Predicting DNA-binding proteins and binding residues by complex structure prediction and application to human proteome

Twenty years of advances in prediction of nucleic acid-binding residues in protein sequences

Computational prediction of nucleic acid-binding residues in protein sequences is an active field of research, with over 80 methods that were released in the past 2 decades. We identify and discuss 87 sequence-based predictors that include dozens of recently published methods that are surveyed for the first time. We overview historical progress and examine multiple practical issues that include availability and impact of predictors, key features of their predictive models, and important aspects related to their training and assessment. We observe that the past decade has brought increased use of deep neural networks and protein language models, which contributed to substantial gains in the predictive performance. We also highlight advancements in vital and challenging issues that include cross-predictions between deoxyribonucleic acid (DNA)-binding and ribonucleic acid (RNA)-binding residues and targeting the two distinct sources of binding annotations, structure-based versus intrinsic disorder-based. The methods trained on the structure-annotated interactions tend to perform poorly on the disorder-annotated binding and vice versa, with only a few methods that target and perform well across both annotation types. The cross-predictions are a significant problem, with some predictors of DNA-binding or RNA-binding residues indiscriminately predicting interactions with both nucleic acid types. Moreover, we show that methods with web servers are cited substantially more than tools without implementation or with no longer working implementations, motivating the development and long-term maintenance of the web servers. We close by discussing future research directions that aim to drive further progress in this area.

DeepDBS: Identification of DNA-binding sites in protein sequences by using deep representations and random forest

Interactions of biological molecules in organisms are considered to be primary factors for the lifecycle of that organism. Various important biological functions are dependent on such interactions and among different kinds of interactions, the protein DNA interactions are very important for the processes of transcription, regulation of gene expression, DNA repairing and packaging. Thus, keeping the knowledge of such interactions and the sites of those interactions is necessary to study the mechanism of various biological processes. As experimental identification through biological assays is quite resource-demanding, costly and error-prone, scientists opt for the computational methods for efficient and accurate identification of such DNA-protein interaction sites. Thus, herein, we propose a novel and accurate method namely DeepDBS for the identification of DNA-binding sites in proteins, using primary amino acid sequences of proteins under study. From protein sequences, deep representations were computed through a one-dimensional convolution neural network (1D-CNN), recurrent neural network (RNN) and long short-term memory (LSTM) network and were further used to train a Random Forest classifier. Random Forest with LSTM-based features outperformed the other models, as well as the existing state-of-the-art methods with an accuracy score of 0.99 for self-consistency test, 10-fold cross-validation, 5-fold cross-validation, and jackknife validation while 0.92 for independent dataset testing. It is concluded based on results that the DeepDBS can help accurate and efficient identification of DNA binding sites (DBS) in proteins.

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.

DBPboost:A method of classification of DNA-binding proteins based on improved differential evolution algorithm and feature extraction

DNA-binding proteins are a class of proteins that can interact with DNA molecules through physical and chemical interactions. Their main functions include regulating gene expression, maintaining chromosome structure and stability, and more. DNA-binding proteins play a crucial role in cellular and molecular biology, as they are essential for maintaining normal cellular physiological functions and adapting to environmental changes. The prediction of DNA-binding proteins has been a hot topic in the field of bioinformatics. The key to accurately classifying DNA-binding proteins is to find suitable feature sources and explore the information they contain. Although there are already many models for predicting DNA-binding proteins, there is still room for improvement in mining feature source information and calculation methods. In this study, we created a model called DBPboost to better identify DNA-binding proteins. The innovation of this study lies in the use of eight feature extraction methods, the improvement of the feature selection step, which involves selecting some features first and then performing feature selection again after feature fusion, and the optimization of the differential evolution algorithm in feature fusion, which improves the performance of feature fusion. The experimental results show that the prediction accuracy of the model on the UniSwiss dataset is 89.32%, and the sensitivity is 89.01%, which is better than most existing models.

