Evaluating native-like structures of RNA-protein complexes through the deep learning method

AI-integrated network for RNA complex structure and dynamic prediction

RNA complexes are essential components in many cellular processes. The functions of these complexes are linked to their tertiary structures, which are shaped by detailed interface information, such as binding sites, interface contact, and dynamic conformational changes. Network-based approaches have been widely used to analyze RNA complex structures. With their roots in the graph theory, these methods have a long history of providing insight into the static and dynamic properties of RNA molecules. These approaches have been effective in identifying functional binding sites and analyzing the dynamic behavior of RNA complexes. Recently, the advent of artificial intelligence (AI) has brought transformative changes to the field. These technologies have been increasingly applied to studying RNA complex structures, providing new avenues for understanding the complex interactions within RNA complexes. By integrating AI with traditional network analysis methods, researchers can build more accurate models of RNA complex structures, predict their dynamic behaviors, and even design RNA-based inhibitors. In this review, we introduce the integration of network-based methodologies with AI techniques to enhance the understanding of RNA complex structures. We examine how these advanced computational tools can be used to model and analyze the detailed interface information and dynamic behaviors of RNA molecules. Additionally, we explore the potential future directions of how AI-integrated networks can aid in the modeling and analyzing RNA complex structures.

Advances and Challenges in Scoring Functions for RNA-Protein Complex Structure Prediction

RNA-protein complexes play a crucial role in cellular functions, providing insights into cellular mechanisms and potential therapeutic targets. However, experimental determination of these complex structures is often time-consuming and resource-intensive, and it rarely yields high-resolution data. Many computational approaches have been developed to predict RNA-protein complex structures in recent years. Despite these advances, achieving accurate and high-resolution predictions remains a formidable challenge, primarily due to the limitations inherent in current RNA-protein scoring functions. These scoring functions are critical tools for evaluating and interpreting RNA-protein interactions. This review comprehensively explores the latest advancements in scoring functions for RNA-protein docking, delving into the fundamental principles underlying various approaches, including coarse-grained knowledge-based, all-atom knowledge-based, and machine-learning-based methods. We critically evaluate the strengths and limitations of existing scoring functions, providing a detailed performance assessment. Considering the significant progress demonstrated by machine learning techniques, we discuss emerging trends and propose future research directions to enhance the accuracy and efficiency of scoring functions in RNA-protein complex prediction. We aim to inspire the development of more sophisticated and reliable computational tools in this rapidly evolving field.

Generative language models on nucleotide sequences of human genes

Language models, especially transformer-based ones, have achieved colossal success in natural language processing. To be precise, studies like BERT for natural language understanding and works like GPT-3 for natural language generation are very important. If we consider DNA sequences as a text written with an alphabet of four letters representing the nucleotides, they are similar in structure to natural languages. This similarity has led to the development of discriminative language models such as DNABERT in the field of DNA-related bioinformatics. To our knowledge, however, the generative side of the coin is still largely unexplored. Therefore, we have focused on the development of an autoregressive generative language model such as GPT-3 for DNA sequences. Since working with whole DNA sequences is challenging without extensive computational resources, we decided to conduct our study on a smaller scale and focus on nucleotide sequences of human genes, i.e. unique parts of DNA with specific functions, rather than the whole DNA. This decision has not significantly changed the structure of the problem, as both DNA and genes can be considered as 1D sequences consisting of four different nucleotides without losing much information and without oversimplification. First of all, we systematically studied an almost entirely unexplored problem and observed that recurrent neural networks (RNNs) perform best, while simple techniques such as N-grams are also promising. Another beneficial point was learning how to work with generative models on languages we do not understand, unlike natural languages. The importance of using real-world tasks beyond classical metrics such as perplexity was noted. In addition, we examined whether the data-hungry nature of these models can be altered by selecting a language with minimal vocabulary size, four due to four different types of nucleotides. The reason for reviewing this was that choosing such a language might make the problem easier. However, in this study, we found that this did not change the amount of data required very much.

