特征选择
计算机科学
水准点(测量)
人工智能
二元分类
机器学习
背景(考古学)
选择(遗传算法)
随机森林
领域(数学)
模式识别(心理学)
否定选择
假阳性率
过程(计算)
数据挖掘
数学
支持向量机
化学
生物
古生物学
生物化学
大地测量学
基因组
基因
纯数学
地理
操作系统
作者
Mohammad Morovvati Sharifabad,Razieh Sheikhpour,Sajjad Gharaghani
标识
DOI:10.1016/j.vascn.2022.107191
摘要
Machine learning-based approaches in the field of drug discovery have dramatically reduced the time and cost of the laboratory process of detecting potential drug-target interactions (DTIs). Standard binary classifiers require both positive and negative samples in the training and validation phases. One of the major challenges in the DTI context is the lack of access to non-interacting pairs as negative samples in the learning process. Many recent studies in this field have randomly selected negative samples from unlabeled drug-target pairs. Therefore, due to the probability of the presence of unknown positive samples in a set considered as negative samples, the model results may be affected and appear with a high rate of false positive. In this study, an algorithm called Reliable Non-Interacting Drug-Target Pairs (RNIDTP) is proposed to select reliable negative samples and an efficient algorithm to select relevant features for drug-target interaction prediction. To validate the performance of the proposed RNIDTP algorithm in the selection of negative samples, a benchmark drug-target interactions dataset is used. The results demonstrate the superiority of the proposed algorithm compared with other algorithms in most cases. The results also indicate that by using an appropriate algorithm for the selection of negative samples, the performance of the learning process is significantly increased compared to random selection.
科研通智能强力驱动
Strongly Powered by AbleSci AI