In silico characterization and prediction of global protein-mRNA interactions in yeast

Exploring the functionality and conservation of Alba proteins in Trypanosoma cruzi: A focus on biological diversity and RNA binding ability

Trypanosoma cruzi is the causative agent of Chagas disease, as well as a trypanosomatid parasite with a complex biological cycle that requires precise mechanisms for regulating gene expression. In Trypanosomatidae, gene regulation occurs mainly at the mRNA level through the recognition of cis elements by RNA-binding proteins (RBPs). Alba family members are ubiquitous DNA/RNA-binding proteins with representatives in trypanosomatid parasites functionally related to gene expression regulation. Although T. cruzi possesses two groups of Alba proteins (Alba1/2 and Alba30/40), their functional role remains poorly understood. Thus, herein, a characterization of T. cruzi Alba (TcAlba) proteins was undertaken. Physicochemical, structural, and phylogenetic analysis of TcAlba showed features compatible with RBPs, such as hydrophilicity, RBP domains/motifs, and evolutionary conservation of the Alba-domain, mainly regarding other trypanosomatid Alba. However, in silico RNA interaction analysis of T. cruzi Alba proteins showed that TcAlba30/40 proteins, but not TcAlba1/2, would directly interact with the assayed RNA molecules, suggesting that these two groups of TcAlba proteins have different targets. Given the marked differences existing between both T. cruzi Alba groups (TcAlba1/2 and TcAlba30/40), regarding sequence divergence, RNA binding potential, and life-cycle expression patterns, we suggest that they would be involved in different biological processes.

LION: an integrated R package for effective prediction of ncRNA-protein interaction

Understanding ncRNA-protein interaction is of critical importance to unveil ncRNAs' functions. Here, we propose an integrated package LION which comprises a new method for predicting ncRNA/lncRNA-protein interaction as well as a comprehensive strategy to meet the requirement of customisable prediction. Experimental results demonstrate that our method outperforms its competitors on multiple benchmark datasets. LION can also improve the performance of some widely used tools and build adaptable models for species- and tissue-specific prediction. We expect that LION will be a powerful and efficient tool for the prediction and analysis of ncRNA/lncRNA-protein interaction. The R Package LION is available on GitHub at https://github.com/HAN-Siyu/LION/.

A Max-Margin Model for Predicting Residue-Base Contacts in Protein-RNA Interactions

Protein-RNA interactions (PRIs) are essential for many biological processes, so understanding aspects of the sequences and structures involved in PRIs is important for unraveling such processes. Because of the expensive and time-consuming techniques required for experimental determination of complex protein-RNA structures, various computational methods have been developed to predict PRIs. However, most of these methods focus on predicting only RNA-binding regions in proteins or only protein-binding motifs in RNA. Methods for predicting entire residue-base contacts in PRIs have not yet achieved sufficient accuracy. Furthermore, some of these methods require the identification of 3D structures or homologous sequences, which are not available for all protein and RNA sequences. Here, we propose a prediction method for predicting residue-base contacts between proteins and RNAs using only sequence information and structural information predicted from sequences. The method can be applied to any protein-RNA pair, even when rich information such as its 3D structure, is not available. In this method, residue-base contact prediction is formalized as an integer programming problem. We predict a residue-base contact map that maximizes a scoring function based on sequence-based features such as k-mers of sequences and the predicted secondary structure. The scoring function is trained using a max-margin framework from known PRIs with 3D structures. To verify our method, we conducted several computational experiments. The results suggest that our method, which is based on only sequence information, is comparable with RNA-binding residue prediction methods based on known binding data.

Recent advances in predicting protein-lncRNA interactions using machine learning methods

Long non-coding RNAs (LncRNAs) are a type of RNA with little or no protein-coding ability. Their length is more than 200 nucleotides. A large number of studies have indicated that lncRNAs play a significant role in various biological processes, including chromatin organizations, epigenetic programmings, transcriptional regulations, post-transcriptional processing, and circadian mechanism at the cellular level. Since lncRNAs perform vast functions through their interactions with proteins, identifying lncRNA-protein interaction is crucial to the understandings of the lncRNA molecular functions. However, due to the high cost and time-consuming disadvantage of experimental methods, a variety of computational methods have emerged. Recently, many effective and novel machine learning methods have been developed. In general, these methods fall into two categories: semi-supervised learning methods and supervised learning methods. The latter category can be further classified into the deep learning-based method, the ensemble learning-based method, and the hybrid method. In this paper, we focused on supervised learning methods. We summarized the state-of-the-art methods in predicting lncRNA-protein interactions. Furthermore, the performance and the characteristics of different methods have also been compared in this work. Considering the limits of the existing models, we analyzed the problems and discussed future research potentials.

Capsule-LPI: a LncRNA-protein interaction predicting tool based on a capsule network

BACKGROUND

Long noncoding RNAs (lncRNAs) play important roles in multiple biological processes. Identifying LncRNA-protein interactions (LPIs) is key to understanding lncRNA functions. Although some LPIs computational methods have been developed, the LPIs prediction problem remains challenging. How to integrate multimodal features from more perspectives and build deep learning architectures with better recognition performance have always been the focus of research on LPIs.

RESULTS

We present a novel multichannel capsule network framework to integrate multimodal features for LPI prediction, Capsule-LPI. Capsule-LPI integrates four groups of multimodal features, including sequence features, motif information, physicochemical properties and secondary structure features. Capsule-LPI is composed of four feature-learning subnetworks and one capsule subnetwork. Through comprehensive experimental comparisons and evaluations, we demonstrate that both multimodal features and the architecture of the multichannel capsule network can significantly improve the performance of LPI prediction. The experimental results show that Capsule-LPI performs better than the existing state-of-the-art tools. The precision of Capsule-LPI is 87.3%, which represents a 1.7% improvement. The F-value of Capsule-LPI is 92.2%, which represents a 1.4% improvement.

