Prediction of Protein–Protein Interaction Sites with Machine-Learning-Based Data-Cleaning and Post-Filtering Procedures

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.

DeepBSRPred: deep learning-based binding site residue prediction for proteins

MOTIVATION

Proteins-protein interactions (PPIs) are important to govern several cellular activities. Amino acid residues, which are located at the interface are known as the binding sites and the information about binding sites helps to understand the binding affinities and functions of protein-protein complexes.

RESULTS

We have developed a deep neural network-based method, DeepBSRPred, for predicting the binding sites using protein sequence information and predicted structures from AlphaFold2. Specific sequence and structure-based features include position-specific scoring matrix (PSSM), solvent accessible surface area, conservation score and amino acid properties, and residue depth, respectively. Our method predicted the binding sites with an average F1 score of 0.73 in a dataset of 1236 proteins. Further, we compared the performance with other existing methods in the literature using four benchmark datasets and our method outperformed those methods.

AVAILABILITY AND IMPLEMENTATION

The DeepBSRPred web server can be found at https://web.iitm.ac.in/bioinfo2/deepbsrpred/index.html , along with all datasets used in this study. The trained models, the DeepBSRPred standalone source code, and the feature computation pipeline are freely available at https://web.iitm.ac.in/bioinfo2/deepbsrpred/download.html .

Application of Machine Learning in Material Synthesis and Property Prediction

Material innovation plays a very important role in technological progress and industrial development. Traditional experimental exploration and numerical simulation often require considerable time and resources. A new approach is urgently needed to accelerate the discovery and exploration of new materials. Machine learning can greatly reduce computational costs, shorten the development cycle, and improve computational accuracy. It has become one of the most promising research approaches in the process of novel material screening and material property prediction. In recent years, machine learning has been widely used in many fields of research, such as superconductivity, thermoelectrics, photovoltaics, catalysis, and high-entropy alloys. In this review, the basic principles of machine learning are briefly outlined. Several commonly used algorithms in machine learning models and their primary applications are then introduced. The research progress of machine learning in predicting material properties and guiding material synthesis is discussed. Finally, a future outlook on machine learning in the materials science field is presented.

Recent advances in predicting protein-protein interactions with the aid of artificial intelligence algorithms

Protein-protein interactions (PPIs) are essential in the regulation of biological functions and cell events, therefore understanding PPIs have become a key issue to understanding the molecular mechanism and investigating the design of drugs. Here we highlight the major developments in computational methods developed for predicting PPIs by using types of artificial intelligence algorithms. The first part introduces the source of experimental PPI data. The second part is devoted to the PPI prediction methods based on sequential information. The third part covers representative methods using structural information as the input feature. The last part is methods designed by combining different types of features. For each part, the state-of-the-art computational PPI prediction methods are reviewed in an inclusive view. Finally, we discuss the flaws existing in this area and future directions of next-generation algorithms.

DELPHI: accurate deep ensemble model for protein interaction sites prediction

MOTIVATION

Proteins usually perform their functions by interacting with other proteins, which is why accurately predicting protein-protein interaction (PPI) binding sites is a fundamental problem. Experimental methods are slow and expensive. Therefore, great efforts are being made towards increasing the performance of computational methods.

RESULTS

We propose DEep Learning Prediction of Highly probable protein Interaction sites (DELPHI), a new sequence-based deep learning suite for PPI-binding sites prediction. DELPHI has an ensemble structure which combines a CNN and a RNN component with fine tuning technique. Three novel features, HSP, position information and ProtVec are used in addition to nine existing ones. We comprehensively compare DELPHI to nine state-of-the-art programmes on five datasets, and DELPHI outperforms the competing methods in all metrics even though its training dataset shares the least similarities with the testing datasets. In the most important metrics, AUPRC and MCC, it surpasses the second best programmes by as much as 18.5% and 27.7%, respectively. We also demonstrated that the improvement is essentially due to using the ensemble model and, especially, the three new features. Using DELPHI it is shown that there is a strong correlation with protein-binding residues (PBRs) and sites with strong evolutionary conservation. In addition, DELPHI's predicted PBR sites closely match known data from Pfam. DELPHI is available as open-sourced standalone software and web server.

AVAILABILITY AND IMPLEMENTATION

The DELPHI web server can be found at delphi.csd.uwo.ca/, with all datasets and results in this study. The trained models, the DELPHI standalone source code, and the feature computation pipeline are freely available at github.com/lucian-ilie/DELPHI.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Prediction of protein-binding residues: dichotomy of sequence-based methods developed using structured complexes versus disordered proteins

MOTIVATION

There are over 30 sequence-based predictors of the protein-binding residues (PBRs). They use either structure-annotated or disorder-annotated training datasets, potentially creating a dichotomy where the structure-/disorder-specific models may not be able to cross-over to accurately predict the other type. Moreover, the structure-trained predictors were shown to substantially cross-predict PBRs among residues that interact with non-protein partners (nucleic acids and small ligands). We address these issues by performing first-of-its-kind comparative study of a representative collection of disorder- and structure-trained predictors using a comprehensive benchmark set with the structure- and disorder-derived annotations of PBRs (to analyze the cross-over) and the protein-, nucleic acid- and small ligand-binding proteins (to study the cross-predictions).

