Biologically informed deep neural network for prostate cancer discovery.
Biologically informed deep neural network for prostate cancer discovery.
复制标题
DOI：
10.1038/s41586-021-03922-4
复制
发表时间：
2021-10
期刊：
影响因子：
64.8
通讯作者：
Van Allen EM
中科院分区：
文献类型：
--
作者：
Elmarakeby HA;Hwang J;Arafeh R;Crowdis J;Gang S;Liu D;AlDubayan SH;Salari K;Kregel S;Richter C;Arnoff TE;Park J;Hahn WC;Van Allen EM
前列腺癌临床侵袭性表型的分子特征的确定仍然是一个主要的生物学和临床挑战。应用于生物医学问题的机器学习模型在可解释性方面的最新进展可能使临床癌症基因组学的发现和预测成为可能。在这里，我们开发了P-Net-一种生物信息的深度学习模型-根据治疗耐药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靶向治疗耐药的分子驱动因素。我们证明了P-网可以使用分子数据来预测癌症状态，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的分子变化的候选基因，如MDM4和FGFR1，它们与预测晚期疾病有关，并在体外得到验证。广泛地说，生物信息完全可解释的神经网络使前列腺癌的临床前发现和临床预测成为可能，并可能在各种癌症类型中普遍适用。已经开发出一个生物学上知情的、可解释的深度学习模型，以评估癌症治疗耐药的分子驱动因素，预测临床结果，并指导疾病进展的假说。
The determination of molecular features that mediate clinically aggressive phenotypes in prostate cancer remains a major biological and clinical challenge. Recent advances in interpretability of machine learning models as applied to biomedical problems may enable discovery and prediction in clinical cancer genomics. 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. A biologically informed, interpretable deep learning model has been developed to evaluate molecular drivers of resistance to cancer treatment, predict clinical outcomes and guide hypotheses on disease progression.
登录
查看更多内容
DOI：
10.1016/j.neo.2016.01.006
发表时间：
2016-04
期刊：
Neoplasia (New York, N.Y.)
影响因子：
--
作者：
Feng FY;Zhang Y;Kothari V;Evans JR;Jackson WC;Chen W;Johnson SB;Luczak C;Wang S;Hamstra DA
通讯作者：
Hamstra DA
影响因子：
8.8
作者：
Hwang, Justin H.;Seo, Ji-Heui;Hahn, William C.
通讯作者：
Hahn, William C.
影响因子：
--
作者：
Chopra, Harman;Khan, Zara;Zhu, Yan
通讯作者：
Zhu, Yan
DOI：
10.1073/pnas.1203789109
发表时间：
2012-07-17
影响因子：
11.1
作者：
Graves, Bradford;Thompson, Thelma;Vassilev, Lyubomir T.
通讯作者：
Vassilev, Lyubomir T.
DOI：
10.1073/pnas.1411446111
发表时间：
2014-07-29
影响因子：
11.1
作者：
Hieronymus, Haley;Schultz, Nikolaus;Sawyers, Charles L.
通讯作者：
Sawyers, Charles L.