A Comparative Review of Deep Learning Methods for RNA Tertiary Structure Prediction
Martinovic, I.; Vlasic, T.; Li, Y.; Hooi, B.; Zhang, Y.; Sikic, M.
Show abstract
Several deep learning-based tools for RNA 3D structure prediction have recently emerged, including DRfold, DeepFoldRNA, RhoFold, RoseTTAFoldNA, trRosettaRNA, and AlphaFold 3. In this study, we systematically evaluate these six models on three datasets: RNA Puzzles, CASP15 RNA targets, and a newly generated dataset of sequentially distinct RNAs, which serves as a benchmark for generalization capabilities. To ensure a robust evaluation, we also introduce a fourth, more stringent dataset that contains both sequentially and structurally distinct RNAs. We observed that each model predicts the best structure for certain RNAs, and evaluated whether commonly used scoring functions, Rosetta score and ARES, can reliably identify the most accurate structure from the predictions. Finally, since many RNA chains in the Protein Data Bank are part of complexes, we compare the performance of RoseTTAFoldNA and AlphaFold 3 in predicting RNA structures within complexes versus isolated RNA chains extracted from these complexes. This comprehensive evaluation highlights the strengths and limitations of current deep learning-based tools and provides valuable insights for advancing RNA 3D structure prediction.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Systematic benchmarking of deep-learning methods for tertiary RNA structure prediction 97%
- Structural comparison of protein-RNA homologous interfaces reveals widespread overall conservation contrasted with versatility in polar contacts 96%
- RNA structure prediction using positive and negative evolutionary information 95%
Similar papers in this journal
- A comprehensive survey of long-range tertiary interactions and motifs in non-coding RNA structures 98%
- ARTEMIS - a method for topology-independent superposition of RNA 3D structures and structure-based sequence alignment 97%
- UFold: Fast and Accurate RNA Secondary Structure Prediction with Deep Learning 96%
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.