Spaces:
Sleeping
Sleeping
File size: 12,403 Bytes
a1af661 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 |
import logging
import sys
import numpy as np
sys.path.append("../")
# from tdc.multi_pred import GDA
import pandas as pd
from torch.utils.data import Dataset
LOGGER = logging.getLogger(__name__)
class GDA_Dataset(Dataset):
"""
Candidate Dataset for:
ALL gene-to-disease interactions
"""
def __init__(self, data_examples):
self.protein_seqs = data_examples[0]
self.disease_dess = data_examples[1]
self.scores = data_examples[2]
def __getitem__(self, query_idx):
protein_seq = self.protein_seqs[query_idx]
disease_des = self.disease_dess[query_idx]
score = self.scores[query_idx]
return protein_seq, disease_des, score
def __len__(self):
return len(self.protein_seqs)
class TDC_Pretrain_Dataset(Dataset):
"""
Dataset of TDC:
ALL gene-disease associations
"""
def __init__(self, data_dir="../../data/pretrain/", test=False):
LOGGER.info("Initializing TDC Pretraining Dataset ! ...")
data = GDA(name="DisGeNET") # , path=data_dir
data.neg_sample(frac = 1)
data.binarize(threshold = 0, order = 'ascending')
self.datasets = data.get_split()
self.name = "DisGeNET"
self.dataset_df = self.datasets['train']
# self.dataset_df = pd.read_csv(f"{data_dir}/disgenet_gda.csv")
self.dataset_df = self.dataset_df[
["Gene", "Disease", "Y"]
].dropna() # Drop missing values.
# print(self.dataset_df.head())
print(
f"{data_dir}TDC training dataset loaded, found associations: {len(self.dataset_df.index)}"
)
self.protein_seqs = self.dataset_df["Gene"].values
self.disease_dess = self.dataset_df["Disease"].values
self.scores = len(self.dataset_df["Y"].values) * [1]
def __getitem__(self, query_idx):
protein_seq = self.protein_seqs[query_idx]
disease_des = self.disease_dess[query_idx]
score = self.scores[query_idx]
return protein_seq, disease_des, score
def __len__(self):
return len(self.protein_seqs)
class GDA_Pretrain_Dataset(Dataset):
"""
Candidate Dataset for:
ALL gene-disease associations
"""
def __init__(self, data_dir="../../data/pretrain/", test=False, split="train", val_ratio=0.2):
LOGGER.info("Initializing GDA Pretraining Dataset ! ...")
self.dataset_df = pd.read_csv(f"{data_dir}/disgenet_gda.csv")
self.dataset_df = self.dataset_df[["proteinSeq", "diseaseDes", "score"]].dropna()
self.dataset_df = self.dataset_df.sample(frac=1, random_state=42).reset_index(drop=True)
num_val_samples = int(len(self.dataset_df) * val_ratio)
if split == "train":
self.dataset_df = self.dataset_df[:-num_val_samples]
print(f"{data_dir}disgenet_gda.csv loaded, found train associations: {len(self.dataset_df.index)}")
elif split == "val":
self.dataset_df = self.dataset_df[-num_val_samples:]
print(f"{data_dir}disgenet_gda.csv loaded, found valid associations: {len(self.dataset_df.index)}")
if test:
self.protein_seqs = self.dataset_df["proteinSeq"].values[:128]
self.disease_dess = self.dataset_df["diseaseDes"].values[:128]
self.scores = 128 * [1]
else:
self.protein_seqs = self.dataset_df["proteinSeq"].values
self.disease_dess = self.dataset_df["diseaseDes"].values
self.scores = len(self.dataset_df["score"].values) * [1]
def __getitem__(self, query_idx):
protein_seq = self.protein_seqs[query_idx]
disease_des = self.disease_dess[query_idx]
score = self.scores[query_idx]
return protein_seq, disease_des, score
def __len__(self):
return len(self.protein_seqs)
