ConvsPPIS: Identifying Protein-protein Interaction Sites by an Ensemble Convolutional Neural Network with Feature Graph

MR2CPPIS: Accurate prediction of protein-protein interaction sites based on multi-scale Res2Net with coordinate attention mechanism

Proteins play a vital role in various biological processes and achieve their functions through protein-protein interactions (PPIs). Thus, accurate identification of PPI sites is essential. Traditional biological methods for identifying PPIs are costly, labor-intensive, and time-consuming. The development of computational prediction methods for PPI sites offers promising alternatives. Most known deep learning (DL) methods employ layer-wise multi-scale CNNs to extract features from protein sequences. But, these methods usually neglect the spatial positions and hierarchical information embedded within protein sequences, which are actually crucial for PPI site prediction. In this paper, we propose MR2CPPIS, a novel sequence-based DL model that utilizes the multi-scale Res2Net with coordinate attention mechanism to exploit multi-scale features and enhance PPI site prediction capability. We leverage the multi-scale Res2Net to expand the receptive field for each network layer, thus capturing multi-scale information of protein sequences at a granular level. To further explore the local contextual features of each target residue, we employ a coordinate attention block to characterize the precise spatial position information, enabling the network to effectively extract long-range dependencies. We evaluate our MR2CPPIS on three public benchmark datasets (Dset 72, Dset 186, and PDBset 164), achieving state-of-the-art performance. The source codes are available at https://github.com/YyinGong/MR2CPPIS.

GHGPR-PPIS: A graph convolutional network for identifying protein-protein interaction site using heat kernel with Generalized PageRank techniques and edge self-attention feature processing block

Accurately pinpointing protein-protein interaction site (PPIS) on the molecular level is of utmost significance for annotating protein function and comprehending the mechanisms underpinning various diseases. While numerous computational methods for predicting PPIS have emerged, they have indeed mitigated the labor and time constraints associated with traditional experimental methods. However, the predictive accuracy of these methods has yet to reach the desired threshold. In this context, we proposed a groundbreaking graph-based computational model called GHGPR-PPIS. This innovative model leveraged a graph convolutional network using heat kernel (GraphHeat) in conjunction with Generalized PageRank techniques (GHGPR) to predict PPIS. Additionally, building upon the GHGPR framework, we devised an edge self-attention feature processing block, further augmenting the performance of the model. Experimental findings conclusively demonstrated that GHGPR-PPIS surpassed all competing state-of-the-art models when evaluated on the benchmark test set. Impressively, on two distinct independent test sets and a specific protein chain, GHGPR-PPIS consistently demonstrated superior generalization performance and practical applicability compared to the comparative model, AGAT-PPIS. Lastly, leveraging the t-SNE dimensionality reduction algorithm and clustering visualization technique, we delved into an interpretability analysis of the effectiveness of GHGPR-PPIS by meticulously comparing the outputs from different stages of the model.

Protein-protein interaction site prediction by model ensembling with hybrid feature and self-attention

BACKGROUND

Protein-protein interactions (PPIs) are crucial in various biological functions and cellular processes. Thus, many computational approaches have been proposed to predict PPI sites. Although significant progress has been made, these methods still have limitations in encoding the characteristics of each amino acid in sequences. Many feature extraction methods rely on the sliding window technique, which simply merges all the features of residues into a vector. The importance of some key residues may be weakened in the feature vector, leading to poor performance.

RESULTS

We propose a novel sequence-based method for PPI sites prediction. The new network model, PPINet, contains multiple feature processing paths. For a residue, the PPINet extracts the features of the targeted residue and its context separately. These two types of features are processed by two paths in the network and combined to form a protein representation, where the two types of features are of relatively equal importance. The model ensembling technique is applied to make use of more features. The base models are trained with different features and then ensembled via stacking. In addition, a data balancing strategy is presented, by which our model can get significant improvement on highly unbalanced data.

CONCLUSION

The proposed method is evaluated on a fused dataset constructed from Dset186, Dset_72, and PDBset_164, as well as the public Dset_448 dataset. Compared with current state-of-the-art methods, the performance of our method is better than the others. In the most important metrics, such as AUPRC and recall, it surpasses the second-best programmer on the latter dataset by 6.9% and 4.7%, respectively. We also demonstrated that the improvement is essentially due to using the ensemble model, especially, the hybrid feature. We share our code for reproducibility and future research at https://github.com/CandiceCong/StackingPPINet .

