EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Multiple sequence alignment-based RNA language model and its application to structural inference

Yikun Zhang, Mei Lang, Jiuhong Jiang, Zhiqiang Gao iD, Fan Xu, Thomas Litfin, Ke Chen, Jaswinder Singh, Xiansong Huang, Guoli Song, Yonghong Tian, Jian Zhan iD und 2 weitere

Nucleic Acids Research · 11.01.2024 · 52 (1) · e3-e3

DOI: 10.1093/nar/gkad1031 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Nucleic Acids Research, online erschienen am 06.11.2023. Verfasst von Yikun Zhang und 13 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronic and Computer Engineering, Peking University, Shenzhen 518055, China. Hauptthemen laut MEDLINE: RNA, Sequence Alignment, Machine Learning. Die Arbeit wurde bisher 123-mal zitiert (Crossref) und nennt 71 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Natural Science Foundation of China, Shenzhen Science and Technology Program, National Key R&D Program of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Compared with proteins, DNA and RNA are more difficult languages to interpret because four-letter coded DNA/RNA sequences have less information content than 20-letter coded protein sequences. While BERT (Bidirectional Encoder Representations from Transformers)-like language models have been developed for RNA, they are ineffective at capturing the evolutionary information from homologous sequences because unlike proteins, RNA sequences are less conserved. Here, we have developed an unsupervised multiple sequence alignment-based RNA language model (RNA-MSM) by utilizing homologous sequences from an automatic pipeline, RNAcmap, as it can provide significantly more homologous sequences than manually annotated Rfam. We demonstrate that the resulting unsupervised, two-dimensional attention maps and one-dimensional embeddings from RNA-MSM contain structural information. In fact, they can be directly mapped with high accuracy to 2D base pairing probabilities and 1D solvent accessibilities, respectively. Further fine-tuning led to significantly improved performance on these two downstream tasks compared with existing state-of-the-art techniques including SPOT-RNA2 and RNAsnap2. By comparison, RNA-FM, a BERT-based RNA language model, performs worse than one-hot encoding with its embedding in base pair and solvent-accessible surface area prediction. We anticipate that the pre-trained RNA-MSM model can be fine-tuned on many other tasks related to RNA structure and function.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

RNASequence AlignmentMachine LearningDNAProteinsSolvents

Substanzen

DNAProteinsRNASolvents

Autor:innen und Institutionen

  • School of Electronic and Computer Engineering, Peking University, Shenzhen 518055, China.
  • AI for Science (AI4S)-Preferred Program, Peking University Shenzhen Graduate School, Shenzen 518055, China.
  • Institute of Systems and Physical Biology, Shenzhen Bay Laboratory, Shenzhen 518107, China.
  • Shanghai Artificial Intelligence Laboratory, Shanghai 200232, China.
  • Peng Cheng Laboratory, Shenzhen 518066, China.
  • Institute for Glycomics, Griffith University, Parklands Dr, Southport, QLD 4215, Australia.

ORCID-Profile: Zhiqiang Gao, Jian Zhan, Yaoqi Zhou

Förderung

  • Natural Science Foundation of China
  • Shenzhen Science and Technology Program
  • National Key R&D Program of China
  • Griffith University

Zitieren

APA

Zhang, Y., Lang, M., Jiang, J., Gao, Z., Xu, F., Litfin, T., Chen, K., Singh, J., Huang, X., Song, G., Tian, Y., Zhan, J., Chen, J., & Zhou, Y. (2024). Multiple sequence alignment-based RNA language model and its application to structural inference. Nucleic Acids Research, 52(1), e3-e3. https://doi.org/10.1093/nar/gkad1031

Vancouver

Zhang Y, Lang M, Jiang J, Gao Z, Xu F, Litfin T, et al. Multiple sequence alignment-based RNA language model and its application to structural inference. Nucleic Acids Research. 2024;52(1):e3-e3. doi:10.1093/nar/gkad1031

BibTeX
@article{Zhang2024,
  author = {Zhang, Yikun and Lang, Mei and Jiang, Jiuhong and Gao, Zhiqiang and Xu, Fan and Litfin, Thomas and Chen, Ke and Singh, Jaswinder and Huang, Xiansong and Song, Guoli and Tian, Yonghong and Zhan, Jian and Chen, Jie and Zhou, Yaoqi},
  title = {Multiple sequence alignment-based RNA language model and its application to structural inference},
  journal = {Nucleic Acids Research},
  year = {2024},
  volume = {52},
  number = {1},
  pages = {e3--e3},
  doi = {10.1093/nar/gkad1031}
}
Kostenlos starten →