Deep-WET: a deep learning-based approach for predicting DNA-binding proteins using word embedding techniques with weighted features

DNA-binding proteins (DBPs) play a significant role in all phases of genetic processes, including DNA recombination, repair, and modification. They are often utilized in drug discovery as fundamental elements of steroids, antibiotics, and anticancer drugs. Predicting them poses the most challenging task in proteomics research. Conventional experimental methods for DBP identification are costly and sometimes biased toward prediction. Therefore, developing powerful computational methods that can accurately and rapidly identify DBPs from sequence information is an urgent need. In this study, we propose a novel deep learning-based method called Deep-WET to accurately identify DBPs from primary sequence information. In Deep-WET, we employed three powerful feature encoding schemes containing Global Vectors, Word2Vec, and fastText to encode the protein sequence. Subsequently, these three features were sequentially combined and weighted using the weights obtained from the elements learned through the differential evolution (DE) algorithm. To enhance the predictive performance of Deep-WET, we applied the SHapley Additive exPlanations approach to remove irrelevant features. Finally, the optimal feature subset was input into convolutional neural networks to construct the Deep-WET predictor. Both cross-validation and independent tests indicated that Deep-WET achieved superior predictive performance compared to conventional machine learning classifiers. In addition, in extensive independent test, Deep-WET was effective and outperformed than several state-of-the-art methods for DBP prediction, with accuracy of 78.08%, MCC of 0.559, and AUC of 0.805. This superior performance shows that Deep-WET has a tremendous predictive capacity to predict DBPs. The web server of Deep-WET and curated datasets in this study are available at https://deepwet-dna.monarcatechnical.com/ . The proposed Deep-WET is anticipated to serve the community-wide effort for large-scale identification of potential DBPs.

MV-H-RKM: A Multiple View-Based Hypergraph Regularized Restricted Kernel Machine for Predicting DNA-Binding Proteins

DNA-binding proteins (DBPs) have a significant impact on many life activities, so identification of DBPs is a crucial issue. And it is greatly helpful to understand the mechanism of protein-DNA interactions. In traditional experimental methods, it is significant time-consuming and labor-consuming to identify DBPs. In recent years, many researchers have proposed lots of different DBP identification methods based on machine learning algorithm to overcome shortcomings mentioned above. However, most existing methods cannot get satisfactory results. In this paper, we focus on developing a new predictor of DBPs, called Multi-View Hypergraph Restricted Kernel Machines (MV-H-RKM). In this method, we extract five features from the three views of the proteins. To fuse these features, we couple them by means of the shared hidden vector. Besides, we employ the hypergraph regularization to enforce the structure consistency between original features and the hidden vector. Experimental results show that the accuracy of MV-H-RKM is 84.09% and 85.48% on PDB1075 and PDB186 data set respectively, and demonstrate that our proposed method performs better than other state-of-the-art approaches. The code is publicly available at https://github.com/ShixuanGG/MV-H-RKM.

Improving DNA-Binding Protein Prediction Using Three-Part Sequence-Order Feature Extraction and a Deep Neural Network Algorithm

Identification of the DNA-binding protein (DBP) helps dig out information embedded in the DNA-protein interaction, which is significant to understanding the mechanisms of DNA replication, transcription, and repair. Although existing computational methods for predicting the DBPs based on protein sequences have obtained great success, there is still room for improvement since the sequence-order information is not fully mined in these methods. In this study, a new three-part sequence-order feature extraction (called TPSO) strategy is developed to extract more discriminative information from protein sequences for predicting the DBPs. For each query protein, TPSO first divides its primary sequence features into N- and C-terminal fragments and then extracts the numerical pseudo features of three parts including the full sequence and these two fragments, respectively. Based on TPSO, a novel deep learning-based method, called TPSO-DBP, is proposed, which employs the sequence-based single-view features, the bidirectional long short-term memory (BiLSTM) and fully connected (FC) neural networks to learn the DBP prediction model. Empirical outcomes reveal that TPSO-DBP can achieve an accuracy of 87.01%, covering 85.30% of all DBPs, while achieving a Matthew's correlation coefficient value (0.741) that is significantly higher than most existing state-of-the-art DBP prediction methods. Detailed data analyses have indicated that the advantages of TPSO-DBP lie in the utilization of TPSO, which helps extract more concealed prominent patterns, and the deep neural network framework composed of BiLSTM and FC that learns the nonlinear relationships between input features and DBPs. The standalone package and web server of TPSO-DBP are freely available at https://jun-csbio.github.io/TPSO-DBP/.

