Unstructured linker regions play a role in the differential splicing activities of paralogous RNA binding proteins PTBP1 and PTBP2.

RNA Binding Proteins regulate, in part, alternative pre-mRNA splicing and, in turn, gene expression patterns. Polypyrimidine tract binding proteins PTBP1 and PTBP2 are paralogous RNA binding proteins sharing 74% amino acid sequence identity. Both proteins contain four structured RNA-recognition motifs (RRMs) connected by linker regions and an N-terminal region. Despite their similarities, the paralogs have distinct tissue-specific expression patterns and can regulate discrete sets of target exons. How two highly structurally similar proteins can exert different splicing outcomes is not well understood. Previous studies revealed that PTBP2 is post-translationally phosphorylated in the unstructured N-terminal, Linker 1, and Linker 2 regions that share less sequence identity with PTBP1 signifying a role for these regions in dictating the paralog's distinct splicing activities. To this end, we conducted bioinformatics analysis to determine the evolutionary conservation of RRMs versus linker regions in PTBP1 and PTBP2 across species. To determine the role of PTBP2 unstructured regions in splicing activity, we created hybrid PTBP1-PTBP2 constructs that had counterpart PTBP1 regions swapped to an otherwise PTBP2 protein and assayed on differentially regulated exons. We also conducted molecular dynamics studies to investigate how negative charges introduced by phosphorylation in PTBP2 unstructured regions can alter their physical properties. Collectively, results from our studies reveal an important role for PTBP2 unstructured regions and suggest a role for phosphorylation in the differential splicing activities of the paralogs on certain regulated exons.

Polypyrimidine tract binding protein 1 (PTBP1) contains a novel regulatory sequence, the rBH3, that binds the prosurvival protein MCL1.

The maturation of RNA from its nascent transcription to ultimate utilization (e.g., translation, miR-mediated RNA silencing, etc.) involves an intricately coordinated series of biochemical reactions regulated by RNA-binding proteins (RBPs). Over the past several decades, there has been extensive effort to elucidate the biological factors that control specificity and selectivity of RNA target binding and downstream function. Polypyrimidine tract binding protein 1 (PTBP1) is an RBP that is involved in all steps of RNA maturation and serves as a key regulator of alternative splicing, and therefore, understanding its regulation is of critical biologic importance. While several mechanisms of RBP specificity have been proposed (e.g., cell-specific expression of RBPs and secondary structure of target RNA), recently, protein-protein interactions with individual domains of RBPs have been suggested to be important determinants of downstream function. Here, we demonstrate a novel binding interaction between the first RNA recognition motif 1 (RRM1) of PTBP1 and the prosurvival protein myeloid cell leukemia-1 (MCL1). Using both in silico and in vitro analyses, we demonstrate that MCL1 binds a novel regulatory sequence on RRM1. NMR spectroscopy reveals that this interaction allosterically perturbs key residues in the RNA-binding interface of RRM1 and negatively impacts RRM1 association with target RNA. Furthermore, pulldown of MCL1 by endogenous PTBP1 verifies that these proteins interact in an endogenous cellular environment, establishing the biological relevance of this binding event. Overall, our findings suggest a novel mechanism of regulation of PTBP1 in which a protein-protein interaction with a single RRM can impact RNA association.

The latest role of nerve-specific splicing factor PTBP1 in the transdifferentiation of glial cells into neurons.

Central nervous system injury diseases can cause the loss of many neurons, and it is difficult to regenerate. The field of regenerative medicine believes that supplementing the missing neurons may be an ideal method for nerve injury repair. Recent studies have found that down-regulation of polypyrimidine tract binding protein 1 (PTBP1) expression can make glial cells transdifferentiate into different types of neurons, which is expected to be an alternative therapy to restore neuronal function. This article summarized the research progress on the structure and biological function of the PTBP family, the mutual regulation of PTBP1 and PTBP2, their role in neurogenesis, and the latest research progress in targeting PTBP1 to mediate the transdifferentiation of glial cells into neurons, which may provide some new strategies and new ideas for the future treatment of central nervous system injury and neurodegenerative diseases. This article is categorized under: RNA Processing > Splicing Regulation/Alternative Splicing.

Allosteric mechanism for SL RNA recognition by polypyrimidine tract binding protein RRM1: An atomistic MD simulation and network-based study.