RESULTS

Three predictors provide accurate results: SCRIBER, ANCHOR and disoRDPbind. Some of the structure-trained methods make accurate predictions on the structure-annotated proteins. Similarly, the disorder-trained predictors predict well on the disorder-annotated proteins. However, the considered predictors generally fail to cross-over, with the exception of SCRIBER. Our study also reveals that virtually all methods substantially cross-predict PBRs, except for SCRIBER for the structure-annotated proteins and disoRDPbind for the disorder-annotated proteins. We formulate a novel hybrid predictor, hybridPBRpred, that combines results produced by disoRDPbind and SCRIBER to accurately predict disorder- and structure-annotated PBRs. HybridPBRpred generates accurate results that cross-over structure- and disorder-annotated proteins and produces relatively low amount of cross-predictions, offering an accurate alternative to predict PBRs.

AVAILABILITY AND IMPLEMENTATION

HybridPBRpred webserver, benchmark dataset and supplementary information are available at http://biomine.cs.vcu.edu/servers/hybridPBRpred/.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

PROBselect: accurate prediction of protein-binding residues from proteins sequences via dynamic predictor selection

Motivation

Knowledge of protein-binding residues (PBRs) improves our understanding of protein−protein interactions, contributes to the prediction of protein functions and facilitates protein−protein docking calculations. While many sequence-based predictors of PBRs were published, they offer modest levels of predictive performance and most of them cross-predict residues that interact with other partners. One unexplored option to improve the predictive quality is to design consensus predictors that combine results produced by multiple methods.

Results

We empirically investigate predictive performance of a representative set of nine predictors of PBRs. We report substantial differences in predictive quality when these methods are used to predict individual proteins, which contrast with the dataset-level benchmarks that are currently used to assess and compare these methods. Our analysis provides new insights for the cross-prediction concern, dissects complementarity between predictors and demonstrates that predictive performance of the top methods depends on unique characteristics of the input protein sequence. Using these insights, we developed PROBselect, first-of-its-kind consensus predictor of PBRs. Our design is based on the dynamic predictor selection at the protein level, where the selection relies on regression-based models that accurately estimate predictive performance of selected predictors directly from the sequence. Empirical assessment using a low-similarity test dataset shows that PROBselect provides significantly improved predictive quality when compared with the current predictors and conventional consensuses that combine residue-level predictions. Moreover, PROBselect informs the users about the expected predictive quality for the prediction generated from a given input protein.

Availability and implementation

PROBselect is available at http://bioinformatics.csu.edu.cn/PROBselect/home/index.

Supplementary information

Supplementary data are available at Bioinformatics online.

Boosting Granular Support Vector Machines for the Accurate Prediction of Protein-Nucleotide Binding Sites

AIM AND OBJECTIVE

The accurate identification of protein-ligand binding sites helps elucidate protein function and facilitate the design of new drugs. Machine-learning-based methods have been widely used for the prediction of protein-ligand binding sites. Nevertheless, the severe class imbalance phenomenon, where the number of nonbinding (majority) residues is far greater than that of binding (minority) residues, has a negative impact on the performance of such machine-learning-based predictors.

MATERIALS AND METHODS

In this study, we aim to relieve the negative impact of class imbalance by Boosting Multiple Granular Support Vector Machines (BGSVM). In BGSVM, each base SVM is trained on a granular training subset consisting of all minority samples and some reasonably selected majority samples. The efficacy of BGSVM for dealing with class imbalance was validated by benchmarking it with several typical imbalance learning algorithms. We further implemented a protein-nucleotide binding site predictor, called BGSVM-NUC, with the BGSVM algorithm.

RESULTS

Rigorous cross-validation and independent validation tests for five types of proteinnucleotide interactions demonstrated that the proposed BGSVM-NUC achieves promising prediction performance and outperforms several popular sequence-based protein-nucleotide binding site predictors. The BGSVM-NUC web server is freely available at http://csbio.njust.edu.cn/bioinf/BGSVM-NUC/ for academic use.

SCRIBER: accurate and partner type-specific prediction of protein-binding residues from proteins sequences

Motivation

Accurate predictions of protein-binding residues (PBRs) enhances understanding of molecular-level rules governing protein–protein interactions, helps protein–protein docking and facilitates annotation of protein functions. Recent studies show that current sequence-based predictors of PBRs severely cross-predict residues that interact with other types of protein partners (e.g. RNA and DNA) as PBRs. Moreover, these methods are relatively slow, prohibiting genome-scale use.