CONCLUSIONS

This study provides a novel and feasible LPI prediction tool based on the integration of multimodal features and a capsule network. A webserver ( http://csbg-jlu.site/lpc/predict ) is developed to be convenient for users.

RNA-protein interactions: Central players in coordination of regulatory networks

Changes in the abundance of protein and RNA molecules can impair the formation of complexes in the cell leading to toxicity and death. Here we exploit the information contained in protein, RNA and DNA interaction networks to provide a comprehensive view of the regulation layers controlling the concentration-dependent formation of assemblies in the cell. We present the emerging concept that RNAs can act as scaffolds to promote the formation ribonucleoprotein complexes and coordinate the post-transcriptional layer of gene regulation. We describe the structural and interaction network properties that characterize the ability of protein and RNA molecules to interact and phase separate in liquid-like compartments. Finally, we show that presence of structurally disordered regions in proteins correlate with the propensity to undergo liquid-to-solid phase transitions and cause human diseases. Also see the video abstract here https://youtu.be/kfpqibsNfS0.

RPI-SE: a stacking ensemble learning framework for ncRNA-protein interactions prediction using sequence information

Background

The interactions between non-coding RNAs (ncRNA) and proteins play an essential role in many biological processes. Several high-throughput experimental methods have been applied to detect ncRNA-protein interactions. However, these methods are time-consuming and expensive. Accurate and efficient computational methods can assist and accelerate the study of ncRNA-protein interactions.

Results

In this work, we develop a stacking ensemble computational framework, RPI-SE, for effectively predicting ncRNA-protein interactions. More specifically, to fully exploit protein and RNA sequence feature, Position Weight Matrix combined with Legendre Moments is applied to obtain protein evolutionary information. Meanwhile, k-mer sparse matrix is employed to extract efficient feature of ncRNA sequences. Finally, an ensemble learning framework integrated different types of base classifier is developed to predict ncRNA-protein interactions using these discriminative features. The accuracy and robustness of RPI-SE was evaluated on three benchmark data sets under five-fold cross-validation and compared with other state-of-the-art methods.

Conclusions

The results demonstrate that RPI-SE is competent for ncRNA-protein interactions prediction task with high accuracy and robustness. It’s anticipated that this work can provide a computational prediction tool to advance ncRNA-protein interactions related biomedical research.

The Architecture of the Human RNA-Binding Protein Regulatory Network

RNA-binding proteins (RBPs) are key players of post-transcriptional regulation of gene expression, relying on competitive and cooperative interactions to fine-tune their action. Several studies have described individual interactions of RBPs with RBP mRNAs. Here we present a systematic network investigation of fifty thousand interactions between RBPs and the UTRs of RBP mRNAs. We identified two structural features in this network. RBP clusters are groups of densely interconnected RBPs co-binding their targets, suggesting a tight control of cooperative and competitive behaviors. RBP chains are hierarchical structures connecting RBP clusters and driven by evolutionarily ancient RBPs. These features suggest that RBP chains may coordinate the different cell programs controlled by RBP clusters. Under this model, the regulatory signal flows through chains from one cluster to another, implementing elaborate regulatory plans. This work thus suggests RBP-RBP interactions as a backbone driving post-transcriptional regulation of gene expression to control RBPs action on their targets.

•

The RBP-RBP network is a robust and efficient hierarchical structure

•

The RBP-RBP network is formed by RBP clusters and chains

•

RBP-RBP interactions cluster to cooperate and compete on common target mRNAs

•

RBP chains are master regulatory units of the cell led by ancient RBPs

Recent Advances in Machine Learning Based Prediction of RNA-protein Interactions

The interactions between RNAs and proteins play critical roles in many biological processes. Therefore, characterizing these interactions becomes critical for mechanistic, biomedical, and clinical studies. Many experimental methods can be used to determine RNA-protein interactions in multiple aspects. However, due to the facts that RNA-protein interactions are tissuespecific and condition-specific, as well as these interactions are weak and frequently compete with each other, those experimental techniques can not be made full use of to discover the complete spectrum of RNA-protein interactions. To moderate these issues, continuous efforts have been devoted to developing high quality computational techniques to study the interactions between RNAs and proteins. Many important progresses have been achieved with the application of novel techniques and strategies, such as machine learning techniques. Especially, with the development and application of CLIP techniques, more and more experimental data on RNA-protein interaction under specific biological conditions are available. These CLIP data altogether provide a rich source for developing advanced machine learning predictors. In this review, recent progresses on computational predictors for RNA-protein interaction were summarized in the following aspects: dataset, prediction strategies, and input features. Possible future developments were also discussed at the end of the review.

Cellular models of Batten disease

The Neuronal Ceroid Lipofuscinoses (NCL), otherwise known as Batten disease, are a group of neurodegenerative diseases caused by mutations in 13 known genes. All except one NCL is autosomal recessive in inheritance, with similar aetiology and characterised by the accumulation of autofluorescent storage material in the lysosomes of cells. Age of onset and the rate of progression vary between the NCLs. They are collectively one of the most common lysosomal storage diseases, but the enigma remains of how genetically distinct diseases result in such remarkably similar pathogenesis. Much has been learnt from cellular studies about the function of the proteins encoded by the affected genes. Such research has utilised primitive unicellular models such as yeast and amoeba containing gene orthologues, cells derived from naturally occurring (sheep) and genetically engineered (mouse) animal models or patient-derived cells. Most recently, patient-derived induced pluripotent stem cell (iPSC) lines have been differentiated into neural cell-types to study molecular pathogenesis in the cells most profoundly affected by disease. Here, we review how cell models have informed much of the biochemical understanding of the NCLs and how more complex models are being used to further this understanding and potentially act as platforms for therapeutic efficacy studies in the future.

