Accurate RNA 3D structure prediction using a language model-based deep learning approach

Accurate prediction of RNA three-dimensional (3D) structures remains an unsolved challenge. Determining RNA 3D structures is crucial for understanding their functions and informing RNA-targeting drug development and synthetic biology design. The structural flexibility of RNA, which leads to the scarcity of experimentally determined data, complicates computational prediction efforts. Here we present RhoFold+, an RNA language model-based deep learning method that accurately predicts 3D structures of single-chain RNAs from sequences. By integrating an RNA language model pretrained on ~23.7 million RNA sequences and leveraging techniques to address data scarcity, RhoFold+ offers a fully automated end-to-end pipeline for RNA 3D structure prediction. Retrospective evaluations on RNA-Puzzles and CASP15 natural RNA targets demonstrate the superiority of RhoFold+ over existing methods, including human expert groups. Its efficacy and generalizability are further validated through cross-family and cross-type assessments, as well as time-censored benchmarks. Additionally, RhoFold+ predicts RNA secondary structures and interhelical angles, providing empirically verifiable features that broaden its applicability to RNA structure and function studies.

Authors

Institutions

Publication Details

Journal
Nature Methods
Published
2024-11-21
DOI
https://doi.org/10.1038/s41592-024-02487-0
Citations
166
Primary Topic
RNA and protein synthesis mechanisms
Type
article
Field-Weighted Citation Impact
38.81

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Accurate RNA 3D structure prediction using a language model-based deep learning approach

Liang Hong, Jin Xiao, Di Liu, Siqi Sun et al.
166 citations
Nature Methods
RNA and protein synthesis mechanisms
38.81
article

Accurate RNA 3D structure prediction using a language model-based deep learning approach

Liang Hong, Jin Xiao, Di Liu, Siqi Sun, Liangzhen Zheng, Zhihang Hu, Irwin King, Yixuan Wang, Felix Wong, Peng Yin, James J. Collins, Jiuming Wang, Yu Li, Sheng Wang, Jiayang Chen, Tao Shen, Tejas Krishnamoorthi
article en
166 citations

Abstract

Accurate prediction of RNA three-dimensional (3D) structures remains an unsolved challenge. Determining RNA 3D structures is crucial for understanding their functions and informing RNA-targeting drug development and synthetic biology design. The structural flexibility of RNA, which leads to the scarcity of experimentally determined data, complicates computational prediction efforts. Here we present RhoFold+, an RNA language model-based deep learning method that accurately predicts 3D structures of single-chain RNAs from sequences. By integrating an RNA language model pretrained on ~23.7 million RNA sequences and leveraging techniques to address data scarcity, RhoFold+ offers a fully automated end-to-end pipeline for RNA 3D structure prediction. Retrospective evaluations on RNA-Puzzles and CASP15 natural RNA targets demonstrate the superiority of RhoFold+ over existing methods, including human expert groups. Its efficacy and generalizability are further validated through cross-family and cross-type assessments, as well as time-censored benchmarks. Additionally, RhoFold+ predicts RNA secondary structures and interhelical angles, providing empirically verifiable features that broaden its applicability to RNA structure and function studies.

Nature MethodsVol. 21(12)
Broad Institute (US), Harvard University (US), Shenzhen Institute of Information Technology (CN), Chinese University of Hong Kong (HK), Fudan University (CN), WuXi AppTec (China) (CN), Midea Group (China) (CN), Coherus BioSciences (United States) (US), Chinese University of Hong Kong, Shenzhen (CN), Shenzhen Institutes of Advanced Technology (CN), Inspire Institute (US), Center for Systems Biology (US), Viva Biotech (China) (CN), Arizona State University (US), Massachusetts Institute of Technology (US), University of Hong Kong (HK)
Bowling Green State University, Research Grants Council, University Grants Committee, Fudan University, Innovation and Technology Commission, Chinese University of Hong Kong, Innovation and Technology Fund, National Institutes of Health, National Institute of Allergy and Infectious Diseases
Openalex Percentile: Top 0%
RNA and protein synthesis mechanisms
38.81
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.