Biology subjects

Marsico, A.

Publications and source records attributed to Marsico, A..

At least 19 recordsLinked to original sources

bioRxiv2026

PARNET: A CLIP-SEQ-BASED FOUNDATION MODEL FOR RNA SEQUENCE REPRESENTATION LEARNING

RNA-binding proteins (RBPs) orchestrate a complex combinatorial regulatory "code" that governs RNA splicing, stability, localization, and translation. Learning the relationship between RNA sequences and these processes is a central challenge in genomics. Foundation models, notably RNA language models, have emerged as the dominant approach, learning general-purpose representations from unlabeled sequence at scale. While RNA language models have demonstrated impressive performance across a broad range of downstream tasks, they generally learn from sequence reconstruction objectives alone, lacking direct connections to the regulatory principles that govern RNA function. Here we introduce Parnet, an RNA foundation model trained directly and exclusively on experimental CLIP-seq data. Parnet is a multi-task foundation model trained end-to-end on 223 eCLIP-seq experiments spanning 150 RBPs to predict base-resolution RBP binding profiles directly from RNA sequence. This CLIP-seq pretraining strategy departs fundamentally from the masked-language-modeling paradigm, anchoring learned RNA representations directly in measured protein-RNA interactions rather than sequence statistics. Parnet substantially outperforms its single-task predecessor RBPNet in binding profile and motif recovery, generalizes to unseen cell types and iCLIP data, and recapitulates position-dependent splicing regulation. Frozen Parnet embeddings, without task-specific fine-tuning, match or exceed the performance of both task-specific tools, as well as larger self-supervised RNA and genomic language models across diverse downstream tasks, including RNA biotype classification, lncRNA chromatin localization, translational efficiency, splice-site recognition, intron retention, and non-coding variant effect prediction. Importantly, Parnet remains mechanistically interpretable, tracing predictions back to the specific RBPs and motifs that drive them. These results establish the RBP interactome as a compact, functionally sufficient, and interpretable basis for foundation model pretraining in RNA biology.

bioinformatics↗

bioRxiv2026

Organisational principles of long non-coding RNAs revealed by exon deletion

Long non-coding RNAs (lncRNAs) regulate cell phenotypes in health and disease, yet how function is encoded in their sequence remains poorly understood. Current models propose a modular architecture composed of discrete functional elements, but this is based on a limited set of paradigmatic examples and methods for mapping function to sequence are limited in scope and resolution. Here, we establish a high-throughput CRISPR-Cas9 strategy for dissecting lncRNA functional architecture at exon resolution. Using cell fitness as a phenotypic readout, we screened 358 exons from 107 lncRNAs across four human cell lines. We report that (1) a large proportion of exons have no detectable function, (2) a minority of exons are functional in any given cell line (19-111 exons), equivalent to one-fifth of total transcript nucleotides on average, and (3) functionality is enriched towards the 5 end of the transcript. We developed a database of putative lncRNA functional elements, ElementaLdb, and demonstrated through statistical and experimental analyses that lncRNA function depends on transposable elements, microRNA response elements and RNA binding protein sites. These sub-genic functional maps expand the catalogue of experimentally defined lncRNA functional elements by an order of magnitude, illuminate molecular mechanisms and broadly support a modular organisation for lncRNAs.

genomics↗

bioRxiv2026

FENNEC: Fine-Tuned Ensemble Neural Networks Accelerate Chemically Modified siRNA Design and Screening

