Robotics & Machine Learning Daily News2024,Issue(Nov.14) :175-176.

Learning Binding Affinities via Fine-tuning of Protein and Ligand Language Model s

通过精细调节蛋白质和配体语言模型学习结合亲和力

Robotics & Machine Learning Daily News2024,Issue(Nov.14) :175-176.

Learning Binding Affinities via Fine-tuning of Protein and Ligand Language Model s

通过精细调节蛋白质和配体语言模型学习结合亲和力

扫码查看

摘要

由一名新闻记者-机器人与机器学习日报的工作人员新闻编辑每日新闻-根据新闻报道的预印摘要,我们的记者获得了新闻报道的基本信息以下报价来源于BI orxiv.org:“准确的蛋白质-配体结合亲和力在线预测是有效识别HIT的必要条件”在大型分子库中。常用的基于结构的方法,如giga-docking,常常失败有效的Y级化合物和基于自由能的方法虽然准确,但对于大规模筛选来说计算过于繁琐。现有的深度学习模型很难实现新的目标或目标药物和目前的评估方法并不能准确反映现实世界的表现。

Abstract

By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - According to news reporting based on a preprint abstract, our journalists obtained thefollowing quote sourced from bi orxiv.org:“Accurate in-silico prediction of protein-ligand binding affinity is essential f or efficient hit identificationin large molecular libraries. Commonly used stru cture-based methods such as giga-docking often fail torank compounds effectivel y, and free energy-based approaches, while accurate, are too computationally int ensive for large-scale screening. Existing deep learning models struggle to gene ralize to new targets ordrugs, and current evaluation methods do not reflect re al-world performance accurately.

Key words

Bioinformatics/Biotechnology/Biotechno logy - Bioinformatics/Cyborgs/Emerging Technologies/Information Technology/M achine Learning

引用本文复制引用

出版年

2024
Robotics & Machine Learning Daily News

Robotics & Machine Learning Daily News

ISSN:
段落导航相关论文