Kinome inhibition states and multiomics data enable prediction of cell viability in diverse cancer types.
Kinome inhibition states and multiomics data enable prediction of cell viability in diverse cancer types.
复制标题
DOI：
10.1371/journal.pcbi.1010888
复制
发表时间：
2023-02
影响因子：
4.3
通讯作者：
中科院分区：
文献类型：
--
作者：
蛋白激酶在广泛的细胞过程中起着至关重要的作用，抑制激酶活性的化合物成为靶向治疗发展的主要焦点，特别是在癌症中。因此，表征激酶对抑制剂治疗的反应行为以及下游细胞反应的努力已经在越来越大的范围内进行。先前使用较小数据集的工作使用细胞系的基线分析和有限的kinome分析数据来试图预测小分子对细胞活力的影响，但是这些工作没有使用多剂量激酶谱，并且在非常有限的外部验证下获得了低准确性。这项工作的重点是两个大规模的主要数据类型，激酶抑制剂谱和基因表达，以预测细胞活力筛选的结果。我们描述了结合这些数据集的过程，检查了它们与细胞活力相关的特性，并最终开发了一套计算模型，实现了相当高的预测精度（R2为0.78，RMSE为0.154）。使用这些模型，我们确定了一组激酶，其中一些尚未得到充分研究，它们在细胞活力预测模型中具有强烈的影响。此外，我们还测试了更广泛的多组学数据集是否可以改善模型结果，并发现蛋白质组学激酶抑制剂谱是最具信息量的数据类型。最后，我们在几种三阴性和HER2阳性乳腺癌细胞系中验证了模型预测的一小部分，证明该模型对未包含在训练数据集中的化合物和细胞系表现良好。总的来说，这一结果表明，kinome的通用知识可以预测非常特定的细胞表型，并且有可能整合到靶向治疗开发管道中。能够预测患者的肿瘤对特定药物治疗的反应是精准肿瘤学领域的核心目标。靶向治疗的一个新兴趋势是关注蛋白激酶，这是一个由500多种蛋白质组成的综合通讯网络，在几乎所有癌症的发生和进展中起着核心作用。尽管这些药物在肿瘤学家的治疗工具箱中越来越重要，但我们预测肿瘤对特定治疗反应的能力很差。为了看看我们是否能提高预测癌症对激酶抑制剂治疗反应的能力，我们利用了一个大型实验数据集，量化了这些药物对激酶的影响。在机器学习模型中使用这些激酶抑制状态数据，我们发现我们可以高精度地预测代表27种癌症类型的癌细胞系的反应。包括可以在临床环境中收集的细胞系特异性基因表达数据，进一步提高了预测的准确性。总之，这些结果表明，对kinome抑制状态的了解具有显著的潜力，可以提高我们设计和提供更有效的靶向癌症治疗的能力。
Protein kinases play a vital role in a wide range of cellular processes, and compounds that inhibit kinase activity emerging as a primary focus for targeted therapy development, especially in cancer. Consequently, efforts to characterize the behavior of kinases in response to inhibitor treatment, as well as downstream cellular responses, have been performed at increasingly large scales. Previous work with smaller datasets have used baseline profiling of cell lines and limited kinome profiling data to attempt to predict small molecule effects on cell viability, but these efforts did not use multi-dose kinase profiles and achieved low accuracy with very limited external validation. This work focuses on two large-scale primary data types, kinase inhibitor profiles and gene expression, to predict the results of cell viability screening. We describe the process by which we combined these data sets, examined their properties in relation to cell viability and finally developed a set of computational models that achieve a reasonably high prediction accuracy (R2 of 0.78 and RMSE of 0.154). Using these models, we identified a set of kinases, several of which are understudied, that are strongly influential in the cell viability prediction models. In addition, we also tested to see if a wider range of multiomics data sets could improve the model results and found that proteomic kinase inhibitor profiles were the single most informative data type. Finally, we validated a small subset of the model predictions in several triple-negative and HER2 positive breast cancer cell lines demonstrating that the model performs well with compounds and cell lines that were not included in the training data set. Overall, this result demonstrates that generic knowledge of the kinome is predictive of very specific cell phenotypes, and has the potential to be integrated into targeted therapy development pipelines. Being able to predict how a patient’s tumor will respond to a specific drug treatment is a core goal in the field of precision oncology. An emerging trend in targeted therapies is a focus on protein kinases, a family of over 500 proteins that form an integrated communication network that plays a central role in the development and progression of nearly all cancers. Despite the growing importance of these drugs in the oncologist’s therapeutic toolbox, our ability to predict the response of a tumor to a given treatment is poor. To see if we could improve our ability to predict a cancer’s response to kinase inhibitor treatment, we leveraged a large experimental dataset that quantifies the effect of these drugs on the kinases. Using these kinase inhibition state data within machine learning models, we found that we could predict the response of cancer cell lines representing over 27 cancer types with high accuracy. Including cell line-specific gene expression data that could be gathered in a clinical setting further improved the accuracy of predictions. Together, these results suggest that knowledge of the inhibition state of the kinome has significant potential to improve our ability to design and deliver more effective targeted cancer treatments.
登录
查看更多内容
影响因子：
64.8
作者：
Ghandi, Mahmoud;Huang, Franklin W.;Sellers, William R.
通讯作者：
Sellers, William R.
影响因子：
22.7
作者：
Corsello, Steven M.;Nagari, Rohith T.;Golub, Todd R.
通讯作者：
Golub, Todd R.
影响因子：
14.9
作者：
Berginski ME;Moret N;Liu C;Goldfarb D;Sorger PK;Gomez SM
通讯作者：
Gomez SM
DOI：
10.13345/j.cjb.200450
发表时间：
2021-04-25
期刊：
Sheng wu gong cheng xue bao = Chinese journal of biotechnology
影响因子：
--
作者：
Lu, Jiaxing;Chen, Ming;Yu, Xiaoqing
通讯作者：
Yu, Xiaoqing
DOI：
10.1093/jncimonographs/lgz008
发表时间：
2019-08-01
期刊：
Journal of the National Cancer Institute Monographs
影响因子：
--
作者：
Keefe, Dorothy M. K.;Bateman, Emma H.
通讯作者：
Bateman, Emma H.