# # 分离正负样本
# positive_samples = self.dataset_df[self.dataset_df["score"] == 1]
# negative_samples = self.dataset_df[self.dataset_df["score"] == 0]
# # 打乱并划分正样本
# positive_samples = positive_samples.sample(frac=1, random_state=42).reset_index(drop=True)
# num_pos_val_samples = int(len(positive_samples) * val_ratio)
# # 打乱并划分负样本
# negative_samples = negative_samples.sample(frac=1, random_state=42).reset_index(drop=True)
# num_neg_val_samples = int(len(negative_samples) * val_ratio)
# if split == "train":
# self.dataset_df = pd.concat([positive_samples[:-num_pos_val_samples], negative_samples[:-num_neg_val_samples]])
# print(f"{data_dir}disgenet_gda.csv loaded, found associations: {len(self.dataset_df.index)}")
# elif split == "val":
# self.dataset_df = pd.concat([positive_samples[-num_pos_val_samples:], negative_samples[-num_neg_val_samples:]])
# print(f"{data_dir}disgenet_gda.csv loaded, found associations: {len(self.dataset_df.index)}")
# Shuffle and split data
# class GDA_Pretrain_Dataset(Dataset):
# """
# Candidate Dataset for:
# ALL gene-disease associations
# """
# def __init__(self, data_dir="../../data/pretrain/", test=False):
# LOGGER.info("Initializing GDA Pretraining Dataset ! ...")
# updated = pd.read_csv(f"{data_dir}/disgenet_updated.csv")
# data = GDA(name="DisGeNET")
# data = data.get_data()
# data = data[['Gene_ID','Disease_ID']].dropna()
# self.dataset_df = pd.read_csv(f"{data_dir}/disgenet_gda.csv")
# num_unique_diseaseId = self.dataset_df['diseaseId'].nunique()
# num_unique_geneId = self.dataset_df['geneId'].nunique()
# print(f"Number of unique 'diseaseId': {num_unique_diseaseId}")
# print(f"Number of unique 'geneId': {num_unique_geneId}")
# num_of_c0002395 = self.dataset_df[self.dataset_df['diseaseId'] == 'C0002395'].shape[0]
# print(f"Alzheimer Number in 2020：{num_of_c0002395}")
# Convert 'Gene_ID' and 'Disease_ID' to str before merge
# data['Gene_ID'] = data['Gene_ID'].astype(str)
# data['Disease_ID'] = data['Disease_ID'].astype(str)
# Similarly for 'geneId' and 'diseaseId', if they're not already of type 'str'
# self.dataset_df['geneId'] = self.dataset_df['geneId'].astype(str)
# self.dataset_df['diseaseId'] = self.dataset_df['diseaseId'].astype(str)
# # 合并两个DataFrame并找出不同的行
# merged = df.merge(self.dataset_df, how='outer', indicator=True)
# differences = merged[merged['_merge'] != 'both']
# differences.to_csv('/nfs/dpa_pretrain/data/pretrain/differences.csv', index=False)
# Check for overlap between TDC dataset and DisGeNET dataset
# merged_df = pd.merge(data, self.dataset_df, how='inner', left_on=['Gene_ID','Disease_ID'], right_on=['geneId','diseaseId'])
