Prediction of RNA-binding amino acids from protein and RNA sequences

A comprehensive review of protein-centric predictors for biomolecular interactions: from proteins to nucleic acids and beyond

Proteins interact with diverse ligands to perform a large number of biological functions, such as gene expression and signal transduction. Accurate identification of these protein-ligand interactions is crucial to the understanding of molecular mechanisms and the development of new drugs. However, traditional biological experiments are time-consuming and expensive. With the development of high-throughput technologies, an increasing amount of protein data is available. In the past decades, many computational methods have been developed to predict protein-ligand interactions. Here, we review a comprehensive set of over 160 protein-ligand interaction predictors, which cover protein-protein, protein-nucleic acid, protein-peptide and protein-other ligands (nucleotide, heme, ion) interactions. We have carried out a comprehensive analysis of the above four types of predictors from several significant perspectives, including their inputs, feature profiles, models, availability, etc. The current methods primarily rely on protein sequences, especially utilizing evolutionary information. The significant improvement in predictions is attributed to deep learning methods. Additionally, sequence-based pretrained models and structure-based approaches are emerging as new trends.

A deep learning-based method for the prediction of DNA interacting residues in a protein

DNA-protein interaction is one of the most crucial interactions in the biological system, which decides the fate of many processes such as transcription, regulation and splicing of genes. In this study, we trained our models on a training dataset of 646 DNA-binding proteins having 15 636 DNA interacting and 298 503 non-interacting residues. Our trained models were evaluated on an independent dataset of 46 DNA-binding proteins having 965 DNA interacting and 9911 non-interacting residues. All proteins in the independent dataset have less than 30% of sequence similarity with proteins in the training dataset. A wide range of traditional machine learning and deep learning (1D-CNN) techniques-based models have been developed using binary, physicochemical properties and Position-Specific Scoring Matrix (PSSM)/evolutionary profiles. In the case of machine learning technique, eXtreme Gradient Boosting-based model achieved a maximum area under the receiver operating characteristics (AUROC) curve of 0.77 on the independent dataset using PSSM profile. Deep learning-based model achieved the highest AUROC of 0.79 on the independent dataset using a combination of all three profiles. We evaluated the performance of existing methods on the independent dataset and observed that our proposed method outperformed all the existing methods. In order to facilitate scientific community, we developed standalone software and web server, which are accessible from https://webs.iiitd.edu.in/raghava/dbpred.

Amino Acid Composition in Various Types of Nucleic Acid-Binding Proteins

Nucleic acid-binding proteins are traditionally divided into two categories: With the ability to bind DNA or RNA. In the light of new knowledge, such categorizing should be overcome because a large proportion of proteins can bind both DNA and RNA. Another even more important features of nucleic acid-binding proteins are so-called sequence or structure specificities. Proteins able to bind nucleic acids in a sequence-specific manner usually contain one or more of the well-defined structural motifs (zinc-fingers, leucine zipper, helix-turn-helix, or helix-loop-helix). In contrast, many proteins do not recognize nucleic acid sequence but rather local DNA or RNA structures (G-quadruplexes, i-motifs, triplexes, cruciforms, left-handed DNA/RNA form, and others). Finally, there are also proteins recognizing both sequence and local structural properties of nucleic acids (e.g., famous tumor suppressor p53). In this mini-review, we aim to summarize current knowledge about the amino acid composition of various types of nucleic acid-binding proteins with a special focus on significant enrichment and/or depletion in each category.

Comprehensive Survey and Comparative Assessment of RNA-Binding Residue Predictions with Analysis by RNA Type

With close to 30 sequence-based predictors of RNA-binding residues (RBRs), this comparative survey aims to help with understanding and selection of the appropriate tools. We discuss past reviews on this topic, survey a comprehensive collection of predictors, and comparatively assess six representative methods. We provide a novel and well-designed benchmark dataset and we are the first to report and compare protein-level and datasets-level results, and to contextualize performance to specific types of RNAs. The methods considered here are well-cited and rely on machine learning algorithms on occasion combined with homology-based prediction. Empirical tests reveal that they provide relatively accurate predictions. Virtually all methods perform well for the proteins that interact with rRNAs, some generate accurate predictions for mRNAs, snRNA, SRP and IRES, while proteins that bind tRNAs are predicted poorly. Moreover, except for DRNApred, they confuse DNA and RNA-binding residues. None of the six methods consistently outperforms the others when tested on individual proteins. This variable and complementary protein-level performance suggests that users should not rely on applying just the single best dataset-level predictor. We recommend that future work should focus on the development of approaches that facilitate protein-level selection of accurate predictors and the consensus-based prediction of RBRs.