•

Developments made in cellular models for neuronal ceroid lipofuscinosis (NCL) in basic biology and use as therapeutic platforms.

•

Cellular models elucidating function of NCL proteins.

•

NCL proteins implicated in the mTor signalling pathway.

•

Patient-derived induced pluripotent stem cell (iPSC) lines have been differentiated into neural cell-types providing insights into the molecular pathogenesis of NCL.

DM-RPIs: Predicting ncRNA-protein interactions using stacked ensembling strategy

ncRNA-protein interactions (ncRPIs) play an important role in a number of cellular processes, such as post-transcriptional modification, transcriptional regulation, disease progression and development. Since experimental methods are expensive and time-consuming to identify the ncRPIs, we proposed a computational method, Deep Mining ncRNA-Protein Interactions (DM-RPIs), for identifying the ncRPIs. In order to descending dimension and excavating hidden information from k-mer frequency of RNA and protein sequences, using the Deep Stacking Auto-encoders Networks (DSANs) model refined the raw data. Three common machine learning algorithms, Support Vector Machine (SVM), Random Forest (RF), and Convolution Neural Network (CNN), were separately trained as individual predictors and then the three individual predictors were integrated together using stacked ensembling strategy. Based on the RPI2241 dataset, DM-RPI obtains an accuracy of 0.851, precision of 0.852, sensitivity of 0.873, specificity of 0.826, and MCC of 0.701, which is promising and pioneering for the prediction of ncRPIs.

R-DeeP: Proteome-wide and Quantitative Identification of RNA-Dependent Proteins by Density Gradient Ultracentrifugation

The comprehensive but specific identification of RNA-binding proteins as well as the discovery of RNA-associated protein functions remain major challenges in RNA biology. Here we adapt the concept of RNA dependence, defining a protein as RNA dependent when its interactome depends on RNA. We converted this concept into a proteome-wide, unbiased, and enrichment-free screen called R-DeeP (RNA-dependent proteins), based on density gradient ultracentrifugation. Quantitative mass spectrometry identified 1,784 RNA-dependent proteins, including 537 lacking known links to RNA. Exploiting the quantitative nature of R-DeeP, proteins were classified as not, partially, or completely RNA dependent. R-DeeP identified the transcription factor CTCF as completely RNA dependent, and we uncovered that RNA is required for the CTCF-chromatin association. Additionally, R-DeeP allows reconstruction of protein complexes based on co-segregation. The whole dataset is available at http://R-DeeP.dkfz.de, providing proteome-wide, specific, and quantitative identification of proteins with RNA-dependent interactions and aiming at future functional discovery of RNA-protein complexes.

beRBP: binding estimation for human RNA-binding proteins

Identifying binding targets of RNA-binding proteins (RBPs) can greatly facilitate our understanding of their functional mechanisms. Most computational methods employ machine learning to train classifiers on either RBP-specific targets or pooled RBP-RNA interactions. The former strategy is more powerful, but it only applies to a few RBPs with a large number of known targets; conversely, the latter strategy sacrifices prediction accuracy for a wider application, since specific interaction features are inevitably obscured through pooling heterogeneous datasets. Here, we present beRBP, a dual approach to predict human RBP-RNA interaction given PWM of a RBP and one RNA sequence. Based on Random Forests, beRBP not only builds a specific model for each RBP with a decent number of known targets, but also develops a general model for RBPs with limited or null known targets. The specific and general models both compared well with existing methods on three benchmark datasets. Notably, the general model achieved a better performance than existing methods on most novel RBPs. Overall, as a composite solution overarching the RBP-specific and RBP-General strategies, beRBP is a promising tool for human RBP binding estimation with good prediction accuracy and a broad application scope.

Prediction of RNA-protein interactions using conjoint triad feature and chaos game representation

RNA-protein interactions (RPIs) play a very important role in a wide range of post-transcriptional regulations, and identifying whether a given RNA-protein pair can form interactions or not is a vital prerequisite for dissecting the regulatory mechanisms of functional RNAs. Currently, expensive and time-consuming biological assays can only determine a very small portion of all RPIs, which calls for computational approaches to help biologists efficiently and correctly find candidate RPIs. Here, we integrated a successful computing algorithm, conjoint triad feature (CTF), and another method, chaos game representation (CGR), for representing RNA-protein pairs and by doing so developed a prediction model based on these representations and random forest (RF) classifiers. When testing two benchmark datasets, RPI369 and RPI2241, the combined method (CTF+CGR) showed some superiority compared with four existing tools. Especially on RPI2241, the CTF+CGR method improved prediction accuracy (ACC) from 0.91 (the best record of all published works) to 0.95. When independently testing a newly constructed dataset, RPI1449, which only contained experimentally validated RPIs released between 2014 and 2016, our method still showed some generalization capability with an ACC of 0.75. Accordingly, we believe that our hybrid CTF+CGR method will be an important tool for predicting RPIs in the future.

