Leveraging permutation testing to assess confidence in positive-unlabeled learning applied to high-dimensional biological datasets

BACKGROUND

Compared to traditional supervised machine learning approaches employing fully labeled samples, positive-unlabeled (PU) learning techniques aim to classify "unlabeled" samples based on a smaller proportion of known positive examples. This more challenging modeling goal reflects many real-world scenarios in which negative examples are not available-posing direct challenges to defining prediction accuracy and robustness. While several studies have evaluated predictions learned from only definitive positive examples, few have investigated whether correct classification of a high proportion of known positives (KP) samples from among unlabeled samples can act as a surrogate to indicate model quality.

RESULTS

In this study, we report a novel methodology combining multiple established PU learning-based strategies with permutation testing to evaluate the potential of KP samples to accurately classify unlabeled samples without using "ground truth" positive and negative labels for validation. Multivariate synthetic and real-world high-dimensional benchmark datasets were employed to demonstrate the suitability of the proposed pipeline to provide evidence of model robustness across varied underlying ground truth class label compositions among the unlabeled set and with different proportions of KP examples. Comparisons between model performance with actual and permuted labels could be used to distinguish reliable from unreliable models.

CONCLUSIONS

As in fully supervised machine learning, permutation testing offers a means to set a baseline "no-information rate" benchmark in the context of semi-supervised PU learning inference tasks-providing a standard against which model performance can be compared.

Learning peptide properties with positive examples only

Deep learning can create accurate predictive models by exploiting existing large-scale experimental data, and guide the design of molecules. However, a major barrier is the requirement of both positive and negative examples in the classical supervised learning frameworks. Notably, most peptide databases come with missing information and low number of observations on negative examples, as such sequences are hard to obtain using high-throughput screening methods. To address this challenge, we solely exploit the limited known positive examples in a semi-supervised setting, and discover peptide sequences that are likely to map to certain antimicrobial properties via positive-unlabeled learning (PU). In particular, we use the two learning strategies of adapting base classifier and reliable negative identification to build deep learning models for inferring solubility, hemolysis, binding against SHP-2, and non-fouling activity of peptides, given their sequence. We evaluate the predictive performance of our PU learning method and show that by only using the positive data, it can achieve competitive performance when compared with the classical positive-negative (PN) classification approach, where there is access to both positive and negative examples.

Positive-unlabeled learning identifies vaccine candidate antigens in the malaria parasite Plasmodium falciparum

Malaria vaccine development is hampered by extensive antigenic variation and complex life stages of Plasmodium species. Vaccine development has focused on a small number of antigens, many of which were identified without utilizing systematic genome-level approaches. In this study, we implement a machine learning-based reverse vaccinology approach to predict potential new malaria vaccine candidate antigens. We assemble and analyze P. falciparum proteomic, structural, functional, immunological, genomic, and transcriptomic data, and use positive-unlabeled learning to predict potential antigens based on the properties of known antigens and remaining proteins. We prioritize candidate antigens based on model performance on reference antigens with different genetic diversity and quantify the protein properties that contribute most to identifying top candidates. Candidate antigens are characterized by gene essentiality, gene ontology, and gene expression in different life stages to inform future vaccine development. This approach provides a framework for identifying and prioritizing candidate vaccine antigens for a broad range of pathogens.

Learning Peptide Properties with Positive Examples Only

Deep learning can create accurate predictive models by exploiting existing large-scale experimental data, and guide the design of molecules. However, a major barrier is the requirement of both positive and negative examples in the classical supervised learning frameworks. Notably, most peptide databases come with missing information and low number of observations on negative examples, as such sequences are hard to obtain using high-throughput screening methods. To address this challenge, we solely exploit the limited known positive examples in a semi-supervised setting, and discover peptide sequences that are likely to map to certain antimicrobial properties via positive-unlabeled learning (PU). In particular, we use the two learning strategies of adapting base classifier and reliable negative identification to build deep learning models for inferring solubility, hemolysis, binding against SHP-2, and non-fouling activity of peptides, given their sequence. We evaluate the predictive performance of our PU learning method and show that by only using the positive data, it can achieve competitive performance when compared with the classical positive-negative (PN) classification approach, where there is access to both positive and negative examples.