Constructive Prediction of Potential RNA Aptamers for a Protein Target

Aptamers are short single-stranded nucleic acids that bind to target molecules with high affinity and selectivity. Aptamers are generally identified in vitro by performing SELEX (systematic evolution of ligands by exponential enrichment). Complementing the SELEX process, several computational methods have been proposed in the search for aptamers. However, many of these methods cannot be applied for finding new aptamers, either because they are classifiers for determining whether an RNA and protein interact with each other, or because they are limited to a specific target only. Hence, we developed a new random forest (RF) model for finding potential RNA aptamers for a protein target. From an extensive analysis of protein-RNA complexes including RNA aptamers-protein complexes, we identified key features of interacting RNA and protein molecules, and structural constraints on RNA aptamers. The potential RNA aptamers predicted by our method reveal similar secondary and protein-binding structures as the actual RNA aptamers. The RF model showed a reliable performance in both cross validations and independent testing. The key features of interacting RNA and protein molecules and the structural constraints identified in our study were effective in finding potential aptamers for a protein target. Although preliminary, our results are promising, and we believe this approach will be useful in reducing time and money spent on in vitro experiments by substantially limiting the size of the initial pool of nucleic acid sequences.

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.

Comprehensive review and empirical analysis of hallmarks of DNA-, RNA- and protein-binding residues in protein chains

Proteins interact with a variety of molecules including proteins and nucleic acids. We review a comprehensive collection of over 50 studies that analyze and/or predict these interactions. While majority of these studies address either solely protein–DNA or protein–RNA binding, only a few have a wider scope that covers both protein–protein and protein–nucleic acid binding. Our analysis reveals that binding residues are typically characterized with three hallmarks: relative solvent accessibility (RSA), evolutionary conservation and propensity of amino acids (AAs) for binding. Motivated by drawbacks of the prior studies, we perform a large-scale analysis to quantify and contrast the three hallmarks for residues that bind DNA-, RNA-, protein- and (for the first time) multi-ligand-binding residues that interact with DNA and proteins, and with RNA and proteins. Results generated on a well-annotated data set of over 23 000 proteins show that conservation of binding residues is higher for nucleic acid- than protein-binding residues. Multi-ligand-binding residues are more conserved and have higher RSA than single-ligand-binding residues. We empirically show that each hallmark discriminates between binding and nonbinding residues, even predicted RSA, and that combining them improves discriminatory power for each of the five types of interactions. Linear scoring functions that combine these hallmarks offer good predictive performance of residue-level propensity for binding and provide intuitive interpretation of predictions. Better understanding of these residue-level interactions will facilitate development of methods that accurately predict binding in the exponentially growing databases of protein sequences.

A MOTIF-BASED METHOD FOR PREDICTING INTERFACIAL RESIDUES IN BOTH THE RNA AND PROTEIN COMPONENTS OF PROTEIN-RNA COMPLEXES

Efforts to predict interfacial residues in protein-RNA complexes have largely focused on predicting RNA-binding residues in proteins. Computational methods for predicting protein-binding residues in RNA sequences, however, are a problem that has received relatively little attention to date. Although the value of sequence motifs for classifying and annotating protein sequences is well established, sequence motifs have not been widely applied to predicting interfacial residues in macromolecular complexes. Here, we propose a novel sequence motif-based method for "partner-specific" interfacial residue prediction. Given a specific protein-RNA pair, the goal is to simultaneously predict RNA binding residues in the protein sequence and protein-binding residues in the RNA sequence. In 5-fold cross validation experiments, our method, PS-PRIP, achieved 92% Specificity and 61% Sensitivity, with a Matthews correlation coefficient (MCC) of 0.58 in predicting RNA-binding sites in proteins. The method achieved 69% Specificity and 75% Sensitivity, but with a low MCC of 0.13 in predicting protein binding sites in RNAs. Similar performance results were obtained when PS-PRIP was tested on two independent "blind" datasets of experimentally validated protein- RNA interactions, suggesting the method should be widely applicable and valuable for identifying potential interfacial residues in protein-RNA complexes for which structural information is not available. The PS-PRIP webserver and datasets are available at: http://pridb.gdcb.iastate.edu/PSPRIP/.

A Large-Scale Assessment of Nucleic Acids Binding Site Prediction Programs

Computational prediction of nucleic acid binding sites in proteins are necessary to disentangle functional mechanisms in most biological processes and to explore the binding mechanisms. Several strategies have been proposed, but the state-of-the-art approaches display a great diversity in i) the definition of nucleic acid binding sites; ii) the training and test datasets; iii) the algorithmic methods for the prediction strategies; iv) the performance measures and v) the distribution and availability of the prediction programs. Here we report a large-scale assessment of 19 web servers and 3 stand-alone programs on 41 datasets including more than 5000 proteins derived from 3D structures of protein-nucleic acid complexes. Well-defined binary assessment criteria (specificity, sensitivity, precision, accuracy…) are applied. We found that i) the tools have been greatly improved over the years; ii) some of the approaches suffer from theoretical defects and there is still room for sorting out the essential mechanisms of binding; iii) RNA binding and DNA binding appear to follow similar driving forces and iv) dataset bias may exist in some methods.

