'
# self.input_path = '/share/Data/processed/nr40/comp_image_ca_multiview'
self.target_path = './data/nr40/tor'
with open('./data/nr40/dataset_list/%s.txt' % file_list) as f:
self.file_list = f.read().split('\n')
length = {}
with open('./data/nr40/len.txt') as f:
lines = f.read().split('\n')
for line in lines[:-1]:
filename, l_ = line.split(':')
length[filename] = int(l_)
len_sep_files = [[] for _ in range(2000)]
lengths = []
for filename in self.file_list:
lengths.append(length[filename])
len_sep_files[length[filename]].append(filename)
self.batchs = rep_utils.group_files(len_sep_files, lengths, aa_batchsize)
def __init__(self, path, aa_batchsize=60):
self.input_path = path
list_path = '/home/caiyi/data/rocklin/src/struct_ssm_test/set_full.txt'
with open(list_path) as f:
lines = f.read().split('\n')
self.file_list = lines[:-1]
length_file = '/home/caiyi/data/rocklin/src/len1.txt'
length = {}
with open(length_file) as f:
lines = f.read().split('\n')
for line in lines[:-1]:
filename, l = line.split(':')
length[filename] = int(l)
len_seq_files = [[] for _ in range(2000)]
lengths = []
for filename in self.file_list:
filename = filename[:-4]
lengths.append(length[filename])
len_seq_files[length[filename]].append(filename)
# len_seq_files为按seq_length从小到大分类的文件名
self.batchs = rep_utils.group_files(len_seq_files, lengths,
aa_batchsize)