HNetGO: protein function prediction via heterogeneous network transformer

Protein function annotation is one of the most important research topics for revealing the essence of life at molecular level in the post-genome era. Current research shows that integrating multisource data can effectively improve the performance of protein function prediction models. However, the heavy reliance on complex feature engineering and model integration methods limits the development of existing methods. Besides, models based on deep learning only use labeled data in a certain dataset to extract sequence features, thus ignoring a large amount of existing unlabeled sequence data. Here, we propose an end-to-end protein function annotation model named HNetGO, which innovatively uses heterogeneous network to integrate protein sequence similarity and protein-protein interaction network information and combines the pretraining model to extract the semantic features of the protein sequence. In addition, we design an attention-based graph neural network model, which can effectively extract node-level features from heterogeneous networks and predict protein function by measuring the similarity between protein nodes and gene ontology term nodes. Comparative experiments on the human dataset show that HNetGO achieves state-of-the-art performance on cellular component and molecular function branches.

Improving protein-protein interaction site prediction using deep residual neural network

Accurate identification of protein-protein interaction (PPI) sites is significantly important for understanding the mechanism of life and developing new drugs. However, it is expensive and time-consuming to identify PPI sites using wet-lab experiments. Developing computational methods is a new road to identify PPI sites, which can accelerate the procedure of PPI-related research. In this study, we propose a novel deep learning-based method (called D-PPIsite) to improve the accuracy of sequence-based PPI site prediction. In D-PPIsite, four discriminative sequence-driven features, i.e., position specific scoring matrix, relative solvent accessibility, position information and physical properties, are employed to feed into a well-designed deep learning module, consisting of convolutional, squeeze and excitation, and fully connected layers, to learn a prediction model. To reduce the risk of a single prediction model getting stuck in local optima, multiple prediction models with different initialization parameters are selected and integrated into one final model using the mean ensemble strategy. Experimental results on five independent testing data sets demonstrate that the proposed D-PPIsite can achieve an average accuracy of 80.2% and precision of 36.9%, covering 53.5% of all PPI sites while achieving the average Matthews correlation coefficient value (0.330) that is significantly higher than most of existing state-of-the-art prediction methods. We implement a new standalone-version predictor for predicting PPI sites, which is freely available at https://github.com/MingDongup/D-PPIsite for academic use.

Analyzing Effect of Multi-Modality in Predicting Protein-Protein Interactions

Nowadays, multiple sources of information about proteins are available such as protein sequences, 3D structures, Gene Ontology (GO), etc. Most of the works on protein-protein interaction (PPI) identification had utilized these information about proteins, mainly sequence-based, but individually. The new advances in deep learning techniques allow us to leverage multiple sources/modalities of proteins, which complement each other. Some recent works have shown that multi-modal PPI models perform better than uni-modal approaches. This paper aims to investigate whether the performance of multi-modal PPI models is always consistent or depends on other factors such as dataset distribution, algorithms used to learn features, etc. We have used three modalities for this study: Protein sequence, 3D structure, and GO. Various techniques, including deep learning algorithms, are employed to extract features from multiple sources of proteins. These feature vectors from different modalities are then integrated in several combinations (bi-modal and tri-modal) to predict PPI. To conduct this study, we have used Human and S. cerevisiae PPI datasets. The obtained results demonstrate the potentiality of a multi-modal approach and deep learning techniques in predicting protein interactions. However, the predictive capability of a model for PPI depends on feature extraction methods as well. Also, increasing the modality does not always ensure performance improvement. In this study, the PPI model integrating two modalities outperforms the designed uni-modal and tri-modal PPI models.

