Few-shot learning creates predictive models of drug response that translate from high-throughput screens to individual patients.

Few-shot learning creates predictive models of drug response that translate from high-throughput screens to individual patients.
复制标题

少量学习创建了药物反应的预测模型,这些模型可以从高通量筛选转化为个体患者。

DOI:
10.1038/s43018-020-00169-2
复制
发表时间:
2021-03
期刊:
影响因子:
22.7
通讯作者:
Ideker T
Ideker T
中科院分区:
医学1区
文献类型:
--
作者:
Ma J;Fong SH;Luo Y;Bakkenist CJ;Shen JP;Mourragui S;Wessels LFA;Hafner M;Sharan R;Peng J;Ideker T

文献摘要

参考文献

被引文献

相似文献

细胞系筛选创建了用于学习药物反应预测标志物的广泛数据集,但这些模型由于其不同的背景和有限的数据而不易于转化为临床。在本研究中,我们应用了最近开发的技术,少数机器学习,在细胞系中训练一个通用的神经网络模型,可以使用很少的额外样本来调整到新的环境。当在不同组织类型之间切换以及从细胞系模型转移到临床环境(包括患者来源的肿瘤细胞和患者来源的异种移植物)时,该模型快速适应。它也可以被解释为确定对药物反应最重要的分子特征,突出RB1和SMAD 4在对CDK抑制的反应中以及RNF8和CHD 4在对ATM抑制的反应中的关键作用。少数学习框架提供了一个桥梁,从高通量筛选中调查的许多样本(多个中的n个)到个体患者的独特背景(一个中的n个)。
Cell-line screens create expansive datasets for learning predictive markers of drug response, but these models do not readily translate to the clinic with its diverse contexts and limited data. In the present study, we apply a recently developed technique, few-shot machine learning, to train a versatile neural network model in cell lines that can be tuned to new contexts using few additional samples. The model quickly adapts when switching among different tissue types and in moving from cell-line models to clinical contexts, including patient-derived tumor cells and patient-derived xenografts. It can also be interpreted to identify the molecular features most important to a drug response, highlighting critical roles for RB1 and SMAD4 in the response to CDK inhibition and RNF8 and CHD4 in the response to ATM inhibition. The few-shot learning framework provides a bridge from the many samples surveyed in high-throughput screens (n-of-many) to the distinctive contexts of individual patients (n-of-one).
DOI: 10.1038/nm.3954
发表时间: 2015-11-01
期刊: NATURE MEDICINE
影响因子: 82.9
作者:
Gao, Hui;Korn, Joshua M.;Sellers, William R.
通讯作者: Sellers, William R.
DOI: 10.1038/nmeth.4083
发表时间: 2017-01
期刊: Nature methods
影响因子: 48
作者:
Li T;Wernersson R;Hansen RB;Horn H;Mercer J;Slodkowicz G;Workman CT;Rigina O;Rapacki K;Stærfeldt HH;Brunak S;Jensen TS;Lage K
通讯作者: Lage K
DOI: 10.1038/s41586-019-1186-3
发表时间: 2019-05-23
期刊: NATURE
影响因子: 64.8
作者:
Ghandi, Mahmoud;Huang, Franklin W.;Sellers, William R.
通讯作者: Sellers, William R.
DOI: 10.4161/cc.4.1.1366
发表时间: 2005-01-01
期刊: CELL CYCLE
影响因子: 4.3
作者:
Liu, F;Matsuura, I
通讯作者: Matsuura, I
DOI: 10.1038/s41467-019-13027-2
发表时间: 2019-11-06
影响因子: 16.6
作者:
Kim, Yongsoo;Bismeijer, Tycho;Vis, Daniel J.
通讯作者: Vis, Daniel J.