HydRA: Deep-learning models for predicting RNA-binding capacity from protein interaction association context and protein sequence

Key RNA-binding proteins in renal fibrosis: a comprehensive bioinformatics and machine learning framework for diagnostic and therapeutic insights

BACKGROUND

Renal fibrosis is a critical factor in chronic kidney disease progression, with limited diagnostic and therapeutic options. Emerging evidence suggests RNA-binding proteins (RBPs) are pivotal in regulating cellular mechanisms underlying fibrosis.

METHODS

Utilizing an extensive GEO dataset (175 renal fibrosis and 99 normal kidney samples), we identified and validated key RBPs through integrated bioinformatics and machine learning approaches, including lasso and logistic regression models. Differentially expressed genes were analyzed for pathway enrichment using Gene Ontology and KEGG. Single-cell RNA sequencing delineated cell-specific RBP expression, and a murine unilateral ureteral obstruction (UUO) model provided experimental validation.

RESULTS

A diagnostic model incorporating five RBPs (FKBP11, DCDC2, COL6A3, PLCB4, and GNB5) achieved high accuracy (AUC = 0.899) and robust external validation. These RBPs are implicated in immune-mediated pathways such as cytokine signaling and inflammatory responses. Single-cell analysis highlighted their expression in specific renal cell populations, underscoring functional diversity. Immunofluorescence linked FKBP11 with macrophage infiltration, suggesting its potential as a therapeutic target.

CONCLUSION

his study identifies novel RBPs associated with renal fibrosis, advancing the understanding of its pathogenesis and offering actionable biomarkers and therapeutic targets. The integration of bioinformatics and machine learning emphasizes their translational potential in kidney care.

RegRNA 3.0: expanding regulatory RNA analysis with new features for motif, interaction, and annotation

Functional RNA molecules are crucial for biological processes from gene regulation to protein synthesis, and analyzing functional motifs and elements is essential for understanding RNA regulation. Building on RegRNA 1.0 and 2.0, we present RegRNA 3.0, a sophisticated meta-workflow that integrates 26 computational tools and 28 databases for annotation, enabling one-step and customizable RNA motif predictions. RegRNA streamlines multi-step analysis and enhances result interpretation with interactive visualizations and comprehensive reporting tools. When provided with an RNA sequence, RegRNA 3.0 generates predictions for RNA functional motifs, RNA interaction motifs, and comprehensive RNA annotations. Specifically, RNA functional motifs include core promoter elements, RNA decay, G-quadruplex, and 14 previous types. RNA interaction motifs include newly added RNA-ligand interactions and RNA-binding protein predictions, along with three previous types. RNA annotation includes RNA family classification, blood exosomes RNA, subcellular localizations, A-to-I editing events, modifications, and 3D structures, along with four previously supported features. RegRNA 3.0 accelerates gene regulation and RNA biology discoveries by offering a user-friendly platform for identifying and analyzing RNA motifs and interactions. The web interface has been improved for intuitive visualizations of predicted motifs and structures, with flexible download options in multiple formats. It is available at http://awi.cuhk.edu.cn/∼RegRNA/.

An atlas of RNA-dependent proteins in cell division reveals the riboregulation of mitotic protein-protein interactions

Ribonucleoprotein complexes are dynamic assemblies of RNA with RNA-binding proteins, which modulate the fate of RNA. Inversely, RNA riboregulates the interactions and functions of the associated proteins. Dysregulation of ribonucleoprotein functions is linked to diseases such as cancer and neurological disorders. In dividing cells, RNA and RNA-binding proteins are present in mitotic structures, but their impact on cell division remains unclear. By applying the proteome-wide R-DeeP strategy to cells synchronized in mitosis versus interphase integrated with the RBP2GO knowledge, we provided an atlas of RNA-dependent proteins in cell division, accessible at R-DeeP3.dkfz.de. We uncovered AURKA, KIFC1 and TPX2 as unconventional RNA-binding proteins. KIFC1 was identified as a new substrate of AURKA, and new TPX2-interacting protein. Their pair-wise interactions were RNA dependent. In addition, RNA stimulated AURKA kinase activity and stabilized its conformation. In this work, we highlighted riboregulation of major mitotic factors as an additional complexity level of cell division.

