A machine learning approach to predict metabolic pathway dynamics from time-series multiomics data.
A machine learning approach to predict metabolic pathway dynamics from time-series multiomics data.
复制标题
DOI：
10.1038/s41540-018-0054-3
复制
发表时间：
2018
影响因子：
4
通讯作者：
Martin HG
中科院分区：
文献类型：
--
作者：
Costello Z;Martin HG
新的合成生物学能力有望大大提高我们设计生物系统的能力。然而，实现这一潜力的一个根本障碍是我们无法准确预测修改相应基因型后的生物学行为。动力学模型传统上用于预测生物工程系统中的途径动力学，但它们需要大量的时间来开发，并且严重依赖于领域专业知识。在这里，我们展示了机器学习和丰富的多组学数据（蛋白质组学和代谢组学）的组合可以用于以自动化的方式有效地预测通路动态。新方法优于经典的动力学模型，并产生定性和定量的预测，可用于有效地指导生物工程的努力。这种方法系统地利用任意数量的新数据来改进预测，并且不假设任何特定的相互作用，而是隐含地选择最具预测性的相互作用。新的合成生物学能力（例如CRISPR）大大提高了我们为社会利益（生物燃料，医疗药物）设计生物系统的能力。然而，这一努力受到阻碍，因为我们无法可靠地预测我们的生物工程努力的结果。数学动力学模型传统上用于预测途径动力学，但它们需要很长时间才能开发，并且需要大量的生物学专业知识。在这里，我们用机器学习方法代替传统的动力学模型，这种方法能够直接从数据示例中学习路径动力学。这种新方法可以系统地应用于任何产品，途径或宿主，并显着加快生物工程。
New synthetic biology capabilities hold the promise of dramatically improving our ability to engineer biological systems. However, a fundamental hurdle in realizing this potential is our inability to accurately predict biological behavior after modifying the corresponding genotype. Kinetic models have traditionally been used to predict pathway dynamics in bioengineered systems, but they take significant time to develop, and rely heavily on domain expertise. Here, we show that the combination of machine learning and abundant multiomics data (proteomics and metabolomics) can be used to effectively predict pathway dynamics in an automated fashion. The new method outperforms a classical kinetic model, and produces qualitative and quantitative predictions that can be used to productively guide bioengineering efforts. This method systematically leverages arbitrary amounts of new data to improve predictions, and does not assume any particular interactions, but rather implicitly chooses the most predictive ones. New synthetic biology capabilities (e.g. CRISPR) dramatically improve our ability to engineer biological systems for the benefit of society (biofuels, medical drugs). However, this effort is hampered because we cannot reliably predict the outcome of our bioengineering efforts. Mathematical kinetic models have been traditionally used to predict pathway dynamics, but they take a long time to develop and require significant biological expertize. Here, we substitute traditional kinetic models with a machine learning approach that is able to learn pathway dynamics straight from data examples. This new approach can be systematically applied to any product, pathway or host and significantly speeds up bioengineering.
登录
查看更多内容
影响因子：
4.3
作者：
Dyar KA;Eckel-Mahan KL
通讯作者：
Eckel-Mahan KL
影响因子：
64.8
作者：
Esteva A;Kuprel B;Novoa RA;Ko J;Swetter SM;Blau HM;Thrun S
通讯作者：
Thrun S
DOI：
10.1002/wsbm.1198
发表时间：
2013-01
影响因子：
7.9
作者：
Chen, Rui;Snyder, Michael
通讯作者：
Snyder, Michael
影响因子：
4
作者：
Chubukov V;Mukhopadhyay A;Petzold CJ;Keasling JD;Martín HG
通讯作者：
Martín HG
DOI：
10.1073/pnas.0707476104
发表时间：
2007-10-02
影响因子：
11.1
作者：
Daran-Lapujade, Pascale;Rossell, Sergio;Bakker, Barbara M.
通讯作者：
Bakker, Barbara M.