Discovering design principles of collagen molecular stability using a genetic algorithm, deep learning, and experimental validation.
Discovering design principles of collagen molecular stability using a genetic algorithm, deep learning, and experimental validation.
复制标题
DOI：
10.1073/pnas.2209524119
复制
发表时间：
2022-10-04
影响因子：
11.1
通讯作者：
中科院分区：
文献类型：
--
作者：
Collagen is the most abundant structural protein in humans and as such, is often used in biomedical applications for tissue repair and regeneration. Designing de novo collagen to maintain its structural integrity in vivo, important for its mechanical performance and subsequent utility, remains a challenge today. In this work, we develop a deep learning framework to generate collagen sequences with desired thermal stability and validate our deep learning framework using both simulation and experiment. Given this validation, we discover key insights into the prevalence of amino acids in collagen triple helices and find a mechanistic relationship between our simulations and experiment. This framework enables researchers to develop collagen sequences with desired thermal stability for biomedical applications. Collagen is the most abundant structural protein in humans, providing crucial mechanical properties, including high strength and toughness, in tissues. Collagen-based biomaterials are, therefore, used for tissue repair and regeneration. Utilizing collagen effectively during materials processing ex vivo and subsequent function in vivo requires stability over wide temperature ranges to avoid denaturation and loss of structure, measured as melting temperature (Tm). Although significant research has been conducted on understanding how collagen primary amino acid sequences correspond to Tm values, a robust framework to facilitate the design of collagen sequences with specific Tm remains a challenge. Here, we develop a general model using a genetic algorithm within a deep learning framework to design collagen sequences with specific Tm values. We report 1,000 de novo collagen sequences, and we show that we can efficiently use this model to generate collagen sequences and verify their Tm values using both experimental and computational methods. We find that the model accurately predicts Tm values within a few degrees centigrade. Further, using this model, we conduct a high-throughput study to identify the most frequently occurring collagen triplets that can be directly incorporated into collagen. We further discovered that the number of hydrogen bonds within collagen calculated with molecular dynamics (MD) is directly correlated to the experimental measurement of triple-helical quality. Ultimately, we see this work as a critical step to helping researchers develop collagen sequences with specific Tm values for intended materials manufacturing methods and biomedical applications, realizing a mechanistic materials by design paradigm.
登录
查看更多内容
影响因子：
2.7
作者：
Buehler, Markus J.
通讯作者：
Buehler, Markus J.
影响因子：
3.6
作者：
Katoch S;Chauhan SS;Kumar V
通讯作者：
Kumar V
对评估生物聚合物结构过程 - 过程关系的合并实验和计算程序的综述。
影响因子：
14
作者：
Gronau, Greta;Krishnaji, Sreevidhya T.;Kinahan, Michelle E.;Giesa, Tristan;Wong, Joyce Y.;Kaplan, David L.;Buehler, Markus J.
通讯作者：
Buehler, Markus J.
影响因子：
15
作者：
Bretscher, LE;Jenkins, CL;Raines, RT
通讯作者：
Raines, RT
影响因子：
3.4
作者：
Buehler, Markus J.;Wong, Sophie Y.
通讯作者：
Wong, Sophie Y.