RNA sequence analysis landscape: A comprehensive review of task types, databases, datasets, word embedding methods, and language models

Deciphering information of RNA sequences reveals their diverse roles in living organisms, including gene regulation and protein synthesis. Aberrations in RNA sequence such as dysregulation and mutations can drive a diverse spectrum of diseases including cancers, genetic disorders, and neurodegenerative conditions. Furthermore, researchers are harnessing RNA's therapeutic potential for transforming traditional treatment paradigms into personalized therapies through the development of RNA-based drugs and gene therapies. To gain insights of biological functions and to detect diseases at early stages and develop potent therapeutics, researchers are performing diverse types RNA sequence analysis tasks. RNA sequence analysis through conventional wet-lab methods is expensive, time-consuming and error prone. To enable large-scale RNA sequence analysis, empowerment of wet-lab experimental methods with Artificial Intelligence (AI) applications necessitates scientists to have a comprehensive knowledge of both DNA and AI fields. While molecular biologists encounter challenges in understanding AI methods, computer scientists often lack basic foundations of RNA sequence analysis tasks. Considering the absence of a comprehensive literature that bridges this research gap and promotes the development of AI-driven RNA sequence analysis applications, the contributions of this manuscript are manifold: It equips AI researchers with biological foundations of 47 distinct RNA sequence analysis tasks. It sets a stage for development of benchmark datasets related to 47 distinct RNA sequence analysis tasks by facilitating cruxes of 64 different biological databases. It presents word embeddings and language models applications across 47 distinct RNA sequence analysis tasks. It streamlines the development of new predictors by providing a comprehensive survey of 58 word embeddings and 70 language models based predictive pipelines performance values as well as top performing traditional sequence encoding based predictors and their performances across 47 RNA sequence analysis tasks.

Translation efficiency covariation across cell types is a conserved organizing principle of mammalian transcriptomes

Characterization of shared patterns of RNA expression between genes across conditions has led to the discovery of regulatory networks and novel biological functions. However, it is unclear if such coordination extends to translation, a critical step in gene expression. Here, we uniformly analyzed 3,819 ribosome profiling datasets from 117 human and 94 mouse tissues and cell lines. We introduce the concept of Translation Efficiency Covariation (TEC), identifying coordinated translation patterns across cell types. We nominate potential mechanisms driving shared patterns of translation regulation. TEC is conserved across human and mouse cells and helps uncover gene functions. Moreover, our observations indicate that proteins that physically interact are highly enriched for positive covariation at both translational and transcriptional levels. Our findings establish translational covariation as a conserved organizing principle of mammalian transcriptomes.

Inhibition of RNA splicing triggers CHMP7 nuclear entry, impacting TDP-43 function and leading to the onset of ALS cellular phenotypes

Amyotrophic lateral sclerosis (ALS) is linked to the reduction of certain nucleoporins in neurons. Increased nuclear localization of charged multivesicular body protein 7 (CHMP7), a protein involved in nuclear pore surveillance, has been identified as a key factor damaging nuclear pores and disrupting transport. Using CRISPR-based microRaft, followed by gRNA identification (CRaft-ID), we discovered 55 RNA-binding proteins (RBPs) that influence CHMP7 localization, including SmD1, a survival of motor neuron (SMN) complex component. Immunoprecipitation-mass spectrometry (IP-MS) and enhanced crosslinking and immunoprecipitation (CLIP) analyses revealed CHMP7's interactions with SmD1, small nuclear RNAs, and splicing factor mRNAs in motor neurons (MNs). ALS induced pluripotent stem cell (iPSC)-MNs show reduced SmD1 expression, and inhibiting SmD1/SMN complex increased CHMP7 nuclear localization. Crucially, overexpressing SmD1 in ALS iPSC-MNs restored CHMP7's cytoplasmic localization and corrected STMN2 splicing. Our findings suggest that early ALS pathogenesis is driven by SMN complex dysregulation.

