Artificial intelligence method to design and fold alpha-helical structural proteins from the primary amino acid sequence
The development of rational techniques to discover new mechanically relevant proteins for use in variety of applications ranging from mechanics, agriculture to biotechnology remains an outstanding nanomechanical design problem. The key barrier is to design a sequence to fold into a predictable struc...
| Main Authors: | , , , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Elsevier BV
2020
|
| Online Access: | https://hdl.handle.net/1721.1/125636 |
| _version_ | 1826199993300549632 |
|---|---|
| author | Qin, Zhao Wu, Lingfei Sun, Hui Huo, Siyu Ma, Tengfei Lim, Eugene J. Chen, Pin-Yu Marelli, Benedetto 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 Qin, Zhao Wu, Lingfei Sun, Hui Huo, Siyu Ma, Tengfei Lim, Eugene J. Chen, Pin-Yu Marelli, Benedetto Buehler, Markus J |
| author_sort | Qin, Zhao |
| collection | MIT |
| description | The development of rational techniques to discover new mechanically relevant proteins for use in variety of applications ranging from mechanics, agriculture to biotechnology remains an outstanding nanomechanical design problem. The key barrier is to design a sequence to fold into a predictable structure to achieve a certain material function. Focused on alpha-helical proteins (as found in skin, hair, and many other mechanically relevant protein materials), we report a Multi-scale Neighborhood-based Neural Network (MNNN) model to learn how a specific amino acid sequence folds into a protein structure. The algorithm predicts the protein structure without using a template or co-evolutional information at a maximum error of 2.1 Å. We find that the prediction accuracy is higher than other models and the prediction consumes less than six orders of magnitude time than ab initio folding methods. We demonstrate that MNNN can predict the structure of an unknown protein that agrees with experiments, and our model hence shows a great advantage in the rational design of de novo proteins. Keywords: Protein; artificial intelligence; machine learning; deep neural networks; folding; structure prediction; computation |
| first_indexed | 2024-09-23T11:29:03Z |
| format | Article |
| id | mit-1721.1/125636 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T11:29:03Z |
| publishDate | 2020 |
| publisher | Elsevier BV |
| record_format | dspace |
| spelling | mit-1721.1/1256362022-09-27T19:53:08Z Artificial intelligence method to design and fold alpha-helical structural proteins from the primary amino acid sequence Qin, Zhao Wu, Lingfei Sun, Hui Huo, Siyu Ma, Tengfei Lim, Eugene J. Chen, Pin-Yu Marelli, Benedetto Buehler, Markus J Massachusetts Institute of Technology. Department of Civil and Environmental Engineering The development of rational techniques to discover new mechanically relevant proteins for use in variety of applications ranging from mechanics, agriculture to biotechnology remains an outstanding nanomechanical design problem. The key barrier is to design a sequence to fold into a predictable structure to achieve a certain material function. Focused on alpha-helical proteins (as found in skin, hair, and many other mechanically relevant protein materials), we report a Multi-scale Neighborhood-based Neural Network (MNNN) model to learn how a specific amino acid sequence folds into a protein structure. The algorithm predicts the protein structure without using a template or co-evolutional information at a maximum error of 2.1 Å. We find that the prediction accuracy is higher than other models and the prediction consumes less than six orders of magnitude time than ab initio folding methods. We demonstrate that MNNN can predict the structure of an unknown protein that agrees with experiments, and our model hence shows a great advantage in the rational design of de novo proteins. Keywords: Protein; artificial intelligence; machine learning; deep neural networks; folding; structure prediction; computation 2020-06-02T20:02:12Z 2020-06-02T20:02:12Z 2020-02 2019-12 2020-05-19T15:33:36Z Article http://purl.org/eprint/type/JournalArticle 2352-4316 https://hdl.handle.net/1721.1/125636 Qin, Zhao, et al. "Artificial intelligence method to design and fold alpha-helical structural proteins from the primary amino acid sequence." Extreme Mechanics Letters, 36 (April 2020): 100652 en http://dx.doi.org/10.1016/j.eml.2020.100652 Extreme Mechanics Letters Creative Commons Attribution-NonCommercial-NoDerivs License http://creativecommons.org/licenses/by-nc-nd/4.0/ application/pdf Elsevier BV bioRxiv |
| spellingShingle | Qin, Zhao Wu, Lingfei Sun, Hui Huo, Siyu Ma, Tengfei Lim, Eugene J. Chen, Pin-Yu Marelli, Benedetto Buehler, Markus J Artificial intelligence method to design and fold alpha-helical structural proteins from the primary amino acid sequence |
| title | Artificial intelligence method to design and fold alpha-helical structural proteins from the primary amino acid sequence |
| title_full | Artificial intelligence method to design and fold alpha-helical structural proteins from the primary amino acid sequence |
| title_fullStr | Artificial intelligence method to design and fold alpha-helical structural proteins from the primary amino acid sequence |
| title_full_unstemmed | Artificial intelligence method to design and fold alpha-helical structural proteins from the primary amino acid sequence |
| title_short | Artificial intelligence method to design and fold alpha-helical structural proteins from the primary amino acid sequence |
| title_sort | artificial intelligence method to design and fold alpha helical structural proteins from the primary amino acid sequence |
| url | https://hdl.handle.net/1721.1/125636 |
| work_keys_str_mv | AT qinzhao artificialintelligencemethodtodesignandfoldalphahelicalstructuralproteinsfromtheprimaryaminoacidsequence AT wulingfei artificialintelligencemethodtodesignandfoldalphahelicalstructuralproteinsfromtheprimaryaminoacidsequence AT sunhui artificialintelligencemethodtodesignandfoldalphahelicalstructuralproteinsfromtheprimaryaminoacidsequence AT huosiyu artificialintelligencemethodtodesignandfoldalphahelicalstructuralproteinsfromtheprimaryaminoacidsequence AT matengfei artificialintelligencemethodtodesignandfoldalphahelicalstructuralproteinsfromtheprimaryaminoacidsequence AT limeugenej artificialintelligencemethodtodesignandfoldalphahelicalstructuralproteinsfromtheprimaryaminoacidsequence AT chenpinyu artificialintelligencemethodtodesignandfoldalphahelicalstructuralproteinsfromtheprimaryaminoacidsequence AT marellibenedetto artificialintelligencemethodtodesignandfoldalphahelicalstructuralproteinsfromtheprimaryaminoacidsequence AT buehlermarkusj artificialintelligencemethodtodesignandfoldalphahelicalstructuralproteinsfromtheprimaryaminoacidsequence |