RNA-protein interactions in an unstructured context

Despite their importance, our understanding of noncovalent RNA-protein interactions is incomplete. This especially concerns the binding between RNA and unstructured protein regions, a widespread class of such interactions. Here, we review the recent experimental and computational work on RNA-protein interactions in an unstructured context with a particular focus on how such interactions may be shaped by the intrinsic interaction affinities between individual nucleobases and protein side chains. Specifically, we articulate the claim that the universal genetic code reflects the binding specificity between nucleobases and protein side chains and that, in turn, the code may be seen as the Rosetta stone for understanding RNA-protein interactions in general.

A Data Driven Model for Predicting RNA-Protein Interactions based on Gradient Boosting Machine

RNA protein interactions (RPI) play a pivotal role in the regulation of various biological processes. Experimental validation of RPI has been time-consuming, paving the way for computational prediction methods. The major limiting factor of these methods has been the accuracy and confidence of the predictions, and our in-house experiments show that they fail to accurately predict RPI involving short RNA sequences such as TERRA RNA. Here, we present a data-driven model for RPI prediction using a gradient boosting classifier. Amino acids and nucleotides are classified based on the high-resolution structural data of RNA protein complexes. The minimum structural unit consisting of five residues is used as the descriptor. Comparative analysis of existing methods shows the consistently higher performance of our method irrespective of the length of RNA present in the RPI. The method has been successfully applied to map RPI networks involving both long noncoding RNA as well as TERRA RNA. The method is also shown to successfully predict RNA and protein hubs present in RPI networks of four different organisms. The robustness of this method will provide a way for predicting RPI networks of yet unknown interactions for both long noncoding RNA and microRNA.

A Deep Learning Framework for Robust and Accurate Prediction of ncRNA-Protein Interactions Using Evolutionary Information

The interactions between non-coding RNAs (ncRNAs) and proteins play an important role in many biological processes, and their biological functions are primarily achieved by binding with a variety of proteins. High-throughput biological techniques are used to identify protein molecules bound with specific ncRNA, but they are usually expensive and time consuming. Deep learning provides a powerful solution to computationally predict RNA-protein interactions. In this work, we propose the RPI-SAN model by using the deep-learning stacked auto-encoder network to mine the hidden high-level features from RNA and protein sequences and feed them into a random forest (RF) model to predict ncRNA binding proteins. Stacked assembling is further used to improve the accuracy of the proposed method. Four benchmark datasets, including RPI2241, RPI488, RPI1807, and NPInter v2.0, were employed for the unbiased evaluation of five established prediction tools: RPI-Pred, IPMiner, RPISeq-RF, lncPro, and RPI-SAN. The experimental results show that our RPI-SAN model achieves much better performance than other methods, with accuracies of 90.77%, 89.7%, 96.1%, and 99.33%, respectively. It is anticipated that RPI-SAN can be used as an effective computational tool for future biomedical researches and can accurately predict the potential ncRNA-protein interacted pairs, which provides reliable guidance for biological research.

RPiRLS: Quantitative Predictions of RNA Interacting with Any Protein of Known Sequence

RNA-protein interactions (RPIs) have critical roles in numerous fundamental biological processes, such as post-transcriptional gene regulation, viral assembly, cellular defence and protein synthesis. As the number of available RNA-protein binding experimental data has increased rapidly due to high-throughput sequencing methods, it is now possible to measure and understand RNA-protein interactions by computational methods. In this study, we integrate a sequence-based derived kernel with regularized least squares to perform prediction. The derived kernel exploits the contextual information around an amino acid or a nucleic acid as well as the repetitive conserved motif information. We propose a novel machine learning method, called RPiRLS to predict the interaction between any RNA and protein of known sequences. For the RPiRLS classifier, each protein sequence comprises up to 20 diverse amino acids but for the RPiRLS-7G classifier, each protein sequence is represented by using 7-letter reduced alphabets based on their physiochemical properties. We evaluated both methods on a number of benchmark data sets and compared their performances with two newly developed and state-of-the-art methods, RPI-Pred and IPMiner. On the non-redundant benchmark test sets extracted from the PRIDB, the RPiRLS method outperformed RPI-Pred and IPMiner in terms of accuracy, specificity and sensitivity. Further, RPiRLS achieved an accuracy of 92% on the prediction of lncRNA-protein interactions. The proposed method can also be extended to construct RNA-protein interaction networks. The RPiRLS web server is freely available at http://bmc.med.stu.edu.cn/RPiRLS.

Specifying RNA-Binding Regions in Proteins by Peptide Cross-Linking and Affinity Purification

RNA-binding proteins (RBPs) allow cells to carry out pre-RNA processing and post-transcriptional regulation of gene expression, and aberrations in RBP functions have been linked to many diseases, including neurological disorders and cancer. Human cells encode thousands of RNA-binding proteins with unique RNA-binding properties. These properties are regulated through modularity of a large variety of RNA-binding domains, rendering RNA-protein interactions difficult to study. Recently, the introduction of proteomics methods has provided novel insights into RNA-binding proteins at a systems level. However, determining the exact protein sequence regions that interact with RNA remains challenging and laborious, especially considering that many RBPs lack canonical RNA-binding domains. Here we describe a streamlined proteomic workflow called peptide cross-linking and affinity purification (pCLAP) that allows rapid characterization of RNA-binding regions in proteins. pCLAP is based upon the combined use of UV cross-linking and enzymatic digestion of RNA-bound proteins followed by single-shot mass spectrometric analysis. To benchmark our method, we identified the binding regions for polyadenylated RNA-binding proteins in HEK293 cells, allowing us to map the mRNA interaction regions of more than 1000 RBPs with very high reproducibility from replicate single-shot analyses. Our results show specific enrichment of many known RNA-binding regions on many known RNA-binding proteins, confirming the specificity of our approach.

