Browse
Submit Data
Databases
API
Help

Dataset Information

0 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Improved modeling of RNA-binding protein motifs in an interpretable neural model of RNA splicing.

ABSTRACT: Sequence-specific RNA-binding proteins (RBPs) play central roles in splicing decisions. Here, we describe a modular splicing architecture that leverages in vitro-derived RNA affinity models for 79 human RBPs and the annotated human genome to produce improved models of RBP binding and activity. Binding and activity are modeled by separate Motif and Aggregator components that can be mixed and matched, enforcing sparsity to improve interpretability. Training a new Adjusted Motif (AM) architecture on the splicing task not only yields better splicing predictions but also improves prediction of RBP-binding sites in vivo and of splicing activity, assessed using independent data.

SUBMITTER: Gupta K

PROVIDER: S-EPMC10790492 | biostudies-literature | 2024 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Publications

Improved modeling of RNA-binding protein motifs in an interpretable neural model of RNA splicing.

Gupta Kavi K Yang Chenxi C McCue Kayla K Bastani Osbert O Sharp Phillip A PA Burge Christopher B CB Solar-Lezama Armando A

Genome biology 20240116 1

Sequence-specific RNA-binding proteins (RBPs) play central roles in splicing decisions. Here, we describe a modular splicing architecture that leverages in vitro-derived RNA affinity models for 79 human RBPs and the annotated human genome to produce improved models of RBP binding and activity. Binding and activity are modeled by separate Motif and Aggregator components that can be mixed and matched, enforcing sparsity to improve interpretability. Training a new Adjusted Motif (AM) architecture o ...[more]

PMID: 38229106

Similar Datasets

An engineered RNA binding protein with improved splicing regulation.

Project description:The muscleblind-like (MBNL) family of proteins are key developmental regulators of alternative splicing. Sequestration of MBNL proteins by expanded CUG/CCUG repeat RNA transcripts is a major pathogenic mechanism in the neuromuscular disorder myotonic dystrophy (DM). MBNL1 contains four zinc finger (ZF) motifs that form two tandem RNA binding domains (ZF1-2 and ZF3-4) which each bind YGCY RNA motifs. In an effort to determine the differences in function between these domains, we designed and characterized synthetic MBNL proteins with duplicate ZF1-2 or ZF3-4 domains, referred to as MBNL-AA and MBNL-BB, respectively. Analysis of splicing regulation revealed that MBNL-AA had up to 5-fold increased splicing activity while MBNL-BB had 4-fold decreased activity compared to a MBNL protein with the canonical arrangement of zinc finger domains. RNA binding analysis revealed that the variations in splicing activity are due to differences in RNA binding specificities between the two ZF domains rather than binding affinity. Our findings indicate that ZF1-2 drives splicing regulation via recognition of YGCY RNA motifs while ZF3-4 acts as a general RNA binding domain. Our studies suggest that synthetic MBNL proteins with improved or altered splicing activity have the potential to be used as both tools for investigating splicing regulation and protein therapeutics for DM and other microsatellite diseases.

| S-EPMC5888374 | biostudies-literature

An interpretable RNA foundation model for exploring functional RNA motifs in plants.

Project description:The complex 'language' of plant RNA encodes a vast array of biological regulatory elements that orchestrate crucial aspects of plant growth, development and adaptation to environmental stresses. Recent advancements in foundation models (FMs) have demonstrated their unprecedented potential to decipher complex 'language' in biology. In this study, we introduced PlantRNA-FM, a high-performance and interpretable RNA FM specifically designed for plants. PlantRNA-FM was pretrained on an extensive dataset, integrating RNA sequences and RNA structure information from 1,124 distinct plant species. PlantRNA-FM exhibits superior performance in plant-specific downstream tasks. PlantRNA-FM achieves an F1 score of 0.974 for genic region annotation, whereas the current best-performing model achieves 0.639. Our PlantRNA-FM is empowered by our interpretable framework that facilitates the identification of biologically functional RNA sequence and structure motifs, including both RNA secondary and tertiary structure motifs across transcriptomes. Through experimental validations, we revealed translation-associated RNA motifs in plants. Our PlantRNA-FM also highlighted the importance of the position information of these functional RNA motifs in genic regions. Taken together, our PlantRNA-FM facilitates the exploration of functional RNA motifs across the complexity of transcriptomes, empowering plant scientists with capabilities for programming RNA codes in plants.

| S-EPMC11652376 | biostudies-literature

Improved analysis of (e)CLIP data with RCRUNCH yields a compendium of RNA-binding protein binding sites and motifs.

