Machine Learning on a Robotic Platform for the Design of Polymer-Protein Hybrids.
Machine Learning on a Robotic Platform for the Design of Polymer-Protein Hybrids.
复制标题
用于设计聚合物-蛋白质杂交物的机器人平台上的机器学习。
DOI：
10.1002/adma.202201809
复制
发表时间：
2022-07
影响因子：
29.4
通讯作者：
Gormley, Adam J.
中科院分区：
文献类型：
--
作者：
Tamasi, Matthew J.;Patel, Roshan A.;Borca, Carlos H.;Kosuri, Shashank;Mugnier, Heloise;Upadhya, Rahul;Murthy, N. Sanjeeva;Webb, Michael A.;Gormley, Adam J.
关键词：
聚合物-蛋白质杂交体是一种有趣的材料，可以增强蛋白质在非天然环境中的稳定性，从而增强其在各种医学，商业和工业应用中的实用性。一种稳定策略涉及设计合成的无规共聚物，其组成与蛋白质表面相协调，但由于巨大的化学和组成空间，合理的设计变得复杂。在这里，报告了一种基于主动机器学习设计蛋白质稳定共聚物的策略，该策略由自动化材料合成和表征平台提供便利。该方法的多功能性和鲁棒性是通过成功鉴定共聚物来证明的，所述共聚物在暴露于热变性条件下后保留或甚至增强三种化学上不同的酶的活性。虽然系统筛选的结果喜忧参半，积极学习适当地确定独特和有效的共聚物化学稳定的每种酶。总的来说，这项工作拓宽了设计适合目的的合成共聚物的能力，这些共聚物促进或以其他方式操纵蛋白质活性，并扩展到设计稳健的聚合物-蛋白质杂化材料。聚合物-蛋白质杂化物（PPH）为工业和医学应用中的蛋白质稳定提供了新的机会。利用自动化聚合物合成和主动机器学习的组合，我们报告了一个“学习-设计-测试-构建”策略，用于蛋白质定制的共聚物设计和合成。此外，利用大量实验数据，探索PPH内的结构与功能关系，并进行生物物理表征，以阐明PPH内稳定性的潜在机制。
Polymer–protein hybrids are intriguing materials that can bolster protein stability in non-native environments, thereby enhancing their utility in diverse medicinal, commercial, and industrial applications. One stabilization strategy involves designing synthetic random copolymers with compositions attuned to the protein surface, but rational design is complicated by the vast chemical and composition space. Here, a strategy is reported to design protein-stabilizing copolymers based on active machine learning, facilitated by automated material synthesis and characterization platforms. The versatility and robustness of the approach is demonstrated by the successful identification of copolymers that preserve, or even enhance, the activity of three chemically distinct enzymes following exposure to thermal denaturing conditions. Although systematic screening results in mixed success, active learning appropriately identifies unique and effective copolymer chemistries for the stabilization of each enzyme. Overall, this work broadens the capabilities to design fit-for-purpose synthetic copolymers that promote or otherwise manipulate protein activity, with extensions toward the design of robust polymer–protein hybrid materials. Polymer-protein hybrids (PPHs) offer new opportunities for protein stabilization in industrial and medical applications. Utilizing a combination of automated polymer synthesis and active machine learning, we report a “Learn-Design-Test-Build” strategy for protein-tailored copolymer design and synthesis. Further, utilizing large quantities of experimental data, structure-function relationships within PPHs are probed and biophysical characterization is performed to elucidate potential mechanisms of stability within PPHs.
登录
查看更多内容
影响因子：
16.6
作者：
Jablonka KM;Jothiappan GM;Wang S;Smit B;Yoo B
通讯作者：
Yoo B
影响因子：
18.2
作者：
Lin, Tzyy-Shyang;Coley, Connor W.;Olsen, Bradley D.
通讯作者：
Olsen, Bradley D.
影响因子：
1.9
作者：
Kim, Chiho;Chandrasekaran, Anand;Ramprasad, Rampi
通讯作者：
Ramprasad, Rampi
DOI：
10.1002/anie.201711044
发表时间：
2018-02-05
期刊：
Angewandte Chemie (International ed. in English)
影响因子：
--
作者：
Gormley AJ;Yeow J;Ng G;Conway Ó;Boyer C;Chapman R
通讯作者：
Chapman R
影响因子：
2.9
作者：
Chattopadhyay, K;Mazumdar, S
通讯作者：
Mazumdar, S