arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.04313cs.LG
收藏

利用删失回归标签增强药物发现中的不确定性量化

Enhancing Uncertainty Quantification in Drug Discovery with Censored Regression Labels

AstraZeneca R&D(阿斯利康研发部);ELLIS Unit Linz(林茨ELLIS单元);Institute for Machine Learning(机器学习研究所);Johannes Kepler University Linz(约翰内斯·开普勒大学林茨分校);KU Leuven(鲁汶大学);Chalmers University of Technology(查尔姆斯理工大学)

Emma Svensson, Hannah Rosa Friesacher, Susanne Winiwarter, Lewis Mervin, Adam Arany, Ola Engkvist

AI总结:

针对药物发现中稀疏精确观测与删失阈值标签未被不确定性方法充分利用的问题,本文用 Tobit 模型改造集成、贝叶斯和高斯模型,证明删失标签能显著提升真实制药场景建模的准确性与可靠性。

摘要:

在药物发现的早期阶段,关于继续开展哪些实验的决策可能会受到计算模型的影响。由于实验耗时且成本高昂,这些决策至关重要。因此,准确量化机器学习预测中的不确定性正变得不可或缺,以便最优地使用资源并提升对模型的信任。尽管药物发现中的计算方法常受限于数据有限和实验观测稀疏,但仍可能存在以删失标签形式出现的额外信息;这类标签提供的是阈值,而非观测的精确值。然而,用于量化机器学习不确定性的标准方法无法充分利用删失标签。在本研究中,我们借助生存分析中的 Tobit 模型,对基于集成的模型、贝叶斯模型和高斯模型进行改造,使其具备从删失标签中学习的工具。我们的结果表明,尽管删失标签只包含部分信息,但它们对于准确、可靠地建模真实制药场景至关重要。

英文摘要:

In the early stages of drug discovery, decisions regarding which experiments to pursue can be influenced by computational models. These decisions are critical due to the time-consuming and expensive nature of the experiments. Therefore, it is becoming essential to accurately quantify the uncertainty in machine learning predictions, such that resources can be used optimally and trust in the models improves. While computational methods for drug discovery often suffer from limited data and sparse experimental observations, additional information can exist in the form of censored labels that provide thresholds rather than precise values of observations. However, the standard approaches that quantify uncertainty in machine learning cannot fully utilize censored labels. In this work, we adapt ensemble-based, Bayesian, and Gaussian models with tools to learn from censored labels by using the Tobit model from survival analysis. Our results demonstrate that despite the partial information available in censored labels, they are essential to accurately and reliably model the real pharmaceutical setting.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