Role of RNA-binding Proteins in Regulating Cell Adhesion and Progression of the Atherosclerotic Plaque and Plaque Erosion

PURPOSE OF REVIEW

RNA-binding proteins (RBPs) have emerged as crucial regulators of post-transcriptional processes, influencing the fate of RNA. This review delves into the biological functions of RBPs and their role in alternative splicing concerning atherosclerosis (AS), highlighting their participation in essential cellular processes. Our goal is to offer new insights for cardiovascular disease research and treatment.

RECENT FINDING

Dysregulation of RBPs is associated with various human diseases, including autoimmune and neurological disorders. The role of RBPs in the pathogenesis of AS is progressively being elucidated, as they influence plaque formation and disease progression by regulating cell function and gene expression. RBPs play intricate biological roles in regulating pre-mRNA, including editing, splicing, stability and translation. Alternative splicing has been demonstrated to enhance biological complexity and diversity. Our findings indicate that alternative splicing is extensively involved in the pathogenesis of AS. The dysregulated expression of specific RBPs in AS is linked to the production of adhesion molecules and vascular endothelium damage. Further research on RBPs could pave the way for the development of novel therapeutic targets.

Integrated Biochemical and Computational Methods for Deciphering RNA-Processing Codes

RNA processing involves steps such as capping, splicing, polyadenylation, modification, and nuclear export. These steps are essential for transforming genetic information in DNA into proteins and contribute to RNA diversity and complexity. Many biochemical methods have been developed to profile and quantify RNAs, as well as to identify the interactions between RNAs and RNA-binding proteins (RBPs), especially when coupled with high-throughput sequencing technologies. With the rapid accumulation of diverse data, it is crucial to develop computational methods to convert the big data into biological knowledge. In particular, machine learning and deep learning models are commonly utilized to learn the rules or codes governing the transformation from DNA sequences to intriguing RNAs based on manually designed or automatically extracted features. When precise enough, the RNA codes can be incredibly useful for predicting RNA products, decoding the molecular mechanisms, forecasting the impact of disease variants on RNA processing events, and identifying driver mutations. In this review, we systematically summarize the biochemical and computational methods for deciphering five important RNA codes related to alternative splicing, alternative polyadenylation, RNA localization, RNA modifications, and RBP binding. For each code, we review the main types of experimental methods used to generate training data, as well as the key features, strategic model structures, and advantages of representative tools. We also discuss the challenges encountered in developing predictive models using large language models and extensive domain knowledge. Additionally, we highlight useful resources and propose ways to improve computational tools for studying RNA codes.

Large-scale map of RNA-binding protein interactomes across the mRNA life cycle

mRNAs interact with RNA-binding proteins (RBPs) throughout their processing and maturation. While efforts have assigned RBPs to RNA substrates, less exploration has leveraged protein-protein interactions (PPIs) to study proteins in mRNA life-cycle stages. We generated an RNA-aware, RBP-centric PPI map across the mRNA life cycle in human cells by immunopurification-mass spectrometry (IP-MS) of ∼100 endogenous RBPs with and without RNase, augmented by size exclusion chromatography-mass spectrometry (SEC-MS). We identify 8,742 known and 20,802 unreported interactions between 1,125 proteins and determine that 73% of the IP-MS-identified interactions are RNA regulated. Our interactome links many proteins, some with unknown functions, to specific mRNA life-cycle stages, with nearly half associated with multiple stages. We demonstrate the value of this resource by characterizing the splicing and export functions of enhancer of rudimentary homolog (ERH), and by showing that small nuclear ribonucleoprotein U5 subunit 200 (SNRNP200) interacts with stress granule proteins and binds cytoplasmic RNA differently during stress.

