通过共识模型增强静氨酸结合亲和力预测:Tox24挑战的见解
Xiaolin Pan1, Yaowen Gu1, Weijun Zhou1
1Department of Chemistry, New York University, New York, New York 10003, United States.
这项研究开发了一种深度学习共识模型,以预测TTR的结合亲和力,整合多种分子数据类型. 该模型实现了高精度,证明了其在识别有毒化合物和评估内分泌干扰风险方面的潜力.
科学领域:
- 计算化学是一种计算化学.
- 毒理学 毒理学 毒理学
- 分子建模分子建模
背景情况:
- 晶氨酸 (TTR) 对于甲状腺激素的运输和平衡至关重要.
- 与TTR相互作用的外源化合物可以破坏内分泌功能并引起毒性.
研究的目的:
- 开发一个基于深度学习的共识模型来预测TTR结合亲和力.
- 评估模型在Tox24挑战中的表现,并评估其用于识别潜在的TTR结合剂的实用性.
主要方法:
- 整合了三个深度学习模型 (sPhysNet,KANO,GGAP-CPI) 使用2D,3D和蛋白质-连接体相互作用数据.
- 开发了一个共识模型,以提高TTR结合亲和力的预测准确度.
- 利用集合输出的标准偏差作为预测的不确定性估计.
主要成果:
- 在盲目测试中,共识模型获得了20.8的RMSE,在Tox24挑战中排名第五.
- 在一项回顾性研究中,纳入额外的数据将RMSE降低到20.6.
- 随着模型不确定性的增加,预测误差和RMSE增加,验证不确定性作为信心指标.
结论:
- 将不同模式的回归模型结合起来,可以显著提高TTR结合亲和度的预测准确性.
- 开发的共识模型是TTR结合剂及其亲缘关系的in silico预测的宝贵工具.
- 不确定性估计提供了可靠的预测信心指标,有助于风险评估.
更多相关视频
07:08Optimization of Synthetic Proteins: Identification of Interpositional Dependencies Indicating Structurally and/or Functionally Linked Residues
Published on: July 14, 2015
16:02Demonstration of the Sequence Alignment to Predict Across Species Susceptibility Tool for Rapid Assessment of Protein Conservation
Published on: February 10, 2023
相关概念视频
Predicting Molecular Geometry
Relative Strengths of Conjugate Acid-Base Pairs
Common Ion Effect
Predicting Reaction Outcomes
Toxic Reactions: Overview
Toxicity falls into two primary categories: local and systemic.
Local toxicity appears at the exposure site, such as protein denaturation caused by caustic substances.
In contrast, systemic toxicity requires the toxic agent's absorption and distribution,...
Parameters Affecting Nonlinear Elimination: Zero-Order Input, First-Order Absorption and Two-Compartment Model
When a drug is administered through a constant intravenous infusion and eliminated via nonlinear pharmacokinetics, it follows zero-order input. For example, oral drugs undergo first-order absorption upon administration and are eliminated through nonlinear pharmacokinetics.
In the case of subcutaneously administered drugs,...