To Improve Prediction of Binding Residues With DNA, RNA, Carbohydrate, and Peptide Via Multi-Task Deep Neural Networks

MOTIVATION

The interactions of proteins with DNA, RNA, peptide, and carbohydrate play key roles in various biological processes. The studies of uncharacterized protein-molecules interactions could be aided by accurate predictions of residues that bind with partner molecules. However, the existing methods for predicting binding residues on proteins remain of relatively low accuracies due to the limited number of complex structures in databases. As different types of molecules partially share chemical mechanisms, the predictions for each molecular type should benefit from the binding information with other molecule types.

RESULTS

In this study, we employed a multiple task deep learning strategy to develop a new sequence-based method for simultaneously predicting binding residues/sites with multiple important molecule types named MTDsite. By combining four training sets for DNA, RNA, peptide, and carbohydrate-binding proteins, our method yielded accurate and robust predictions with AUC values of 0.852, 0836, 0.758, and 0.776 on their respective independent test sets, which are 0.52 to 6.6% better than other state-of-the-art methods. To my best knowledge, this is the first method using multi-task framework to predict multiple molecular binding sites simultaneously.

DBP-iDWT: Improving DNA-Binding Proteins Prediction Using Multi-Perspective Evolutionary Profile and Discrete Wavelet Transform

DNA-binding proteins (DBPs) have crucial biotic activities including DNA replication, recombination, and transcription. DBPs are highly concerned with chronic diseases and are used in the manufacturing of antibiotics and steroids. A series of predictors were established to identify DBPs. However, researchers are still working to further enhance the identification of DBPs. This research designed a novel predictor to identify DBPs more accurately. The features from the sequences are transformed by F-PSSM (Filtered position-specific scoring matrix), PSSM-DPC (Position specific scoring matrix-dipeptide composition), and R-PSSM (Reduced position-specific scoring matrix). To eliminate the noisy attributes, we extended DWT (discrete wavelet transform) to F-PSSM, PSSM-DPC, and R-PSSM and introduced three novel descriptors, namely, F-PSSM-DWT, PSSM-DPC-DWT, and R-PSSM-DWT. Onward, the training of the four models were performed using LiXGB (Light eXtreme gradient boosting), XGB (eXtreme gradient boosting, ERT (extremely randomized trees), and Adaboost. LiXGB with R-PSSM-DWT has attained 6.55% higher accuracy on training and 5.93% on testing dataset than the best existing predictors. The results reveal the excellent performance of our novel predictor over the past studies. DBP-iDWT would be fruitful for establishing more operative therapeutic strategies for fatal disease treatment.

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.

DNA-binding protein prediction based on deep transfer learning

The study of DNA binding proteins (DBPs) is of great importance in the biomedical field and plays a key role in this field. At present, many researchers are working on the prediction and detection of DBPs. Traditional DBP prediction mainly uses machine learning methods. Although these methods can obtain relatively high pre-diction accuracy, they consume large quantities of human effort and material resources. Transfer learning has certain advantages in dealing with such prediction problems. Therefore, in the present study, two features were extracted from a protein sequence, a transfer learning method was used, and two classical transfer learning algorithms were compared to transfer samples and construct data sets. In the final step, DBPs are detected by building a deep learning neural network model in a way that uses attention mechanisms.

DNAgenie: accurate prediction of DNA-type-specific binding residues in protein sequences

Efforts to elucidate protein-DNA interactions at the molecular level rely in part on accurate predictions of DNA-binding residues in protein sequences. While there are over a dozen computational predictors of the DNA-binding residues, they are DNA-type agnostic and significantly cross-predict residues that interact with other ligands as DNA binding. We leverage a custom-designed machine learning architecture to introduce DNAgenie, first-of-its-kind predictor of residues that interact with A-DNA, B-DNA and single-stranded DNA. DNAgenie uses a comprehensive physiochemical profile extracted from an input protein sequence and implements a two-step refinement process to provide accurate predictions and to minimize the cross-predictions. Comparative tests on an independent test dataset demonstrate that DNAgenie outperforms the current methods that we adapt to predict residue-level interactions with the three DNA types. Further analysis finds that the use of the second (refinement) step leads to a substantial reduction in the cross predictions. Empirical tests show that DNAgenie's outputs that are converted to coarse-grained protein-level predictions compare favorably against recent tools that predict which DNA-binding proteins interact with double-stranded versus single-stranded DNAs. Moreover, predictions from the sequences of the whole human proteome reveal that the results produced by DNAgenie substantially overlap with the known DNA-binding proteins while also including promising leads for several hundred previously unknown putative DNA binders. These results suggest that DNAgenie is a valuable tool for the sequence-based characterization of protein functions. The DNAgenie's webserver is available at http://biomine.cs.vcu.edu/servers/DNAgenie/.