Small interfering RNAs (siRNAs) are a clinically validated therapeutic modality, yet designing potent chemically modified siRNAs remains a costly and iterative process, limited by scarce public data. Computational prediction of siRNA efficacy is therefore essential for rational design and accelerated preclinical development. However, despite the critical role of chemical modifications in therapeutic performance, current state-of-the-art machine learning methods either are not designed to model the chemical diversity of therapeutic siRNAs, or exhibit poor generalization performance. Here, we present FENNEC (Fine-Tuned Ensemble of Neural Networks for siRNA Efficiency Characterization), a machine-learning framework for predicting siRNA activity across chemically diverse design spaces. To support this effort, we curated the largest patent-derived dataset to date of chemically modified siRNAs from 42 patents using OCR-based table extraction and stringent filtering. FENNEC combines temporal convolutional networks with thermodynamic descriptors, experimental covariates, and embeddings from RNA foundation models to capture both local chemical determinants and broader target-context information. Importantly, we show that language-model-derived embeddings provide meaningful higher-order representations of target transcripts, particularly in data-scarce settings. FENNEC achieved robust predictive performance across both gene-level and scaffold-level validation settings, with additional experimental validation on a novel AHSA1-targeting dataset further supporting its generalizability across chemically modified siRNAs. In benchmarking, FENNEC outperformed classical machine-learning and state-of-the-art deep learning models, demonstrating generalization to unseen chemistry. Model interpretation recovered established design principles, including position-specific effects of glycol nucleic acid, 2'-fluoro modifications, and phosphorothioate backbones. Furthermore, in silico perturbation analyses suggest that FENNEC can serve not only as a predictive model, but also as an oracle for the design and optimization of chemically modified siRNAs. Together, our work addresses a key gap in the field by enabling chemically aware deep learning for siRNA design, supported by a large and diverse collection of chemically modified siRNA measurements.

bioinformatics↗

bioRxiv2026

Pan-cancer discovery of driver mutations in long noncoding RNAs reveals widespread functional rewiring of RNA regulatory elements

Most somatic mutations in cancer occur outside protein-coding genes, yet the functional impact of these mutations remains largely unknown. Long noncoding RNAs (lncRNAs) represent a major class of cancer-promoting genes whose molecular mechanisms are poorly understood. While individual driver mutations in lncRNAs have been identified, detecting such driver lncRNAs at scale requires large tumour genome cohorts. We analyse 12,631 cancer genomes from the 100,000 Genomes Project (100kGP) and identify 121 lncRNAs under positive selection across 19 cancer types. These driver lncRNAs are independently supported by functional genomic screens, germline predisposing variants, mutual exclusivity with protein-coding drivers, and independent oncogenic lncRNA catalogues. Overall, approximately two-thirds of analysed tumours harbour at least one lncRNA driver mutation. Leveraging the depth of this dataset, we demonstrate that somatic mutations preferentially target and remodel RNA-binding protein (RBP) interaction sites to potentiate oncogenic lncRNAs, including MALAT1, SNHG14 and NEAT1. From these data, we derive a model in which somatic mutations liberate oncogenic lncRNAs from repressive RNA:protein interactions. This work expands the number and nature of cancer driver genes, identifies targets for RNA-directed therapies, and demonstrates that with large tumour mutation catalogues we can dissect the molecular mechanisms of noncoding genes.

Cancer Biology↗

bioRxiv2026

RIBEX: Predicting and Explaining RNA Binding Across Structured and Intrinsically Disordered Regions (IDR)-rich Proteins

MotivationRNA-binding proteins (RBPs) regulate post-transcriptional processes, yet many remain undiscovered because RNA-binding activity often occurs outside canonical RNA-binding domains (RBDs), including within intrinsically disordered regions (IDRs) or through protein complexes. Computational methods can help identify novel RBPs, but approaches relying solely on sequence-derived features or ignoring the cellular interaction context are limited in capturing the complexity of RNA-binding behavior. To date, no framework rigorously integrates both sequence information and protein interaction context for RBP prediction. ResultsWe introduce RIBEX, a multimodal framework that combines protein language model (pLM) embeddings with protein interactome topology to improve RBP prediction and interpretation. Specifically, we integrate sequence representations with graph-derived positional encodings (PE) from the human STRING protein-protein interaction (PPI) network. PE are computed using Personalized PageRank, reduced with principal component analysis, and fused with pooled sequence embeddings through FiLM conditioning, while Low-Rank Adaptation (LoRA) enables parameter-efficient task adaptation. Across both an annotation-based benchmark and experimental RNA Interactome Capture (RIC) dataset, PE consistently improves predictive performance, indicating that interactome topology provides complementary information beyond sequence features. LoRA adaptation of ESM2-650M further yields larger gains than simply scaling frozen backbone size. RIBEX outperforms state-of-the-art methods such as RBP-TSTL and HydRA, particularly on challenging subsets including proteins lacking canonical RBDs and those enriched in IDRs. For interpretability, we combine sequence-level computational alanine scanning with network-level positional-encoding ablation and inverse-PCA mapping, recovering known RNA-binding domains, IDR-associated contributions, and functional interactome communities linked to RBP predictions.