Results

We propose a novel, accurate and fast sequence-based predictor of PBRs that minimizes the cross-predictions. Our SCRIBER (SeleCtive pRoteIn-Binding rEsidue pRedictor) method takes advantage of three innovations: comprehensive dataset that covers multiple types of binding residues, novel types of inputs that are relevant to the prediction of PBRs, and an architecture that is tailored to reduce the cross-predictions. The dataset includes complete protein chains and offers improved coverage of binding annotations that are transferred from multiple protein–protein complexes. We utilize innovative two-layer architecture where the first layer generates a prediction of protein-binding, RNA-binding, DNA-binding and small ligand-binding residues. The second layer re-predicts PBRs by reducing overlap between PBRs and the other types of binding residues produced in the first layer. Empirical tests on an independent test dataset reveal that SCRIBER significantly outperforms current predictors and that all three innovations contribute to its high predictive performance. SCRIBER reduces cross-predictions by between 41% and 69% and our conservative estimates show that it is at least 3 times faster. We provide putative PBRs produced by SCRIBER for the entire human proteome and use these results to hypothesize that about 14% of currently known human protein domains bind proteins.

Availability and implementation

SCRIBER webserver is available at http://biomine.cs.vcu.edu/servers/SCRIBER/.

Supplementary information

Supplementary data are available at Bioinformatics online.

ProNA2020 predicts protein-DNA, protein-RNA, and protein-protein binding proteins and residues from sequence

The intricate details of how proteins bind to proteins, DNA, and RNA are crucial for the understanding of almost all biological processes. Disease-causing sequence variants often affect binding residues. Here, we described a new, comprehensive system of in silico methods that take only protein sequence as input to predict binding of protein to DNA, RNA, and other proteins. Firstly, we needed to develop several new methods to predict whether or not proteins bind (per-protein prediction). Secondly, we developed independent methods that predict which residues bind (per-residue). Not requiring three-dimensional information, the system can predict the actual binding residue. The system combined homology-based inference with machine learning and motif-based profile-kernel approaches with word-based (ProtVec) solutions to machine learning protein level predictions. This achieved an overall non-exclusive three-state accuracy of 77% ± 1% (±one standard error) corresponding to a 1.8 fold improvement over random (best classification for protein-protein with F1 = 91 ± 0.8%). Standard neural networks for per-residue binding residue predictions appeared best for DNA-binding (Q2 = 81 ± 0.9%) followed by RNA-binding (Q2 = 80 ± 1%) and worst for protein-protein binding (Q2 = 69 ± 0.8%). The new method, dubbed ProNA2020, is available as code through github (https://github.com/Rostlab/ProNA2020.git) and through PredictProtein (www.predictprotein.org).

Protein-protein interaction sites prediction by ensemble random forests with synthetic minority oversampling technique

MOTIVATION

The prediction of protein-protein interaction (PPI) sites is a key to mutation design, catalytic reaction and the reconstruction of PPI networks. It is a challenging task considering the significant abundant sequences and the imbalance issue in samples.

RESULTS

A new ensemble learning-based method, Ensemble Learning of synthetic minority oversampling technique (SMOTE) for Unbalancing samples and RF algorithm (EL-SMURF), was proposed for PPI sites prediction in this study. The sequence profile feature and the residue evolution rates were combined for feature extraction of neighboring residues using a sliding window, and the SMOTE was applied to oversample interface residues in the feature space for the imbalance problem. The Multi-dimensional Scaling feature selection method was implemented to reduce feature redundancy and subset selection. Finally, the Random Forest classifiers were applied to build the ensemble learning model, and the optimal feature vectors were inserted into EL-SMURF to predict PPI sites. The performance validation of EL-SMURF on two independent validation datasets showed 77.1% and 77.7% accuracy, which were 6.2-15.7% and 6.1-18.9% higher than the other existing tools, respectively.