TargetDBP+: Enhancing the Performance of Identifying DNA-Binding Proteins via Weighted Convolutional Features

Protein-DNA interactions exist ubiquitously and play important roles in the life cycles of living cells. The accurate identification of DNA-binding proteins (DBPs) is one of the key steps to understand the mechanisms of protein-DNA interactions. Although many DBP identification methods have been proposed, the current performance is still unsatisfactory. In this study, a new method, called TargetDBP+, is developed to further enhance the performance of identifying DBPs. In TargetDBP+, five convolutional features are first extracted from five feature sources, i.e., amino acid one-hot matrix (AAOHM), position-specific scoring matrix (PSSM), predicted secondary structure probability matrix (PSSPM), predicted solvent accessibility probability matrix (PSAPM), and predicted probabilities of DNA-binding sites (PPDBSs); second, the five features are weightedly and serially combined using the weights of all of the elements learned by the differential evolution algorithm; and finally, the DBP identification model of TargetDBP+ is trained using the support vector machine (SVM) algorithm. To evaluate the developed TargetDBP+ and compare it with other existing methods, a new gold-standard benchmark data set, called UniSwiss, is constructed, which consists of 4881 DBPs and 4881 non-DBPs extracted from the UniprotKB/Swiss-Prot database. Experimental results demonstrate that TargetDBP+ can obtain an accuracy of 85.83% and precision of 88.45% covering 82.41% of all DBP data on the independent validation subset of UniSwiss, with the MCC value (0.718) being significantly higher than those of other state-of-the-art control methods. The web server of TargetDBP+ is accessible at http://csbio.njust.edu.cn/bioinf/targetdbpplus/; the UniSwiss data set and stand-alone program of TargetDBP+ are accessible at https://github.com/jun-csbio/TargetDBPplus.

Integrating sequence and gene expression information predicts genome-wide DNA-binding proteins and suggests a cooperative mechanism

DNA-binding proteins (DBPs) perform diverse biological functions ranging from transcription to pathogen sensing. Machine learning methods can not only identify DBPs de novo but also provide insights into their DNA-recognition dynamics. However, it remains unclear whether available methods that can accurately predict DNA-binding sites in known DBPs can also identify novel DBPs. Moreover, sequence information is blind to the cellular- and disease-specific contexts of DBP activities, whereas the under-utilized knowledge from public gene expression data offers great promise. To address these issues, we have developed novel methods for predicting DBPs by integrating sequence and gene expression-derived features and applied them to explore human, mouse and Arabidopsis proteomes. While our sequence-based models outperformed the gene expression-based ones, some proteins with weaker DBP-like sequence features were correctly predicted by gene expression-based features, suggesting that these proteins acquire a tangible DBP functionality in a conducive gene expression environment. Analysis of motif enrichment among the co-expressed genes of top 100 candidates DBPs from hitherto unannotated genes provides further avenues to explore their functional associations.

DP-BINDER: machine learning model for prediction of DNA-binding proteins by fusing evolutionary and physicochemical information