Project description:We present RCRUNCH, an end-to-end solution to CLIP data analysis for identification of binding sites and sequence specificity of RNA-binding proteins. RCRUNCH can analyze not only reads that map uniquely to the genome but also those that map to multiple genome locations or across splice boundaries and can consider various types of background in the estimation of read enrichment. By applying RCRUNCH to the eCLIP data from the ENCODE project, we have constructed a comprehensive and homogeneous resource of in-vivo-bound RBP sequence motifs. RCRUNCH automates the reproducible analysis of CLIP data, enabling studies of post-transcriptional control of gene expression.

| S-EPMC10108518 | biostudies-literature

Deciphering RNA splicing logic with interpretable machine learning.

Project description:Machine learning methods, particularly neural networks trained on large datasets, are transforming how scientists approach scientific discovery and experimental design. However, current state-of-the-art neural networks are limited by their uninterpretability: Despite their excellent accuracy, they cannot describe how they arrived at their predictions. Here, using an "interpretable-by-design" approach, we present a neural network model that provides insights into RNA splicing, a fundamental process in the transfer of genomic information into functional biochemical products. Although we designed our model to emphasize interpretability, its predictive accuracy is on par with state-of-the-art models. To demonstrate the model's interpretability, we introduce a visualization that, for any given exon, allows us to trace and quantify the entire decision process from input sequence to output splicing prediction. Importantly, the model revealed uncharacterized components of the splicing logic, which we experimentally validated. This study highlights how interpretable machine learning can advance scientific discovery.

| S-EPMC10576025 | biostudies-literature

Trans-regulation of RNA-binding protein motifs by microRNA.

Project description:The wide array of vital functions that RNA performs is dependent on its ability to dynamically fold into different structures in response to intracellular and extracellular changes. RNA-binding proteins regulate much of this activity by targeting specific RNA structures or motifs. One of these structures, the 3-way RNA junction, is characteristically found in ribosomal RNA and results from the RNA folding in cis, to produce three separate helices that meet around a central unpaired region. Here we demonstrate that 3-way junctions can also form in trans as a result of the binding of microRNAs in an unconventional manner with mRNA by splinting two non-contiguous regions together. This may be used to reinforce the base of a stem-loop motif being targeted by an RNA-binding protein. Trans interactions between non-coding RNA and mRNA may be used to control the post-transcriptional regulatory code and suggests a possible role for some of the recently described transcripts of unknown function expressed from the human genome.

| S-EPMC4006066 | biostudies-literature

dSreg: a Bayesian model to integrate changes in splicing and RNA-binding protein activity.

Project description:MOTIVATION:Alternative splicing (AS) is an important mechanism in the generation of transcript diversity across mammals. AS patterns are dynamically regulated during development and in response to environmental changes. Defects or perturbations in its regulation may lead to cancer or neurological disorders, among other pathological conditions. The regulatory mechanisms controlling AS in a given biological context are typically inferred using a two-step framework: differential AS analysis followed by enrichment methods. These strategies require setting rather arbitrary thresholds and are prone to error propagation along the analysis. RESULTS:To overcome these limitations, we propose dSreg, a Bayesian model that integrates RNA-seq with data from regulatory features, e.g. binding sites of RNA-binding proteins. dSreg identifies the key underlying regulators controlling AS changes and quantifies their activity while simultaneously estimating the changes in exon inclusion rates. dSreg increased both the sensitivity and the specificity of the identified AS changes in simulated data, even at low read coverage. dSreg also showed improved performance when analyzing a collection of knock-down RNA-binding proteins' experiments from ENCODE, as opposed to traditional enrichment methods, such as over-representation analysis and gene set enrichment analysis. dSreg opens the possibility to integrate a large amount of readily available RNA-seq datasets at low coverage for AS analysis and allows more cost-effective RNA-seq experiments. AVAILABILITY AND IMPLEMENTATION:dSreg was implemented in python using stan and is freely available to the community at https://bitbucket.org/cmartiga/dsreg. SUPPLEMENTARY INFORMATION:Supplementary data are available at Bioinformatics online.

| S-EPMC7141860 | biostudies-literature

RNANetMotif: Identifying sequence-structure RNA network motifs in RNA-protein binding sites.

