Molecular pathways enhance drug response prediction using transfer learning from cell lines to tumors and patient-derived xenografts.
Molecular pathways enhance drug response prediction using transfer learning from cell lines to tumors and patient-derived xenografts.
复制标题
DOI：
10.1038/s41598-022-20646-1
复制
发表时间：
2022-09-27
影响因子：
4.6
通讯作者：
Gottlieb, Assaf
中科院分区：
文献类型：
--
作者：
Tang, Yi-Ching;Powell, Reid T.;Gottlieb, Assaf
计算模型已成功预测癌细胞系数据中的药物敏感性，为指导精准医疗创造了机会。然而，将这些模型转化为肿瘤仍然具有挑战性。我们提出了一种新的迁移学习工作流程，根据基因组特征衍生的分子途径，将药物敏感性预测模型从大规模癌细胞系转移到肿瘤和患者来源的异种移植物。我们进一步计算特征重要性，以确定对药物反应预测最重要的途径。我们在肿瘤 (AUROC = 0.77) 和三阴性乳腺癌患者来源的异种移植物 (RMSE = 0.11) 上获得了良好的性能。利用特征重要性，我们强调了乳腺癌患者依维莫司敏感性中的 ER-高尔基体运输途径与 II 类组蛋白脱乙酰酶和白细胞介素 12 在三阴性乳腺癌药物反应中的作用之间的关联。通路信息支持药物反应预测模型从细胞系到肿瘤的转移，并可以提供预测的生物学解释，作为临床环境中使用的踏脚石。
Computational models have been successful in predicting drug sensitivity in cancer cell line data, creating an opportunity to guide precision medicine. However, translating these models to tumors remains challenging. We propose a new transfer learning workflow that transfers drug sensitivity predicting models from large-scale cancer cell lines to both tumors and patient derived xenografts based on molecular pathways derived from genomic features. We further compute feature importance to identify pathways most important to drug response prediction. We obtained good performance on tumors (AUROC = 0.77) and patient derived xenografts from triple negative breast cancers (RMSE = 0.11). Using feature importance, we highlight the association between ER-Golgi trafficking pathway in everolimus sensitivity within breast cancer patients and the role of class II histone deacetylases and interlukine-12 in response to drugs for triple-negative breast cancer. Pathway information support transfer of drug response prediction models from cell lines to tumors and can provide biological interpretation underlying the predictions, serving as a steppingstone towards usage in clinical setting.
登录
查看更多内容
影响因子：
82.9
作者：
Gao, Hui;Korn, Joshua M.;Sellers, William R.
通讯作者：
Sellers, William R.
影响因子：
5.8
作者：
Liberzon, Arthur;Subramanian, Aravind;Mesirov, Jill P.
通讯作者：
Mesirov, Jill P.
影响因子：
4.6
作者：
Powell RT;Redwood A;Liu X;Guo L;Cai S;Zhou X;Tu Y;Zhang X;Qi Y;Jiang Y;Echeverria G;Feng N;Ma X;Giuliani V;Marszalek JR;Heffernan TP;Vellano CP;White JB;Stephan C;Davies PJ;Moulder S;Symmans WF;Chang JT;Piwnica-Worms H
通讯作者：
Piwnica-Worms H
影响因子：
5.2
作者：
Gruener RF;Ling A;Chang YF;Morrison G;Geeleher P;Greene GL;Huang RS
通讯作者：
Huang RS
影响因子：
9.5
作者：
Azuaje F
通讯作者：
Azuaje F