Polypyrimidine tract-binding protein (PTB), an RNA-binding protein, is involved in the regulation of diverse processes in mRNA metabolism. However, the allosteric modulation of its binding with RNA remains unclear. We explore the dynamic characteristics of PTB RNA recognition motif 1 (RRM1) in its RNA-free and wild-type/mutant RNA-bound states to understand the issues using molecular dynamics (MD) simulation, perturbation response scanning (PRS) and protein structure network (PSN) models. It is found that RNA binding strengthens RRM1 stability, while L151G mutation in α3 helix far away from the interface makes the complex unstable. The latter is caused by long-distance dynamic couplings, which makes intermolecular electrostatic and entropy energies unfavorable. The weakened couplings between interface ß sheets and C-terminal parts upon mutation reveal RNA recognition is co-regulated by these regions. Interestingly, PRS analysis reveals the allostery caused by the perturbation on α3 helix has already been pre-encoded in the equilibrium dynamics of the protein structure. PSN analysis shows the details of the allosteric signal transmission, revealing the necessity of strong couplings between α3 helix and interface for maintaining the high binding affinity. This study sheds light on the mechanisms of PTB allostery and RNA recognition and can provide important information for drug design.

Polypyrimidine-Tract-Binding Protein Isoforms Differentially Regulate the Hepatitis C Virus Internal Ribosome Entry Site.

Translation initiation of the hepatitis C virus (HCV) mRNA depends on an internal ribosome entry site (IRES) that encompasses most of the 5'UTR and includes nucleotides of the core coding region. This study shows that the polypyrimidine-tract-binding protein (PTB), an RNA-binding protein with four RNA recognition motifs (RRMs), binds to the HCV 5'UTR, stimulating its IRES activity. There are three isoforms of PTB: PTB1, PTB2, and PTB4. Our results show that PTB1 and PTB4, but not PTB2, stimulate HCV IRES activity in HuH-7 and HEK293T cells. In HuH-7 cells, PTB1 promotes HCV IRES-mediated initiation more strongly than PTB4. Mutations in PTB1, PTB4, RRM1/RRM2, or RRM3/RRM4, which disrupt the RRM's ability to bind RNA, abrogated the protein's capacity to stimulate HCV IRES activity in HuH-7 cells. In HEK293T cells, PTB1 and PTB4 stimulate HCV IRES activity to similar levels. In HEK293T cells, mutations in RRM1/RRM2 did not impact PTB1's ability to promote HCV IRES activity; and mutations in PTB1 RRM3/RRM4 domains reduced, but did not abolish, the protein's capacity to stimulate HCV IRES activity. In HEK293T cells, mutations in PTB4 RRM1/RRM2 abrogated the protein's ability to promote HCV IRES activity, and mutations in RRM3/RRM4 have no impact on PTB4 ability to enhance HCV IRES activity. Therefore, PTB1 and PTB4 differentially stimulate the IRES activity in a cell type-specific manner. We conclude that PTB1 and PTB4, but not PTB2, act as IRES transacting factors of the HCV IRES.

Identification and Characterization of a Minimal Functional Splicing Regulatory Protein, PTBP1.

Polypyrimidine tract binding protein 1 (PTBP1) is a well-studied RNA binding protein that serves as an important model for understanding molecular mechanisms underlying alternative splicing regulation. PTBP1 has four RNA binding domains (RBDs) connected via linker regions. Additionally, PTBP1 has an N-terminal unstructured region that contains nuclear import and export sequences. Each RBD can bind to pyrimidine rich elements with high affinity to mediate splicing activity. Studies support a variety of models for how PTBP1 can mediate splicing regulation on target exons. Obtaining a detailed atomic view hinges on determining a crystal structure of PTBP1 bound to a target RNA transcript. Here, we created a minimal functional PTBP1 with deletions in both linker 1 and linker 2 regions and assayed for activity on certain regulated exons, including the c-Src N1 exon. We show that for a subset of PTBP1-regulated exons the linker regions are not necessary for splicing repression activity. Gel mobility shift assays reveal the linker deletion mutant binds with 12-fold higher affinity to a target RNA sequence compared to wild-type PTBP1. A minimal PTBP1 that also contains an N-terminal region deletion binds to a target RNA with an affinity higher than that of wild-type PTBP1. Moreover, this minimal protein oligomerizes readily to form a distinct higher-order complex previously shown to be required for mediating splicing repression. This minimal functional PTBP1 protein can serve as a candidate for future structure studies to understand the mechanism of splicing repression for certain regulated exons.