Predicting Small Molecule Binding Nucleotides in RNA Structures Using RNA Surface Topography

RNA small molecule interactions play a crucial role in drug discovery and inhibitor design. Identifying RNA small molecule binding nucleotides is essential and requires methods that exhibit a high predictive ability to facilitate drug discovery and inhibitor design. Existing methods can predict the binding nucleotides of simple RNA structures, but it is hard to predict binding nucleotides in complex RNA structures with junctions. To address this limitation, we developed a new deep learning model based on spatial correlation, ZHmolReSTasite, which can accurately predict binding nucleotides of small and large RNA with junctions. We utilize RNA surface topography to consider the spatial correlation, characterizing nucleotides from sequence and tertiary structures to learn a high-level representation. Our method outperforms existing methods for benchmark test sets composed of simple RNA structures, achieving precision values of 72.9% on TE18 and 76.7% on RB9 test sets. For a challenging test set composed of RNA structures with junctions, our method outperforms the second best method by 11.6% in precision. Moreover, ZHmolReSTasite demonstrates robustness regarding the predicted RNA structures. In summary, ZHmolReSTasite successfully incorporates spatial correlation, outperforms previous methods on small and large RNA structures using RNA surface topography, and can provide valuable insights into RNA small molecule prediction and accelerate RNA inhibitor design.

Single-sequence protein-RNA complex structure prediction by geometric attention-enabled pairing of biological language models

Ground-breaking progress has been made in structure prediction of biomolecular assemblies, including the recent breakthrough of AlphaFold 3. However, it remains challenging for AlphaFold 3 and other state-of-the-art deep learning-based methods to accurately predict protein-RNA complex structures, in part due to the limited availability of evolutionary and structural information related to protein-RNA interactions that are used as inputs to the existing approaches. Here, we introduce ProRNA3D-single, a new deep-learning framework for protein-RNA complex structure prediction with only single-sequence input. Using a novel geometric attention-enabled pairing of biological language models of protein and RNA, a previously unexplored avenue, ProRNA3D-single enables the prediction of interatomic protein-RNA interaction maps, which are then transformed into multi-scale geometric restraints for modeling 3D structures of protein-RNA complexes via geometry optimization. Benchmark tests show that ProRNA3D-single convincingly outperforms current state-of-the-art methods including AlphaFold 3, particularly when evolutionary information is limited; and exhibits remarkable robustness and performance resilience by attaining better accuracy with only single-sequence input than what most methods can achieve even with explicit evolutionary information. Freely available at https://github.com/Bhattacharya-Lab/ProRNA3D-single, ProRNA3D-single should be broadly useful for modeling 3D structures of protein-RNA complexes at scale, regardless of the availability of evolutionary information.

Review and Comparative Analysis of Methods and Advancements in Predicting Protein Complex Structure

Protein complexes perform diverse biological functions, and obtaining their three-dimensional structure is critical to understanding and grasping their functions. In many cases, it's not just two proteins interacting to form a dimer; instead, multiple proteins interact to form a multimer. Experimentally resolving protein complex structures can be quite challenging. Recently, there have been efforts and methods that build upon prior predictions of dimer structures to attempt to predict multimer structures. However, in comparison to monomeric protein structure prediction, the accuracy of protein complex structure prediction remains relatively low. This paper provides an overview of recent advancements in efficient computational models for predicting protein complex structures. We introduce protein-protein docking methods in detail and summarize their main ideas, applicable modes, and related information. To enhance prediction accuracy, other critical protein-related information is also integrated, such as predicting interchain residue contact, utilizing experimental data like cryo-EM experiments, and considering protein interactions and non-interactions. In addition, we comprehensively review computational approaches for end-to-end prediction of protein complex structures based on artificial intelligence (AI) technology and describe commonly used datasets and representative evaluation metrics in protein complexes. Finally, we analyze the formidable challenges faced in current protein complex structure prediction tasks, including the structure prediction of heteromeric complex, disordered regions in complex, antibody-antigen complex, and RNA-related complex, as well as the evaluation metrics for complex assessment. We hope that this work will provide comprehensive knowledge of complex structure predictions to contribute to future advanced predictions.

Mitochondrial RNA Helicases: Key Players in the Regulation of Plant Organellar RNA Splicing and Gene Expression

Mitochondrial genomes of land plants are large and exhibit a complex mode of gene organization and expression, particularly at the post-transcriptional level. The primary organellar transcripts in plants undergo extensive maturation steps, including endo- and/or exo-nucleolytic cleavage, RNA-base modifications (mostly C-to-U deaminations) and both 'cis'- and 'trans'-splicing events. These essential processing steps rely on the activities of a large set of nuclear-encoded factors. RNA helicases serve as key players in RNA metabolism, participating in the regulation of transcription, mRNA processing and translation. They unwind RNA secondary structures and facilitate the formation of ribonucleoprotein complexes crucial for various stages of gene expression. Furthermore, RNA helicases are involved in RNA metabolism by modulating pre-mRNA maturation, transport and degradation processes. These enzymes are, therefore, pivotal in RNA quality-control mechanisms, ensuring the fidelity and efficiency of RNA processing and turnover in plant mitochondria. This review summarizes the significant roles played by helicases in regulating the highly dynamic processes of mitochondrial transcription, RNA processing and translation in plants. We further discuss recent advancements in understanding how dysregulation of mitochondrial RNA helicases affects the splicing of organellar genes, leading to respiratory dysfunctions, and consequently, altered growth, development and physiology of land plants.

