当前位置: X-MOL 学术Nature › 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.)
Biologically informed deep neural network for prostate cancer discovery
Nature ( IF 64.8 ) Pub Date : 2021-09-22 , DOI: 10.1038/s41586-021-03922-4
Haitham A Elmarakeby 1, 2, 3 , Justin Hwang 4 , Rand Arafeh 1, 2 , Jett Crowdis 1, 2 , Sydney Gang 1 , David Liu 1, 2 , Saud H AlDubayan 1, 2 , Keyan Salari 1, 2, 5 , Steven Kregel 6 , Camden Richter 1 , Taylor E Arnoff 1, 2 , Jihye Park 1, 2 , William C Hahn 1, 2 , Eliezer M Van Allen 1, 2
Affiliation  

The determination of molecular features that mediate clinically aggressive phenotypes in prostate cancer remains a major biological and clinical challenge1,2. Recent advances in interpretability of machine learning models as applied to biomedical problems may enable discovery and prediction in clinical cancer genomics3,4,5. Here we developed P-NET—a biologically informed deep learning model—to stratify patients with prostate cancer by treatment-resistance state and evaluate molecular drivers of treatment resistance for therapeutic targeting through complete model interpretability. We demonstrate that P-NET can predict cancer state using molecular data with a performance that is superior to other modelling approaches. Moreover, the biological interpretability within P-NET revealed established and novel molecularly altered candidates, such as MDM4 and FGFR1, which were implicated in predicting advanced disease and validated in vitro. Broadly, biologically informed fully interpretable neural networks enable preclinical discovery and clinical prediction in prostate cancer and may have general applicability across cancer types.



中文翻译:

用于发现前列腺癌的生物学深度神经网络

确定介导前列腺癌临床侵袭性表型的分子特征仍然是一项重大的生物学和临床挑战1,2。机器学习模型在应用于生物医学问题的可解释性方面的最新进展可能有助于临床癌症基因组学的发现和预测3,4,5。在这里,我们开发了 P-NET(一种生物学信息深度学习模型),通过治疗抵抗状态对前列腺癌患者进行分层,并通过完整的模型可解释性评估治疗抵抗的分子驱动因素以实现治疗靶向。我们证明 P-NET 可以使用分子数据预测癌症状态,其性能优于其他建模方法。此外,P-NET 内的生物学可解释性揭示了已建立的和新颖的分子改变候选物,例如MDM4FGFR1,它们与预测晚期疾病有关并在体外得到验证。从广义上讲,生物学信息完全可解释的神经网络能够实现前列腺癌的临床前发现和临床预测,并且可能具有跨癌症类型的普遍适用性。

更新日期:2021-09-22
down
wechat
bug