Prediction of lncRNA-protein interactions using HeteSim scores based on heterogeneous networks

Massive studies have indicated that long non-coding RNAs (lncRNAs) are critical for the regulation of cellular biological processes by binding with RNA-related proteins. However, only a few experimentally supported lncRNA-protein associations have been reported. Existing network-based methods are typically focused on intrinsic features of lncRNA and protein but ignore the information implicit in the topologies of biological networks associated with lncRNAs. Considering the limitations in previous methods, we propose PLPIHS, an effective computational method for Predicting lncRNA-Protein Interactions using HeteSim Scores. PLPIHS uses the HeteSim measure to calculate the relatedness score for each lncRNA-protein pair in the heterogeneous network, which consists of lncRNA-lncRNA similarity network, lncRNA-protein association network and protein-protein interaction network. An SVM classifier to predict lncRNA-protein interactions is built with the HeteSim scores. The results show that PLPIHS performs significantly better than the existing state-of-the-art approaches and achieves an AUC score of 0.97 in the leave-one-out validation test. We also compare the performances of networks with different connectivity density and find that PLPIHS performs well across all the networks. Furthermore, we use the proposed method to identify the related proteins for lncRNA MALAT1. Highly-ranked proteins are verified by the biological studies and demonstrate the effectiveness of our method.

Selecting high-quality negative samples for effectively predicting protein-RNA interactions

Background

The identification of Protein-RNA Interactions (PRIs) is important to understanding cell activities. Recently, several machine learning-based methods have been developed for identifying PRIs. However, the performance of these methods is unsatisfactory. One major reason is that they usually use unreliable negative samples in the training process.

Methods

For boosting the performance of PRI prediction, we propose a novel method to generate reliable negative samples. Concretely, we firstly collect the known PRIs as positive samples for generating positive sets. For each positive set, we construct two corresponding negative sets, one is by our method and the other by random method. Each positive set is combined with a negative set to form a dataset for model training and performance evaluation. Consequently, we get 18 datasets of different species and different ratios of negative samples to positive samples.

Secondly, sequence-based features are extracted to represent each of PRIs and protein-RNA pairs in the datasets. A filter-based method is employed to cut down the dimensionality of feature vectors for reducing computational cost. Finally, the performance of support vector machine (SVM), random forest (RF) and naive Bayes (NB) is evaluated on the generated 18 datasets.

Results

Extensive experiments show that comparing to using randomly-generated negative samples, all classifiers achieve substantial performance improvement by using negative samples selected by our method. The improvements on accuracy and geometric mean for the SVM classifier, the RF classifier and the NB classifier are as high as 204.5 and 68.7%, 174.5 and 53.9%, 80.9 and 54.3%, respectively.

Conclusion

Our method is useful to the identification of PRIs.

Computational Prediction of RNA-Protein Interactions

Experimental methods for identifying protein(s) bound by a specific promoter-associated RNA (paRNA) of interest can be expensive, difficult, and time-consuming. This chapter describes a general computational framework for identifying potential binding partners in RNA-protein complexes or RNA-protein interaction networks. Protocols for using three web-based tools to predict RNA-protein interaction partners are outlined. Also, tables listing additional webservers and software tools for predicting RNA-protein interactions, as well as databases that contain valuable information about known RNA-protein complexes and recognition sites for RNA-binding proteins, are provided. Although only one of the tools described, lncPro, was designed expressly to identify proteins that bind long noncoding RNAs (including paRNAs), all three approaches can be applied to predict potential binding partners for both coding and noncoding RNAs (ncRNAs).

Oxidative stress response pathways: Fission yeast as archetype

Schizosaccharomyces pombe is a popular model eukaryotic organism to study diverse aspects of mammalian biology, including responses to cellular stress triggered by redox imbalances within its compartments. The review considers the current knowledge on the signaling pathways that govern the transcriptional response of fission yeast cells to elevated levels of hydrogen peroxide. Particular attention is paid to the mechanisms that yeast cells employ to promote cell survival in conditions of intermediate and acute oxidative stress. The role of the Sty1/Spc1/Phh1 mitogen-activated protein kinase in regulating gene expression at multiple levels is discussed in detail.

aPPRove: An HMM-Based Method for Accurate Prediction of RNA-Pentatricopeptide Repeat Protein Binding Events

Pentatricopeptide repeat containing proteins (PPRs) bind to RNA transcripts originating from mitochondria and plastids. There are two classes of PPR proteins. The P class contains tandem P-type motif sequences, and the PLS class contains alternating P, L and S type sequences. In this paper, we describe a novel tool that predicts PPR-RNA interaction; specifically, our method, which we call aPPRove, determines where and how a PLS-class PPR protein will bind to RNA when given a PPR and one or more RNA transcripts by using a combinatorial binding code for site specificity proposed by Barkan et al. Our results demonstrate that aPPRove successfully locates how and where a PPR protein belonging to the PLS class can bind to RNA. For each binding event it outputs the binding site, the amino-acid-nucleotide interaction, and its statistical significance. Furthermore, we show that our method can be used to predict binding events for PLS-class proteins using a known edit site and the statistical significance of aligning the PPR protein to that site. In particular, we use our method to make a conjecture regarding an interaction between CLB19 and the second intronic region of ycf3. The aPPRove web server can be found at www.cs.colostate.edu/~approve.