HLGNN-MDA: Heuristic Learning Based on Graph Neural Networks for miRNA-Disease Association Prediction

Identifying disease-related miRNAs can improve the understanding of complex diseases. However, experimentally finding the association between miRNAs and diseases is expensive in terms of time and resources. The computational screening of reliable miRNA-disease associations has thus become a necessary tool to guide biological experiments. "Similar miRNAs will be associated with the same disease" is the assumption on which most current miRNA-disease association prediction methods rely; however, biased prior knowledge, and incomplete and inaccurate miRNA similarity data and disease similarity data limit the performance of the model. Here, we propose heuristic learning based on graph neural networks to predict microRNA-disease associations (HLGNN-MDA). We learn the local graph topology features of the predicted miRNA-disease node pairs using graph neural networks. In particular, our improvements to the graph convolution layer of the graph neural network enable it to learn information among homogeneous nodes and among heterogeneous nodes. We illustrate the performance of HLGNN-MDA by performing tenfold cross-validation against excellent baseline models. The results show that we have promising performance in multiple metrics. We also focus on the role of the improvements to the graph convolution layer in the model. The case studies are supported by evidence on breast cancer, hepatocellular carcinoma and renal cell carcinoma. Given the above, the experiments demonstrate that HLGNN-MDA can serve as a reliable method to identify novel miRNA-disease associations.

Struct2Graph: a graph attention network for structure based predictions of protein-protein interactions

BACKGROUND

Development of new methods for analysis of protein-protein interactions (PPIs) at molecular and nanometer scales gives insights into intracellular signaling pathways and will improve understanding of protein functions, as well as other nanoscale structures of biological and abiological origins. Recent advances in computational tools, particularly the ones involving modern deep learning algorithms, have been shown to complement experimental approaches for describing and rationalizing PPIs. However, most of the existing works on PPI predictions use protein-sequence information, and thus have difficulties in accounting for the three-dimensional organization of the protein chains.

RESULTS

In this study, we address this problem and describe a PPI analysis based on a graph attention network, named Struct2Graph, for identifying PPIs directly from the structural data of folded protein globules. Our method is capable of predicting the PPI with an accuracy of 98.89% on the balanced set consisting of an equal number of positive and negative pairs. On the unbalanced set with the ratio of 1:10 between positive and negative pairs, Struct2Graph achieves a fivefold cross validation average accuracy of 99.42%. Moreover, Struct2Graph can potentially identify residues that likely contribute to the formation of the protein-protein complex. The identification of important residues is tested for two different interaction types: (a) Proteins with multiple ligands competing for the same binding area, (b) Dynamic protein-protein adhesion interaction. Struct2Graph identifies interacting residues with 30% sensitivity, 89% specificity, and 87% accuracy.

CONCLUSIONS

In this manuscript, we address the problem of prediction of PPIs using a first of its kind, 3D-structure-based graph attention network (code available at https://github.com/baranwa2/Struct2Graph ). Furthermore, the novel mutual attention mechanism provides insights into likely interaction sites through its unsupervised knowledge selection process. This study demonstrates that a relatively low-dimensional feature embedding learned from graph structures of individual proteins outperforms other modern machine learning classifiers based on global protein features. In addition, through the analysis of single amino acid variations, the attention mechanism shows preference for disease-causing residue variations over benign polymorphisms, demonstrating that it is not limited to interface residues.

Protein Function Analysis through Machine Learning

Machine learning (ML) has been an important arsenal in computational biology used to elucidate protein function for decades. With the recent burgeoning of novel ML methods and applications, new ML approaches have been incorporated into many areas of computational biology dealing with protein function. We examine how ML has been integrated into a wide range of computational models to improve prediction accuracy and gain a better understanding of protein function. The applications discussed are protein structure prediction, protein engineering using sequence modifications to achieve stability and druggability characteristics, molecular docking in terms of protein-ligand binding, including allosteric effects, protein-protein interactions and protein-centric drug discovery. To quantify the mechanisms underlying protein function, a holistic approach that takes structure, flexibility, stability, and dynamics into account is required, as these aspects become inseparable through their interdependence. Another key component of protein function is conformational dynamics, which often manifest as protein kinetics. Computational methods that use ML to generate representative conformational ensembles and quantify differences in conformational ensembles important for function are included in this review. Future opportunities are highlighted for each of these topics.