Artificial intelligence methods enhance the discovery of RNA interactions

Understanding how RNAs interact with proteins, RNAs, or other molecules remains a challenge of main interest in biology, given the importance of these complexes in both normal and pathological cellular processes. Since experimental datasets are starting to be available for hundreds of functional interactions between RNAs and other biomolecules, several machine learning and deep learning algorithms have been proposed for predicting RNA-RNA or RNA-protein interactions. However, most of these approaches were evaluated on a single dataset, making performance comparisons difficult. With this review, we aim to summarize recent computational methods, developed in this broad research area, highlighting feature encoding and machine learning strategies adopted. Given the magnitude of the effect that dataset size and quality have on performance, we explored the characteristics of these datasets. Additionally, we discuss multiple approaches to generate datasets of negative examples for training. Finally, we describe the best-performing methods to predict interactions between proteins and specific classes of RNA molecules, such as circular RNAs (circRNAs) and long non-coding RNAs (lncRNAs), and methods to predict RNA-RNA or RNA-RBP interactions independently of the RNA type.

Benchmarks in antimicrobial peptide prediction are biased due to the selection of negative data

Antimicrobial peptides (AMPs) are a heterogeneous group of short polypeptides that target not only microorganisms but also viruses and cancer cells. Due to their lower selection for resistance compared with traditional antibiotics, AMPs have been attracting the ever-growing attention from researchers, including bioinformaticians. Machine learning represents the most cost-effective method for novel AMP discovery and consequently many computational tools for AMP prediction have been recently developed. In this article, we investigate the impact of negative data sampling on model performance and benchmarking. We generated 660 predictive models using 12 machine learning architectures, a single positive data set and 11 negative data sampling methods; the architectures and methods were defined on the basis of published AMP prediction software. Our results clearly indicate that similar training and benchmark data set, i.e. produced by the same or a similar negative data sampling method, positively affect model performance. Consequently, all the benchmark analyses that have been performed for AMP prediction models are significantly biased and, moreover, we do not know which model is the most accurate. To provide researchers with reliable information about the performance of AMP predictors, we also created a web server AMPBenchmark for fair model benchmarking. AMPBenchmark is available at http://BioGenies.info/AMPBenchmark.

Roles of Emerging RNA-Binding Activity of cGAS in Innate Antiviral Response

cGAS, a DNA sensor in mammalian cells, catalyzes the generation of 2'-3'-cyclic AMP-GMP (cGAMP) once activated by the binding of free DNA. cGAMP can bind to STING, activating downstream TBK1-IRF-3 signaling to initiate the expression of type I interferons. Although cGAS has been considered a traditional DNA-binding protein, several lines of evidence suggest that cGAS is a potential RNA-binding protein (RBP), which is mainly supported by its interactions with RNAs, RBP partners, RNA/cGAS-phase-separations as well as its structural similarity with the dsRNA recognition receptor 2'-5' oligoadenylate synthase. Moreover, two influential studies reported that the cGAS-like receptors (cGLRs) of fly Drosophila melanogaster sense RNA and control 3'-2'-cGAMP signaling. In this review, we summarize and discuss in depth recent studies that identified or implied cGAS as an RBP. We also comprehensively summarized current experimental methods and computational tools that can identify or predict RNAs that bind to cGAS. Based on these discussions, we appeal that the RNA-binding activity of cGAS cannot be ignored in the cGAS-mediated innate antiviral response. It will be important to identify RNAs that can bind and regulate the activity of cGAS in cells with or without virus infection. Our review provides novel insight into the regulation of cGAS by its RNA-binding activity and extends beyond its DNA-binding activity. Our review would be significant for understanding the precise modulation of cGAS activity, providing the foundation for the future development of drugs against cGAS-triggering autoimmune diseases such as Aicardi-Gourtières syndrome.

Positive-unlabeled learning in bioinformatics and computational biology: a brief review

Conventional supervised binary classification algorithms have been widely applied to address significant research questions using biological and biomedical data. This classification scheme requires two fully labeled classes of data (e.g. positive and negative samples) to train a classification model. However, in many bioinformatics applications, labeling data is laborious, and the negative samples might be potentially mislabeled due to the limited sensitivity of the experimental equipment. The positive unlabeled (PU) learning scheme was therefore proposed to enable the classifier to learn directly from limited positive samples and a large number of unlabeled samples (i.e. a mixture of positive or negative samples). To date, several PU learning algorithms have been developed to address various biological questions, such as sequence identification, functional site characterization and interaction prediction. In this paper, we revisit a collection of 29 state-of-the-art PU learning bioinformatic applications to address various biological questions. Various important aspects are extensively discussed, including PU learning methodology, biological application, classifier design and evaluation strategy. We also comment on the existing issues of PU learning and offer our perspectives for the future development of PU learning applications. We anticipate that our work serves as an instrumental guideline for a better understanding of the PU learning framework in bioinformatics and further developing next-generation PU learning frameworks for critical biological applications.