IPMiner: hidden ncRNA-protein interaction sequential pattern mining with stacked autoencoder for accurate computational prediction

BACKGROUND

Non-coding RNAs (ncRNAs) play crucial roles in many biological processes, such as post-transcription of gene regulation. ncRNAs mainly function through interaction with RNA binding proteins (RBPs). To understand the function of a ncRNA, a fundamental step is to identify which protein is involved into its interaction. Therefore it is promising to computationally predict RBPs, where the major challenge is that the interaction pattern or motif is difficult to be found.

RESULTS

In this study, we propose a computational method IPMiner (Interaction Pattern Miner) to predict ncRNA-protein interactions from sequences, which makes use of deep learning and further improves its performance using stacked ensembling. One of the IPMiner's typical merits is that it is able to mine the hidden sequential interaction patterns from sequence composition features of protein and RNA sequences using stacked autoencoder, and then the learned hidden features are fed into random forest models. Finally, stacked ensembling is used to integrate different predictors to further improve the prediction performance. The experimental results indicate that IPMiner achieves superior performance on the tested lncRNA-protein interaction dataset with an accuracy of 0.891, sensitivity of 0.939, specificity of 0.831, precision of 0.945 and Matthews correlation coefficient of 0.784, respectively. We further comprehensively investigate IPMiner on other RNA-protein interaction datasets, which yields better performance than the state-of-the-art methods, and the performance has an increase of over 20 % on some tested benchmarked datasets. In addition, we further apply IPMiner for large-scale prediction of ncRNA-protein network, that achieves promising prediction performance.

CONCLUSION

By integrating deep neural network and stacked ensembling, from simple sequence composition features, IPMiner can automatically learn high-level abstraction features, which had strong discriminant ability for RNA-protein detection. IPMiner achieved high performance on our constructed lncRNA-protein benchmark dataset and other RNA-protein datasets. IPMiner tool is available at http://www.csbio.sjtu.edu.cn/bioinf/IPMiner .

RNAcommender: genome-wide recommendation of RNA-protein interactions

MOTIVATION

Information about RNA-protein interactions is a vital pre-requisite to tackle the dissection of RNA regulatory processes. Despite the recent advances of the experimental techniques, the currently available RNA interactome involves a small portion of the known RNA binding proteins. The importance of determining RNA-protein interactions, coupled with the scarcity of the available information, calls for in silico prediction of such interactions.

RESULTS

We present RNAcommender, a recommender system capable of suggesting RNA targets to unexplored RNA binding proteins, by propagating the available interaction information taking into account the protein domain composition and the RNA predicted secondary structure. Our results show that RNAcommender is able to successfully suggest RNA interactors for RNA binding proteins using little or no interaction evidence. RNAcommender was tested on a large dataset of human RBP-RNA interactions, showing a good ranking performance (average AUC ROC of 0.75) and significant enrichment of correct recommendations for 75% of the tested RBPs. RNAcommender can be a valid tool to assist researchers in identifying potential interacting candidates for the majority of RBPs with uncharacterized binding preferences.

AVAILABILITY AND IMPLEMENTATION

The software is freely available at http://rnacommender.disi.unitn.it CONTACT: gianluca.corrado@unitn.it or andrea.passerini@unitn.itSupplementary information: Supplementary data are available at Bioinformatics online.

Dissecting the expression relationships between RNA-binding proteins and their cognate targets in eukaryotic post-transcriptional regulatory networks

RNA-binding proteins (RBPs) are pivotal in orchestrating several steps in the metabolism of RNA in eukaryotes thereby controlling an extensive network of RBP-RNA interactions. Here, we employed CLIP (cross-linking immunoprecipitation)-seq datasets for 60 human RBPs and RIP-ChIP (RNP immunoprecipitation-microarray) data for 69 yeast RBPs to construct a network of genome-wide RBP- target RNA interactions for each RBP. We show in humans that majority (~78%) of the RBPs are strongly associated with their target transcripts at transcript level while ~95% of the studied RBPs were also found to be strongly associated with expression levels of target transcripts when protein expression levels of RBPs were employed. At transcript level, RBP - RNA interaction data for the yeast genome, exhibited a strong association for 63% of the RBPs, confirming the association to be conserved across large phylogenetic distances. Analysis to uncover the features contributing to these associations revealed the number of target transcripts and length of the selected protein-coding transcript of an RBP at the transcript level while intensity of the CLIP signal, number of RNA-Binding domains, location of the binding site on the transcript, to be significant at the protein level. Our analysis will contribute to improved modelling and prediction of post-transcriptional networks.

Barcelona conference on epigenetics and cancer 2015: Coding and non-coding functions of the genome

The Barcelona Conference on Epigenetics and Cancer (BCEC) entitled "Coding and Non-Coding functions of the Genome" took place October 29-30, 2015 in Barcelona. The 2015 BCEC was the third edition of a series of annual conferences jointly organized by 5 leading research centers in Barcelona together with B-Debate, an initiative of BioCat. Luciano Di Croce from the Center for Genomic Regulation and Marcus Buschbeck from the Josep Carreras Leukemia Research Institute put together the scientific program with a particular focus on the role of non-coding RNAs in enhancer regulation, epigenetic control by Polycomb complexes, histone variants, and nuclear organization. In one and a half days, 22 talks and 56 posters were presented to an audience of 215 participants.

