Predicting patient response with models trained on cell lines and patient-derived xenografts by nonlinear transfer learning
Predicting patient response with models trained on cell lines and patient-derived xenografts by nonlinear transfer learning
复制标题
DOI：
10.1073/pnas.2106682118
复制
发表时间：
2021-12-07
影响因子：
11.1
通讯作者：
Wessels, Lodewyk F. A.
中科院分区：
文献类型：
--
作者：
Mourragui, Soufiane M. C.;Loog, Marco;Wessels, Lodewyk F. A.
临床前模型一直是癌症研究的主力，产生了大量的药物反应数据。不幸的是，将来自这些数据集的响应生物标志物转化为人类肿瘤已被证明是特别具有挑战性的。为了应对这一挑战，我们开发了TRANSAT，这是一个计算框架，它构建了一个共识空间来捕获临床前模型和人类肿瘤共同的生物学过程，并利用这个空间来构建药物反应预测因子，这些预测因子可以从临床前模型稳健地转移到人类肿瘤。与四种竞争方法（包括两种深度学习方法）相比，TRANSACT在癌症基因组图谱的23种药物预测挑战和Hartwig医学基金会的226种转移性肿瘤上表现良好。我们证明，反应预测提供了一个强大的性能为一些治疗的高临床重要性：铂类化疗，吉西他滨，紫杉醇。与其他方法相比，我们通过正确识别靶向治疗的已知生物标志物来证明TRANSACT预测因子的可解释性，并且我们提出了介导对两种化疗药物的耐药性的潜在机制。
Preclinical models have been the workhorse of cancer research, producing massive amounts of drug response data. Unfortunately, translating response biomarkers derived from these datasets to human tumors has proven to be particularly challenging. To address this challenge, we developed TRANSACT, a computational framework that builds a consensus space to capture biological processes common to preclinical models and human tumors and exploits this space to construct drug response predictors that robustly transfer from preclinical models to human tumors. TRANSACT performs favorably compared to four competing approaches, including two deep learning approaches, on a set of 23 drug prediction challenges on The Cancer Genome Atlas and 226 metastatic tumors from the Hartwig Medical Foundation. We demonstrate that response predictions deliver a robust performance for a number of therapies of high clinical importance: platinum-based chemotherapies, gemcitabine, and paclitaxel. In contrast to other approaches, we demonstrate the interpretability of the TRANSACT predictors by correctly identifying known biomarkers of targeted therapies, and we propose potential mechanisms that mediate the resistance to two chemotherapeutic agents.