Assessing the accuracy of direct-coupling analysis for RNA contact prediction

Towards parsimonious generative modeling of RNA families

Generative probabilistic models emerge as a new paradigm in data-driven, evolution-informed design of biomolecular sequences. This paper introduces a novel approach, called Edge Activation Direct Coupling Analysis (eaDCA), tailored to the characteristics of RNA sequences, with a strong emphasis on simplicity, efficiency, and interpretability. eaDCA explicitly constructs sparse coevolutionary models for RNA families, achieving performance levels comparable to more complex methods while utilizing a significantly lower number of parameters. Our approach demonstrates efficiency in generating artificial RNA sequences that closely resemble their natural counterparts in both statistical analyses and SHAPE-MaP experiments, and in predicting the effect of mutations. Notably, eaDCA provides a unique feature: estimating the number of potential functional sequences within a given RNA family. For example, in the case of cyclic di-AMP riboswitches (RF00379), our analysis suggests the existence of approximately 1039 functional nucleotide sequences. While huge compared to the known <4000 natural sequences, this number represents only a tiny fraction of the vast pool of nearly 1082 possible nucleotide sequences of the same length (136 nucleotides). These results underscore the promise of sparse and interpretable generative models, such as eaDCA, in enhancing our understanding of the expansive RNA sequence space.

pycofitness-Evaluating the fitness landscape of RNA and protein sequences

MOTIVATION

The accurate prediction of how mutations change biophysical properties of proteins or RNA is a major goal in computational biology with tremendous impacts on protein design and genetic variant interpretation. Evolutionary approaches such as coevolution can help solving this issue.

RESULTS

We present pycofitness, a standalone Python-based software package for the in silico mutagenesis of protein and RNA sequences. It is based on coevolution and, more specifically, on a popular inverse statistical approach, namely direct coupling analysis by pseudo-likelihood maximization. Its efficient implementation and user-friendly command line interface make it an easy-to-use tool even for researchers with no bioinformatics background. To illustrate its strengths, we present three applications in which pycofitness efficiently predicts the deleteriousness of genetic variants and the effect of mutations on protein fitness and thermodynamic stability.

AVAILABILITY AND IMPLEMENTATION

https://github.com/KIT-MBS/pycofitness.

trRosettaRNA: automated prediction of RNA 3D structure with transformer network

RNA 3D structure prediction is a long-standing challenge. Inspired by the recent breakthrough in protein structure prediction, we developed trRosettaRNA, an automated deep learning-based approach to RNA 3D structure prediction. The trRosettaRNA pipeline comprises two major steps: 1D and 2D geometries prediction by a transformer network; and 3D structure folding by energy minimization. Benchmark tests suggest that trRosettaRNA outperforms traditional automated methods. In the blind tests of the 15th Critical Assessment of Structure Prediction (CASP15) and the RNA-Puzzles experiments, the automated trRosettaRNA predictions for the natural RNAs are competitive with the top human predictions. trRosettaRNA also outperforms other deep learning-based methods in CASP15 when measured by the Z-score of the Root-Mean-Square Deviation. Nevertheless, it remains challenging to predict accurate structures for synthetic RNAs with an automated approach. We hope this work could be a good start toward solving the hard problem of RNA structure prediction with deep learning.

Thirteen dubious ways to detect conserved structural RNAs

Covariation induced by compensatory base substitutions in RNA alignments is a great way to deduce conserved RNA structure, in principle. In practice, success depends on many factors, importantly the quality and depth of the alignment and the choice of covariation statistic. Measuring covariation between pairs of aligned positions is easy. However, using covariation to infer evolutionarily conserved RNA structure is complicated by other extraneous sources of covariation such as that resulting from homologous sequences having evolved from a common ancestor. In order to provide evidence of evolutionarily conserved RNA structure, a method to distinguish covariation due to sources other than RNA structure is necessary. Moreover, there are several sorts of artifactually generated covariation signals that can further confound the analysis. Additionally, some covariation signal is difficult to detect due to incomplete comparative data. Here, we investigate and critically discuss the practice of inferring conserved RNA structure by comparative sequence analysis. We provide new methods on how to approach and decide which of the numerous long non-coding RNAs (lncRNAs) have biologically relevant structures.

A reproducibility analysis-based statistical framework for residue-residue evolutionary coupling detection

Direct coupling analysis (DCA) has been widely used to infer evolutionary coupled residue pairs from the multiple sequence alignment (MSA) of homologous sequences. However, effectively selecting residue pairs with significant evolutionary couplings according to the result of DCA is a non-trivial task. In this study, we developed a general statistical framework for significant evolutionary coupling detection, referred to as irreproducible discovery rate (IDR)-DCA, which is based on reproducibility analysis of the coupling scores obtained from DCA on manually created MSA replicates. IDR-DCA was applied to select residue pairs for contact prediction for monomeric proteins, protein-protein interactions and monomeric RNAs, in which three different versions of DCA were applied. We demonstrated that with the application of IDR-DCA, the residue pairs selected using a universal threshold always yielded stable performance for contact prediction. Comparing with the application of carefully tuned coupling score cutoffs, IDR-DCA always showed better performance. The robustness of IDR-DCA was also supported through the MSA downsampling analysis. We further demonstrated the effectiveness of applying constraints obtained from residue pairs selected by IDR-DCA to assist RNA secondary structure prediction.

