Unknown

Dataset Information

0

Integrating end-to-end learning with deep geometrical potentials for ab initio RNA structure prediction.

ABSTRACT: RNAs are fundamental in living cells and perform critical functions determined by their tertiary architectures. However, accurate modeling of 3D RNA structure remains a challenging problem. We present a novel method, DRfold, to predict RNA tertiary structures by simultaneous learning of local frame rotations and geometric restraints from experimentally solved RNA structures, where the learned knowledge is converted into a hybrid energy potential to guide RNA structure assembly. The method significantly outperforms previous approaches by >73.3% in TM-score on a sequence-nonredundant dataset containing recently released structures. Detailed analyses showed that the major contribution to the improvements arise from the deep end-to-end learning supervised with the atom coordinates and the composite energy function integrating complementary information from geometry restraints and end-to-end learning models. The open-source DRfold program with fast training protocol allows large-scale application of high-resolution RNA structure modeling and can be further improved with future expansion of RNA structure databases.

SUBMITTER: Li Y 

PROVIDER: S-EPMC10505173 | biostudies-literature | 2023 Sep

REPOSITORIES: biostudies-literature

Json Xml
altmetric image

Publications

Integrating end-to-end learning with deep geometrical potentials for ab initio RNA structure prediction.

Li Yang Y   Zhang Chengxin C   Feng Chenjie C   Pearce Robin R   Lydia Freddolino P P   Zhang Yang Y  

Nature communications 20230916 1

RNAs are fundamental in living cells and perform critical functions determined by their tertiary architectures. However, accurate modeling of 3D RNA structure remains a challenging problem. We present a novel method, DRfold, to predict RNA tertiary structures by simultaneous learning of local frame rotations and geometric restraints from experimentally solved RNA structures, where the learned knowledge is converted into a hybrid energy potential to guide RNA structure assembly. The method signif  ...[more]

Similar Datasets

Unknown Fast and accurate Ab Initio Protein structure prediction using deep learning potentials.
| S-EPMC9518900 | biostudies-literature
Unknown Deep learning geometrical potential for high-accuracy <i>ab initio</i> protein structure prediction.
| S-EPMC9160776 | biostudies-literature
Unknown Curriculum learning for ab initio deep learned refractive optics.
| S-EPMC11297943 | biostudies-literature
Unknown Deep learning sequence-based ab initio prediction of variant effects on expression and disease risk.
| S-EPMC6094955 | biostudies-literature
Unknown Ab Initio Calculations of the Redox Potentials of Additives for Lithium-Ion Batteries and Their Prediction through Machine Learning.
| S-EPMC6644342 | biostudies-literature
Unknown Integrating ab initio and template-based algorithms for protein-protein complex structure prediction.
| S-EPMC7523679 | biostudies-literature
Unknown IPred - integrating ab initio and evidence based gene predictions to improve prediction accuracy.
| S-EPMC4345001 | biostudies-literature
Unknown Deep-learning density functional theory Hamiltonian for efficient ab initio electronic-structure calculation.
| S-EPMC11499279 | biostudies-literature
Unknown Analytical ab initio hessian from a deep learning potential for transition state optimization.
| S-EPMC11473838 | biostudies-literature
Unknown Integrating Cross-Linking Experiments with Ab Initio Protein-Protein Docking.
| S-EPMC6084434 | biostudies-literature