Understanding how biomolecules interact is a major task of systems biology. To model protein-nucleic acid interactions, it is important to identify the DNA or RNA-binding residues in proteins. Protein sequence features, including the biochemical property of amino acids and evolutionary information in terms of position-specific scoring matrix (PSSM), have been used for DNA or RNA-binding site prediction. However, PSSM is rather designed for PSI-BLAST searches, and it may not contain all the evolutionary information for modelling DNA or RNA-binding sites in protein sequences. In the present study, several new descriptors of evolutionary information have been developed and evaluated for sequence-based prediction of DNA and RNA-binding residues using support vector machines (SVMs). The new descriptors were shown to improve classifier performance. Interestingly, the best classifiers were obtained by combining the new descriptors and PSSM, suggesting that they captured different aspects of evolutionary information for DNA and RNA-binding site prediction. The SVM classifiers achieved 77.3% sensitivity and 79.3% specificity for prediction of DNA-binding residues, and 71.6% sensitivity and 78.7% specificity for RNA-binding site prediction. Predictions at this level of accuracy may provide useful information for modelling protein-nucleic acid interactions in systems biology studies. We have thus developed a web-based tool called BindN+ (
 http://bioinfo.ggc.org/bindn+/
 ) to make the SVM classifiers accessible to the research community.

BindN+ for accurate prediction of DNA and RNA-binding residues from protein sequence features

The recent emergence of deep learning to characterize complex patterns of protein big data reveals its potential to address the classic challenges in the field of protein data mining. Much research has revealed the promise of deep learning as a powerful tool to transform protein big data into valuable knowledge, leading to scientific discoveries and practical solutions. In this review, we summarize recent publications on deep learning predictive approaches in the field of mining protein data. The application architectures of these methods include multilayer perceptrons, stacked autoencoders, deep belief networks, two- or three-dimensional convolutional neural networks, recurrent neural networks, graph neural networks, and complex neural networks and are described from five perspectives: residue-level prediction, sequence-level prediction, three-dimensional structural analysis, interaction prediction, and mass spectrometry data mining. The advantages and deficiencies of these architectures are presented in relation to various tasks in protein data mining. Additionally, some practical issues and their future directions are discussed, such as robust deep learning for protein noisy data, architecture optimization for specific tasks, efficient deep learning for limited protein data, multimodal deep learning for heterogeneous protein data, and interpretable deep learning for protein understanding. This review provides comprehensive perspectives on general deep learning techniques for protein data analysis.

Deep learning for mining protein data

Structure comparison and alignment are of fundamental importance in structural biology studies. We developed the first universal platform, US-align, to uniformly align monomer and complex structures of different macromolecules-proteins, RNAs and DNAs. The pipeline is built on a uniform TM-score objective function coupled with a heuristic alignment searching algorithm. Large-scale benchmarks demonstrated consistent advantages of US-align over state-of-the-art methods in pairwise and multiple structure alignments of different molecules. Detailed analyses showed that the main advantage of US-align lies in the extensive optimization of the unified objective function powered by efficient heuristic search iterations, which substantially improve the accuracy and speed of the structural alignment process. Meanwhile, the universal protocol fusing different molecular and structural types helps facilitate the heterogeneous oligomer structure comparison and template-based protein-protein and protein-RNA/DNA docking. 

/pdf/us-align-universal-structure-alignments-of-proteins-nucleic-2hb2uquo.pdf

US-align: universal structure alignments of proteins, nucleic acids, and macromolecular complexes

RBPro-RF: Use Chou’s 5-steps rule to predict RNA-binding proteins via random forest with elastic net

Motivation Comparison of RNA 3D structures can be used to infer functional relationship of RNA molecules. Most of the current RNA structure alignment programs are built on size-dependent scales, which complicate the interpretation of structure and functional relations. Meanwhile, the low speed prevents the programs from being applied to large-scale RNA structural database search. Results We developed an open-source algorithm, RNA-align, for RNA 3D structure alignment which has the structure similarity scaled by a size-independent and statistically interpretable scoring metric. Large-scale benchmark tests show that RNA-align significantly outperforms other state-of-the-art programs in both alignment accuracy and running speed. The major advantage of RNA-align lies at the quick convergence of the heuristic alignment iterations and the coarse-grained secondary structure assignment, both of which are crucial to the speed and accuracy of RNA structure alignments. Availability and implementation https://zhanglab.ccmb.med.umich.edu/RNA-align/. Supplementary information Supplementary data are available at Bioinformatics online.

