当前位置: X-MOL 学术J. Chem. Inf. Model. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Predicting In Vivo Compound Brain Penetration Using Multi-task Graph Neural Networks
Journal of Chemical Information and Modeling ( IF 5.6 ) Pub Date : 2022-06-23 , DOI: 10.1021/acs.jcim.2c00412
Seid Hamzic 1 , Richard Lewis 1 , Sandrine Desrayaud 1 , Cihan Soylu 2 , Mike Fortunato 2 , Grégori Gerebtzoff 1 , Raquel Rodríguez-Pérez 1
Affiliation  

Assessing whether compounds penetrate the brain can become critical in drug discovery, either to prevent adverse events or to reach the biological target. Generally, pre-clinical in vivo studies measuring the ratio of brain and blood concentrations (Kp) are required to estimate the brain penetration potential of a new drug entity. In this work, we developed machine learning models to predict in vivo compound brain penetration (as LogKp) from chemical structure. Our results show the benefit of including in vitro experimental data as auxiliary tasks in multi-task graph neural network (MT-GNN) models. MT-GNNs outperformed single-task (ST) models solely trained on in vivo brain penetration data. The best-performing MT-GNN regression model achieved a coefficient of determination of 0.42 and a mean absolute error of 0.39 (2.5-fold) on a prospective validation set and outperformed all tested ST models. To facilitate decision-making, compounds were classified into brain-penetrant or non-penetrant, achieving a Matthew’s correlation coefficient of 0.66. Taken together, our findings indicate that the inclusion of in vitro assay data as MT-GNN auxiliary tasks improves in vivo brain penetration predictions and prospective compound prioritization.

中文翻译:

使用多任务图神经网络预测体内复合脑渗透

评估化合物是否穿透大脑对于药物发现至关重要,无论是预防不良事件还是达到生物学目标。通常,需要通过测量脑浓度和血液浓度 ( Kp )比率的临床前体内研究来估计新药物实体的脑渗透潜力。在这项工作中,我们开发了机器学习模型来预测体内复合脑渗透(如 Log K p) 从化学结构。我们的结果显示了将体外实验数据作为辅助任务包含在多任务图神经网络 (MT-GNN) 模型中的好处。MT-GNN 优于仅在体内大脑穿透数据上训练的单任务 (ST) 模型。表现最好的 MT-GNN 回归模型在前瞻性验证集上实现了 0.42 的确定系数和 0.39(2.5 倍)的平均绝对误差,并且优于所有测试的 ST 模型。为了便于决策,化合物被分为脑渗透性或非渗透性,达到 0.66 的马修相关系数。综上所述,我们的研究结果表明,将体外测定数据作为 MT-GNN 辅助任务改进了体内脑渗透预测和预期的化合物优先级。
更新日期:2022-06-23
down
wechat
bug