Biology subjects

Szikszai, M.

Publications and source records attributed to Szikszai, M..

4 recordsLinked to original sources

bioRxiv2025

Deep Learning for RNA Secondary Structure Determination: Gauging Generalizability and Broadening the Scope of Traditional Methods

The diverse regulatory functions, protein production capacity, and stability of natural and synthetic RNAs are closely tied to their ability to fold into intricate structures. Determining RNA structure is thus fundamental to RNA biology and bioengineering. Among existing approaches to structure determination, computational secondary structure prediction offers a rapid and low-cost strategy and is thus widely used, especially when seeking to identify functional RNA elements in large transcriptomes or screen massive libraries of novel designs. While traditional approaches rely on detailed measurements of folding energetics and/or probabilistic modeling of structural data, recent years have witnessed a surge in deep learning methods, inspired by their tremendous success in protein structure prediction. However, the limited diversity and volume of known RNA structures can impede their ability to accurately predict structures markedly different from the ones they have seen. This is known as the generalization gap and currently poses a major barrier to progress in the field. In this Perspective article, we gauge method generalizability using a new benchmark dataset of structured RNAs we curated from the Protein Data Bank. We also discuss the emergence of deep learning methods for predicting structure probing data and use a new dataset to underscore generalization challenges unique to this domain along with directions for future improvement. Expanding beyond improving predictive accuracy, we review how advances in deep learning have recently enabled scalable and accessible optimization of traditional structure prediction methods and their seamless integration with modern neural networks.

bioinformatics↗

bioRxiv2025

On inputs to deep learning for RNA 3D structure prediction

Today, there are several effective deep learning models for predicting the 3D structure of proteins. Building on their success, models have been developed for predicting the 3D structure of non-coding RNAs. Unfortunately, these models are much less accurate than their protein counterparts. In this paper, we highlight differences between protein and RNA structure, and demonstrate methods for deep learning targeted at addressing those differences, with the aim of prompting discussion on these topics. We present an RNA-specific pipeline for generating structural Multiple Sequence Alignments (MSAs). Derived from the structural alignments, we introduce engineered evolutionary features that strongly inform RNA structure. Further, from the crystal structure, we derive structural features describing RNA base pairing. These evolutionary and structural features can be used in loss functions at different stages of training. Finally, we discuss different cropping strategies informed by RNA structure.

bioinformatics↗

bioRxiv2024

RNA3DB: a dataset for training and benchmarking deep learning models for RNA structure prediction

With advances in protein structure prediction thanks to deep learning models like AlphaFold, RNA structure prediction has recently received increased attention from deep learning researchers. RNAs introduce substantial challenges due to the sparser availability and lower structural diversity of the experimentally resolved RNA structures in comparison to protein structures. These challenges are often poorly addressed by the existing literature, many of which report inflated performance due to using training and testing sets with significant structural overlap. Further, the most recent Critical Assessment of Structure Prediction (CASP15) has shown that deep learning models for RNA structure are currently outperformed by traditional methods. In this paper we present RNA3DB, a dataset of structured RNAs, derived from the Protein Data Bank (PDB), that is designed for training and benchmarking deep learning models. The RNA3DB method arranges the RNA 3D chains into distinct groups (Components) that are non-redundant both with regard to sequence as well as structure, providing a robust way of dividing training, validation, and testing sets. Any split of these structurally-dissimilar Components are guaranteed to produce test and validations sets that are distinct by sequence and structure from those in the training set. We provide the RNA3DB dataset, a particular train/test split of the RNA3DB Components (in an approximate 70/30 ratio) that will be updated periodically. We also provide the RNA3DB methodology along with the source-code, with the goal of creating a reproducible and customizable tool for producing structurally-dissimilar dataset splits for structural RNAs. Graphical Abstract O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=140 SRC="FIGDIR/small/578025v3_ufig1.gif" ALT="Figure 1"> View larger version (39K): org.highwire.dtl.DTLVardef@cb3aa2org.highwire.dtl.DTLVardef@7685fdorg.highwire.dtl.DTLVardef@156ca35org.highwire.dtl.DTLVardef@f58d72_HPS_FORMAT_FIGEXP M_FIG C_FIG HighlightsO_LIWhile there is a recent surge in applying deep learning to RNA structure prediction, domain experts have raised concerns about generalization and current trends in benchmarking. C_LIO_LIMany of the concerns primarily relate to how novel RNA families-i.e. families unseen in the training set-are benchmarked, and whether the models are effective at handling such cases. Performance on bench-marks reflective of real-world applications, such as CASP15 and RNA-Puzzles, is poor for RNA deep learning models. C_LIO_LIWe present a dataset-RNA3DB-that is designed for training and bench-marking deep learning models for RNA structure prediction. RNA3DB provides coverage of all RNA chains found in the Protein Data Bank (PDB). C_LIO_LIRNA3DB is clustered into groups that are both sequentially and structurally non-redundant, providing a robust way of creating training, validation, and testing sets for deep learning models. Along with the dataset, we also provide a transparent methodology as well as the source-code, making our tool both reproducible and customizable. C_LI

bioinformatics↗

bioRxiv2022

Deep learning models for RNA secondary structure prediction (probably) do not generalise across families

AO_SCPLOWBSTRACTC_SCPLOWO_ST_ABSMotivationC_ST_ABSThe 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 it is nearly trivial with convolutional neural networks to generate pseudo-free energy changes, modeled 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 generalisation despite the widespread assumption in the literature, and provide strong evidence that many existing learning-based models have not generalised inter-family. AvailabilitySource code and data is available at https://github.com/marcellszi/dl-rna.

bioinformatics↗