The RNA-binding protein PTBP1 promotes ATPase-dependent dissociation of the RNA helicase UPF1 to protect transcripts from nonsense-mediated mRNA decay.

The sequence-specific RNA-binding proteins PTBP1 (polypyrimidine tract-binding protein 1) and HNRNP L (heterogeneous nuclear ribonucleoprotein L) protect mRNAs from nonsense-mediated decay (NMD) by preventing the UPF1 RNA helicase from associating with potential decay targets. Here, by analyzing in vitro helicase activity, dissociation of UPF1 from purified mRNPs, and transcriptome-wide UPF1 RNA binding, we present the mechanistic basis for inhibition of NMD by PTBP1. Unlike mechanisms of RNA stabilization that depend on direct competition for binding sites among protective RNA-binding proteins and decay factors, PTBP1 promotes displacement of UPF1 already bound to potential substrates. Our results show that PTBP1 directly exploits the tendency of UPF1 to release RNA upon ATP binding and hydrolysis. We further find that UPF1 sensitivity to PTBP1 is coordinated by a regulatory loop in domain 1B of UPF1. We propose that the UPF1 regulatory loop and protective proteins control kinetic proofreading of potential NMD substrates, presenting a new model for RNA helicase regulation and target selection in the NMD pathway.

Structural basis of UCUU RNA motif recognition by splicing factor RBM20.

The vertebrate splicing factor RBM20 (RNA binding motif protein 20) regulates protein isoforms important for heart development and function, with mutations in the gene linked to cardiomyopathy. Previous studies have identified the four nucleotide RNA motif UCUU as a common element in pre-mRNA targeted by RBM20. Here, we have determined the structure of the RNA Recognition Motif (RRM) domain from mouse RBM20 bound to RNA containing a UCUU sequence. The atomic details show that the RRM domain spans a larger region than initially proposed in order to interact with the complete UCUU motif, with a well-folded C-terminal helix encoded by exon 8 critical for high affinity binding. This helix only forms upon binding RNA with the final uracil, and removing the helix reduces affinity as well as specificity. We therefore find that RBM20 uses a coupled folding-binding mechanism by the C-terminal helix to specifically recognize the UCUU RNA motif.

Roles of PTBP1 in alternative splicing, glycolysis, and oncogensis.

Polypyrimidine tract-binding protein 1 (PTBP1) plays an essential role in splicing and is expressed in almost all cell types in humans, unlike the other proteins of the PTBP family. PTBP1 mediates several cellular processes in certain types of cells, including the growth and differentiation of neuronal cells and activation of immune cells. Its function is regulated by various molecules, including microRNAs (miRNAs), long non-coding RNAs (lncRNAs), and RNA-binding proteins. PTBP1 plays roles in various diseases, particularly in some cancers, including colorectal cancer, renal cell cancer, breast cancer, and glioma. In cancers, it acts mainly as a regulator of glycolysis, apoptosis, proliferation, tumorigenesis, invasion, and migration. The role of PTBP1 in cancer has become a popular research topic in recent years, and this research has contributed greatly to the formulation of a useful therapeutic strategy for cancer. In this review, we summarize recent findings related to PTBP1 and discuss how it regulates the development of cancer cells.

A transient α-helix in the N-terminal RNA recognition motif of polypyrimidine tract binding protein senses RNA secondary structure.

The polypyrimidine tract binding protein (PTB) is a multi-domain protein involved in alternative splicing, mRNA localization, stabilization, polyadenylation and translation initiation from internal ribosome entry sites (IRES). In this latter process, PTB promotes viral translation by interacting extensively with complex structured regions in the 5'-untranslated regions of viral RNAs at pyrimidine-rich targets located in single strand and hairpin regions. To better understand how PTB recognizes structured elements in RNA targets, we solved the solution structure of the N-terminal RNA recognition motif (RRM) in complex with an RNA hairpin embedding the loop sequence UCUUU, which is frequently found in IRESs of the picornovirus family. Surprisingly, a new three-turn α3 helix C-terminal to the RRM, folds upon binding the RNA hairpin. Although α3 does not mediate any contacts to the RNA, it acts as a sensor of RNA secondary structure, suggesting a role for RRM1 in detecting pyrimidine tracts in the context of structured RNA. Moreover, the degree of helix formation depends on the RNA loop sequence. Finally, we show that the α3 helix region, which is highly conserved in vertebrates, is crucial for PTB function in enhancing Encephalomyocarditis virus IRES activity.

