State‑of‑the‑art medical studies proved that predicting CYP450 enzyme inhibitors is beneficial in the early stage of drug discovery. However, accurate machine learning-based (ML) in silico methods for predicting CYP450 inhibitors remains challenging. Here, we introduce GTransCYPs, an improved graph neural network (GNN) with a transformer mechanism for predicting CYP450 inhibitors. This model significantly enhances the discrimination between inhibitors and non-inhibitors for five major CYP450 isozymes: 1A2, 2C9, 2C19, 2D6, and 3A4. GTransCYPs learns information patterns from molecular graphs by aggregating node and edge representations using a transformer. The GTransCYPs model utilizes transformer convolution layers to process features, followed by a global attention-pooling technique to synthesize the graph-level information. This information is then fed through successive linear layers for final output generation. Experimental results demonstrate that the GTransCYPs model achieved high performance, outperforming other state-of-the-art methods in CYP450 prediction. Scientific contribution The prediction of CYP450 inhibition via computational techniques utilizing biological information has emerged as a cost-effective and highly efficient approach. Here, we presented a deep learning (DL) architecture based on GNN with transformer mechanism and attention pooling (GTransCYPs) to predict CYP450 inhibitors. Four GTransCYPs of different pooling technique were tested on an experimental tasks on the CYP450 prediction problem for the first time. Graph transformer with attention pooling algorithm achieved the best performances. Comparative and ablation experiments provide evidence of the efficacy of our proposed method in predicting CYP450 inhibitors. The source code is publicly available at https://github.com/zonwoo/GTransCYPs .

中文翻译：

---

GTransCYP：一种改进的图转换器神经网络，具有注意力汇集功能，可可靠地预测 CYP450 抑制剂


最先进的医学研究证明，预测 CYP450 酶抑制剂在药物发现的早期阶段是有益的。然而，用于预测 CYP450 抑制剂的准确基于机器学习 （ML） 的计算机方法仍然具有挑战性。在这里，我们介绍了 GTransCYPs，这是一种改进的图神经网络 （GNN），具有用于预测 CYP450 抑制剂的 transformer 机制。该模型显著增强了 5 种主要 CYP450 同工酶（1A2、2C9、2C19、2D6 和 3A4）的抑制剂和非抑制剂之间的区分。GTransCYPs 通过使用转换器聚合节点和边缘表示，从分子图中学习信息模式。GTransCYPs 模型利用 transformer 卷积层来处理特征，然后使用全局注意力池技术来合成图形级信息。然后，此信息通过连续的线性层馈送，以生成最终输出。实验结果表明，GTransCYPs 模型实现了高性能，在 CYP450 预测方面优于其他最先进的方法。科学贡献 通过利用生物信息的计算技术预测 CYP450 抑制已成为一种经济高效且高效的方法。在这里，我们提出了一种基于 GNN 的深度学习 （DL） 架构，具有转换器机制和注意力池 （GTransCYP） 来预测 CYP450 抑制剂。首次在 CYP450 预测问题的实验任务中测试了四种不同池化技术的 GTransCYP。带有注意力池算法的 Graph transformer 取得了最佳性能。比较和消融实验证明了我们提出的方法在预测 CYP450 抑制剂方面的有效性。 源代码在 https://github.com/zonwoo/GTransCYPs 上公开提供。