Knowledge from Large-Scale Protein Contact Prediction Models Can Be Transferred to the Data-Scarce RNA Contact Prediction Task

TL;DR

This paper demonstrates that knowledge from large-scale protein contact prediction models can be effectively transferred to improve RNA contact prediction, addressing data scarcity issues in RNA structural modeling.

Contribution

The study introduces a transfer learning framework that leverages protein co-evolution models to enhance RNA contact prediction, a novel approach in the field.

Findings

Transfer learning significantly improves RNA contact prediction accuracy.

Protein structural patterns are transferable to RNA structures.

Framework reduces data scarcity challenges in RNA modeling.

Abstract

RNA, whose functionality is largely determined by its structure, plays an important role in many biological activities. The prediction of pairwise structural proximity between each nucleotide of an RNA sequence can characterize the structural information of the RNA. Historically, this problem has been tackled by machine learning models using expert-engineered features and trained on scarce labeled datasets. Here, we find that the knowledge learned by a protein-coevolution Transformer-based deep neural network can be transferred to the RNA contact prediction task. As protein datasets are orders of magnitude larger than those for RNA contact prediction, our findings and the subsequent framework greatly reduce the data scarcity bottleneck. Experiments confirm that RNA contact prediction through transfer learning using a publicly available protein model is greatly improved. Our findings indicate that the learned structural patterns of proteins can be transferred to RNAs, opening up potential new avenues for research.