Global analysis of LARP1 translation targets reveals tunable and dynamic features of 5' TOP motifs.

Terminal oligopyrimidine (TOP) motifs are sequences at the 5' ends of mRNAs that link their translation to the mTOR Complex 1 (mTORC1) nutrient-sensing signaling pathway. They are commonly regarded as discrete elements that reside on ∼100 mRNAs that mostly encode translation factors. However, the full spectrum of TOP sequences and their prevalence throughout the transcriptome remain unclear, primarily because of uncertainty over the mechanism that detects them. Here, we globally analyzed translation targets of La-related protein 1 (LARP1), an RNA-binding protein and mTORC1 effector that has been shown to repress TOP mRNA translation in a few specific cases. We establish that LARP1 is the primary translation regulator of mRNAs with classical TOP motifs genome-wide, and also that these motifs are extreme instances of a broader continuum of regulatory sequences. We identify the features of TOP sequences that determine their potency and quantify these as a metric that accurately predicts mTORC1/LARP1 regulation called a TOPscore. Analysis of TOPscores across the transcriptomes of 16 mammalian tissues defines a constitutive "core" set of TOP mRNAs, but also identifies tissue-specific TOP mRNAs produced via alternative transcription initiation sites. These results establish the central role of LARP1 in TOP mRNA regulation on a transcriptome scale and show how it connects mTORC1 to a tunable and dynamic program of gene expression that is tailored to specific biological contexts.

Heteromeric RNP Assembly at LINEs Controls Lineage-Specific RNA Processing.

Long mammalian introns make it challenging for the RNA processing machinery to identify exons accurately. We find that LINE-derived sequences (LINEs) contribute to this selection by recruiting dozens of RNA-binding proteins (RBPs) to introns. This includes MATR3, which promotes binding of PTBP1 to multivalent binding sites within LINEs. Both RBPs repress splicing and 3' end processing within and around LINEs. Notably, repressive RBPs preferentially bind to evolutionarily young LINEs, which are located far from exons. These RBPs insulate the LINEs and the surrounding intronic regions from RNA processing. Upon evolutionary divergence, changes in RNA motifs within LINEs lead to gradual loss of their insulation. Hence, older LINEs are located closer to exons, are a common source of tissue-specific exons, and increasingly bind to RBPs that enhance RNA processing. Thus, LINEs are hubs for the assembly of repressive RBPs and also contribute to the evolution of new, lineage-specific transcripts in mammals. VIDEO ABSTRACT.

Conservation of polypyrimidine tract binding proteins and their putative target RNAs in several storage root crops.

BACKGROUND: Polypyrimidine-tract binding proteins (PTBs) are ubiquitous RNA-binding proteins in plants and animals that play diverse role in RNA metabolic processes. PTB proteins bind to target RNAs through motifs rich in cytosine/uracil residues to fine-tune transcript metabolism. Among tuber and root crops, potato has been widely studied to understand the mobile signals that activate tuber development. Potato PTBs, designated as StPTB1 and StPTB6, function in a long-distance transport system by binding to specific mRNAs (StBEL5 and POTH1) to stabilize them and facilitate their movement from leaf to stolon, the site of tuber induction, where they activate tuber and root growth. Storage tubers and root crops are important sustenance food crops grown throughout the world. Despite the availability of genome sequence for sweet potato, cassava, carrot and sugar beet, the molecular mechanism of root-derived storage organ development remains completely unexplored. Considering the pivotal role of PTBs and their target RNAs in potato storage organ development, we propose that a similar mechanism may be prevalent in storage root crops as well. RESULTS: Through a bioinformatics survey utilizing available genome databases, we identify the orthologues of potato PTB proteins and two phloem-mobile RNAs, StBEL5 and POTH1, in five storage root crops - sweet potato, cassava, carrot, radish and sugar beet. Like potato, PTB1/6 type proteins from these storage root crops contain four conserved RNA Recognition Motifs (characteristic of RNA-binding PTBs) in their protein sequences. Further, 3´ UTR (untranslated region) analysis of BEL5 and POTH1 orthologues revealed the presence of several cytosine/uracil motifs, similar to those present in potato StBEL5 and POTH1 RNAs. Using RT-qPCR assays, we verified the presence of these related transcripts in leaf and root tissues of these five storage root crops. Similar to potato, BEL5-, PTB1/6- and POTH1-like orthologue RNAs from the aforementioned storage root crops exhibited differential accumulation patterns in leaf and storage root tissues. CONCLUSIONS: Our results suggest that the PTB1/6-like orthologues and their putative targets, BEL5- and POTH1-like mRNAs, from storage root crops could interact physically, similar to that in potato, and potentially, could function as key molecular signals controlling storage organ development in root crops.