Integrated multi-omics analysis of zinc-finger proteins uncovers roles in RNA regulation

RNA interactome studies have revealed that hundreds of zinc-finger proteins (ZFPs) are candidate RNA-binding proteins (RBPs), yet their RNA substrates and functional significance remain largely uncharacterized. Here, we present a systematic multi-omics analysis of the DNA- and RNA-binding targets and regulatory roles of more than 100 ZFPs representing 37 zinc-finger families. We show that multiple ZFPs are previously unknown regulators of RNA splicing, alternative polyadenylation, stability, or translation. The examined ZFPs show widespread sequence-specific RNA binding and preferentially bind proximal to transcription start sites. Additionally, several ZFPs associate with their targets at both the DNA and RNA levels. We highlight ZNF277, a C2H2 ZFP that binds thousands of RNA targets and acts as a multi-functional RBP. We also show that ZNF473 is a DNA/RNA-associated protein that regulates the expression and splicing of cell cycle genes. Our results reveal diverse roles for ZFPs in transcriptional and post-transcriptional gene regulation.

pyRBDome: a comprehensive computational platform for enhancing RNA-binding proteome data

High-throughput proteomics approaches have revolutionised the identification of RNA-binding proteins (RBPome) and RNA-binding sequences (RBDome) across organisms. Yet, the extent of noise, including false positives, associated with these methodologies, is difficult to quantify as experimental approaches for validating the results are generally low throughput. To address this, we introduce pyRBDome, a pipeline for enhancing RNA-binding proteome data in silico. It aligns the experimental results with RNA-binding site (RBS) predictions from distinct machine-learning tools and integrates high-resolution structural data when available. Its statistical evaluation of RBDome data enables quick identification of likely genuine RNA-binders in experimental datasets. Furthermore, by leveraging the pyRBDome results, we have enhanced the sensitivity and specificity of RBS detection through training new ensemble machine-learning models. pyRBDome analysis of a human RBDome dataset, compared with known structural data, revealed that although UV-cross-linked amino acids were more likely to contain predicted RBSs, they infrequently bind RNA in high-resolution structures. This discrepancy underscores the limitations of structural data as benchmarks, positioning pyRBDome as a valuable alternative for increasing confidence in RBDome datasets.

An atlas of RNA-dependent proteins in cell division reveals the riboregulation of mitotic protein-protein interactions

Ribonucleoprotein complexes are dynamic assemblies of RNA with RNA-binding proteins (RBPs), which can modulate the fate of the RNA molecules from transcription to degradation. Vice versa, RNA can regulate the interactions and functions of the associated proteins. Dysregulation of RBPs is linked to diseases such as cancer and neurological disorders. RNA and RBPs are present in mitotic structures like the centrosomes and spindle microtubules, but their influence on mitotic spindle integrity remains unknown. Thus, we applied the R-DeeP strategy for the proteome-wide identification of RNA-dependent proteins and complexes to cells synchronized in mitosis versus interphase. The resulting atlas of RNA-dependent proteins in cell division can be accessed through the R-DeeP 3.0 database (R-DeeP3.dkfz.de). It revealed key mitotic factors as RNA-dependent such as AURKA, KIFC1 and TPX2 that were linked to RNA despite their lack of canonical RNA-binding domains. KIFC1 was identified as a new interaction partner and phosphorylation substrate of AURKA at S349 and T359. In addition, KIFC1 interacted with both, AURKA and TPX2, in an RNA-dependent manner. Our data suggest a riboregulation of mitotic protein-protein interactions during spindle assembly, offering new perspectives on the control of cell division processes by RNA-protein complexes.