Specificity and nonspecificity in RNA-protein interactions

To fully understand the regulation of gene expression, it is critical to quantitatively define whether and how RNA-binding proteins (RBPs) discriminate between alternative binding sites in RNAs. Here, we describe new methods that measure protein binding to large numbers of RNA variants, and ways to analyse and interpret data obtained by these approaches, including affinity distributions and free energy landscapes. We discuss how the new methodologies and the associated concepts enable the development of inclusive, quantitative models for RNA-protein interactions that transcend the traditional binary classification of RBPs as either specific or nonspecific.

Revealing protein-lncRNA interaction

Long non-coding RNAs (lncRNAs) are associated to a plethora of cellular functions, most of which require the interaction with one or more RNA-binding proteins (RBPs); similarly, RBPs are often able to bind a large number of different RNAs. The currently available knowledge is already drawing an intricate network of interactions, whose deregulation is frequently associated to pathological states. Several different techniques were developed in the past years to obtain protein–RNA binding data in a high-throughput fashion. In parallel, in silico inference methods were developed for the accurate computational prediction of the interaction of RBP–lncRNA pairs. The field is growing rapidly, and it is foreseeable that in the near future, the protein–lncRNA interaction network will rise, offering essential clues for a better understanding of lncRNA cellular mechanisms and their disease-associated perturbations.

Computationally predicting protein-RNA interactions using only positive and unlabeled examples

Protein–RNA interactions (PRIs) are considerably important in a wide variety of cellular processes, ranging from transcriptional and post-transcriptional regulations of gene expression to the active defense of host against virus. With the development of high throughput technology, large amounts of PRI information is available for computationally predicting unknown PRIs. In recent years, a number of computational methods for predicting PRIs have been developed in the literature, which usually artificially construct negative samples based on verified nonredundant datasets of PRIs to train classifiers. However, such negative samples are not real negative samples, some even may be unknown positive samples. Consequently, the classifiers trained with such training datasets cannot achieve satisfactory prediction performance. In this paper, we propose a novel method PRIPU that employs biased-support vector machine (SVM) for predicting Protein-RNA Interactions using only Positive and Unlabeled examples. To the best of our knowledge, this is the first work that predicts PRIs using only positive and unlabeled samples. We first collect known PRIs as our benchmark datasets and extract sequence-based features to represent each PRI. To reduce the dimension of feature vectors for lowering computational cost, we select a subset of features by a filter-based feature selection method. Then, biased-SVM is employed to train prediction models with different PRI datasets. To evaluate the new method, we also propose a new performance measure called explicit positive recall (EPR), which is specifically suitable for the task of learning positive and unlabeled data. Experimental results over three datasets show that our method not only outperforms four existing methods, but also is able to predict unknown PRIs. Source code, datasets and related documents of PRIPU are available at: http://admis.fudan.edu.cn/projects/pripu.htm .

The neuronal ceroid lipofuscinoses: Opportunities from model systems

The neuronal ceroid lipofuscinoses are a group of severe and progressive neurodegenerative disorders, generally with childhood onset. Despite the fact that these diseases remain fatal, significant breakthroughs have been made in our understanding of the genetics that underpin these conditions. This understanding has allowed the development of a broad range of models to study disease processes, and to develop new therapeutic approaches. Such models have contributed significantly to our knowledge of these conditions. In this review we will focus on the advantages of each individual model, describe some of the contributions the models have made to our understanding of the broader disease biology and highlight new techniques and approaches relevant to the study and potential treatment of the neuronal ceroid lipofuscinoses. This article is part of a Special Issue entitled: "Current Research on the Neuronal Ceroid Lipofuscinoses (Batten Disease)".

RPI-Pred: predicting ncRNA-protein interaction using sequence and structural information

RNA-protein complexes are essential in mediating important fundamental cellular processes, such as transport and localization. In particular, ncRNA-protein interactions play an important role in post-transcriptional gene regulation like mRNA localization, mRNA stabilization, poly-adenylation, splicing and translation. The experimental methods to solve RNA-protein interaction prediction problem remain expensive and time-consuming. Here, we present the RPI-Pred (RNA-protein interaction predictor), a new support-vector machine-based method, to predict protein-RNA interaction pairs, based on both the sequences and structures. The results show that RPI-Pred can correctly predict RNA-protein interaction pairs with ∼94% prediction accuracy when using sequence and experimentally determined protein and RNA structures, and with ∼83% when using sequences and predicted protein and RNA structures. Further, our proposed method RPI-Pred was superior to other existing ones by predicting more experimentally validated ncRNA-protein interaction pairs from different organisms. Motivated by the improved performance of RPI-Pred, we further applied our method for reliable construction of ncRNA-protein interaction networks. The RPI-Pred is publicly available at: http://ctsb.is.wfubmc.edu/projects/rpi-pred.

Protein-specific prediction of mRNA binding using RNA sequences, binding motifs and predicted secondary structures

Background

RNA-binding proteins interact with specific RNA molecules to regulate important cellular processes. It is therefore necessary to identify the RNA interaction partners in order to understand the precise functions of such proteins. Protein-RNA interactions are typically characterized using in vivo and in vitro experiments but these may not detect all binding partners. Therefore, computational methods that capture the protein-dependent nature of such binding interactions could help to predict potential binding partners in silico.

Results

We have developed three methods to predict whether an RNA can interact with a particular RNA-binding protein using support vector machines and different features based on the sequence (the Oli method), the motif score (the OliMo method) and the secondary structure (the OliMoSS method). We applied these approaches to different experimentally-derived datasets and compared the predictions with RNAcontext and RPISeq. Oli outperformed OliMoSS and RPISeq, confirming our protein-specific predictions and suggesting that tetranucleotide frequencies are appropriate discriminative features. Oli and RNAcontext were the most competitive methods in terms of the area under curve. A precision-recall curve analysis achieved higher precision values for Oli. On a second experimental dataset including real negative binding information, Oli outperformed RNAcontext with a precision of 0.73 vs. 0.59.

