ACLPred:一种可解释的机器学习和基于树的组合模型用于抗癌带预测
Arvind Kumar Yadav1, Jun-Mo Kim2
1Functional Genomics & Bioinformatics Laboratory, Department of Animal Science and Technology, Chung-Ang University, Anseong, 17546, Gyeonggi-do, Republic of Korea.
机器学习 (ML) 通过分析分子性质来加速新抗癌药物的发现. 一种名为ACLPred的新工具使用Light Gradient Boosting Machine (LGBM) 准确预测潜在的抗癌化合物,从而节省时间和资源.
科学领域:
- 计算化学
- 化学信息学
- 在药物发现中使用机器学习
背景情况:
- 越来越多的癌症需要新的治疗药物.
- 传统的实验性药物查需要大量资源.
- 机器学习为识别抗癌化合物提供了快速,经济高效的替代方案.
研究的目的:
- 开发和验证用于预测小分子抗癌活性的机器学习模型.
- 确定对抗癌性能的关键分子特征.
- 为研究人员创建一个可访问的工具来选潜在的候选药物.
主要方法:
- 使用已知抗癌和非抗癌化合物的分子描述器训练分类模型.
- 应用多步特征选择来识别重要的分子描述.
- 采用和评估各种机器学习算法,包括光梯度增强机 (LGBM).
- 使用SHapley添加式解释 (SHAP) 进行模型解释.
主要成果:
- 该模型的预测准确率为90.33%,AUROC为97.31%.
- 开发的工具ACLPred显示出比现有方法更高的预测准确性和通用性.
- SHAP分析表明,拓分子特征显著影响了模型的预测.
结论:
- 机器学习,特别是ACLPred中实施的LGBM算法,为识别潜在的抗癌化合物提供了有效和准确的方法.
- ACLPred提供了一个易于使用的开源解决方案,
- 拓特征对于预测抗癌活性至关重要,为未来的药物设计提供了洞察力.
更多相关视频
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
07:13Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
Published on: April 18, 2025
相关概念视频
Ligand Binding Sites
Protein-ligand interactions are quite specific; even though numerous potential ligands surround a cellular protein at any given time, only a particular ligand can bind to that protein. Moreover, a ligand binds only to a dedicated area on the surface of the protein, known as the...
Conserved Binding Sites
Binding sites are often located in large pockets, and if their location on a protein’s surface is unknown, it can be predicted using various approaches. The energetic method computationally...
Combination Therapies and Personalized Medicine
The combination of the drug acetazolamide and sulforaphane is a good example of combination therapy to treat cancer. The cells in the interior of a large tumor often die due to the hypoxic and...
The Equilibrium Binding Constant and Binding Strength