DNA-binding proteins (DBPs) participate in various biological processes including DNA replication, recombination, and repair. In the human genome, about 6-7% of these proteins are utilized for genes encoding. DBPs shape the DNA into a compact structure known chromatin while some of these proteins regulate the chromosome packaging and transcription process. In the pharmaceutical industry, DBPs are used as a key component of antibiotics, steroids, and cancer drugs. These proteins also involve in biophysical, biological, and biochemical studies of DNA. Due to the crucial role in various biological activities, identification of DBPs is a hot issue in protein science. A series of experimental and computational methods have been proposed, however, some methods didn't achieve the desired results while some are inadequate in its accuracy and authenticity. Still, it is highly desired to present more intelligent computational predictors. In this work, we introduce an innovative computational method namely DP-BINDER based on physicochemical and evolutionary information. We captured local highly decisive features from physicochemical properties of primary protein sequences via normalized Moreau-Broto autocorrelation (NMBAC) and evolutionary information by position specific scoring matrix-transition probability composition (PSSM-TPC) and pseudo-position specific scoring matrix (PsePSSM) using training and independent datasets. The optimal features were selected by the support vector machine-recursive feature elimination and correlation bias reduction (SVM-RFE + CBR) from fused features and were fed into random forest (RF) and support vector machine (SVM). Our method attained 92.46% and 89.58% accuracy with jackknife and ten-fold cross-validation, respectively on the training dataset, while 81.17% accuracy on the independent dataset for prediction of DBPs. These results demonstrate that our method attained the highest success rate in the literature. The superiority of DP-BINDER over existing approaches due to several reasons including abstraction of local dominant features via effective feature descriptors, utilization of appropriate feature selection algorithms and effective classifier.

Computational prediction of functions of intrinsically disordered regions

Intrinsically disorder regions (IDRs) are abundant in nature, particularly among Eukaryotes. While they facilitate a wide spectrum of cellular functions including signaling, molecular assembly and recognition, translation, transcription and regulation, only several hundred IDRs are annotated functionally. This annotation gap motivates the development of fast and accurate computational methods that predict IDR functions directly from protein sequences. We introduce and describe a comprehensive collection of 25 methods that provide accurate predictions of IDRs that interact with proteins and nucleic acids, that function as flexible linkers and that moonlight multiple functions. Virtually all of these predictors can be accessed online and many were developed in the last few years. They utilize a wide range of predictive architectures and take advantage of modern machine learning algorithms. Our empirical analysis shows that predictors that are available as webservers enjoy high rates of citations, attesting to their practical value and popularity. The most cited methods include DISOPRED3, ANCHOR, alpha-MoRFpred, MoRFpred, fMoRFpred and MoRFCHiBi. We present two case studies to demonstrate that predictions produced by these computational tools are relatively easy to interpret and that they deliver valuable functional clues. However, the current computational tools cover a relatively narrow range of disorder functions. Further development efforts that would cover a broader range of functions should be pursued. We demonstrate that a sufficient amount of functionally annotated IDRs that are associated with several other disorder functions is already available and can be used to design and validate novel predictors.

Prediction of RNA- and DNA-Binding Proteins Using Various Machine Learning Classifiers

BACKGROUND

Nucleic acid-binding proteins play major roles in different biological processes, such as transcription, splicing and translation. Therefore, the nucleic acid-binding function prediction of proteins is a step toward full functional annotation of proteins. The aim of our research was the improvement of nucleic-acid binding function prediction.

METHODS

In the current study, nine machine-learning algorithms were used to predict RNA- and DNA-binding proteins and also to discriminate between RNA-binding proteins and DNA-binding proteins. The electrostatic features were utilized for prediction of each function in corresponding adapted protein datasets. The leave-one-out cross-validation process was used to measure the performance of employed classifiers.

RESULTS

Radial basis function classifier gave the best results in predicting RNA- and DNA-binding proteins in comparison with other classifiers applied. In discriminating between RNA- and DNA-binding proteins, multilayer perceptron classifier was the best one.

CONCLUSION

Our findings show that the prediction of nucleic acid-binding function based on these simple electrostatic features can be improved by applied classifiers. Moreover, a reasonable progress to distinguish between RNA- and DNA-binding proteins has been achieved.

Computational Prediction of Carbohydrate-Binding Proteins and Binding Sites

Protein-carbohydrate interaction is essential for biological systems, and carbohydrate-binding proteins (CBPs) are important targets when designing antiviral and anticancer drugs. Due to the high cost and difficulty associated with experimental approaches, many computational methods have been developed as complementary approaches to predict CBPs or carbohydrate-binding sites. However, most of these computational methods are not publicly available. Here, we provide a comprehensive review of related studies and demonstrate our two recently developed bioinformatics methods. The method SPOT-CBP is a template-based method for detecting CBPs based on structure through structural homology search combined with a knowledge-based scoring function. This method can yield model complex structure in addition to accurate prediction of CBPs. Furthermore, it has been observed that similarly accurate predictions can be made using structures from homology modeling, which has significantly expanded its applicability. The other method, SPRINT-CBH, is a de novo approach that predicts binding residues directly from protein sequences by using sequence information and predicted structural properties. This approach does not need structurally similar templates and thus is not limited by the current database of known protein-carbohydrate complex structures. These two complementary methods are available at https://sparks-lab.org. © 2018 by John Wiley & Sons, Inc.