MutCov: A pipeline for evaluating the effect of mutations in spike protein on infectivity and antigenicity of SARS-CoV-2

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), causing an outbreak of coronavirus disease 2019 (COVID-19), is a major threat to public health worldwide. Previous studies have shown that the spike protein of SARS-CoV-2 determines viral infectivity and major antigenicity. However, the spike protein has been undergoing various mutations, which bring a great challenge to the prevention and treatment of COVID-19. Here we present the MutCov, a pipeline for evaluating the effect of mutations in spike protein on infectivity and antigenicity of SARS-CoV-2 by calculating the binding free energy between spike protein and angiotensin-converting enzyme 2 (ACE2) or neutralizing monoclonal antibody (mAb). The predicted infectivity and antigenicity were highly consistent with biologically experimental results, and demonstrated that the MutCov achieved good prediction performance. In conclusion, the MutCov is of high importance for systematically evaluating the effect of novel mutations and improving the prevention and treatment of COVID-19. The source code and installation instruction of MutCov are freely available at http://jianglab.org.cn/MutCov.

iKcr_CNN: A novel computational tool for imbalance classification of human nonhistone crotonylation sites based on convolutional neural networks with focal loss

Lysine crotonylation (Kcr) is a newly discovered protein post-translational modification and has been proved to be widely involved in various biological processes and human diseases. Thus, the accurate and fast identification of this modification became the preliminary task in investigating the related biological functions. Due to the long duration, high cost and intensity of traditional high-throughput experimental techniques, constructing bioinformatics predictors based on machine learning algorithms is treated as a most popular solution. Although dozens of predictors have been reported to identify Kcr sites, only two, nhKcr and DeepKcrot, focused on human nonhistone protein sequences. Moreover, due to the imbalance nature of data distribution, associated detection performance is severely biased towards the major negative samples and remains much room for improvement. In this research, we developed a convolutional neural network framework, dubbed iKcr_CNN, to identify the human nonhistone Kcr modification. To overcome the imbalance issue (Kcr: 15,274; non-Kcr: 74,018 with imbalance ratio: 1:4), we applied the focal loss function instead of the standard cross-entropy as the indicator to optimize the model, which not only assigns different weights to samples belonging to different categories but also distinguishes easy- and hard-classified samples. Ultimately, the obtained model presents more balanced prediction scores between real-world positive and negative samples than existing tools. The user-friendly web server is accessible at ikcrcnn.webmalab.cn/, and the involved Python scripts can be conveniently downloaded at github.com/lijundou/iKcr_CNN/. The proposed model may serve as an efficient tool to assist academicians with their experimental researches.

Protein Function Prediction Based on PPI Networks: Network Reconstruction vs Edge Enrichment

Over the past decades, massive amounts of protein-protein interaction (PPI) data have been accumulated due to the advancement of high-throughput technologies, and but data quality issues (noise or incompleteness) of PPI have been still affecting protein function prediction accuracy based on PPI networks. Although two main strategies of network reconstruction and edge enrichment have been reported on the effectiveness of boosting the prediction performance in numerous literature studies, there still lack comparative studies of the performance differences between network reconstruction and edge enrichment. Inspired by the question, this study first uses three protein similarity metrics (local, global and sequence) for network reconstruction and edge enrichment in PPI networks, and then evaluates the performance differences of network reconstruction, edge enrichment and the original networks on two real PPI datasets. The experimental results demonstrate that edge enrichment work better than both network reconstruction and original networks. Moreover, for the edge enrichment of PPI networks, the sequence similarity outperformes both local and global similarity. In summary, our study can help biologists select suitable pre-processing schemes and achieve better protein function prediction for PPI networks.

Testing Gene-Gene Interactions Based on a Neighborhood Perspective in Genome-wide Association Studies

Unexplained genetic variation that causes complex diseases is often induced by gene-gene interactions (GGIs). Gene-based methods are one of the current statistical methodologies for discovering GGIs in case-control genome-wide association studies that are not only powerful statistically, but also interpretable biologically. However, most approaches include assumptions about the form of GGIs, which results in poor statistical performance. As a result, we propose gene-based testing based on the maximal neighborhood coefficient (MNC) called gene-based gene-gene interaction through a maximal neighborhood coefficient (GBMNC). MNC is a metric for capturing a wide range of relationships between two random vectors with arbitrary, but not necessarily equal, dimensions. We established a statistic that leverages the difference in MNC in case and in control samples as an indication of the existence of GGIs, based on the assumption that the joint distribution of two genes in cases and controls should not be substantially different if there is no interaction between them. We then used a permutation-based statistical test to evaluate this statistic and calculate a statistical p-value to represent the significance of the interaction. Experimental results using both simulation and real data showed that our approach outperformed earlier methods for detecting GGIs.

