Knowledge from Large-Scale Protein Contact Prediction Models Can Be Transferred to the Data-Scarce RNA Contact Prediction Task
This work addresses the data scarcity bottleneck in RNA contact prediction, which is important for understanding RNA structure and function in biology, and is incremental as it applies an existing protein model to a new domain.
The paper tackles the problem of predicting RNA structural contacts, which is hindered by scarce labeled data, by transferring knowledge from a large-scale protein contact prediction model, resulting in greatly improved prediction performance.
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.