EUVIMEDEUVIMED entdecken
Crossref

Protein multi‐level structure feature‐integrated deep learning method for mutational effect prediction

Ai-Ping Pang, Yongsheng Luo, Junping Zhou, Xue Cai, Lianggang Huang, Bo Zhang, Zhi-Qiang Liu, Yu-Guo Zheng

Biotechnology Journal · 2024

DOI: 10.1002/biot.202400203 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biotechnology Journal, 2024. Verfasst von Ai-Ping Pang und 7 weiteren Autor:innen. Beteiligte Einrichtung: National and Local Joint Engineering Research Center for Biomanufacturing of Chiral Chemicals, Zhejiang University of Technology, Hangzhou, People's …. Hauptthemen laut MEDLINE: Deep Learning, Mutation, Proteins. Die Arbeit nennt 56 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Natural Science Foundation of Zhejiang Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Through iterative rounds of mutation and selection, proteins can be engineered to enhance their desired biological functions. Nevertheless, identifying optimal mutation sites for directed evolution remains challenging due to the vastness of the protein sequence landscape and the epistatic mutational effects across residues. To address this challenge, we introduce MLSmut, a deep learning‐based approach that leverages multi‐level structural features of proteins. MLSmut extracts salient information from protein co‐evolution, sequence semantics, and geometric features to predict the mutational effect. Extensive benchmark evaluations on 10 single‐site and two multi‐site deep mutation scanning datasets demonstrate that MLSmut surpasses existing methods in predicting mutational outcomes. To overcome the limited training data availability, we employ a two‐stage training strategy: initial coarse‐tuning on a large corpus of unlabeled protein data followed by fine‐tuning on a curated dataset of 40−100 experimental measurements. This approach enables our model to achieve satisfactory performance on downstream protein prediction tasks. Importantly, our model holds the potential to predict the mutational effects of any protein sequence. Collectively, these findings suggest that our approach can substantially reduce the reliance on laborious wet lab experiments and deepen our understanding of the intricate relationships between mutations and protein function.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningMutationProteinsComputational BiologyDatabases, ProteinProtein Engineering

Stichwörter der Autor:innen

deep learningdirected evolutionmutational effect

Substanzen

Proteins

Autor:innen und Institutionen

  • National and Local Joint Engineering Research Center for Biomanufacturing of Chiral Chemicals, Zhejiang University of Technology, Hangzhou, People's Republic of China.
  • Key Laboratory of Bioorganic Synthesis of Zhejiang Province, College of Biotechnology and Bioengineering, Zhejiang University of Technology, Hangzhou, People's Republic of China.
  • Institute of Natural Sciences, Shanghai Jiao Tong University, Shanghai, China.

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • Natural Science Foundation of Zhejiang Province

Zitieren

APA

Pang, A. P., Luo, Y., Zhou, J., Cai, X., Huang, L., Zhang, B., Liu, Z. Q., & Zheng, Y. G. (2024). Protein multi‐level structure feature‐integrated deep learning method for mutational effect prediction. Biotechnology Journal. https://doi.org/10.1002/biot.202400203

Vancouver

Pang AP, Luo Y, Zhou J, Cai X, Huang L, Zhang B, et al. Protein multi‐level structure feature‐integrated deep learning method for mutational effect prediction. Biotechnology Journal. 2024. doi:10.1002/biot.202400203

BibTeX
@article{Pang2024,
  author = {Pang, Ai-Ping and Luo, Yongsheng and Zhou, Junping and Cai, Xue and Huang, Lianggang and Zhang, Bo and Liu, Zhi-Qiang and Zheng, Yu-Guo},
  title = {Protein multi‐level structure feature‐integrated deep learning method for mutational effect prediction},
  journal = {Biotechnology Journal},
  year = {2024},
  doi = {10.1002/biot.202400203}
}
Kostenlos starten →