Conclusions

Our experiments showed that features based on primary sequence information are sufficiently discriminating to predict specific RNA-protein interactions. Sequence motifs and secondary structure information were not necessary to improve these predictions. Finally we confirmed that protein-specific experimental data concerning RNA-protein interactions are valuable sources of information that can be used for the efficient training of models for in silico predictions. The scripts are available upon request to the corresponding author.

Predicting the dynamics of protein abundance

Protein synthesis is finely regulated across all organisms, from bacteria to humans, and its integrity underpins many important processes. Emerging evidence suggests that the dynamic range of protein abundance is greater than that observed at the transcript level. Technological breakthroughs now mean that sequencing-based measurement of mRNA levels is routine, but protocols for measuring protein abundance remain both complex and expensive. This paper introduces a Bayesian network that integrates transcriptomic and proteomic data to predict protein abundance and to model the effects of its determinants. We aim to use this model to follow a molecular response over time, from condition-specific data, in order to understand adaptation during processes such as the cell cycle. With microarray data now available for many conditions, the general utility of a protein abundance predictor is broad. Whereas most quantitative proteomics studies have focused on higher organisms, we developed a predictive model of protein abundance for both Saccharomyces cerevisiae and Schizosaccharomyces pombe to explore the latitude at the protein level. Our predictor primarily relies on mRNA level, mRNA-protein interaction, mRNA folding energy and half-life, and tRNA adaptation. The combination of key features, allowing for the low certainty and uneven coverage of experimental observations, gives comparatively minor but robust prediction accuracy. The model substantially improved the analysis of protein regulation during the cell cycle: predicted protein abundance identified twice as many cell-cycle-associated proteins as experimental mRNA levels. Predicted protein abundance was more dynamic than observed mRNA expression, agreeing with experimental protein abundance from a human cell line. We illustrate how the same model can be used to predict the folding energy of mRNA when protein abundance is available, lending credence to the emerging view that mRNA folding affects translation efficiency. The software and data used in this research are available at http://bioinf.scmb.uq.edu.au/proteinabundance/.

Discovery of protein–RNA networks

We review the latest advances and future challenges in experimental and computational investigation of protein–RNA networks.

Computational identification of protein binding sites on RNAs using high-throughput RNA structure-probing data

MOTIVATION

High-throughput sequencing has been used to probe RNA structures, by treating RNAs with reagents that preferentially cleave or mark certain nucleotides according to their local structures, followed by sequencing of the resulting fragments. The data produced contain valuable information for studying various RNA properties.

RESULTS

We developed methods for statistically modeling these structure-probing data and extracting structural features from them. We show that the extracted features can be used to predict RNA 'zipcodes' in yeast, regions bound by the She complex in asymmetric localization. The prediction accuracy was better than using raw RNA probing data or sequence features. We further demonstrate the use of the extracted features in identifying binding sites of RNA binding proteins from whole-transcriptome global photoactivatable-ribonucleoside-enhanced cross-linking and immunopurification (gPAR-CLIP) data.

AVAILABILITY

The source code of our implemented methods is available at http://yiplab.cse.cuhk.edu.hk/probrna/ CONTACT: kevinyip@cse.cuhk.edu.hk Supplementary information: Supplementary data are available at Bioinformatics online.

Predicting RNA-protein interactions using only sequence information

Background

RNA-protein interactions (RPIs) play important roles in a wide variety of cellular processes, ranging from transcriptional and post-transcriptional regulation of gene expression to host defense against pathogens. High throughput experiments to identify RNA-protein interactions are beginning to provide valuable information about the complexity of RNA-protein interaction networks, but are expensive and time consuming. Hence, there is a need for reliable computational methods for predicting RNA-protein interactions.

Results

We propose RPISeq, a family of classifiers for predicting RNA-protein interactions using only sequence information. Given the sequences of an RNA and a protein as input, RPIseq predicts whether or not the RNA-protein pair interact. The RNA sequence is encoded as a normalized vector of its ribonucleotide 4-mer composition, and the protein sequence is encoded as a normalized vector of its 3-mer composition, based on a 7-letter reduced alphabet representation. Two variants of RPISeq are presented: RPISeq-SVM, which uses a Support Vector Machine (SVM) classifier and RPISeq-RF, which uses a Random Forest classifier. On two non-redundant benchmark datasets extracted from the Protein-RNA Interface Database (PRIDB), RPISeq achieved an AUC (Area Under the Receiver Operating Characteristic (ROC) curve) of 0.96 and 0.92. On a third dataset containing only mRNA-protein interactions, the performance of RPISeq was competitive with that of a published method that requires information regarding many different features (e.g., mRNA half-life, GO annotations) of the putative RNA and protein partners. In addition, RPISeq classifiers trained using the PRIDB data correctly predicted the majority (57-99%) of non-coding RNA-protein interactions in NPInter-derived networks from E. coli, S. cerevisiae, D. melanogaster, M. musculus, and H. sapiens.

Conclusions

Our experiments with RPISeq demonstrate that RNA-protein interactions can be reliably predicted using only sequence-derived information. RPISeq offers an inexpensive method for computational construction of RNA-protein interaction networks, and should provide useful insights into the function of non-coding RNAs. RPISeq is freely available as a web-based server at http://pridb.gdcb.iastate.edu/RPISeq/.