Spin labelling for integrative structure modelling: a case study of the polypyrimidine-tract binding protein 1 domains in complexes with short RNAs.

A combined method, employing NMR and EPR spectroscopies, has demonstrated its strength in solving structures of protein/RNA and other types of biomolecular complexes. This method works particularly well when the large biomolecular complex consists of a limited number of rigid building blocks, such as RNA-binding protein domains (RBDs). A variety of spin labels is available for such studies, allowing for conventional as well as spectroscopically orthogonal double electron-electron resonance (DEER) measurements in EPR. In this work, we compare different types of nitroxide-based and Gd(iii)-based spin labels attached to isolated RBDs of the polypyrimidine-tract binding protein 1 (PTBP1) and to short RNA fragments. In particular, we demonstrate experiments on spectroscopically orthogonal labelled RBD/RNA complexes. For all experiments we analyse spin labelling, DEER method performance, resulting distance distributions, and their consistency with the predictions from the spin label rotamers analysis. This work provides a set of intra-domain calibration DEER data, which can serve as a basis to start structure determination of the full length PTBP1 complex with an RNA derived from encephalomycarditis virus (EMCV) internal ribosomal entry site (IRES). For a series of tested labelling sites, we discuss their particular advantages and drawbacks in such a structure determination approach.

Intrinsically disordered sequences enable modulation of protein phase separation through distributed tyrosine motifs.

Liquid-liquid phase separation (LLPS) is thought to contribute to the establishment of many biomolecular condensates, eukaryotic cell structures that concentrate diverse macromolecules but lack a bounding membrane. RNA granules control RNA metabolism and comprise a large class of condensates that are enriched in RNA-binding proteins and RNA molecules. Many RNA granule proteins are composed of both modular domains and intrinsically disordered regions (IDRs) having low amino acid sequence complexity. Phase separation of these molecules likely plays an important role in the generation and stability of RNA granules. To understand how folded domains and IDRs can cooperate to modulate LLPS, we generated a series of engineered proteins. These were based on fusions of an IDR derived from the RNA granule protein FUS (fused in sarcoma) to a multivalent poly-Src homology 3 (SH3) domain protein that phase-separates when mixed with a poly-proline-rich-motif (polyPRM) ligand. We found that the wild-type IDR promotes LLPS of the polySH3-polyPRM system, decreasing the phase separation threshold concentration by 8-fold. Systematic mutation of tyrosine residues in Gly/Ser-Tyr-Gly/Ser motifs of the IDR reduced this effect, depending on the number but not on the position of these substitutions. Mutating all tyrosines to non-aromatic residues or phosphorylating the IDR raised the phase separation threshold above that of the unmodified polySH3-polyPRM pair. These results show that low-complexity IDRs can modulate LLPS both positively and negatively, depending on the degree of aromaticity and phosphorylation status. Our findings provide plausible mechanisms by which these sequences could alter RNA granule properties on evolutionary and cellular timescales.

Matrin3 binds directly to intronic pyrimidine-rich sequences and controls alternative splicing.

Matrin3 is an RNA-binding protein that is localized in the nuclear matrix. Although various roles in RNA metabolism have been reported for Matrin3, in vivo target RNAs to which Matrin3 binds directly have not been investigated comprehensively so far. Here, we show that Matrin3 binds predominantly to intronic regions of pre-mRNAs. Photoactivatable Ribonucleoside-Enhanced Cross-linking and Immunoprecipitation (PAR-CLIP) analysis using human neuronal cells showed that Matrin3 recognized pyrimidine-rich sequences as binding motifs, including the polypyrimidine tract, a splicing regulatory element. Splicing-sensitive microarray analysis showed that depletion of Matrin3 preferentially increased the inclusion of cassette exons that were adjacent to introns that contained Matrin3-binding sites. We further found that although most of the genes targeted by polypyrimidine tract binding protein 1 (PTBP1) were also bound by Matrin3, Matrin3 could control alternative splicing in a PTBP1-independent manner, at least in part. These findings suggest that Matrin3 is a splicing regulator that targets intronic pyrimidine-rich sequences.