bioinformatics↗

bioRxiv2026

Integration of single-cell multi-omic data with graph-based topic modelling

Recent advances in single-cell biology enable the profiling of multiple molecular layers, such as the transcriptome, epigenome, and surface proteins, within a single cell. Tackling the complexity of these data from different perspectives allows researchers to get the most complete insights into the biological properties of cells. Here, we propose a graph-based topic modelling method called bionSBM. Our method leverages well-known community-detection methods for multipartite graphs and the interpretability of topic modelling to cluster and explain high-dimensional, sparse, and noisy single-cell matrices. We applied our algorithm to paired single-cell multi-omics data, such as 10X Multiome, SHARE-seq, and CITE-seq. We showed that it achieves superior performance compared to state-of-the-art methods for ground-truth label retrieval, with high specificity and distinct biological interpretability.

bioinformatics↗

bioRxiv2026

miRXplain: explainable isomiR-aware microRNA target prediction using CLIP-L experiments and hybrid attention transformers

MicroRNAs (miRNAs) are ~22 nt long noncoding RNAs that repress genes by base-pairing with complementary sequences in target mRNAs. Variants known as isomiRs arise from alternative hairpin processing and often shift the canonical seed region, thereby altering their target repertoire. Yet, the mRNA features that enable differential miRNA and isomiR target selection remain poorly understood, largely due to limited high-throughput assays that capture the exact miRNA bound to each target. Existing deep learning methods for miRNA-target prediction have neither leveraged such datasets nor investigated isomiR-specific interactions. To fill this gap, we developed miRXplain, an isomiR-aware transformer that predicts miRNA-mRNA interactions using miRNA and target sequences derived from CLIP-L data, directly linking precise miRNA variants to their target sites. These data however revealed a 5'-end nucleotide bias in target sites, which we corrected to generate high-quality, miRNA-target pairs for training, preserving isomiR-specific signal. miRXplain outperformed all benchmarked models, surpassing TEC-miTarget, in auROC and auPRC with 15x fewer parameters. Attention maps highlighted distinct sequence determinants for canonical versus isomiR interactions, and in silico saturation mutagenesis highlighted the importance of seed and 3' supplementary regions. miRXplain effectively prioritizes pathogenic single-nucleotide variants affecting mRNA-miRNA interactions and reveals isomiR targeting principles that deepen our understanding of miRNA biology.

bioinformatics↗

bioRxiv2025

Integrative Gene and Isoform Co-expression Networks Reveal Regulatory Rewiring in Stress-related Psychiatric Disorders

Isoform-specific expression patterns have been implicated in stress-related psychiatric disorders like major depressive disorder (MDD), yet the extent of their involvement and their interrelationships remain unclear. We constructed co-expression networks for individuals affected (n=210, 81% with depressive symptoms) and unaffected (n=95) by stress-related psychiatric disorders. We incorporated total gene expression (TE) and isoform ratio (IR) data and validated the inferred networks using advanced graph generation techniques. Our analysis revealed distinct network topology and structure between the two groups. Investigation of the 127 shared hubs (degree >= 10) found that these hubs exhibit co-regulatory patterns unique to each network. The affected individuals network also contained 61 hub nodes with a minimum absolute fold increase of two in connectivity compared to the unaffected individuals network. Notably, 49% of these hubs showed evidence for association with psychiatric disorders. Gene Ontology enrichment analysis revealed distinct biological processes associated with hubs, such as mRNA processing for affected and immune response and cell adhesion for unaffected individuals. Enrichment analysis of GWAS loci further supported network-specific findings. Analysis of the isoform-specific nodes showed distinct protein-protein interactions compared to gene-level analysis. This is the first study to demonstrate network-level differences in gene and isoform co-expression patterns between individuals with and without stress-related psychiatric disorders, with a particular focus on depressive symptoms. Our findings provide evidence for substantial rewiring of gene regulatory networks in affected individuals. Incorporating isoform-level data revealed a deeper level of complexity, highlighting the importance of considering isoform variations in understanding the molecular basis of these conditions.