On the Unreported-Profile-is-Negative Assumption for Predictive Cheminformatics

In cheminformatics, compound-target binding profiles has been a main source of data for research. For data repositories that only provide positive profiles, a popular assumption is that unreported profiles are all negative. In this paper, we caution the audience not to take this assumption for granted, and present empirical evidence of its ineffectiveness from a machine learning perspective. Our examination is based on a setting where binding profiles are used as features to train predictive models; we show (1) prediction performance degrades when the assumption fails and (2) explicit recovery of unreported profiles improves prediction performance. In particular, we propose a framework that jointly recovers profiles and learns predictive model, and show it achieves further performance improvement. The presented study not only suggests applying matrix recovery methods to recover unreported profiles, but also initiates a new missing feature problem which we called Learning with Positive and Unknown Features.

LPGNMF: Predicting Long Non-Coding RNA and Protein Interaction Using Graph Regularized Nonnegative Matrix Factorization

Long non-coding RNAs (lncRNA) play crucial roles in a variety of biological processes and complex diseases. Massive studies have indicated that lncRNAs interact with related proteins to exert regulation of cellular biological processes. Because it is time-consuming and expensive to determine lncRNA-protein interaction by experiment, more accurate predictions of interaction by computational methods are imperative. We propose a novel computational approach, predicting lncRNA-protein interaction using graph regularized nonnegative matrix factorization (LPGNMF), to discover unobserved lncRNA-protein association. First, we calculate lncRNA similarity and protein similarity by integrating the lncRNA expression information and gene ontology information. Subsequently, we utilize graph regularized nonnegative matrix factorization framework to predict potential interactions for all lncRNA simultaneously. In the cross validation test, LPGNMF achieves an AUC of 85.2 percent, higher than those of other compared methods. In addition, novel lncRNA-protein interactions detected by LPGNMF are validated by literatures or database. The results indicate that our method is effective to discover potential lncRNA-protein interaction.

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.

A path-based computational model for long non-coding RNA-protein interaction prediction

Recently, lncRNAs have attracted accumulating attentions because more and more experimental researches have shown lncRNA can play critical roles in many biological processes. Predicting potential interactions between lncRNAs and proteins are key to understand the lncRNAs biological functions. But traditional biological experiments are expensive and time-consuming, network similarity methods provide a powerful solution to computationally predict lncRNA-protein interactions. In this work, a novel path-based lncRNA-protein interaction (PBLPI) prediction model is proposed by integrating protein semantic similarity, lncRNA functional similarity, known human lncRNA-protein interactions, and Gaussian interaction profile kernel similarity. PBLPI model utilizes three interlinked sub-graphs to construct a heterogeneous graph, and then infers potential lncRNA-protein interactions through depth-first search algorithm. Consequently, PBLPI achieves reliable performance in the frameworks of 5-fold cross validation (average AUC is 0.9244 and AUPR is 0.6478). In the case study, we use "Mus musculus" data to further validate the reliability of PBLPI method. It is anticipated that PBLPI would become a useful tool to identify potential lncRNA-protein interactions.

Long noncoding RNA: a crosslink in biological regulatory network

Long noncoding RNAs (lncRNAs) had been defined as a novel class of functional RNAs longer than 200 nucleotides around a decade ago. It is widely acknowledged that lncRNAs play a significant role in regulation of gene expression, but the biological and molecular mechanisms are diverse and complex, and remain to be determined. Especially, the regulatory network of lncRNAs associated with other biological molecules is still a controversial matter, thus becoming a new frontier of the studies on transcriptome. Recent advance in high-throughput sequencing technologies and bioinformatics approaches may be an accelerator to lift the mysterious veil. In this review, we will outline well-known associations between lncRNAs and other biological molecules, demonstrate the diverse bioinformatics approaches applied in prediction and analysis of lncRNA interaction and perform a case study for lncRNA linc00460 to concretely decipher the lncRNA regulatory network.

