Discovering design principles of collagen molecular stability using a genetic algorithm, deep learning, and experimental validation
<jats:p> 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 duri...
| Main Authors: | , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Proceedings of the National Academy of Sciences
2023
|
| Online Access: | https://hdl.handle.net/1721.1/148571 |
| _version_ | 1826213668002463744 |
|---|---|
| author | Khare, Eesha Yu, Chi-Hua Gonzalez Obeso, Constancio Milazzo, Mario Kaplan, David L Buehler, Markus J |
| author2 | Massachusetts Institute of Technology. Department of Civil and Environmental Engineering |
| author_facet | Massachusetts Institute of Technology. Department of Civil and Environmental Engineering Khare, Eesha Yu, Chi-Hua Gonzalez Obeso, Constancio Milazzo, Mario Kaplan, David L Buehler, Markus J |
| author_sort | Khare, Eesha |
| collection | MIT |
| description | <jats:p>
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 (T
<jats:sub>m</jats:sub>
). Although significant research has been conducted on understanding how collagen primary amino acid sequences correspond to T
<jats:sub>m</jats:sub>
values, a robust framework to facilitate the design of collagen sequences with specific T
<jats:sub>m</jats:sub>
remains a challenge. Here, we develop a general model using a genetic algorithm within a deep learning framework to design collagen sequences with specific T
<jats:sub>m</jats:sub>
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 T
<jats:sub>m</jats:sub>
values using both experimental and computational methods. We find that the model accurately predicts T
<jats:sub>m</jats:sub>
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 T
<jats:sub>m</jats:sub>
values for intended materials manufacturing methods and biomedical applications, realizing a mechanistic materials by design paradigm.
</jats:p> |
| first_indexed | 2024-09-23T15:52:55Z |
| format | Article |
| id | mit-1721.1/148571 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T15:52:55Z |
| publishDate | 2023 |
| publisher | Proceedings of the National Academy of Sciences |
| record_format | dspace |
| spelling | mit-1721.1/1485712023-03-17T03:05:03Z Discovering design principles of collagen molecular stability using a genetic algorithm, deep learning, and experimental validation Khare, Eesha Yu, Chi-Hua Gonzalez Obeso, Constancio Milazzo, Mario Kaplan, David L Buehler, Markus J Massachusetts Institute of Technology. Department of Civil and Environmental Engineering <jats:p> 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 (T <jats:sub>m</jats:sub> ). Although significant research has been conducted on understanding how collagen primary amino acid sequences correspond to T <jats:sub>m</jats:sub> values, a robust framework to facilitate the design of collagen sequences with specific T <jats:sub>m</jats:sub> remains a challenge. Here, we develop a general model using a genetic algorithm within a deep learning framework to design collagen sequences with specific T <jats:sub>m</jats:sub> 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 T <jats:sub>m</jats:sub> values using both experimental and computational methods. We find that the model accurately predicts T <jats:sub>m</jats:sub> 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 T <jats:sub>m</jats:sub> values for intended materials manufacturing methods and biomedical applications, realizing a mechanistic materials by design paradigm. </jats:p> 2023-03-16T13:24:07Z 2023-03-16T13:24:07Z 2022 2023-03-16T13:20:23Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/148571 Khare, Eesha, Yu, Chi-Hua, Gonzalez Obeso, Constancio, Milazzo, Mario, Kaplan, David L et al. 2022. "Discovering design principles of collagen molecular stability using a genetic algorithm, deep learning, and experimental validation." Proceedings of the National Academy of Sciences of the United States of America, 119 (40). en 10.1073/PNAS.2209524119 Proceedings of the National Academy of Sciences of the United States of America Creative Commons Attribution-NonCommercial-NoDerivs License http://creativecommons.org/licenses/by-nc-nd/4.0/ application/pdf Proceedings of the National Academy of Sciences PNAS |
| spellingShingle | Khare, Eesha Yu, Chi-Hua Gonzalez Obeso, Constancio Milazzo, Mario Kaplan, David L Buehler, Markus J Discovering design principles of collagen molecular stability using a genetic algorithm, deep learning, and experimental validation |
| title | Discovering design principles of collagen molecular stability using a genetic algorithm, deep learning, and experimental validation |
| title_full | Discovering design principles of collagen molecular stability using a genetic algorithm, deep learning, and experimental validation |
| title_fullStr | Discovering design principles of collagen molecular stability using a genetic algorithm, deep learning, and experimental validation |
| title_full_unstemmed | Discovering design principles of collagen molecular stability using a genetic algorithm, deep learning, and experimental validation |
| title_short | Discovering design principles of collagen molecular stability using a genetic algorithm, deep learning, and experimental validation |
| title_sort | discovering design principles of collagen molecular stability using a genetic algorithm deep learning and experimental validation |
| url | https://hdl.handle.net/1721.1/148571 |
| work_keys_str_mv | AT khareeesha discoveringdesignprinciplesofcollagenmolecularstabilityusingageneticalgorithmdeeplearningandexperimentalvalidation AT yuchihua discoveringdesignprinciplesofcollagenmolecularstabilityusingageneticalgorithmdeeplearningandexperimentalvalidation AT gonzalezobesoconstancio discoveringdesignprinciplesofcollagenmolecularstabilityusingageneticalgorithmdeeplearningandexperimentalvalidation AT milazzomario discoveringdesignprinciplesofcollagenmolecularstabilityusingageneticalgorithmdeeplearningandexperimentalvalidation AT kaplandavidl discoveringdesignprinciplesofcollagenmolecularstabilityusingageneticalgorithmdeeplearningandexperimentalvalidation AT buehlermarkusj discoveringdesignprinciplesofcollagenmolecularstabilityusingageneticalgorithmdeeplearningandexperimentalvalidation |