systems biology↗

bioRxiv2024

Path-based reasoning in biomedical knowledge graphs

Understanding complex interactions in biomedical networks is crucial for advancements in biomedicine, but traditional link prediction (LP) methods are limited in capturing this complexity. Representation-based learning techniques improve prediction accuracy by mapping nodes to low-dimensional embeddings, yet they often struggle with interpretability and scalability. We present BioPathNet, a novel graph neural network framework based on the Neural Bellman-Ford Network (NBFNet), addressing these limitations through path-based reasoning for LP in biomedical knowledge graphs. Unlike node-embedding frameworks, BioPathNet learns representations between node pairs by considering all relations along paths, enhancing prediction accuracy and interpretability. This allows visualization of influential paths and facilitates biological validation. BioPathNet leverages a background regulatory graph (BRG) for enhanced message passing and uses stringent negative sampling to improve precision. In evaluations across various LP tasks, such as gene function annotation, drug-disease indication, synthetic lethality, and lncRNA-mRNA interaction prediction, BioPathNet consistently outperformed shallow node embedding methods, relational graph neural networks and task-specific state-of-the-art methods, demonstrating robust performance and versatility. Our study predicts novel drug indications for diseases like acute lymphoblastic leukemia (ALL) and Alzheimers, validated by medical experts and clinical trials. We also identified new synthetic lethality gene pairs and regulatory interactions involving lncRNAs and target genes, confirmed through literature reviews. BioPathNets interpretability will enable researchers to trace prediction paths and gain molecular insights, making it a valuable tool for drug discovery, personalized medicine and biology in general.

bioinformatics↗

bioRxiv2023

Combinatorial microRNA activity is essential for the transition of pluripotent cells from proliferation into dormancy

Dormancy is a key feature of stem cell function in adult tissues as well as embryonic cells in the context of diapause. The establishment of dormancy is an active process that involves extensive transcriptional, epigenetic, and metabolic rewiring1,2. How these processes are coordinated to successfully transition cells to the resting dormant state remains unclear. Here we show that microRNA activity, which is otherwise dispensable for pre-implantation development, is essential for the adaptation of early mouse embryos to the dormant state of diapause. In particular, the pluripotent epiblast depends on miRNA activity, the absence of which results in loss of pluripotent cells. Through integration of high-sensitivity small RNA expression profiling of individual embryos and protein expression of miRNA targets with public data of protein-protein interactions, we constructed the miRNA-mediated regulatory network of mouse early embryos specific to diapause. We find that individual miRNAs contribute to the combinatorial regulation by the network and the perturbation of the network compromises embryo survival in diapause. Without miRNAs, nuclear and cytoplasmic bodies show aberrant expression, concurrent with splicing defects. We identified the nutrient-sensitive transcription factor TFE3 as an upstream regulator of diapause-specific miRNAs, linking cytoplasmic mTOR activity to nuclear miRNA biogenesis. Our results place miRNAs as a critical regulatory layer for the molecular rewiring of early embryos to establish dormancy.

molecular biology↗

bioRxiv2023

A Systematic Benchmark of Machine Learning Methods for Protein-RNA Interaction Prediction

AO_SCPLOWBSTRACTC_SCPLOWRNA-binding proteins (RBPs) are central actors of RNA post-transcriptional regulation. Experiments to profile binding sites of RBPs in vivo are limited to transcripts expressed in the experimental cell type, creating the need for computational methods to infer missing binding information. While numerous machine-learning based methods have been developed for this task, their use of heterogeneous training and evaluation datasets across different sets of RBPs and CLIP-seq protocols makes a direct comparison of their performance difficult. Here, we compile a set of 37 machine learning (primarily deep learning) methods for in vivo RBP-RNA interaction prediction and systematically benchmark a subset of 11 representative methods across hundreds of CLIP-seq datasets and RBPs. Using homogenized sample pre-processing and two negative-class sample generation strategies, we evaluate methods in terms of predictive performance and assess the impact of neural network architectures and input modalities on model performance. We believe that this study will not only enable researchers to choose the optimal prediction method for their tasks at hand, but also aid method developers in developing novel, high-performing methods by introducing a standardized framework for their evaluation.

bioinformatics↗

bioRxiv2022

Towards In-Silico CLIP-seq: Predicting Protein-RNA Interaction via Sequence-to-Signal Learning