CoCoNet-boosting RNA contact prediction by convolutional neural networks

Co-evolutionary models such as direct coupling analysis (DCA) in combination with machine learning (ML) techniques based on deep neural networks are able to predict accurate protein contact or distance maps. Such information can be used as constraints in structure prediction and massively increase prediction accuracy. Unfortunately, the same ML methods cannot readily be applied to RNA as they rely on large structural datasets only available for proteins. Here, we demonstrate how the available smaller data for RNA can be used to improve prediction of RNA contact maps. We introduce an algorithm called CoCoNet that is based on a combination of a Coevolutionary model and a shallow Convolutional Neural Network. Despite its simplicity and the small number of trained parameters, the method boosts the positive predictive value (PPV) of predicted contacts by about 70% with respect to DCA as tested by cross-validation of about eighty RNA structures. However, the direct inclusion of the CoCoNet contacts in 3D modeling tools does not result in a proportional increase of the 3D RNA structure prediction accuracy. Therefore, we suggest that the field develops, in addition to contact PPV, metrics which estimate the expected impact for 3D structure modeling tools better. CoCoNet is freely available and can be found at https://github.com/KIT-MBS/coconet.

adabmDCA: adaptive Boltzmann machine learning for biological sequences

Background

Boltzmann machines are energy-based models that have been shown to provide an accurate statistical description of domains of evolutionary-related protein and RNA families. They are parametrized in terms of local biases accounting for residue conservation, and pairwise terms to model epistatic coevolution between residues. From the model parameters, it is possible to extract an accurate prediction of the three-dimensional contact map of the target domain. More recently, the accuracy of these models has been also assessed in terms of their ability in predicting mutational effects and generating in silico functional sequences.

Results

Our adaptive implementation of Boltzmann machine learning, adabmDCA, can be generally applied to both protein and RNA families and accomplishes several learning set-ups, depending on the complexity of the input data and on the user requirements. The code is fully available at https://github.com/anna-pa-m/adabmDCA. As an example, we have performed the learning of three Boltzmann machines modeling the Kunitz and Beta-lactamase2 protein domains and TPP-riboswitch RNA domain.

Conclusions

The models learned by adabmDCA are comparable to those obtained by state-of-the-art techniques for this task, in terms of the quality of the inferred contact map as well as of the synthetically generated sequences. In addition, the code implements both equilibrium and out-of-equilibrium learning, which allows for an accurate and lossless training when the equilibrium one is prohibitive in terms of computational time, and allows for pruning irrelevant parameters using an information-based criterion.

Probing allosteric regulations with coevolution-driven molecular simulations

Protein-mediated allosteric regulations are essential in biology, but their quantitative characterization continues to posit formidable challenges for both experiments and computations. Here, we combine coevolutionary information, multiscale molecular simulations, and free-energy methods to interrogate and quantify the allosteric regulation of functional changes in protein complexes. We apply this approach to investigate the regulation of adenylyl cyclase (AC) by stimulatory and inhibitory G proteins—a prototypical allosteric system that has long escaped from in-depth molecular characterization. We reveal a surprisingly simple ON/OFF regulation of AC functional dynamics through multiple pathways of information transfer. The binding of G proteins reshapes the free-energy landscape of AC following the classical population-shift paradigm. The model agrees with structural and biochemical data and reveals previously unknown experimentally consistent intermediates. Our approach showcases a general strategy to explore uncharted functional space in complex biomolecular regulations.

Pairing a high-resolution statistical potential with a nucleobase-centric sampling algorithm for improving RNA model refinement

Refining modelled structures to approach experimental accuracy is one of the most challenging problems in molecular biology. Despite many years’ efforts, the progress in protein or RNA structure refinement has been slow because the global minimum given by the energy scores is not at the experimentally determined “native” structure. Here, we propose a fully knowledge-based energy function that captures the full orientation dependence of base–base, base–oxygen and oxygen–oxygen interactions with the RNA backbone modelled by rotameric states and internal energies. A total of 4000 quantum-mechanical calculations were performed to reweight base–base statistical potentials for minimizing possible effects of indirect interactions. The resulting BRiQ knowledge-based potential, equipped with a nucleobase-centric sampling algorithm, provides a robust improvement in refining near-native RNA models generated by a wide variety of modelling techniques.

Predicting RNA structure from sequence is challenging due to the relative sparsity of experimentally-determined RNA 3D structures for model training. Here, the authors propose a way to incorporate knowledge on interactions at the atomic and base–base level to refine the prediction of RNA structures.