In Silico Prediction and Validation of Novel RNA Binding Proteins and Residues in the Human Proteome

Deciphering a complete landscape of protein-RNA interactions in the human proteome remains an elusive challenge. We computationally elucidate RNA binding proteins (RBPs) using an approach that complements previous efforts. We employ two modern complementary sequence-based methods that provide accurate predictions from the structured and the intrinsically disordered sequences, even in the absence of sequence similarity to the known RBPs. We generate and analyze putative RNA binding residues on the whole proteome scale. Using a conservative setting that ensures low, 5% false positive rate, we identify 1511 putative RBPs that include 281 known RBPs and 166 RBPs that were previously predicted. We empirically demonstrate that these overlaps are statistically significant. We also validate the putative RBPs based on two major hallmarks of their RNA binding residues: high levels of evolutionary conservation and enrichment in charged amino acids. Moreover, we show that the novel RBPs are significantly under-annotated functionally which coincides with the fact that they were not yet found to interact with RNAs. We provide two examples of our novel putative RBPs for which there is recent evidence of their interactions with RNAs. The dataset of novel putative RBPs and RNA binding residues for the future hypothesis generation is provided in the Supporting Information.

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.

SPIDER2: A Package to Predict Secondary Structure, Accessible Surface Area, and Main-Chain Torsional Angles by Deep Neural Networks

Predicting one-dimensional structure properties has played an important role to improve prediction of protein three-dimensional structures and functions. The most commonly predicted properties are secondary structure and accessible surface area (ASA) representing local and nonlocal structural characteristics, respectively. Secondary structure prediction is further complemented by prediction of continuous main-chain torsional angles. Here we describe a newly developed method SPIDER2 that utilizes three iterations of deep learning neural networks to improve the prediction accuracy of several structural properties simultaneously. For an independent test set of 1199 proteins SPIDER2 achieves 82 % accuracy for secondary structure prediction, 0.76 for the correlation coefficient between predicted and actual solvent accessible surface area, 19° and 30° for mean absolute errors of backbone φ and ψ angles, respectively, and 8° and 32° for mean absolute errors of Cα-based θ and τ angles, respectively. The method provides state-of-the-art, all-in-one accurate prediction of local structure and solvent accessible surface area. The method is implemented, as a webserver along with a standalone package that are available in our website: http://sparks-lab.org .

Sequence-Based Prediction of Protein-Carbohydrate Binding Sites Using Support Vector Machines

Carbohydrate-binding proteins play significant roles in many diseases including cancer. Here, we established a machine-learning-based method (called sequence-based prediction of residue-level interaction sites of carbohydrates, SPRINT-CBH) to predict carbohydrate-binding sites in proteins using support vector machines (SVMs). We found that integrating evolution-derived sequence profiles with additional information on sequence and predicted solvent accessible surface area leads to a reasonably accurate, robust, and predictive method, with area under receiver operating characteristic curve (AUC) of 0.78 and 0.77 and Matthew's correlation coefficient of 0.34 and 0.29, respectively for 10-fold cross validation and independent test without balancing binding and nonbinding residues. The quality of the method is further demonstrated by having statistically significantly more binding residues predicted for carbohydrate-binding proteins than presumptive nonbinding proteins in the human proteome, and by the bias of rare alleles toward predicted carbohydrate-binding sites for nonsynonymous mutations from the 1000 genome project. SPRINT-CBH is available as an online server at http://sparks-lab.org/server/SPRINT-CBH .

