File size: 10,008 Bytes
ab6c03c | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 | import csv
import os
import json
import argparse
import random
from process_pretrain_data import get_kmer_sentence
max_length = 0
def Process_pair(args):
random.seed(42)
root_path = args.file_path.split('/')[-1]
train_seq1_file = open(args.file_path+"/"+root_path+"_enhancer.fasta", "r")
train_seq2_file = open(args.file_path+"/"+root_path+"_promoter.fasta", "r")
train_label_file = open(args.file_path+"/"+root_path+"_label.txt", "r")
test_seq1_file = open(args.file_path+"/"+root_path+"_enhancer_test.fasta", "r")
test_seq2_file = open(args.file_path+"/"+root_path+"_promoter_test.fasta", "r")
test_label_file = open(args.file_path+"/"+root_path+"_label_test.txt", "r")
train_seq1 = train_seq1_file.readlines()
train_seq2 = train_seq2_file.readlines()
train_label = train_label_file.readlines()
test_seq1 = test_seq1_file.readlines()
test_seq2 = test_seq2_file.readlines()
test_label = test_label_file.readlines()
train_lines = []
test_lines = []
for i in range(len(train_label)):
train_lines.append([train_seq1[2*i+1], train_seq2[2*i+1], train_label[i]])
for i in range(len(test_label)):
test_lines.append([test_seq1[2*i+1], test_seq2[2*i+1], test_label[i]])
random.shuffle(train_lines)
if args.dev:
num_dev = int(len(train_lines)/10)
dev_lines = train_lines[:num_dev]
train_lines = train_lines[num_dev:]
output_path = make_path(args)
suffix = '.csv' if args.csv else '.tsv'
delimiter = ',' if args.csv else '\t'
f_train = open(os.path.join(output_path, "train" + suffix), 'wt')
train_w = csv.writer(f_train, delimiter=delimiter)
train_w.writerow(["seq1", "seq2", "label"])
if args.dev:
f_dev = open(os.path.join(output_path, "dev" + suffix), 'wt')
dev_w = csv.writer(f_dev, delimiter=delimiter)
dev_w.writerow(["seq1", "seq2", "label"])
os.makedirs(os.path.join(output_path, "test"))
f_test = open(os.path.join(output_path, "test", "dev" + suffix), 'wt')
test_w = csv.writer(f_test, delimiter=delimiter)
test_w.writerow(["seq1", "seq2", "label"])
else:
f_test = open(os.path.join(output_path, "dev" + suffix), 'wt')
test_w = csv.writer(f_test, delimiter=delimiter)
test_w.writerow(["seq1", "seq2", "label"])
def write_file_pair(lines, writer, seq1_index=0, seq2_index=1, label_index=2):
for line in lines:
seq1 = get_kmer_sentence(line[seq1_index], kmer=args.kmer, stride=args.stride)
seq2 = get_kmer_sentence(line[seq2_index], kmer=args.kmer, stride=args.stride)
writer.writerow([seq1, seq2, str(int(line[label_index]))])
write_file_pair(train_lines, train_w)
write_file_pair(test_lines, test_w)
if args.dev:
write_file_pair(dev_lines, dev_w)
def make_path(args):
output_path = args.output_path if args.output_path else os.path.join(args.file_path, str(args.kmer))
if not os.path.exists(output_path):
os.makedirs(output_path)
return output_path
def write_file(lines, writer, seq_index=2, label_index=3, kmer=6, stride=1):
global max_length
for line in lines:
sentence = get_kmer_sentence(line[seq_index], kmer=kmer, stride=stride)
if len(sentence.split()) > max_length:
max_length = len(sentence.split())
if label_index == -100:
writer.writerow([sentence, str(0)])
else:
writer.writerow([sentence, str(line[label_index])])
def Process(args):
random.seed(24)
train = os.path.join(args.file_path, "train.csv")
test = os.path.join(args.file_path, "test.csv")
train_file = open(train, "r", encoding="utf-8-sig")
test_file = open(test, "r", encoding="utf-8-sig")
train_lines = list(csv.reader(train_file, delimiter=",", quotechar=None))[1:]
test_lines = list(csv.reader(test_file, delimiter=",", quotechar=None))[1:]
random.shuffle(train_lines)
random.shuffle(test_lines)
if args.dev:
num_dev = int(len(train_lines)/9)
dev_lines = train_lines[:num_dev]
train_lines = train_lines[num_dev:]
print(train_lines[0])
output_path = make_path(args)
suffix = '.csv' if args.csv else '.tsv'
delimiter = ',' if args.csv else '\t'
f_train = open(os.path.join(output_path, "train"+suffix), 'wt')
train_w = csv.writer(f_train, delimiter=delimiter)
train_w.writerow(["sentence", "label"])
if args.dev:
f_dev = open(os.path.join(output_path, "dev"+suffix), 'wt')
dev_w = csv.writer(f_dev, delimiter=delimiter)
dev_w.writerow(["sentence", "label"])
f_test = open(os.path.join(output_path, "test"+suffix), 'wt')