Project description:RNA molecules can adopt stable secondary and tertiary structures, which are essential in mediating physical interactions with other partners such as RNA binding proteins (RBPs) and in carrying out their cellular functions. In vivo and in vitro experiments such as RNAcompete and eCLIP have revealed in vitro binding preferences of RBPs to RNA oligomers and in vivo binding sites in cells. Analysis of these binding data showed that the structure properties of the RNAs in these binding sites are important determinants of the binding events; however, it has been a challenge to incorporate the structure information into an interpretable model. Here we describe a new approach, RNANetMotif, which takes predicted secondary structure of thousands of RNA sequences bound by an RBP as input and uses a graph theory approach to recognize enriched subgraphs. These enriched subgraphs are in essence shared sequence-structure elements that are important in RBP-RNA binding. To validate our approach, we performed RNA structure modeling via coarse-grained molecular dynamics folding simulations for selected 4 RBPs, and RNA-protein docking for LIN28B. The simulation results, e.g., solvent accessibility and energetics, further support the biological relevance of the discovered network subgraphs.

| S-EPMC9275694 | biostudies-literature

Coding relationship links RNA G-quadruplexes and protein RGG motifs in RNA-binding protein autoregulation.

Project description:RNA G-quadruplexes (rG4s), the four-stranded structures formed by guanine-rich RNA sequences, are recognized by regions in RNA-binding proteins (RBPs) that are enriched in arginine-glycine repeats (RGG motifs). Importantly, arginine and glycine are encoded by guanine-rich codons, suggesting that some RGG motifs may both be encoded by and interact with rG4s in autogenous messenger RNAs (mRNAs). By analyzing transcriptome-wide rG4 datasets, we show that hundreds of RGG motifs in humans are at least partly encoded by rG4s, with an increased incidence for longer RGG motifs (~10 or more residues). Using randomized genetic codes, we demonstrate that the rG4/RGG coding relationship derives from the universal genetic code's structure. Moreover, we show that proteins, which contain RGG motifs encoded by experimentally detected rG4s, are significantly enriched in RNA binding relative to all RGG-containing proteins. Finally, using enhanced crosslinking and immunoprecipitation (eCLIP) data, we identify several prominent RBPs, including FUS, FMRP, and G3BP1, which interact with autogenous mRNAs in regions where RGG motifs are encoded by rG4s. Our results define a physically realistic mechanism behind autogenous mRNA/protein interactions that is hardwired in the genetic code structure and may contribute to the establishment of autoregulatory feedback loops in the cell.

| S-EPMC11789052 | biostudies-literature

EquiPNAS: improved protein-nucleic acid binding site prediction using protein-language-model-informed equivariant deep graph neural networks.

Project description:Protein language models (pLMs) trained on a large corpus of protein sequences have shown unprecedented scalability and broad generalizability in a wide range of predictive modeling tasks, but their power has not yet been harnessed for predicting protein-nucleic acid binding sites, critical for characterizing the interactions between proteins and nucleic acids. Here, we present EquiPNAS, a new pLM-informed E(3) equivariant deep graph neural network framework for improved protein-nucleic acid binding site prediction. By combining the strengths of pLM and symmetry-aware deep graph learning, EquiPNAS consistently outperforms the state-of-the-art methods for both protein-DNA and protein-RNA binding site prediction on multiple datasets across a diverse set of predictive modeling scenarios ranging from using experimental input to AlphaFold2 predictions. Our ablation study reveals that the pLM embeddings used in EquiPNAS are sufficiently powerful to dramatically reduce the dependence on the availability of evolutionary information without compromising on accuracy, and that the symmetry-aware nature of the E(3) equivariant graph-based neural architecture offers remarkable robustness and performance resilience. EquiPNAS is freely available at https://github.com/Bhattacharya-Lab/EquiPNAS.

| S-EPMC10954458 | biostudies-literature

EquiPNAS: improved protein-nucleic acid binding site prediction using protein-language-model-informed equivariant deep graph neural networks.

Project description:Protein language models (pLMs) trained on a large corpus of protein sequences have shown unprecedented scalability and broad generalizability in a wide range of predictive modeling tasks, but their power has not yet been harnessed for predicting protein-nucleic acid binding sites, critical for characterizing the interactions between proteins and nucleic acids. Here we present EquiPNAS, a new pLM-informed E(3) equivariant deep graph neural network framework for improved protein-nucleic acid binding site prediction. By combining the strengths of pLM and symmetry-aware deep graph learning, EquiPNAS consistently outperforms the state-of-the-art methods for both protein-DNA and protein-RNA binding site prediction on multiple datasets across a diverse set of predictive modeling scenarios ranging from using experimental input to AlphaFold2 predictions. Our ablation study reveals that the pLM embeddings used in EquiPNAS are sufficiently powerful to dramatically reduce the dependence on the availability of evolutionary information without compromising on accuracy, and that the symmetry-aware nature of the E(3) equivariant graph-based neural architecture offers remarkable robustness and performance resilience. EquiPNAS is freely available at https://github.com/Bhattacharya-Lab/EquiPNAS.

| S-EPMC10515942 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data