# num_matched_pairs = merged_df.shape[0]
# print(f"Number of matched pairs TDC: {num_matched_pairs}")
# merged_dis = pd.merge(data, updated, how='inner', left_on=['Gene','Disease'], right_on=['proteinSeq','diseaseDes'])
# num_matched = merged_dis.shape[0]
# print(f"Number of matched pairs DisGeNET_test: {num_matched}")
# self.dataset_df = self.dataset_df[
# ["proteinSeq", "diseaseDes", "score"]
# ].dropna() # Drop missing values.
# print(self.dataset_df.head()) "proteinSeq", "diseaseDes", "score"
# print(
# f"{data_dir}disgenet_gda.csv loaded, found associations: {len(self.dataset_df.index)}"
# )
# df1 = pd.read_csv(f"{data_dir}/disgenet_gda.csv")
# df1 = df1[
# ["proteinSeq", "diseaseDes", "score"]
# ].dropna()
# # 合并两个DataFrame并找出不同的行
# merged = df1.merge(self.dataset_df, how='outer', indicator=True)
# differences = merged[merged['_merge'] != 'both']
# # 将结果保存到新的文件中
# differences.to_csv('/nfs/dpa_pretrain/data/pretrain/differences.csv', index=False)
# if test:
# self.protein_seqs = self.dataset_df["proteinSeq"].values[:128]
# self.disease_dess = self.dataset_df["diseaseDes"].values[:128]
# self.scores = 128 * [1]
# else:
# self.protein_seqs = self.dataset_df["proteinSeq"].values
# self.disease_dess = self.dataset_df["diseaseDes"].values
# self.scores = len(self.dataset_df["score"].values) * [1]
# def __getitem__(self, query_idx):
# protein_seq = self.protein_seqs[query_idx]
# disease_des = self.disease_dess[query_idx]
# score = self.scores[query_idx]
# return protein_seq, disease_des, score
# def __len__(self):
# return len(self.protein_seqs)
class PPI_Pretrain_Dataset(Dataset):
"""
Candidate Dataset for:
ALL protein-to-protein interactions
"""
def __init__(self, data_dir="../../data/pretrain/", test=False):
LOGGER.info("Initializing metric learning data set! ...")
self.dataset_df = pd.read_csv(f"{data_dir}/string_ppi_900_2m.csv")
self.dataset_df = self.dataset_df[["item_seq_a", "item_seq_b", "score"]]
self.dataset_df = self.dataset_df.dropna()
if test:
self.dataset_df = self.dataset_df.sample(100)
print(
f"{data_dir}/string_ppi_900_2m.csv loaded, found interactions: {len(self.dataset_df.index)}"
)
self.protein_seq1 = self.dataset_df["item_seq_a"].values
self.protein_seq2 = self.dataset_df["item_seq_b"].values
self.scores = len(self.dataset_df["score"].values) * [1]
def __getitem__(self, query_idx):
protein_seq1 = self.protein_seq1[query_idx]
protein_seq2 = self.protein_seq2[query_idx]
score = self.scores[query_idx]
return protein_seq1, protein_seq2, score
def __len__(self):
return len(self.protein_seq1)
class PPI_Dataset(Dataset):
"""
Candidate Dataset for:
ALL protein-to-protein interactions
"""
def __init__(self, protein_seq1, protein_seq2, score):
self.protein_seq1 = protein_seq1
self.protein_seq2 = protein_seq2
self.scores = score
def __getitem__(self, query_idx):
protein_seq1 = self.protein_seq1[query_idx]
protein_seq2 = self.protein_seq2[query_idx]
score = self.scores[query_idx]
return protein_seq1, protein_seq2, score
def __len__(self):
return len(self.protein_seq1)
class DDA_Dataset(Dataset):
"""
Candidate Dataset for:
ALL disease-to-disease associations
"""
def __init__(self, diseaseDes1, diseaseDes2, label):
self.diseaseDes1 = diseaseDes1
self.diseaseDes2 = diseaseDes2
self.label = label
def __getitem__(self, query_idx):
diseaseDes1 = self.diseaseDes1[query_idx]
diseaseDes2 = self.diseaseDes2[query_idx]
label = self.label[query_idx]
return diseaseDes1, diseaseDes2, label
def __len__(self):
return len(self.diseaseDes1)
class DDA_Pretrain_Dataset(Dataset):
"""
Candidate Dataset for:
ALL protein-to-protein interactions
"""
def __init__(self, data_dir="../../data/pretrain/", test=False):
LOGGER.info("Initializing metric learning data set! ...")
self.dataset_df = pd.read_csv(f"{data_dir}disgenet_dda.csv")
self.dataset_df = self.dataset_df.dropna() # Drop missing values.
if test:
self.dataset_df = self.dataset_df.sample(100)
print(
f"{data_dir}disgenet_dda.csv loaded, found associations: {len(self.dataset_df.index)}"
)
self.disease_des1 = self.dataset_df["diseaseDes1"].values
self.disease_des2 = self.dataset_df["diseaseDes2"].values
self.scores = len(self.dataset_df["jaccard_variant"].values) * [1]
def __getitem__(self, query_idx):
disease_des1 = self.disease_des1[query_idx]
disease_des2 = self.disease_des2[query_idx]
score = self.scores[query_idx]
return disease_des1, disease_des2, score
def __len__(self):
return len(self.disease_des1)
|