Construction of Complex Features for Computational Predicting ncRNA-Protein Interaction

Non-coding RNA (ncRNA) plays important roles in many critical regulation processes. Many ncRNAs perform their regulatory functions by the form of RNA-protein complexes. Therefore, identifying the interaction between ncRNA and protein is fundamental to understand functions of ncRNA. Under pressures from expensive cost of experimental techniques, developing an accuracy computational predictive model has become an indispensable way to identify ncRNA-protein interaction. A powerful predicting model of ncRNA-protein interaction needs a good feature set of characterizing the interaction. In this paper, a novel method is put forward to generate complex features for characterizing ncRNA-protein interaction (named CFRP). To obtain a comprehensive description of ncRNA-protein interaction, complex features are generated by non-linear transformations from the traditional k-mer features of ncRNA and protein sequences. To further reduce the dimensions of complex features, a group of discriminative features are selected by random forest. To validate the performances of the proposed method, a series of experiments are carried on several widely-used public datasets. Compared with the traditional k-mer features, the CFRP complex features can boost the performances of ncRNA-protein interaction prediction model. Meanwhile, the CFRP-based prediction model is compared with several state-of-the-art methods, and the results show that the proposed method achieves better performances than the others in term of the evaluation metrics. In conclusion, the complex features generated by CFRP are beneficial for building a powerful predicting model of ncRNA-protein interaction.

Chaperones, Membrane Trafficking and Signal Transduction Proteins Regulate Zaire Ebola Virus trVLPs and Interact With trVLP Elements

Ebolavirus (EBOV) life cycle involves interactions with numerous host factors, but it remains poorly understood, as does pathogenesis. Herein, we synthesized 65 siRNAs targeting host genes mostly connected with aspects of the negative-sense RNA virus life cycle (including viral entry, uncoating, fusion, replication, assembly, and budding). We produced EBOV transcription- and replication-competent virus-like particles (trVLPs) to mimic the EBOV life cycle. After screening host factors associated with the trVLP life cycle, we assessed interactions of host proteins with trVLP glycoprotein (GP), VP40, and RNA by co-immunoprecipitation (Co-IP) and chromatin immunoprecipitation (ChIP). The results demonstrate that RNAi silencing with 11 siRNAs (ANXA5, ARFGAP1, FLT4, GRP78, HSPA1A, HSP90AB1, HSPA8, MAPK11, MEK2, NTRK1, and YWHAZ) decreased the replication efficiency of trVLPs. Co-IP revealed nine candidate host proteins (FLT4, GRP78, HSPA1A, HSP90AB1, HSPA8, MAPK11, MEK2, NTRK1, and YWHAZ) potentially interacting with trVLP GP, and four (ANXA5, GRP78, HSPA1A, and HSP90AB1) potentially interacting with trVLP VP40. Ch-IP identified nine candidate host proteins (ANXA5, ARFGAP1, FLT4, GRP78, HSPA1A, HSP90AB1, MAPK11, MEK2, and NTRK1) interacting with trVLP RNA. This study was based on trVLP and could not replace live ebolavirus entirely; in particular, the interaction between trVLP RNA and host proteins cannot be assumed to be identical in live virus. However, the results provide valuable information for further studies and deepen our understanding of essential host factors involved in the EBOV life cycle.

Effectively Identifying Compound-Protein Interactions by Learning from Positive and Unlabeled Examples

Prediction of compound-protein interactions (CPIs) is to find new compound-protein pairs where a protein is targeted by at least a compound, which is a crucial step in new drug design. Currently, a number of machine learning based methods have been developed to predict new CPIs in the literature. However, as there is not yet any publicly available set of validated negative CPIs, most existing machine learning based approaches use the unknown interactions (not validated CPIs) selected randomly as the negative examples to train classifiers for predicting new CPIs. Obviously, this is not quite reasonable and unavoidably impacts the CPI prediction performance. In this paper, we simply take the unknown CPIs as unlabeled examples, and propose a new method called PUCPI (the abbreviation of PU learning for Compound-Protein Interaction identification) that employs biased-SVM (Support Vector Machine) to predict CPIs using only positive and unlabeled examples. PU learning is a class of learning methods that leans from positive and unlabeled (PU) samples. To the best of our knowledge, this is the first work that identifies CPIs using only positive and unlabeled examples. We first collect known CPIs as positive examples and then randomly select compound-protein pairs not in the positive set as unlabeled examples. For each CPI/compound-protein pair, we extract protein domains as protein features and compound substructures as chemical features, then take the tensor product of the corresponding compound features and protein features as the feature vector of the CPI/compound-protein pair. After that, biased-SVM is employed to train classifiers on different datasets of CPIs and compound-protein pairs. Experiments over various datasets show that our method outperforms six typical classifiers, including random forest, L1- and L2-regularized logistic regression, naive Bayes, SVM and k-nearest neighbor (kNN), and three types of existing CPI prediction models. More information can be found at http://admis.fudan.edu.cn/projects/pucpi.html.