AO_SCPLOWBSTRACTC_SCPLOWUnraveling sequence determinants which drive protein-RNA interaction is crucial for studying binding mechanisms and the impact of genomic variants. While CLIP-seq allows for transcriptome-wide profiling of in vivo protein-RNA interactions, it is limited to expressed transcripts, requiring computational imputation of missing binding information. Existing classification-based methods predict binding with low resolution and depend on prior labeling of transcriptome regions for training. We present RBPNet, a novel deep learning method, which predicts CLIP crosslink count distribution from RNA sequence at single-nucleotide resolution. By training on up to a million regions, RBPNet achieves high generalization on eCLIP, iCLIP and miCLIP assays, outperforming state-of-the-art classifiers. CLIP-seq suffers from various technical biases, complicating downstream interpretation. RBPNet performs bias correction by modeling the raw signal as a mixture of the protein-specific and background signal. Through model interrogation via Integrated Gradients, RBPNet identifies predictive sub-sequences corresponding to known binding motifs and enables variant-impact scoring via in silico mutagenesis. Together, RBPNet improves inference of protein-RNA interaction, as well as mechanistic interpretation of predictions.

bioinformatics↗

bioRxiv2021

Computational Mapping of the Human-SARS-CoV-2 Protein-RNA Interactome

Strong evidence suggests that human human RNA-binding proteins (RBPs) are critical factors for viral infection, yet there is no feasible experimental approach to map exact binding sites of RBPs across the SARS-CoV-2 genome systematically at a large scale. We investigated the role of RBPs in the context of SARS-CoV-2 by constructing the first in silico map of human RBP / viral RNA interactions at nucleotide-resolution using two deep learning methods (pysster and DeepRiPe) trained on data from CLIP-seq experiments. We evaluated conservation of RBP binding between 6 other human pathogenic coronaviruses and identified sites of conserved and differential binding in the UTRs of SARS-CoV-1, SARS-CoV-2 and MERS. We scored the impact of variants from 11 viral strains on protein-RNA interaction, identifying a set of gain-and loss of binding events. Lastly, we linked RBPs to functional data and OMICs from other studies, and identified MBNL1, FTO and FXR2 as potential clinical biomarkers. Our results contribute towards a deeper understanding of how viruses hijack host cellular pathways and are available through a comprehensive online resource (https://sc2rbpmap.helmholtz-muenchen.de).

bioinformatics↗

bioRxiv2021

Distal and proximal cis-regulatory elements sense X-chromosomal dosage and developmental state at the Xist locus

Developmental genes such as Xist, the master regulator of X-chromosome inactivation (XCI), are controlled by complex cis-regulatory landscapes, which decode multiple signals to establish specific spatio-temporal expression patterns. Xist integrates information on X-chromosomal dosage and developmental stage to trigger XCI at the primed pluripotent state in females only. Through a pooled CRISPR interference screen in differentiating mouse embryonic stem cells, we identify functional enhancer elements of Xist during the onset of random XCI. By quantifying how enhancer activity is modulated by X-dosage and differentiation, we find that X-dosage controls the promoter-proximal region in a binary switch-like manner. By contrast, differentiation cues activate a series of distal elements and bring them into closer spatial proximity of the Xist promoter. The strongest distal element is part of an enhancer cluster [~]200 kb upstream of the Xist gene which is associated with a previously unannotated Xist-enhancing regulatory transcript, we named Xert. Developmental cues and X-dosage are thus decoded by distinct regulatory regions, which cooperate to ensure female-specific Xist upregulation at the correct developmental time. Our study is the first step to disentangle how multiple, functionally distinct regulatory regions interact to generate complex expression patterns in mammals.

genomics↗

bioRxiv2020

Distinctive features of long non-coding RNA chromatin (dis-)association

Long non-coding RNAs (lncRNAs) are involved in gene expression regulation in cis and trans. Although enriched in the chromatin cell fraction, to what degree this defines their broad range of functions remains unclear. In addition, the factors that contribute to lncRNA chromatin tethering, as well as the molecular basis of efficient lncRNA chromatin dissociation and its functional impact on enhancer activity and target gene expression, remain to be resolved. Here, we combine pulse-chase metabolic labeling of nascent RNA with chromatin fractionation and transient transcriptome sequencing to follow nascent RNA transcripts from their co-transcriptional state to their release into the nucleoplasm. By incorporating functional and physical characteristics in machine learning models, we find that parameters like co-transcriptional splicing contributes to efficient lncRNA chromatin dissociation. Intriguingly, lncRNAs transcribed from enhancer-like regions display reduced chromatin retention, suggesting that, in addition to splicing, lncRNA chromatin dissociation may contribute to enhancer activity and target gene expression. HighlightsO_LIChromatin (dis-)association of lncRNAs can be modeled using nascent RNA sequencing from pulse-chase chromatin fractionation C_LIO_LIDistinct physical and functional characteristics contribute to lncRNA chromatin (dis-)association C_LIO_LIlncRNAs transcribed from enhancers display increased degree of chromatin dissociation C_LIO_LIlncRNAs of distinct degrees of chromatin association display differential binding probabilities for RNA-binding proteins (RBPs) C_LI

molecular biology↗

bioRxiv2020

Integrated analysis of Xist upregulation and gene silencing at the onset of random X-chromosome inactivation at high temporal and allelic resolution