HIPPO: HIstogram-based Pseudo-POtential for scoring protein-ssRNA fragment-based docking poses

BACKGROUND

The RNA-Recognition motif (RRM) is a protein domain that binds single-stranded RNA (ssRNA) and is present in as much as 2% of the human genome. Despite this important role in biology, RRM-ssRNA interactions are very challenging to study on the structural level because of the remarkable flexibility of ssRNA. In the absence of atomic-level experimental data, the only method able to predict the 3D structure of protein-ssRNA complexes with any degree of accuracy is ssRNA'TTRACT, an ssRNA fragment-based docking approach using ATTRACT. However, since ATTRACT parameters are not ssRNA-specific and were determined in 2010, there is substantial opportunity for enhancement.

RESULTS

Here we present HIPPO, a composite RRM-ssRNA scoring potential derived analytically from contact frequencies in near-native versus non-native docking models. HIPPO consists of a consensus of four distinct potentials, each extracted from a distinct reference pool of protein-trinucleotide docking decoys. To score a docking pose with one potential, for each pair of RNA-protein coarse-grained bead types, each contact is awarded or penalised according to the relative frequencies of this contact distance range among the correct and incorrect poses of the reference pool. Validated on a fragment-based docking benchmark of 57 experimentally solved RRM-ssRNA complexes, HIPPO achieved a threefold or higher enrichment for half of the fragments, versus only a quarter with the ATTRACT scoring function. In particular, HIPPO drastically improved the chance of very high enrichment (12-fold or higher), a scenario where the incremental modelling of entire ssRNA chains from fragments becomes viable. However, for the latter result, more research is needed to make it directly practically applicable. Regardless, our approach already improves upon the state of the art in RRM-ssRNA modelling and is in principle extendable to other types of protein-nucleic acid interactions.

PRA-Pred: Structure-based prediction of protein-RNA binding affinity

Understanding crucial factors that affect the binding affinity of protein-RNA complexes is vital for comprehending their recognition mechanisms. This study involved compiling experimentally measured binding affinity (ΔG) values of 217 protein-RNA complexes and extracting numerous structure-based features, considering RNA, protein, and interactions between protein and RNA. Our findings indicate the significance of RNA base-step parameters, interaction energies, number of atomic contacts in the complex, hydrogen bonds, and contact potentials in understanding the binding affinity. Further, we observed that these factors are influenced by the type of RNA strand and the function of the protein in a protein-RNA complex. Multiple regression equations were developed for different classes of complexes to perform the prediction of the binding affinity between the protein and RNA. We evaluated the models using the jack-knife test and achieved an overall correlation 0.77 between the experimental and predicted binding affinities with a mean absolute error of 1.02 kcal/mol. Furthermore, we introduced a web server, PRA-Pred, intended for the prediction of protein-RNA binding affinity, and it is freely accessible through https://web.iitm.ac.in/bioinfo2/prapred/. We propose that our approach could function as a potential resource for investigating protein-RNA recognitions and developing therapeutic strategies.

Prediction of protein-ligand binding affinity via deep learning models

Accurately predicting the binding affinity between proteins and ligands is crucial in drug screening and optimization, but it is still a challenge in computer-aided drug design. The recent success of AlphaFold2 in predicting protein structures has brought new hope for deep learning (DL) models to accurately predict protein-ligand binding affinity. However, the current DL models still face limitations due to the low-quality database, inaccurate input representation and inappropriate model architecture. In this work, we review the computational methods, specifically DL-based models, used to predict protein-ligand binding affinity. We start with a brief introduction to protein-ligand binding affinity and the traditional computational methods used to calculate them. We then introduce the basic principles of DL models for predicting protein-ligand binding affinity. Next, we review the commonly used databases, input representations and DL models in this field. Finally, we discuss the potential challenges and future work in accurately predicting protein-ligand binding affinity via DL models.

