评估用于分子性质预测的机器学习模型:在分布外数据上的性能和稳定性
Hosein Fooladi1,2,3, Thi Ngoc Lan Vu1,2,3, Miriam Mathea4
1Department of Pharmaceutical Sciences, Division of Pharmaceutical Chemistry, Faculty of Life Sciences, University of Vienna, Josef-Holaubek-Platz 2, 1090 Vienna, Austria.
Journal of chemical information and modeling
|September 15, 2025
概括
用于分子性质预测的机器学习模型在分布外 (OOD) 数据上表现不同. 脚手架分割显示出良好的性能,而相似性聚类则具有挑战性,影响对现实应用的模型选择.
科学领域:
- * 化学信息学 化学信息学
- * 计算化学 计算机化学
- * 机器学习 * 机器学习
背景情况:
- *机器学习模型被广泛用于预测分子性质.
- *性能评估通常使用分布式 (ID) 数据,但实际使用需要分布式 (OOD) 数据.
- *对OOD数据的模型性能评估对于在新化学空间中可靠预测至关重要.
研究的目的:
- *对OOD分子数据的机器学习模型性能进行调查和评估.
- * 在分子性质预测中定义OOD数据生成策略.
- *分析在分销 (ID) 和分销之外 (OOD) 业绩之间的关系.
主要方法:
- * 评估了14个机器学习模型,包括随机森林和图形神经网络 (GNN).
- * 用了八个数据集和十个分割策略来生成OOD数据.
- *使用Bemis-Murcko支架和基于UMAP的集群 (ECFP4指纹) 进行OOD分割.
主要成果:
- *贝米斯-穆尔科支架分割显示模型表现良好,类似于随机分割.
- *基于UMAP的化学相似性聚类呈现了最具挑战性的OOD场景.
- * ID 和 OOD 绩效之间的相关性随着分割策略而有显著的变化 (皮尔森的 r ~ 0.9 对于支架, ~ 0.4 对于集群).
结论:
- * OOD数据生成策略极大地影响了模型性能和ID-OOD相关性.
- *基于架构的分割比基于相似性的聚类对OOD评估来说更不具有挑战性.
- * 模型选择需要仔细考虑与特定应用领域一致的OOD性能.
相关概念视频
Model Approaches for Pharmacokinetic Data: Distributed Parameter Models
242
Pharmacokinetic models are mathematical constructs that represent and predict the time course of drug concentrations in the body, providing meaningful pharmacokinetic parameters. These models are categorized into compartment, physiological, and distributed parameter models.
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...
242
Mechanistic Models: Compartment Models in Individual and Population Analysis
250
Mechanistic models are utilized in individual analysis using single-source data, but imperfections arise due to data collection errors, preventing perfect prediction of observed data. The mathematical equation involves known values (Xi), observed concentrations (Ci), measurement errors (εi), model parameters (ϕj), and the related function (ƒi) for i number of values. Different least-squares metrics quantify differences between predicted and observed values. The ordinary least...
250
Predicting Reaction Outcomes
10.1K
Kinetics describes the rate and path by which a reaction occurs. In contrast, thermodynamics deals with state functions and describes the properties, behavior, and components of a system. It is not concerned with the path taken by the process and cannot address the rate at which a reaction occurs. Although it does provide information about what can happen during a reaction process, it does not describe the detailed steps of what appears on an atomic or a molecular level. On the other hand,...
10.1K
Predicting Molecular Geometry
45.3K
VSEPR Theory for Determination of Electron Pair Geometries
45.3K
Analysis Methods of Pharmacokinetic Data: Model and Model-Independent Approaches
494
Drug disposition in the body is a complex process and can be studied using two major approaches: the model and the model-independent approaches.
The model approach uses mathematical models to describe changes in drug concentration over time. Pharmacokinetic models help characterize drug behavior in patients, predict drug concentration in the body fluids, calculate optimum dosage regimens, and evaluate the risk of toxicity. However, ensuring that the model fits the experimental data accurately...
The model approach uses mathematical models to describe changes in drug concentration over time. Pharmacokinetic models help characterize drug behavior in patients, predict drug concentration in the body fluids, calculate optimum dosage regimens, and evaluate the risk of toxicity. However, ensuring that the model fits the experimental data accurately...
494
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
292
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
292