To ensure dosage compensation between the sexes, one randomly chosen X chromosome is silenced in each female cell in the process of X-chromosome inactivation (XCI). XCI is initiated during early development through upregulation of the long non-coding RNA Xist, which mediates chromosome-wide gene silencing. Cell differentiation, Xist upregulation and silencing are thought to be coupled at multiple levels to ensure inactivation of exactly one out of two X chromosomes. Here we perform an integrated analysis of all three processes through allele-specific single-cell RNA-sequencing. Specifically, we assess the onset of random XCI with high temporal resolution in differentiating mouse embryonic stem cells, and develop dedicated analysis approaches. By exploiting the inter-cellular heterogeneity of XCI onset, we identify Nanog downregulation as its main trigger and discover additional putative Xist regulators. Moreover, we confirm several predictions of the stochastic model of XCI where monoallelic silencing is thought to be ensured through negative feedback regulation. Finally, we show that genetic variation modulates the XCI process at multiple levels, providing a potential explanation for the long-known Xce effect, which leads to preferential inactivation of a specific X chromosome in inter-strain crosses. We thus draw a detailed picture of the different levels of regulation that govern the initiation of XCI. The experimental and computational strategies we have developed here will allow us to profile random XCI in more physiological contexts, including primary human cells in vivo.

genomics↗

bioRxiv2019

Kinetics of Xist-induced gene silencing can be predicted from combinations of epigenetic and genomic features

To initiate X-chromosome inactivation (XCI), the long non-coding RNA Xist mediates chromosome-wide gene silencing of one X chromosome in female mammals to equalize gene dosage between the sexes. The efficiency of gene silencing, however is highly variable across genes, with some genes even escaping XCI in somatic cells. A genes susceptibility to Xist-mediated silencing appears to be determined by a complex interplay of epigenetic and genomic features; however, the underlying rules remain poorly understood. We have quantified chromosome-wide gene silencing kinetics at the level of the nascent transcriptome using allele-specific Precision nuclear Run-On sequencing (PRO-seq). We have developed a Random Forest machine learning model that can predict the measured silencing dynamics based on a large set of epigenetic and genomic features and tested its predictive power experimentally. While the genomic distance to the Xist locus is the prime determinant of the speed of gene silencing, we find that also pre-marking of gene promoters with polycomb complexes is associated with fast silencing. Moreover, a series of features associated with active transcription and the O-GlcNAc transferase Ogt are enriched at rapidly silenced genes. Our machine learning approach can thus uncover the complex combinatorial rules underlying gene silencing during X inactivation.

genomics↗

bioRxiv2018

TriPepSVM - de novo prediction of RNA-binding proteins based on short amino acid motifs

In recent years hundreds of novel RNA-binding proteins (RBPs) have been identified leading to the discovery of novel RNA-binding domains (RBDs). Furthermore, unstructured or disordered low-complexity regions of RBPs have been identified to play an important role in interactions with nucleic acids. However, these advances in understanding RBPs are limited mainly to eukaryotic species and we only have limited tools to faithfully predict RNA-binders from bacteria. Here, we describe a support vector machine (SVM)-based method, called TriPepSVM, for the classification of RNA-binding proteins and non-RBPs. TriPepSVM applies string kernels to directly handle protein sequences using tri-peptide frequencies. Testing the method in human and bacteria, we find that several RBP-enriched tripeptides occur more often in structurally disordered regions of RBPs. TriPepSVM outperforms existing applications, which consider classical structural features of RNA-binding or homology, in the task of RBP prediction in both human and bacteria. Finally, we predict 66 novel RBPs in Salmonella Typhimurium and validate the bacterial proteins ClpX, DnaJ and UbiG to associate with RNA in vivo.

bioinformatics↗