HOMCOS: an updated server to search and model complex 3D structures

The HOMCOS server (http://homcos.pdbj.org) was updated for both searching and modeling the 3D complexes for all molecules in the PDB. As compared to the previous HOMCOS server, the current server targets all of the molecules in the PDB including proteins, nucleic acids, small compounds and metal ions. Their binding relationships are stored in the database. Five services are available for users. For the services “Modeling a Homo Protein Multimer” and “Modeling a Hetero Protein Multimer”, a user can input one or two proteins as the queries, while for the service “Protein-Compound Complex”, a user can input one chemical compound and one protein. The server searches similar molecules by BLAST and KCOMBU. Based on each similar complex found, a simple sequence-replaced model is quickly generated by replacing the residue names and numbers with those of the query protein. A target compound is flexibly superimposed onto the template compound using the program fkcombu. If monomeric 3D structures are input as the query, then template-based docking can be performed. For the service “Searching Contact Molecules for a Query Protein”, a user inputs one protein sequence as the query, and then the server searches for its homologous proteins in PDB and summarizes their contacting molecules as the predicted contacting molecules. The results are summarized in “Summary Bars” or “Site Table”display. The latter shows the results as a one-site-one-row table, which is useful for annotating the effects of mutations. The service “Searching Contact Molecules for a Query Compound” is also available.

Identification of DNA-binding proteins by combining auto-cross covariance transformation and ensemble learning

DNA-binding proteins play a pivotal role in various intra- and extra-cellular activities ranging from DNA replication to gene expression control. With the rapid development of next generation of sequencing technique, the number of protein sequences is unprecedentedly increasing. Thus it is necessary to develop computational methods to identify the DNA-binding proteins only based on the protein sequence information. In this study, a novel method called iDNA-KACC is presented, which combines the Support Vector Machine (SVM) and the auto-cross covariance transformation. The protein sequences are first converted into profile-based protein representation, and then converted into a series of fixed-length vectors by the auto-cross covariance transformation with Kmer composition. The sequence order effect can be effectively captured by this scheme. These vectors are then fed into Support Vector Machine (SVM) to discriminate the DNA-binding proteins from the non DNA-binding ones. iDNA-KACC achieves an overall accuracy of 75.16% and Matthew correlation coefficient of 0.5 by a rigorous jackknife test. Its performance is further improved by employing an ensemble learning approach, and the improved predictor is called iDNA-KACC-EL. Experimental results on an independent dataset shows that iDNA-KACC-EL outperforms all the other state-of-the-art predictors, indicating that it would be a useful computational tool for DNA binding protein identification. .

SNBRFinder: A Sequence-Based Hybrid Algorithm for Enhanced Prediction of Nucleic Acid-Binding Residues

Protein-nucleic acid interactions are central to various fundamental biological processes. Automated methods capable of reliably identifying DNA- and RNA-binding residues in protein sequence are assuming ever-increasing importance. The majority of current algorithms rely on feature-based prediction, but their accuracy remains to be further improved. Here we propose a sequence-based hybrid algorithm SNBRFinder (Sequence-based Nucleic acid-Binding Residue Finder) by merging a feature predictor SNBRFinder^F and a template predictor SNBRFinder^T. SNBRFinder^F was established using the support vector machine whose inputs include sequence profile and other complementary sequence descriptors, while SNBRFinder^T was implemented with the sequence alignment algorithm based on profile hidden Markov models to capture the weakly homologous template of query sequence. Experimental results show that SNBRFinder^F was clearly superior to the commonly used sequence profile-based predictor and SNBRFinder^T can achieve comparable performance to the structure-based template methods. Leveraging the complementary relationship between these two predictors, SNBRFinder reasonably improved the performance of both DNA- and RNA-binding residue predictions. More importantly, the sequence-based hybrid prediction reached competitive performance relative to our previous structure-based counterpart. Our extensive and stringent comparisons show that SNBRFinder has obvious advantages over the existing sequence-based prediction algorithms. The value of our algorithm is highlighted by establishing an easy-to-use web server that is freely accessible at http://ibi.hzau.edu.cn/SNBRFinder.

Template-based prediction of protein function

We discuss recent approaches for structure-based protein function annotation. We focus on template-based methods where the function of a query protein is deduced from that of a template for which both the structure and function are known. We describe the different ways of identifying a template. These are typically based on sequence analysis but new methods based on purely structural similarity are also being developed that allow function annotation based on structural relationships that cannot be recognized by sequence. The growing number of available structures of known function, improved homology modeling techniques and new developments in the use of structure allow template-based methods to be applied on a proteome-wide scale and in many different biological contexts. This progress significantly expands the range of applicability of structural information in function annotation to a level that previously was only achievable by sequence comparison.