RNA-align: quick and accurate alignment of RNA 3D structures based on size-independent TM-scoreRNA

RNA binding protein (RBP) plays an important role in cellular processes. Identifying RBPs by computation and experiment are both essential. Recently, an RBP predictor, RBPPred, is proposed in our group to predict RBPs. However, RBPPred is too slow for that it needs to generate PSSM matrix as its feature. Herein, based on the protein feature of RBPPred and Convolutional Neural Network (CNN), we develop a deep learning model called Deep-RBPPred. With the balance and imbalance training set, we obtain Deep-RBPPred-balance and Deep-RBPPred-imbalance models. Deep-RBPPred has three advantages comparing to previous methods. (1) Deep-RBPPred only needs few physicochemical properties based on protein sequences. (2) Deep-RBPPred runs much faster. (3) Deep-RBPPred has a good generalization ability. In the meantime, Deep-RBPPred is still as good as the state-of-the-art method. Testing in A. thaliana, S. cerevisiae and H. sapiens proteomes, MCC values are 0.82 (0.82), 0.65 (0.69) and 0.85 (0.80) for balance model (imbalance model) when the score cutoff is set to 0.5, respectively. In the same testing dataset, different machine learning algorithms (CNN and SVM) are also compared. The results show that CNN-based model can identify more RBPs than SVM-based. In comparing the balance and imbalance model, both CNN-base and SVM-based tend to favor the majority class in the imbalance set. Deep-RBPPred forecasts 280 (balance model) and 265 (imbalance model) of 299 new RBP. The sensitivity of balance model is about 7% higher than the state-of-the-art method. We also apply deep-RBPPred to 30 eukaryotes and 109 bacteria proteomes downloaded from Uniprot to estimate all possible RBPs. The estimating result shows that rates of RBPs in eukaryote proteomes are much higher than bacteria proteomes.

/pdf/deep-rbppred-predicting-rna-binding-proteins-in-the-proteome-17z9z4pgaz.pdf

Deep-RBPPred: Predicting RNA binding proteins in the proteome scale based on deep learning

The central nervous system (CNS) is vulnerable to viral infection, yet few host factors in the CNS are known to defend against invasion by neurotropic viruses. Long noncoding RNAs (lncRNAs) have been revealed to play critical roles in a wide variety of biological processes and are highly abundant in the mammalian brain, but their roles in defending against invasion of pathogens into the CNS remain unclear. We report here that multiple neurotropic viruses, including rabies virus, vesicular stomatitis virus, Semliki Forest virus, and herpes simplex virus 1, elicit the neuronal expression of a host-encoded lncRNA EDAL. EDAL inhibits the replication of these neurotropic viruses in neuronal cells and rabies virus infection in mouse brains. EDAL binds to the conserved histone methyltransferase enhancer of zest homolog 2 (EZH2) and specifically causes EZH2 degradation via lysosomes, reducing the cellular H3K27me3 level. The antiviral function of EDAL resides in a 56-nt antiviral substructure through which its 18-nt helix-loop intimately contacts multiple EZH2 sites surrounding T309, a known O-GlcNAcylation site. EDAL positively regulates the transcription of Pcp4l1 encoding a 10-kDa peptide, which inhibits the replication of multiple neurotropic viruses. Our findings show that a neuronal lncRNA can exert an effective antiviral function via blocking a specific O-GlcNAcylation that determines EZH2 lysosomal degradation, rather than the traditional interferon-dependent pathway.

/pdf/a-novel-antiviral-lncrna-edal-shields-a-t309-o-glcnacylation-qk5glvt7z1.pdf

A novel antiviral lncRNA, EDAL, shields a T309 O -GlcNAcylation site to promote EZH2 lysosomal degradation

