Department of Quantitative and Computational Biology, University of Southern California, 1050 Childs Way, Los Angeles, CA, 90089, USA.
Sci Rep. 2023 Jul 13;13(1):11344. doi: 10.1038/s41598-023-38429-7.
Precision medicine chooses the optimal drug for a patient by considering individual differences. With the tremendous amount of data accumulated for cancers, we develop an interpretable neural network to predict cancer patient survival based on drug prescriptions and personal transcriptomes (CancerIDP). The deep learning model achieves 96% classification accuracy in distinguishing short-lived from long-lived patients. The Pearson correlation between predicted and actual months-to-death values is as high as 0.937. About 27.4% of patients may survive longer with an alternative medicine chosen by our deep learning model. The median survival time of all patients can increase by 3.9 months. Our interpretable neural network model reveals the most discriminating pathways in the decision-making process, which will further facilitate mechanistic studies of drug development for cancers.
精准医学通过考虑个体差异为患者选择最佳药物。随着癌症相关数据的大量积累，我们开发了一种可解释的神经网络，根据药物处方和个人转录组（CancerIDP）来预测癌症患者的生存情况。该深度学习模型在区分短期和长期患者方面的分类准确率达到 96%。预测和实际死亡时间之间的皮尔逊相关系数高达 0.937。通过我们的深度学习模型选择替代药物，约 27.4%的患者可能会存活更长时间。所有患者的中位生存时间可以增加 3.9 个月。我们的可解释神经网络模型揭示了决策过程中最具区分性的途径，这将进一步促进癌症药物开发的机制研究。