Structure-aware protein-protein interaction site prediction using deep graph convolutional network

MOTIVATION

Protein-protein interactions (PPI) play crucial roles in many biological processes, and identifying PPI sites is an important step for mechanistic understanding of diseases and design of novel drugs. Since experimental approaches for PPI site identification are expensive and time-consuming, many computational methods have been developed as screening tools. However, these methods are mostly based on neighbored features in sequence, and thus limited to capture spatial information.

RESULTS

We propose a deep graph-based framework deep Graph convolutional network for Protein-Protein-Interacting Site prediction (GraphPPIS) for PPI site prediction, where the PPI site prediction problem was converted into a graph node classification task and solved by deep learning using the initial residual and identity mapping techniques. We showed that a deeper architecture (up to eight layers) allows significant performance improvement over other sequence-based and structure-based methods by more than 12.5% and 10.5% on AUPRC and MCC, respectively. Further analyses indicated that the predicted interacting sites by GraphPPIS are more spatially clustered and closer to the native ones even when false-positive predictions are made. The results highlight the importance of capturing spatially neighboring residues for interacting site prediction.

AVAILABILITY AND IMPLEMENTATION

The datasets, the pre-computed features, and the source codes along with the pre-trained models of GraphPPIS are available at https://github.com/biomed-AI/GraphPPIS. The GraphPPIS web server is freely available at https://biomed.nscc-gz.cn/apps/GraphPPIS.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

iRice-MS: An integrated XGBoost model for detecting multitype post-translational modification sites in rice

Post-translational modification (PTM) refers to the covalent and enzymatic modification of proteins after protein biosynthesis, which orchestrates a variety of biological processes. Detecting PTM sites in proteome scale is one of the key steps to in-depth understanding their regulation mechanisms. In this study, we presented an integrated method based on eXtreme Gradient Boosting (XGBoost), called iRice-MS, to identify 2-hydroxyisobutyrylation, crotonylation, malonylation, ubiquitination, succinylation and acetylation in rice. For each PTM-specific model, we adopted eight feature encoding schemes, including sequence-based features, physicochemical property-based features and spatial mapping information-based features. The optimal feature set was identified from each encoding, and their respective models were established. Extensive experimental results show that iRice-MS always display excellent performance on 5-fold cross-validation and independent dataset test. In addition, our novel approach provides the superiority to other existing tools in terms of AUC value. Based on the proposed model, a web server named iRice-MS was established and is freely accessible at http://lin-group.cn/server/iRice-MS.

Secondary structure assignment of proteins in the absence of sequence information

Motivation

The structure of proteins is organized in a hierarchy among which the secondary structure elements, α-helix, β-strand and loop, are the basic bricks. The determination of secondary structure elements usually requires the knowledge of the whole structure. Nevertheless, in numerous experimental circumstances, the protein structure is partially known. The detection of secondary structures from these partial structures is hampered by the lack of information about connecting residues along the primary sequence.

Results

We introduce a new methodology to estimate the secondary structure elements from the values of local distances and angles between the protein atoms. Our method uses a message passing neural network, named Sequoia, which allows the automatic prediction of secondary structure elements from the values of local distances and angles between the protein atoms. This neural network takes as input the topology of the given protein graph, where the vertices are protein residues, and the edges are weighted by values of distances and pseudo-dihedral angles generalizing the backbone angles ϕ and ψ. Any pair of residues, independently of its covalent bonds along the primary sequence of the protein, is tagged with this distance and angle information. Sequoia permits the automatic detection of the secondary structure elements, with an F1-score larger than 80% for most of the cases, when α helices and β strands are predicted. In contrast to the approaches classically used in structural biology, such as DSSP, Sequoia is able to capture the variations of geometry at the interface of adjacent secondary structure element. Due to its general modeling frame, Sequoia is able to handle graphs containing only C α atoms, which is particularly useful on low resolution structural input and in the frame of electron microscopy development.

Availability and implementation

Sequoia source code can be found at https://github.com/Khalife/Sequoia with additional documentation.

Supplementary information

Supplementary data are available at Bioinformatics Advances online.

