Abstract Gaussian process regression (GPR) is a nonparametric probabilistic model capable of computing not only the predicted mean but also the predicted standard deviation, which represents the confidence level of predictions. It offers great flexibility as it can be non‐linearized by designing the kernel function, made robust against outliers by altering the likelihood function, and extended to classification models. Recently, models combining deep learning with GPR, such as Deep Kernel Learning GPR, have been proposed and reported to achieve higher accuracy than GPR. However, due to its nonparametric nature, GPR is challenging to interpret. While Explainable AI (XAI) methods like LIME or kernel SHAP can interpret the predicted mean, interpreting the predicted standard deviation remains difficult. In this study, we propose a novel method to interpret the prediction of GPR by evaluating the importance of explanatory variables. We have incorporated the GPR model with the Integrated Gradients (IG) method to assess the contribution of each feature to the prediction. By evaluating the standard deviation of the posterior distribution, we show that the IG approach provides a detailed decomposition of the predictive uncertainty, attributing it to the uncertainty in individual feature contributions. This methodology not only highlights the variables that are most influential in the prediction but also provides insights into the reliability of the model by quantifying the uncertainty associated with each feature. Through this, we can obtain a deeper understanding of the model′s behavior and foster trust in its predictions, especially in domains where interpretability is as crucial as accuracy.

Fan Zhang

Naoaki Ono

Shigehiko Kanaya

Molecular Informatics

MOLECULAR INFORMATICS 是一个经过同行评审的国际论坛，用于发表关于生物/化学信息学和计算机辅助分子设计的所有分子方面的高质量、跨学科研究。分子信息学于 2010 年在 QSAR 和组合科学领域取得了成功。分子信息学提出的方法创新将导致对配体-受体相互作用、大分子复合物、分子网络、设计概念和过程的更深入理解，这些概念和设计概念展示了想法和设计概念如何导致具有所需的结构或功能，最好包括实验验证。期刊的范围包括但不限于药物发现和化学生物学、蛋白质和核酸工程与设计、纳米分子结构设计、大分子组装体建模策略等领域, 分子网络和系统, 药物和化学基因组学, 计算机辅助筛选策略, 以及用于从头设计生物活性分子的新技术。具有重要的技术浓度期刊范围内的 EPTS 和 ADVANCES。

Molecular Informatics is a peer-reviewed international journal dedicated to publishing high-quality interdisciplinary research in the fields of bioinformatics, cheminformatics, and computer-aided molecular design. Since its inception in 2010, Molecular Informatics has made significant contributions to QSAR and combinatorial science. The innovative methods proposed in the journal lead to a deeper understanding of ligand-receptor interactions, macromolecular complexes, molecular networks, design concepts, and processes. These concepts illustrate how ideas and designs can achieve the desired structure or function, with a strong emphasis on experimental validation. The scope of the journal includes, but is not limited to, drug discovery and chemical biology, protein and nucleic acid engineering and design, nanomolecular structure design, macromolecular assembly modeling strategies, molecular networks and systems, drug and chemical genomics, computer-aided screening strategies, and new technologies for de novo design of bioactive molecules. The journal features significant technical depth across the fields of EPTS and ADVANCES.

《Molecular Informatics》是一个经过同行评审的国际期刊，致力于发表关于生物信息学、化学信息学和计算机辅助分子设计等领域的高质量跨学科研究。自2010年起，《Molecular Informatics》在QSAR和组合科学领域取得了显著成就。期刊提出的创新方法将深入理解配体-受体相互作用、大分子复合物、分子网络、设计理念及其过程。这些理念展示了如何通过设计实现所需的结构或功能，并强调实验验证的重要性。期刊的研究范围包括但不限于药物发现与化学生物学、蛋白质与核酸的工程与设计、纳米分子结构设计、大分子组装体建模策略、分子网络与系统、药物与化学基因组学、计算机辅助筛选策略，以及用于从头设计生物活性分子的创新技术。期刊内容具有重要的技术深度，涵盖了EPTS和ADVANCES等领域。

Category	Quartile
医学	4
医学, 药物化学	4
医学, 计算机跨学科应用	4
医学, 数学与计算生物学	4

Interpret Gaussian Process Models by Using Integrated Gradients

ivySCI AI Smartly Parses PDF, Answers Researchers' Questions, and Helps You Understand Papers in Seconds

Journal Info

Category	Quartile
MATHEMATICAL & COMPUTATIONAL BIOLOGY	2