ArticleBioinformatics (Oxford, England)2022
Deep learning models for RNA secondary structure prediction (probably) do not generalize across families.
Article in Bioinformatics (Oxford, England), 2022. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 48 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
48 citing papers in PubMed.
- Markov models of SHAPE data improve secondary structure prediction.bioRxiv : the preprint server for biology · 2026Article
- UFold-X: an enhanced Dual & Dynamic U-Mamba model for long-range RNA secondary structure prediction.Nucleic acids research · 2026Article
- When does additional information improve accuracy of RNA secondary structure prediction?bioRxiv : the preprint server for biology · 2026Article
- An efficient algorithm for exploring RNA branching conformations under the nearest-neighbor thermodynamic model.Algorithms for molecular biology : AMB · 2026Article
- What does it take to learn the rules of RNA base pairing? A lot less than you may think.Communications biology · 2026Article
- Machine learning for RNA secondary structure prediction: a review of current methods and challenges.RNA (New York, N.Y.) · 2026Review
- Deep learning for RNA secondary structure determination: gauging generalizability and broadening the scope of traditional methods.RNA (New York, N.Y.) · 2026Review
- Retentive Network promotes efficient RNA language modeling of long sequences.Communications biology · 2026Article
- Diverse database and machine learning model to narrow the generalization gap in RNA structure prediction.Science advances · 2026Article
- gCoSRNA: Generalizable Coaxial Stacking Prediction for RNA Junctions Using Secondary Structure.Biomolecules · 2026Article
- Machine Learning Approaches for Predicting RNA-RNA/DNA Interactions.Methods in molecular biology (Clifton, N.J.) · 2026Review
- Designing molecular RNA switches with Restricted Boltzmann machines.Nature communications · 2025Article
- BiRNA-BERT allows efficient RNA language modeling with adaptive tokenization.Communications biology · 2025Article
- Deep Learning for RNA Secondary Structure Determination: Gauging Generalizability and Broadening the Scope of Traditional Methods.bioRxiv : the preprint server for biology · 2025Article
- Modeling RNA duplex dynamics with Gibbs sampling enhances base-pair prediction accuracy and reveals structural activity profiles.NAR genomics and bioinformatics · 2025Article
- Enhanced Generalizability of RNA Secondary Structure Prediction via Convolutional Block Attention Network and Ensemble Learning.Molecules (Basel, Switzerland) · 2025Article
- ECSFinder: optimized prediction of evolutionarily conserved RNA secondary structures from genome sequences.Nucleic acids research · 2025Article
- Improving RNA Secondary Structure Prediction Through Expanded Training Data.bioRxiv : the preprint server for biology · 2025Article
- AlignmentFold and AlignmentPartition: Improving the align-then-fold approach for RNA secondary structure prediction.bioRxiv : the preprint server for biology · 2025Article
- RiNALMo: general-purpose RNA language models can generalize well on structure prediction tasks.Nature communications · 2025Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
5 authors.
Funding
Abstract
motivationThe secondary structure of RNA is of importance to its function. Over the last few years, several papers attempted to use machine learning to improve de novo RNA secondary structure prediction. Many of these papers report impressive results for intra-family predictions but seldom address the much more difficult (and practical) inter-family problem.
resultsWe demonstrate that it is nearly trivial with convolutional neural networks to generate pseudo-free energy changes, modelled after structure mapping data that improve the accuracy of structure prediction for intra-family cases. We propose a more rigorous method for inter-family cross-validation that can be used to assess the performance of learning-based models. Using this method, we further demonstrate that intra-family performance is insufficient proof of generalization despite the widespread assumption in the literature and provide strong evidence that many existing learning-based models have not generalized inter-family. AVAILABILITY AND IMPLEMENTATION: Source code and data are available at https://github.com/marcellszi/dl-rna. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.