Evolutionary conservation of RNA sequence and structure

An RNA structure prediction from a single‐sequence RNA folding program is not evidence for an RNA whose structure is important for function. Random sequences have plausible and complex predicted structures not easily distinguishable from those of structural RNAs. How to tell when an RNA has a conserved structure is a question that requires looking at the evolutionary signature left by the conserved RNA. This question is important not just for long noncoding RNAs which usually lack an identified function, but also for RNA binding protein motifs which can be single stranded RNAs or structures. Here we review recent advances using sequence and structural analysis to determine when RNA structure is conserved or not. Although covariation measures assess structural RNA conservation, one must distinguish covariation due to RNA structure from covariation due to independent phylogenetic substitutions. We review a statistical test to measure false positives expected under the null hypothesis of phylogenetic covariation alone (specificity). We also review a complementary test that measures power, that is, expected covariation derived from sequence variation alone (sensitivity). Power in the absence of covariation signals the absence of a conserved RNA structure. We analyze artifacts that falsely identify conserved RNA structure such as the misuse of programs that do not assess significance, the use of inappropriate statistics confounded by signals other than covariation, or misalignments that induce spurious covariation. Among artifacts that obscure the signal of a conserved RNA structure, we discuss the inclusion of pseudogenes in alignments which increase power but destroy covariation.

This article is categorized under:

RNA Structure and Dynamics > RNA Structure, Dynamics and Chemistry

RNA Evolution and Genomics > Computational Analyses of RNA

RNA Evolution and Genomics > RNA and Ribonucleoprotein Evolution

Machine learning a model for RNA structure prediction

RNA function crucially depends on its structure. Thermodynamic models currently used for secondary structure prediction rely on computing the partition function of folding ensembles, and can thus estimate minimum free-energy structures and ensemble populations. These models sometimes fail in identifying native structures unless complemented by auxiliary experimental data. Here, we build a set of models that combine thermodynamic parameters, chemical probing data (DMS and SHAPE) and co-evolutionary data (direct coupling analysis) through a network that outputs perturbations to the ensemble free energy. Perturbations are trained to increase the ensemble populations of a representative set of known native RNA structures. In the chemical probing nodes of the network, a convolutional window combines neighboring reactivities, enlightening their structural information content and the contribution of local conformational ensembles. Regularization is used to limit overfitting and improve transferability. The most transferable model is selected through a cross-validation strategy that estimates the performance of models on systems on which they are not trained. With the selected model we obtain increased ensemble populations for native structures and more accurate predictions in an independent validation set. The flexibility of the approach allows the model to be easily retrained and adapted to incorporate arbitrary experimental information.

Evolution of frustrated and stabilising contacts in reconstructed ancient proteins

Energetic properties of a protein are a major determinant of its evolutionary fitness. Using a reconstruction algorithm, dating the reconstructed proteins and calculating the interaction network between their amino acids through a coevolutionary approach, we studied how the interactions that stabilise 890 proteins, belonging to five families, evolved for billions of years. In particular, we focused our attention on the network of most strongly attractive contacts and on that of poorly optimised, frustrated contacts. Our results support the idea that the cluster of most attractive interactions extends its size along evolutionary time, but from the data, we cannot conclude that protein stability or that the degree of frustration tends always to decrease.

DSSR-enabled innovative schematics of 3D nucleic acid structures with PyMOL

Sophisticated analysis and simplified visualization are crucial for understanding complicated structures of biomacromolecules. DSSR (Dissecting the Spatial Structure of RNA) is an integrated computational tool that has streamlined the analysis and annotation of 3D nucleic acid structures. The program creates schematic block representations in diverse styles that can be seamlessly integrated into PyMOL and complement its other popular visualization options. In addition to portraying individual base blocks, DSSR can draw Watson-Crick pairs as long blocks and highlight the minor-groove edges. Notably, DSSR can dramatically simplify the depiction of G-quadruplexes by automatically detecting G-tetrads and treating them as large square blocks. The DSSR-enabled innovative schematics with PyMOL are aesthetically pleasing and highly informative: the base identity, pairing geometry, stacking interactions, double-helical stems, and G-quadruplexes are immediately obvious. These features can be accessed via four interfaces: the command-line interface, the DSSR plugin for PyMOL, the web application, and the web application programming interface. The supplemental PDF serves as a practical guide, with complete and reproducible examples. Thus, even beginners or occasional users can get started quickly, especially via the web application at http://skmatic.x3dna.org.

Evaluating DCA-based method performances for RNA contact prediction by a well-curated data set

RNA molecules play many pivotal roles in a cell that are still not fully understood. Any detailed understanding of RNA function requires knowledge of its three-dimensional structure, yet experimental RNA structure resolution remains demanding. Recent advances in sequencing provide unprecedented amounts of sequence data that can be statistically analyzed by methods such as direct coupling analysis (DCA) to determine spatial proximity or contacts of specific nucleic acid pairs, which improve the quality of structure prediction. To quantify this structure prediction improvement, we here present a well curated data set of about 70 RNA structures of high resolution and compare different nucleotide-nucleotide contact prediction methods available in the literature. We observe only minor differences between the performances of the different methods. Moreover, we discuss how robust these predictions are for different contact definitions and how strongly they depend on procedures used to curate and align the families of homologous RNA sequences.