AVAILABILITY AND IMPLEMENTATION

The source codes and data used in this study are publicly available at http://github.com/QUST-AIBBDRC/EL-SMURF/.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Machine Learning and Integrative Analysis of Biomedical Big Data

Recent developments in high-throughput technologies have accelerated the accumulation of massive amounts of omics data from multiple sources: genome, epigenome, transcriptome, proteome, metabolome, etc. Traditionally, data from each source (e.g., genome) is analyzed in isolation using statistical and machine learning (ML) methods. Integrative analysis of multi-omics and clinical data is key to new biomedical discoveries and advancements in precision medicine. However, data integration poses new computational challenges as well as exacerbates the ones associated with single-omics studies. Specialized computational approaches are required to effectively and efficiently perform integrative analysis of biomedical data acquired from diverse modalities. In this review, we discuss state-of-the-art ML-based approaches for tackling five specific computational challenges associated with integrative analysis: curse of dimensionality, data heterogeneity, missing data, class imbalance and scalability issues.

iNuc-ext-PseTNC: an efficient ensemble model for identification of nucleosome positioning by extending the concept of Chou's PseAAC to pseudo-tri-nucleotide composition

Nucleosome is a central element of eukaryotic chromatin, which composes of histone proteins and DNA molecules. It performs vital roles in many eukaryotic intra-nuclear processes, for instance, chromatin structure and transcriptional regulation formation. Identification of nucleosome positioning via wet lab is difficult; so, the attention is diverted towards the accurate intelligent automated prediction. In this regard, a novel intelligent automated model "iNuc-ext-PseTNC" is developed to identify the nucleosome positioning in genomes accurately. In this predictor, the sequences of DNA are mathematically represented by two different discrete feature extraction techniques, namely pseudo-tri-nucleotide composition (PseTNC) and pseudo-di-nucleotide composition. Several contemporary machine learning algorithms were examined. Further, the predictions of individual classifiers were integrated through an evolutionary genetic algorithm. The success rates of the ensemble model are higher than individual classifiers. After analyzing the prediction results, it is noticed that iNuc-ext-PseTNC model has achieved better performance in combination with PseTNC feature space, which are 94.3%, 93.14%, and 88.60% of accuracies using six-fold cross-validation test for the three benchmark datasets S₁, S₂, and S₃, respectively. The achieved outcomes exposed that the results of iNuc-ext-PseTNC model are prominent compared to the existing methods so far notifiable in the literature. It is ascertained that the proposed model might be more fruitful and a practical tool for rudimentary academia and research.

Imbalance learning for the prediction of N6-Methylation sites in mRNAs

Background

N⁶-methyladenosine (m⁶A) is an important epigenetic modification which plays various roles in mRNA metabolism and embryogenesis directly related to human diseases. To identify m⁶A in a large scale, machine learning methods have been developed to make predictions on m⁶A sites. However, there are two main drawbacks of these methods. The first is the inadequate learning of the imbalanced m⁶A samples which are much less than the non-m⁶A samples, by their balanced learning approaches. Second, the features used by these methods are not outstanding to represent m⁶A sequence characteristics.

Results

We propose to use cost-sensitive learning ideas to resolve the imbalance data issues in the human mRNA m⁶A prediction problem. This cost-sensitive approach applies to the entire imbalanced dataset, without random equal-size selection of negative samples, for an adequate learning. Along with site location and entropy features, top-ranked positions with the highest single nucleotide polymorphism specificity in the window sequences are taken as new features in our imbalance learning. On an independent dataset, our overall prediction performance is much superior to the existing predictors. Our method shows stronger robustness against the imbalance changes in the tests on 9 datasets whose imbalance ratios range from 1:1 to 9:1. Our method also outperforms the existing predictors on 1226 individual transcripts. It is found that the new types of features are indeed of high significance in the m⁶A prediction. The case studies on gene c-Jun and CBFB demonstrate the detailed prediction capacity to improve the prediction performance.

Conclusion

The proposed cost-sensitive model and the new features are useful in human mRNA m⁶A prediction. Our method achieves better correctness and robustness than the existing predictors in independent test and case studies. The results suggest that imbalance learning is promising to improve the performance of m⁶A prediction.

Electronic supplementary material

The online version of this article (10.1186/s12864-018-4928-y) contains supplementary material, which is available to authorized users.

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.

MultiP-Apo: A Multilabel Predictor for Identifying Subcellular Locations of Apoptosis Proteins

Apoptosis proteins play an important role in the mechanism of programmed cell death. Predicting subcellular localization of apoptosis proteins is an essential step to understand their functions and identify drugs target. Many computational prediction methods have been developed for apoptosis protein subcellular localization. However, these existing works only focus on the proteins that have one location; proteins with multiple locations are either not considered or assumed as not existing when constructing prediction models, so that they cannot completely predict all the locations of the apoptosis proteins with multiple locations. To address this problem, this paper proposes a novel multilabel predictor named MultiP-Apo, which can predict not only apoptosis proteins with single subcellular location but also those with multiple subcellular locations. Specifically, given a query protein, GO-based feature extraction method is used to extract its feature vector. Subsequently, the GO feature vector is classified by a new multilabel classifier based on the label-specific features. It is the first multilabel predictor ever established for identifying subcellular locations of multilocation apoptosis proteins. As an initial study, MultiP-Apo achieves an overall accuracy of 58.49% by jackknife test, which indicates that our proposed predictor may become a very useful high-throughput tool in this area.