From machine learning to deep learning: Advances in scoring functions for protein–ligand docking,Wiley Interdisciplinary Reviews: Computational Molecular Science

当前位置： X-MOL 学术 › WIREs Comput. Mol. Sci. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

From machine learning to deep learning: Advances in scoring functions for protein–ligand docking
Wiley Interdisciplinary Reviews: Computational Molecular Science ( IF 16.8 ) Pub Date : 2019-06-27 , DOI: 10.1002/wcms.1429
Chao Shen ₁ , Junjie Ding ₂ , Zhe Wang ₁ , Dongsheng Cao ₃ , Xiaoqin Ding ₂ , Tingjun Hou ₁

Affiliation

Molecule docking has been regarded as a routine tool for drug discovery, but its accuracy highly depends on the reliability of scoring functions (SFs). With the rapid development of machine learning (ML) techniques, ML‐based SFs have gradually emerged as a promising alternative for protein–ligand binding affinity prediction and virtual screening, and most of them have shown significantly better performance than a wide range of classical SFs. Emergence of more data‐hungry deep learning (DL) approaches in recent years further fascinates the exploitation of more accurate SFs. Here, we summarize the progress of traditional ML‐based SFs in the last few years and provide insights into recently developed DL‐based SFs. We believe that the continuous improvement in ML‐based SFs can surely guide the early‐stage drug design and accelerate the discovery of new drugs.

中文翻译：

从机器学习到深度学习：蛋白质-配体对接评分功能的进展

分子对接已被认为是药物发现的常规工具，但其准确性高度取决于评分功能（SF）的可靠性。随着机器学习（ML）技术的飞速发展，基于ML的SF逐渐成为蛋白质-配体结合亲和力预测和虚拟筛选的有前途的替代品，并且其中大多数已显示出比广泛的经典SF更好的性能。。近年来，出现了更多需要大量数据的深度学习（DL）方法，这进一步吸引了人们对更精确的SF的利用。在这里，我们总结了传统的基于ML的SF在过去几年中的进展，并提供了对最近开发的基于DL的SF的见解。

更新日期：2019-11-18

点击分享查看原文

点击收藏

阅读更多本刊最新论文