RBPs: an RNA editor's choice

RNA-binding proteins (RBPs) play a key role in gene expression and post-transcriptional RNA regulation. As integral components of ribonucleoprotein complexes, RBPs are susceptible to genomic and RNA Editing derived amino acid substitutions, impacting functional interactions. This article explores the prevalent RNA Editing of RBPs, unravelling the complex interplay between RBPs and RNA Editing events. Emphasis is placed on their influence on single amino acid variants (SAAVs) and implications for disease development. The role of Proteogenomics in identifying SAAVs is briefly discussed, offering insights into the RBP landscape. RNA Editing within RBPs emerges as a promising target for precision medicine, reshaping our understanding of genetic and epigenetic variations in health and disease.

Diagnosis and Molecular Characterization of Potential RNA Binding Protein Involved in the Pathogenesis of Liver Ischemia Reperfusion Injury

Background

Liver ischemia-reperfusion is one of the common complications after liver surgery. Uncontrolled liver ischemia-reperfusion will lead to many serious consequences such as surgical failure. It is an urgent clinical problem to search for diagnostic markers and explore its potential pathogenesis.

Methods

In this study, we focus on 1411 candidate RNA binding protein. Through several GEO (Gene Expression Omnibus) online datasets, we construct a diagnostic model and perform interactive validation. We evaluate the efficacy of the prognostic model. Using bioinformatics methods, we predicted the relevant signaling pathways of liver ischemia-reperfusion and key genes. We also evaluated the association of RNA binding protein with immune cell infiltration. Single cell sequencing datasets were used to explore the expression profiles of key genes at the single cell level. Machine learning algorithm is used to predict key gene RNA binding domains.

Results

ROC (Receiver Operating Characteristic) and DCA (Decision Curve Analysis) curves showed that the above diagnostic model had good and stable diagnostic efficacy and clinical practicability. We identified three key genes (BTG2, CCNL1 and DNAJB1) in liver ischemia-reperfusion. DNAJB1, BTG2 and CCNL1 are mainly expressed in immune cells such as macrophages and T cells, and are closely related to inflammatory pathways such as TNF-α, highlighting their importance in hepatic ischemia reperfusion. We identified RNA-binding domains of the above three genes. We found that the expression of DNAJB1, CCNL1 and BTG2 in the ischemia-reperfusion group were significantly higher than those in the sham operation group.

Conclusion

Our study revealed the importance of the candidate RNA binding protein in liver ischemia reperfusion injury and provided new insights into the therapeutic of hepatic ischemia-reperfusion injury.

Refining the pool of RNA-binding domains advances the classification and prediction of RNA-binding proteins

From transcription to decay, RNA-binding proteins (RBPs) influence RNA metabolism. Using the RBP2GO database that combines proteome-wide RBP screens from 13 species, we investigated the RNA-binding features of 176 896 proteins. By compiling published lists of RNA-binding domains (RBDs) and RNA-related protein family (Rfam) IDs with lists from the InterPro database, we analyzed the distribution of the RBDs and Rfam IDs in RBPs and non-RBPs to select RBDs and Rfam IDs that were enriched in RBPs. We also explored proteins for their content in intrinsically disordered regions (IDRs) and low complexity regions (LCRs). We found a strong positive correlation between IDRs and RBDs and a co-occurrence of specific LCRs. Our bioinformatic analysis indicated that RBDs/Rfam IDs were strong indicators of the RNA-binding potential of proteins and helped predicting new RBP candidates, especially in less investigated species. By further analyzing RBPs without RBD, we predicted new RBDs that were validated by RNA-bound peptides. Finally, we created the RBP2GO composite score by combining the RBP2GO score with new quality factors linked to RBDs and Rfam IDs. Based on the RBP2GO composite score, we compiled a list of 2018 high-confidence human RBPs. The knowledge collected here was integrated into the RBP2GO database at https://RBP2GO-2-Beta.dkfz.de.