test_w = csv.writer(f_test, delimiter=delimiter)
test_w.writerow(["sentence", "label"])
else:
f_test = open(os.path.join(output_path, "dev"+suffix), 'wt')
test_w = csv.writer(f_test, delimiter=delimiter)
test_w.writerow(["sentence", "label"])
write_file(train_lines, train_w, args.seq_index, args.label_index)
write_file(test_lines, test_w, args.seq_index, args.label_index)
if args.dev:
write_file(dev_lines, dev_w)
print("max length: %d" % (max_length))
def Process_UCE(args):
len_count = {}
line2index = {}
pred_file = open(args.file_path, "r", encoding="utf-8-sig")
pred_lines = list(csv.reader(pred_file, delimiter=",", quotechar=None))[1:]
suffix = '.csv' if args.csv else '.tsv'
delimiter = ',' if args.csv else '\t'
f_pred = open(os.path.join(args.output_path, "dev"+suffix), 'wt')
pred_w = csv.writer(f_pred, delimiter=delimiter)
pred_w.writerow(["sentence", "label"])
index = 1
line_num = 0
for line in pred_lines:
len_count[len(line[8])] = len_count.get(len(line[8]), 0) + 1
len_count[len(line[-2])] = len_count.get(len(line[-2]), 0) + 1
cur_index = [index, index+1]
ref = get_kmer_sentence(line[8], args.kmer, args.stride)
pred_w.writerow([ref, 0])
mut1 = get_kmer_sentence(line[-2], args.kmer, args.stride)
pred_w.writerow([mut1, 0])
index += 2
if line[-2] != line[-1]:
len_count[len(line[-1])] = len_count.get(len(line[-1]), 0) + 1
mut2 = get_kmer_sentence(line[-1], args.kmer, args.stride)
pred_w.writerow([mut2, 0])
cur_index.append(index)
index += 1
line2index[line_num] = cur_index
line_num += 1
with open(os.path.join(args.output_path, "line2index.json"), "w") as f:
json.dump(line2index, f)
with open(os.path.join(args.output_path, "lencount.json"), "w") as f:
json.dump(len_count, f)
def Process_Virus(args):
file_path = args.file_path
all_files = os.listdir(file_path)
all_files = [f for f in all_files if not f.startswith("unclass")]
all_lines = []
for i, f in enumerate(all_files):
f_dir = os.path.join(file_path, f)
cur_file = open(f_dir, "r", encoding="utf-8-sig")
cur_lines = list(csv.reader(cur_file, delimiter=",", quotechar=None))[1:]
all_lines.extend(cur_lines)
suffix = '.csv' if args.csv else '.tsv'
delimiter = ',' if args.csv else '\t'
f_pred = open(os.path.join(args.output_path, "dev"+suffix), 'wt')
pred_w = csv.writer(f_pred, delimiter=delimiter)
pred_w.writerow(["sentence", "label"])
index = 1
line_num = 0
for line in pred_lines:
cur_index = [index, index+1]
ref = get_kmer_sentence(line[8], args.kmer, args.stride)
pred_w.writerow([ref, 0])
mut1 = get_kmer_sentence(line[-2], args.kmer, args.stride)
pred_w.writerow([mut1, 0])
index += 2
if line[-2] != line[-1]:
len_count[len(line[-1])] = len_count.get(len(line[-1]), 0) + 1
mut2 = get_kmer_sentence(line[-1], args.kmer, args.stride)
pred_w.writerow([mut2, 0])
cur_index.append(index)
index += 1
line2index[line_num] = cur_index
line_num += 1
with open(os.path.join(args.output_path, "line2index.json"), "w") as f:
json.dump(line2index, f)
with open(os.path.join(args.output_path, "lencount.json"), "w") as f:
def main():
parser = argparse.ArgumentParser()
parser.add_argument(
"--kmer",
default=1,
type=int,
help="K-mer",
)
parser.add_argument(
"--stride",
default=1,
type=int,
help="stride in getting kmer sequence",
)
parser.add_argument(
"--file_path",
default=None,
type=str,
help="The path of the file to be processed",
)
parser.add_argument(
"--output_path",
default=None,
type=str,
help="The path of the processed data",
)
parser.add_argument(
"--dev",
action="store_true",
help="Use this flag to split data as (8:1:1), else (9:1)",
)
parser.add_argument(
"--csv",
action="store_true",
help="if output csv file or not, if not, output tsv",
)
parser.add_argument(
"--pair",
action="store_true",
help="Use this flag to split data as (8:1:1), else (9:1)",
)
parser.add_argument(
"--uce",
action="store_true",
help="Use this flag to split data as (8:1:1), else (9:1)",
)
parser.add_argument(
"--seq_index",
default=2,
type=int,
help="index of seq in the original csv file",
)
parser.add_argument(
"--label_index",
default=3,
type=int,
help="index of label in the original csv file",
)
args = parser.parse_args()
if args.pair:
Process_pair(args)
elif args.uce:
Process_UCE(args)
else:
Process(args)
if __name__ == "__main__":
main()
|