发表机构
Centro Singular de Investigación en Tecnoloxías Intelixentes (CiTIUS), Universidade de Santiago de Compostela（圣地亚哥德孔波斯特拉大学智能技术卓越研究中心（CiTIUS））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出一个统一标准化基准框架，系统评估20多种图深度学习模型在药物发现中的毒性预测性能，并辅以文献分析，提供可靠评估并开源以促进可复现比较。
AI 中文摘要
药物发现是一个成本高昂且高风险的过程，其中与毒性相关的失败仍然是临床前和临床阶段药物损耗的主要原因。因此，对化学毒性进行准确的早期预测对于降低下游成本和改进化合物优先级排序至关重要。在此背景下，图深度学习（GDL）已成为毒性预测的强大范式，利用分子图表示直接从化学结构学习，相比传统方法具有更强的表达能力。尽管提出的模型数量不断增加，但由于数据集、预处理流程和评估协议的不一致性，当前基于文献的比较往往难以解释。为解决这一局限性，我们引入了一个统一且标准化的GDL毒性预测基准测试框架。我们在一致的实验条件下，跨多个数据集和分区策略，系统评估了20多种代表性方法，实现了模型性能的公平且可复现的比较。此外，我们通过结构化的文献分析补充了这一实证研究，以情境化现有方法论趋势和性能声明。我们的结果提供了对当前领域状态更清晰、更可靠的评估，突出了现有图方法的优势与局限性。为支持透明性和可复现性，我们将基准测试框架作为开源软件发布在https://github.com/your-repo，使社区能够在一致条件下评估和比较模型。
英文摘要
Drug discovery is a costly and high-risk process, where toxicity-related failures remain a major cause of attrition in both preclinical and clinical stages. As a result, accurate early prediction of chemical toxicity is essential to reduce downstream costs and improve compound prioritization. In this context, graph deep learning (GDL) has emerged as a powerful paradigm for toxicity prediction, leveraging molecular graph representations to learn directly from chemical structure with improved expressivity over traditional approaches. Despite the growing number of proposed models, current literature-based comparisons are often difficult to interpret due to inconsistencies in datasets, preprocessing pipelines, and evaluation protocols. To address this limitation, we introduce a unified and standardized benchmarking framework for GDL-based toxicity prediction. We systematically evaluate more than 20 representative approaches under consistent experimental conditions and across multiple datasets and partitioning strategies, enabling a fair and reproducible comparison of model performance. In addition, we complement this empirical study with a structured literature analysis to contextualize existing methodological trends and performance claims. Our results provide a clearer and more reliable assessment of the current state of the field, highlighting both the strengths and limitations of existing graph-based approaches. To support transparency and reproducibility, we release our benchmarking framework as open-source software https://gitlab.citius.gal/noel.suarez/benchtox, allowing the community to evaluate and compare models under consistent conditions.