PRIdictor: Protein-RNA Interaction predictor

Several computational methods have been developed to predict RNA-binding sites in protein, but its inverse problem (i.e., predicting protein-binding sites in RNA) has received much less attention. Furthermore, most methods that predict RNA-binding sites in protein do not consider interaction partners of a protein. This paper presents a web server called PRIdictor (Protein-RNA Interaction predictor) which predicts mutual binding sites in RNA and protein at the nucleotide- and residue-level resolutions from their sequences. PRIdictor can be used as a web-based application or web service at http://bclab.inha.ac.kr/pridictor.

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.

Prediction of nucleic acid binding probability in proteins: a neighboring residue network based score

We describe a general binding score for predicting the nucleic acid binding probability in proteins. The score is directly derived from physicochemical and evolutionary features and integrates a residue neighboring network approach. Our process achieves stable and high accuracies on both DNA- and RNA-binding proteins and illustrates how the main driving forces for nucleic acid binding are common. Because of the effective integration of the synergetic effects of the network of neighboring residues and the fact that the prediction yields a hierarchical scoring on the protein surface, energy funnels for nucleic acid binding appear on protein surfaces, pointing to the dynamic process occurring in the binding of nucleic acids to proteins.

Predicting protein-binding RNA nucleotides with consideration of binding partners

In recent years several computational methods have been developed to predict RNA-binding sites in protein. Most of these methods do not consider interacting partners of a protein, so they predict the same RNA-binding sites for a given protein sequence even if the protein binds to different RNAs. Unlike the problem of predicting RNA-binding sites in protein, the problem of predicting protein-binding sites in RNA has received little attention mainly because it is much more difficult and shows a lower accuracy on average. In our previous study, we developed a method that predicts protein-binding nucleotides from an RNA sequence. In an effort to improve the prediction accuracy and usefulness of the previous method, we developed a new method that uses both RNA and protein sequence data. In this study, we identified effective features of RNA and protein molecules and developed a new support vector machine (SVM) model to predict protein-binding nucleotides from RNA and protein sequence data. The new model that used both protein and RNA sequence data achieved a sensitivity of 86.5%, a specificity of 86.2%, a positive predictive value (PPV) of 72.6%, a negative predictive value (NPV) of 93.8% and Matthews correlation coefficient (MCC) of 0.69 in a 10-fold cross validation; it achieved a sensitivity of 58.8%, a specificity of 87.4%, a PPV of 65.1%, a NPV of 84.2% and MCC of 0.48 in independent testing. For comparative purpose, we built another prediction model that used RNA sequence data alone and ran it on the same dataset. In a 10 fold-cross validation it achieved a sensitivity of 85.7%, a specificity of 80.5%, a PPV of 67.7%, a NPV of 92.2% and MCC of 0.63; in independent testing it achieved a sensitivity of 67.7%, a specificity of 78.8%, a PPV of 57.6%, a NPV of 85.2% and MCC of 0.45. In both cross-validations and independent testing, the new model that used both RNA and protein sequences showed a better performance than the model that used RNA sequence data alone in most performance measures. To the best of our knowledge, this is the first sequence-based prediction of protein-binding nucleotides in RNA which considers the binding partner of RNA. The new model will provide valuable information for designing biochemical experiments to find putative protein-binding sites in RNA with unknown structure.

Sequence-based prediction of protein-binding sites in DNA: comparative study of two SVM models