A novel approach to study multi-domain motions in JAK1's activation mechanism based on energy landscape

The family of Janus Kinases (JAKs) associated with the JAK-signal transducers and activators of transcription signaling pathway plays a vital role in the regulation of various cellular processes. The conformational change of JAKs is the fundamental steps for activation, affecting multiple intracellular signaling pathways. However, the transitional process from inactive to active kinase is still a mystery. This study is aimed at investigating the electrostatic properties and transitional states of JAK1 to a fully activation to a catalytically active enzyme. To achieve this goal, structures of the inhibited/activated full-length JAK1 were modelled and the energies of JAK1 with Tyrosine Kinase (TK) domain at different positions were calculated, and Dijkstra's method was applied to find the energetically smoothest path. Through a comparison of the energetically smoothest paths of kinase inactivating P733L and S703I mutations, an evaluation of the reasons why these mutations lead to negative or positive regulation of JAK1 are provided. Our energy analysis suggests that activation of JAK1 is thermodynamically spontaneous, with the inhibition resulting from an energy barrier at the initial steps of activation, specifically the release of the TK domain from the inhibited Four-point-one, Ezrin, Radixin, Moesin-PK cavity. Overall, this work provides insights into the potential pathway for TK translocation and the activation mechanism of JAK1.

Evaluation of DNA-protein complex structures using the deep learning method

Biological processes such as transcription, repair, and regulation require interactions between DNA and proteins. To unravel their functions, it is imperative to determine the high-resolution structures of DNA-protein complexes. However, experimental methods for this purpose are costly and technically demanding. Consequently, there is an urgent need for computational techniques to identify the structures of DNA-protein complexes. Despite technological advancements, accurately identifying DNA-protein complexes through computational methods still poses a challenge. Our team has developed a cutting-edge deep-learning approach called DDPScore that assesses DNA-protein complex structures. DDPScore utilizes a 4D convolutional neural network to overcome limited training data. This approach effectively captures local and global features while comprehensively considering the conformational changes arising from the flexibility during the DNA-protein docking process. DDPScore consistently outperformed the available methods in comprehensive DNA-protein complex docking evaluations, even for the flexible docking challenges. DDPScore has a wide range of applications in predicting and designing structures of DNA-protein complexes.

Challenges in structural modeling of RNA-protein interactions

In the past few years, the number of RNA-binding proteins (RBP) and RNA-RBP interactions has increased significantly. Here, we review recent developments in the methodology for protein-RNA and protein-protein complex structure modeling with deep learning and co-evolution, as well as discuss the challenges and opportunities for building a reliable approach for protein-RNA complex structure modelling. Protein Data bank (PDB) and Cross-linking immunoprecipitation (CLIP) data could be combined together and used to infer 2D geometry of protein-RNA interactions by deep learning.

Computational Modeling of DNA 3D Structures: From Dynamics and Mechanics to Folding

DNA carries the genetic information required for the synthesis of RNA and proteins and plays an important role in many processes of biological development. Understanding the three-dimensional (3D) structures and dynamics of DNA is crucial for understanding their biological functions and guiding the development of novel materials. In this review, we discuss the recent advancements in computer methods for studying DNA 3D structures. This includes molecular dynamics simulations to analyze DNA dynamics, flexibility, and ion binding. We also explore various coarse-grained models used for DNA structure prediction or folding, along with fragment assembly methods for constructing DNA 3D structures. Furthermore, we also discuss the advantages and disadvantages of these methods and highlight their differences.

RPflex: A Coarse-Grained Network Model for RNA Pocket Flexibility Study

RNA regulates various biological processes, such as gene regulation, RNA splicing, and intracellular signal transduction. RNA’s conformational dynamics play crucial roles in performing its diverse functions. Thus, it is essential to explore the flexibility characteristics of RNA, especially pocket flexibility. Here, we propose a computational approach, RPflex, to analyze pocket flexibility using the coarse-grained network model. We first clustered 3154 pockets into 297 groups by similarity calculation based on the coarse-grained lattice model. Then, we introduced the flexibility score to quantify the flexibility by global pocket features. The results show strong correlations between the flexibility scores and root-mean-square fluctuation (RMSF) values, with Pearson correlation coefficients of 0.60, 0.76, and 0.53 in Testing Sets I–III. Considering both flexibility score and network calculations, the Pearson correlation coefficient was increased to 0.71 in flexible pockets on Testing Set IV. The network calculations reveal that the long-range interaction changes contributed most to flexibility. In addition, the hydrogen bonds in the base–base interactions greatly stabilize the RNA structure, while backbone interactions determine RNA folding. The computational analysis of pocket flexibility could facilitate RNA engineering for biological or medical applications.

Methods and Applications in Proteins and RNAs

Proteins and RNAs are primary biomolecules that are involved in most biological processes [...]