Oligomerization regulates the interaction of Gemin5 with members of the SMN complex and the translation machinery

RNA-binding proteins are multifunctional molecules impacting on multiple steps of gene regulation. Gemin5 was initially identified as a member of the survival of motor neurons (SMN) complex. The protein is organized in structural and functional domains, including a WD40 repeats domain at the N-terminal region, a tetratricopeptide repeat (TPR) dimerization module at the central region, and a non-canonical RNA-binding site at the C-terminal end. The TPR module allows the recruitment of the endogenous Gemin5 protein in living cells and the assembly of a dimer in vitro. However, the biological relevance of Gemin5 oligomerization is not known. Here we interrogated the Gemin5 interactome focusing on oligomerization-dependent or independent regions. We show that the interactors associated with oligomerization-proficient domains were primarily annotated to ribosome, splicing, translation regulation, SMN complex, and RNA stability. The presence of distinct Gemin5 protein regions in polysomes highlighted differences in translation regulation based on their oligomerization capacity. Furthermore, the association with native ribosomes and negative regulation of translation was strictly dependent on both the WD40 repeats domain and the TPR dimerization moiety, while binding with the majority of the interacting proteins, including SMN, Gemin2, and Gemin4, was determined by the dimerization module. The loss of oligomerization did not perturb the predominant cytoplasmic localization of Gemin5, reinforcing the cytoplasmic functions of this essential protein. Our work highlights a distinctive role of the Gemin5 domains for its functions in the interaction with members of the SMN complex, ribosome association, and RBP interactome.

Big data and deep learning for RNA biology

The exponential growth of big data in RNA biology (RB) has led to the development of deep learning (DL) models that have driven crucial discoveries. As constantly evidenced by DL studies in other fields, the successful implementation of DL in RB depends heavily on the effective utilization of large-scale datasets from public databases. In achieving this goal, data encoding methods, learning algorithms, and techniques that align well with biological domain knowledge have played pivotal roles. In this review, we provide guiding principles for applying these DL concepts to various problems in RB by demonstrating successful examples and associated methodologies. We also discuss the remaining challenges in developing DL models for RB and suggest strategies to overcome these challenges. Overall, this review aims to illuminate the compelling potential of DL for RB and ways to apply this powerful technology to investigate the intriguing biology of RNA more effectively.

Deep Learning for Elucidating Modifications to RNA-Status and Challenges Ahead

RNA-binding proteins and chemical modifications to RNA play vital roles in the co- and post-transcriptional regulation of genes. In order to fully decipher their biological roles, it is an essential task to catalogue their precise target locations along with their preferred contexts and sequence-based determinants. Recently, deep learning approaches have significantly advanced in this field. These methods can predict the presence or absence of modification at specific genomic regions based on diverse features, particularly sequence and secondary structure, allowing us to decipher the highly non-linear sequence patterns and structures that underlie site preferences. This article provides an overview of how deep learning is being applied to this area, with a particular focus on the problem of mRNA-RBP binding, while also considering other types of chemical modification to RNA. It discusses how different types of model can handle sequence-based and/or secondary-structure-based inputs, the process of model training, including choice of negative regions and separating sets for testing and training, and offers recommendations for developing biologically relevant models. Finally, it highlights four key areas that are crucial for advancing the field.

Exploring new roles for RNA-binding proteins in epigenetic and gene regulation

A significant portion of the human proteome comprises RNA-binding proteins (RBPs) that play fundamental roles in numerous biological processes. In the last decade, there has been a staggering increase in RBP identification and classification, which has fueled interest in the evolving roles of RBPs and RBP-driven molecular mechanisms. Here, we focus on recent insights into RBP-dependent regulation of the epigenetic and transcriptional landscape. We describe advances in methodologies that define the RNA-protein interactome and machine-learning algorithms that are streamlining RBP discovery and predicting new RNA-binding regions. Finally, we present how RBP dysregulation leads to alterations in tumor-promoting gene expression and discuss the potential for targeting these RBPs for the development of new cancer therapeutics.