As many structures of protein-DNA complexes have been known in the past years, several computational methods have been developed to predict DNA-binding sites in proteins. However, its inverse problem (i.e., predicting protein-binding sites in DNA) has received much less attention. One of the reasons is that the differences between the interaction propensities of nucleotides are much smaller than those between amino acids. Another reason is that DNA exhibits less diverse sequence patterns than protein. Therefore, predicting protein-binding DNA nucleotides is much harder than predicting DNA-binding amino acids. We computed the interaction propensity (IP) of nucleotide triplets with amino acids using an extensive dataset of protein-DNA complexes, and developed two support vector machine (SVM) models that predict protein-binding nucleotides from sequence data alone. One SVM model predicts protein-binding nucleotides using DNA sequence data alone, and the other SVM model predicts protein-binding nucleotides using both DNA and protein sequences. In a 10-fold cross-validation with 1519 DNA sequences, the SVM model that uses DNA sequence data only predicted protein-binding nucleotides with an accuracy of 67.0%, an F-measure of 67.1%, and a Matthews correlation coefficient (MCC) of 0.340. With an independent dataset of 181 DNAs that were not used in training, it achieved an accuracy of 66.2%, an F-measure 66.3% and a MCC of 0.324. Another SVM model that uses both DNA and protein sequences achieved an accuracy of 69.6%, an F-measure of 69.6%, and a MCC of 0.383 in a 10-fold cross-validation with 1519 DNA sequences and 859 protein sequences. With an independent dataset of 181 DNAs and 143 proteins, it showed an accuracy of 67.3%, an F-measure of 66.5% and a MCC of 0.329. Both in cross-validation and independent testing, the second SVM model that used both DNA and protein sequence data showed better performance than the first model that used DNA sequence data. To the best of our knowledge, this is the first attempt to predict protein-binding nucleotides in a given DNA sequence from the sequence data alone.

Identifying RNA-binding residues based on evolutionary conserved structural and energetic features

Increasing numbers of protein structures are solved each year, but many of these structures belong to proteins whose sequences are homologous to sequences in the Protein Data Bank. Nevertheless, the structures of homologous proteins belonging to the same family contain useful information because functionally important residues are expected to preserve physico-chemical, structural and energetic features. This information forms the basis of our method, which detects RNA-binding residues of a given RNA-binding protein as those residues that preserve physico-chemical, structural and energetic features in its homologs. Tests on 81 RNA-bound and 35 RNA-free protein structures showed that our method yields a higher fraction of true RNA-binding residues (higher precision) than two structure-based and two sequence-based machine-learning methods. Because the method requires no training data set and has no parameters, its precision does not degrade when applied to 'novel' protein sequences unlike methods that are parameterized for a given training data set. It was used to predict the 'unknown' RNA-binding residues in the C-terminal RNA-binding domain of human CPEB3. The two predicted residues, F430 and F474, were experimentally verified to bind RNA, in particular F430, whose mutation to alanine or asparagine nearly abolished RNA binding. The method has been implemented in a webserver called DR_bind1, which is freely available with no login requirement at http://drbind.limlab.ibms.sinica.edu.tw.

Predicting protein-binding RNA nucleotides using the feature-based removal of data redundancy and the interaction propensity of nucleotide triplets

Several learning approaches have been used to predict RNA-binding amino acids in a protein sequence, but there has been little attempt to predict protein-binding nucleotides in an RNA sequence. One of the reasons is that the differences between nucleotides in their interaction propensity are much smaller than those between amino acids. Another reason is that RNA exhibits less diverse sequence patterns than protein. Therefore, predicting protein-binding RNA nucleotides is much harder than predicting RNA-binding amino acids. We developed a new method that removes data redundancy in a training set of sequences based on their features. The new method constructs a larger and more informative training set than the standard redundancy removal method based on sequence similarity, and the constructed dataset is guaranteed to be redundancy-free. We computed the interaction propensity (IP) of nucleotide triplets by applying a new definition of IP to an extensive dataset of protein-RNA complexes, and developed a support vector machine (SVM) model to predict protein binding sites in RNA sequences. In a 5-fold cross-validation with 812 RNA sequences, the SVM model predicted protein-binding nucleotides with an accuracy of 86.4%, an F-measure of 84.8%, and a Matthews correlation coefficient of 0.66. With an independent dataset of 56 RNA sequences that were not used in training, the resulting accuracy was 68.1% with an F-measure of 71.7% and a Matthews correlation coefficient of 0.35. To the best of our knowledge, this is the first attempt to predict protein-binding RNA nucleotides in a given RNA sequence from the sequence data alone. The SVM model and datasets are freely available for academics at http://bclab.inha.ac.kr/primer.

Towards big data science in the decade ahead from ten years of InCoB and the 1st ISCB-Asia Joint Conference

The 2011 International Conference on Bioinformatics (InCoB) conference, which is the annual scientific conference of the Asia-Pacific Bioinformatics Network (APBioNet), is hosted by Kuala Lumpur, Malaysia, is co-organized with the first ISCB-Asia conference of the International Society for Computational Biology (ISCB). InCoB and the sequencing of the human genome are both celebrating their tenth anniversaries and InCoB’s goalposts for the next decade, implementing standards in bioinformatics and globally distributed computational networks, will be discussed and adopted at this conference. Of the 49 manuscripts (selected from 104 submissions) accepted to BMC Genomics and BMC Bioinformatics conference supplements, 24 are featured in this issue, covering software tools, genome/proteome analysis, systems biology (networks, pathways, bioimaging) and drug discovery and design.