The Ever-Evolving Concept of the Gene: The Use of RNA/Protein Experimental Techniques to Understand Genome Functions

The completion of the human genome sequence together with advances in sequencing technologies have shifted the paradigm of the genome, as composed of discrete and hereditable coding entities, and have shown the abundance of functional noncoding DNA. This part of the genome, previously dismissed as “junk” DNA, increases proportionally with organismal complexity and contributes to gene regulation beyond the boundaries of known protein-coding genes. Different classes of functionally relevant nonprotein-coding RNAs are transcribed from noncoding DNA sequences. Among them are the long noncoding RNAs (lncRNAs), which are thought to participate in the basal regulation of protein-coding genes at both transcriptional and post-transcriptional levels. Although knowledge of this field is still limited, the ability of lncRNAs to localize in different cellular compartments, to fold into specific secondary structures and to interact with different molecules (RNA or proteins) endows them with multiple regulatory mechanisms. It is becoming evident that lncRNAs may play a crucial role in most biological processes such as the control of development, differentiation and cell growth. This review places the evolution of the concept of the gene in its historical context, from Darwin's hypothetical mechanism of heredity to the post-genomic era. We discuss how the original idea of protein-coding genes as unique determinants of phenotypic traits has been reconsidered in light of the existence of noncoding RNAs. We summarize the technological developments which have been made in the genome-wide identification and study of lncRNAs and emphasize the methodologies that have aided our understanding of the complexity of lncRNA-protein interactions in recent years.

Methods for Identification of Protein-RNA Interaction

The importance of RNA-protein interactions in regulation of mRNA and non-coding RNA function is increasingly appreciated. With the development of next generation high-throughput sequencing technologies, a variety of methods have been proposed to comprehensively identify RNA-protein interactions. In this chapter, we discussed the traditional and state-of-the-art technologies that were used to study RNA-protein interaction, including experimental and computational methods. To help highlight the biological significance of RNA-protein interaction in complex diseases, online resources on RNA-protein interactions were briefly discussed. Finally, we discussed the interaction among noncoding RNAs (such as long noncoding RNAs and microRNAs) and proteins, as well as the dysregulation of RNA-protein interaction in complex diseases. These summarization will ultimately provide a more complete picture for understanding of the function of RNA-protein interactions, including how these interaction assembled and how they modulate cellular function in complex diseases.

Fusing multiple protein-protein similarity networks to effectively predict lncRNA-protein interactions

BACKGROUND

Long non-coding RNA (lncRNA) plays important roles in many biological and pathological processes, including transcriptional regulation and gene regulation. As lncRNA interacts with multiple proteins, predicting lncRNA-protein interactions (lncRPIs) is an important way to study the functions of lncRNA. Up to now, there have been a few works that exploit protein-protein interactions (PPIs) to help the prediction of new lncRPIs.

RESULTS

In this paper, we propose to boost the prediction of lncRPIs by fusing multiple protein-protein similarity networks (PPSNs). Concretely, we first construct four PPSNs based on protein sequences, protein domains, protein GO terms and the STRING database respectively, then build a more informative PPSN by fusing these four constructed PPSNs. Finally, we predict new lncRPIs by a random walk method with the fused PPSN and known lncRPIs. Our experimental results show that the new approach outperforms the existing methods.

CONCLUSION

Fusing multiple protein-protein similarity networks can effectively boost the performance of predicting lncRPIs.

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.

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 .

Computational Prediction of RNA-Binding Proteins and Binding Sites

Proteins and RNA interaction have vital roles in many cellular processes such as protein synthesis, sequence encoding, RNA transfer, and gene regulation at the transcriptional and post-transcriptional levels. Approximately 6%–8% of all proteins are RNA-binding proteins (RBPs). Distinguishing these RBPs or their binding residues is a major aim of structural biology. Previously, a number of experimental methods were developed for the determination of protein–RNA interactions. However, these experimental methods are expensive, time-consuming, and labor-intensive. Alternatively, researchers have developed many computational approaches to predict RBPs and protein–RNA binding sites, by combining various machine learning methods and abundant sequence and/or structural features. There are three kinds of computational approaches, which are prediction from protein sequence, prediction from protein structure, and protein-RNA docking. In this paper, we review all existing studies of predictions of RNA-binding sites and RBPs and complexes, including data sets used in different approaches, sequence and structural features used in several predictors, prediction method classifications, performance comparisons, evaluation methods, and future directions.

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.