RNA-protein 3D complex structure prediction is still challenging. Recently, a template-based approach PRIME is proposed in our team to build RNA-protein 3D complex structure models with a higher success rate than computational docking software. However, scoring function of RNA alignment algorithm SARA in PRIME is size-dependent, which limits its ability to detect templates in some cases. Herein, we developed a novel RNA 3D structural alignment approach RMalign, which is based on a size-independent scoring function RMscore. The parameter in RMscore is then optimized in randomly selected RNA pairs and phase transition points (from dissimilar to similar) are determined in another randomly selected RNA pairs. In tRNA benchmarking, the precision of RMscore is higher than that of SARAscore (0.88 and 0.78, respectively) with phase transition points. In balance-FSCOR benchmarking, RMalign performed as good as ESA-RNA with a non-normalized score measuring RNA structural similarity. In balance-x-FSCOR benchmarking, RMalign achieves much better than a state-of-the-art RNA 3D structural alignment approach SARA due to a size-independent scoring function. Take the advantage of RMalign, we update our RNA-protein modeling approach PRIME to version 2.0. The PRIME2.0 significantly improves about 10% success rate than PRIME. Based on a size-independent scoring function RMscore, a novel RNA 3D structural alignment approach RMalign is developed and integrated into PRIME2.0, which could be useful for the biological community in modeling protein-RNA interaction.

/pdf/rmalign-an-rna-structural-alignment-tool-based-on-a-novel-2qp7kntzox.pdf

RMalign: an RNA structural alignment tool based on a novel scoring function RMscore.

Motivation The main function of protein-RNA interaction is to regulate the expression of genes. Therefore, studying protein-RNA interactions is of great significance. The information of three-dimensional (3D) structures reveals that atomic interactions are particularly important. The calculation method for modeling a 3D structure of a complex mainly includes two strategies: free docking and template-based docking. These two methods are complementary in protein-protein docking. Therefore, integrating these two methods may improve the prediction accuracy. Results In this article, we compare the difference between the free docking and the template-based algorithm. Then we show the complementarity of these two methods. Based on the analysis of the calculation results, the transition point is confirmed and used to integrate two docking algorithms to develop P3DOCK. P3DOCK holds the advantages of both algorithms. The results of the three docking benchmarks show that P3DOCK is better than those two non-hybrid docking algorithms. The success rate of P3DOCK is also higher (3-20%) than state-of-the-art hybrid and non-hybrid methods. Finally, the hierarchical clustering algorithm is utilized to cluster the P3DOCK's decoys. The clustering algorithm improves the success rate of P3DOCK. For ease of use, we provide a P3DOCK webserver, which can be accessed at www.rnabinding.com/P3DOCK/P3DOCK.html. An integrated protein-RNA docking benchmark can be downloaded from http://rnabinding.com/P3DOCK/benchmark.html. Availability and implementation www.rnabinding.com/P3DOCK/P3DOCK.html. Supplementary information Supplementary data are available at Bioinformatics online.

P3DOCK: a protein–RNA docking webserver based on template-based and template-free docking

Protein-RNA interaction participates in many biological processes. So, studying protein–RNA interaction can help us to understand the function of protein and RNA. Although the protein–RNA 3D3D model, like PRIME, was useful in building 3D structural complexes, it can’t be used genome-wide, due to lacking RNA 3D structures. To take full advantage of RNA secondary structures revealed from high-throughput sequencing, we present PRIME-3D2D to predict binding sites of protein–RNA interaction. PRIME-3D2D is almost as good as PRIME at modeling protein–RNA complexes. PRIME-3D2D can be used to predict binding sites on PDB data (MCC = 0.75/0.70 for binding sites in protein/RNA) and transcription-wide (MCC = 0.285 for binding sites in RNA). Testing on PDB and yeast transcription-wide data show that PRIME-3D2D performs better than other binding sites predictor. So, PRIME-3D2D can be used to predict the binding sites both on PDB and genome-wide, and it’s freely available. Xie et al. report a new computational method PRIME-3D2D to predict binding sites of protein–RNA interaction by considering protein 3D structure and RNA 2D structure. It is freely available, performs better than other binding sites predictor and is as good as PRIME to model protein–RNA complex.

/pdf/prime-3d2d-is-a-3d2d-model-to-predict-binding-sites-of-2ql195hoiu.pdf

Juan Xie

Papers

Deep-RBPPred: Predicting RNA binding proteins in the proteome scale based on deep learning

A novel antiviral lncRNA, EDAL, shields a T309 O -GlcNAcylation site to promote EZH2 lysosomal degradation

RMalign: an RNA structural alignment tool based on a novel scoring function RMscore.

P3DOCK: a protein–RNA docking webserver based on template-based and template-free docking

PRIME-3D2D is a 3D2D model to predict binding sites of protein-RNA interaction.