MolLedger：一种具有化学基础ADME归因的加性图神经网络

中文摘要 AI 辅助

优化吸收、分布、代谢和排泄（ADME）是小分子药物发现的重要环节。已有许多机器学习模型被构建用于预测ADME性质以推动该优化过程，但解释模型预测结果颇具挑战性。本文提出一种内置有意义原子级归因的新型图神经网络架构MolLedger，其输出预测结果为各原子得分的总和。该加性框架在不损失性能的前提下实现了精确可解释性，因为全局上下文向量为加性头部提供了足够的上下文以生成优质原子级得分。此外，MolLedger生成的归因相比其他可解释性方法更贴合化学性质，这得益于其辅助损失将原子得分锚定到化学性质。通过对多组分子的多种方法解释进行案例研究，结果表明MolLedger在为预测性质变化生成合理解释方面表现优异。

英文摘要

Optimizing absorption, distribution, metabolism, and excretion (ADME) is an important part of small molecule drug discovery. Many machine learning models have been built to predict ADME properties to facilitate this optimization process, but explaining model predictions is challenging. We propose a new graph neural network architecture with built-in atom attributions. Our model MolLedger learns a global context vector for each molecule and a per-atom head to output atom scores that sum to the predicted property. The atom scores are regularized to align with relevant chemical properties. We prove that MolLedger is a universal approximator and demonstrate empirically that the new architecture obtains explainability with little effect on performance. We show that the interpretations from MolLedger are faithful, concordant with held-out physical properties, and align with the changes between matched molecular pairs. Our case studies comparing interpretations from multiple methods on molecular pairs reveal that MolLedger is much better at producing sensible explanations for predicted property changes.

发表机构

• Hamilton College（汉密尔顿学院）

机构由 AI 辅助整理，请以论文原文为准。