Structural modeling of protein-RNA complexes using crosslinking of segmentally isotope-labeled RNA and MS/MS.

Ribonucleoproteins (RNPs) are key regulators of cellular function. We established an efficient approach, crosslinking of segmentally isotope-labeled RNA and tandem mass spectrometry (CLIR-MS/MS), to localize protein-RNA interactions simultaneously at amino acid and nucleotide resolution. The approach was tested on polypyrimidine tract binding protein 1 and U1 small nuclear RNP. Our method provides distance restraints to support integrative atomic-scale structural modeling and to gain mechanistic insights into RNP-regulated processes.

Compositional Control of Phase-Separated Cellular Bodies.

Cellular bodies such as P bodies and PML nuclear bodies (PML NBs) appear to be phase-separated liquids organized by multivalent interactions among proteins and RNA molecules. Although many components of various cellular bodies are known, general principles that define body composition are lacking. We modeled cellular bodies using several engineered multivalent proteins and RNA. In vitro and in cells, these scaffold molecules form phase-separated liquids that concentrate low valency client proteins. Clients partition differently depending on the ratio of scaffolds, with a sharp switch across the phase diagram diagonal. Composition can switch rapidly through changes in scaffold concentration or valency. Natural PML NBs and P bodies show analogous partitioning behavior, suggesting how their compositions could be controlled by levels of PML SUMOylation or cellular mRNA concentration, respectively. The data suggest a conceptual framework for considering the composition and control thereof of cellular bodies assembled through heterotypic multivalent interactions.

Multiple determinants of splicing repression activity in the polypyrimidine tract binding proteins, PTBP1 and PTBP2.

Most human genes generate multiple protein isoforms through alternative pre-mRNA splicing, but the mechanisms controlling alternative splicing choices by RNA binding proteins are not well understood. These proteins can have multiple paralogs expressed in different cell types and exhibiting different splicing activities on target exons. We examined the paralogous polypyrimidine tract binding proteins PTBP1 and PTBP2 to understand how PTBP1 can exhibit greater splicing repression activity on certain exons. Using both an in vivo coexpression assay and an in vitro splicing assay, we show that PTBP1 is more repressive than PTBP2 per unit protein on a target exon. Constructing chimeras of PTBP1 and 2 to determine amino acid features that contribute to their differential activity, we find that multiple segments of PTBP1 increase the repressive activity of PTBP2. Notably, when either RRM1 of PTBP2 or the linker peptide separating RRM2 and RRM3 are replaced with the equivalent PTBP1 sequences, the resulting chimeras are highly active for splicing repression. These segments are distinct from the known region of interaction for the PTBP1 cofactors Raver1 and Matrin3 in RRM2. We find that RRM2 of PTBP1 also increases the repression activity of an otherwise PTBP2 sequence, and that this is potentially explained by stronger binding by Raver1. These results indicate that multiple features over the length of the two proteins affect their ability to repress an exon.

A deep learning framework for modeling structural features of RNA-binding protein targets.

RNA-binding proteins (RBPs) play important roles in the post-transcriptional control of RNAs. Identifying RBP binding sites and characterizing RBP binding preferences are key steps toward understanding the basic mechanisms of the post-transcriptional gene regulation. Though numerous computational methods have been developed for modeling RBP binding preferences, discovering a complete structural representation of the RBP targets by integrating their available structural features in all three dimensions is still a challenging task. In this paper, we develop a general and flexible deep learning framework for modeling structural binding preferences and predicting binding sites of RBPs, which takes (predicted) RNA tertiary structural information into account for the first time. Our framework constructs a unified representation that characterizes the structural specificities of RBP targets in all three dimensions, which can be further used to predict novel candidate binding sites and discover potential binding motifs. Through testing on the real CLIP-seq datasets, we have demonstrated that our deep learning framework can automatically extract effective hidden structural features from the encoded raw sequence and structural profiles, and predict accurate RBP binding sites. In addition, we have conducted the first study to show that integrating the additional RNA tertiary structural features can improve the model performance in predicting RBP binding sites, especially for the polypyrimidine tract-binding protein (PTB), which also provides a new evidence to support the view that RBPs may own specific tertiary structural binding preferences. In particular, the tests on the internal ribosome entry site (IRES) segments yield satisfiable results with experimental support from the literature and further demonstrate the necessity of incorporating RNA tertiary structural information into the prediction model. The source code of our approach can be found in https://github.com/thucombio/deepnet-rbp.