Protein-Protein Docking: Past, Present, and Future

The biological significance of proteins attracted the scientific community in exploring their characteristics. The studies shed light on the interaction patterns and functions of proteins in a living body. Due to their practical difficulties, reliable experimental techniques pave the way for introducing computational methods in the interaction prediction. Automated methods reduced the difficulties but could not yet replace experimental studies as the field is still evolving. Interaction prediction problem being critical needs highly accurate results, but none of the existing methods could offer reliable performance that can parallel with experimental results yet. This article aims to assess the existing computational docking algorithms, their challenges, and future scope. Blind docking techniques are quite helpful when no information other than the individual structures are available. As more and more complex structures are being added to different databases, information-driven approaches can be a good alternative. Artificial intelligence, ruling over the major fields, is expected to take over this domain very shortly.

A Deep Learning and XGBoost-Based Method for Predicting Protein-Protein Interaction Sites

Knowledge about protein-protein interactions is beneficial in understanding cellular mechanisms. Protein-protein interactions are usually determined according to their protein-protein interaction sites. Due to the limitations of current techniques, it is still a challenging task to detect protein-protein interaction sites. In this article, we presented a method based on deep learning and XGBoost (called DeepPPISP-XGB) for predicting protein-protein interaction sites. The deep learning model served as a feature extractor to remove redundant information from protein sequences. The Extreme Gradient Boosting algorithm was used to construct a classifier for predicting protein-protein interaction sites. The DeepPPISP-XGB achieved the following results: area under the receiver operating characteristic curve of 0.681, a recall of 0.624, and area under the precision-recall curve of 0.339, being competitive with the state-of-the-art methods. We also validated the positive role of global features in predicting protein-protein interaction sites.

ORS-Pred: An optimized reduced scheme-based identifier for antioxidant proteins

Antioxidant proteins can terminate a chain of reactions caused by free radicals and protect cells from damage. To identify antioxidant proteins rapidly, a computational model was proposed based on the optimized recoding scheme, sequence information and machine learning methods. First, over 600 recoding schemes were collected to build a scheme set. Then, the original sequence was recoded as a reduced expression whose g-gap dipeptides (g = 0, 1, 2) were used as the features of proteins. Furthermore, a random forest method was used to evaluate the classification ability of the obtained dipeptide features. After going through all schemes, the best predictive performance scheme was chosen as the optimized reduction scheme. Finally, for the RF method, a grid search strategy was used to select a better parameter combination to identify antioxidant proteins. In the experiment, the present method correctly recognized 90.13-99.87% of the antioxidant samples. Other experimental results also proved that the present method was efficient to identify antioxidant proteins. Finally, we also developed a web server that was freely accessible to researchers.

Assessing the Adequacy of Hemodialysis Patients via the Graph-Based Takagi-Sugeno-Kang Fuzzy System

Maintenance hemodialysis is the main method for the treatment of end-stage renal disease in China. The Kt/V value is the gold standard of hemodialysis adequacy. However, Kt/V requires repeated blood drawing and evaluation; it is hard to monitor dialysis adequacy frequently. In order to meet the need for repeated clinical assessments of dialysis adequacy, we want to find a noninvasive way to assess dialysis adequacy. Therefore, we collect some clinically relevant data and develop a machine learning- (ML-) based model to predict dialysis adequacy for clinical hemodialysis patients. We collect 250 patients, including gender, age, ultrafiltration (UF), predialysis body weight (preBW), postdialysis body weights (postBW), blood pressure (BP), heart rate (HR), and blood flow (BF). An efficient graph-based Takagi-Sugeno-Kang Fuzzy System (G-TSK-FS) model is proposed to predict the dialysis adequacy of hemodialysis patients. The root mean square error (RMSE) of our model is 0.1578. The proposed model can be used as a feasible method to predict dialysis adequacy, providing a new way for clinical practice. Our G-TSK-FS model could be used as a feasible method to predict dialysis adequacy, providing a new way for clinical practice.

A Self-Representation-Based Fuzzy SVM Model for Predicting Vascular Calcification of Hemodialysis Patients

In end-stage renal disease (ESRD), vascular calcification risk factors are essential for the survival of hemodialysis patients. To effectively assess the level of vascular calcification, the machine learning algorithm can be used to predict the vascular calcification risk in ESRD patients. As the amount of collected data is unbalanced under different risk levels, it has an influence on the classification task. So, an effective fuzzy support vector machine based on self-representation (FSVM-SR) is proposed to predict vascular calcification risk in this work. In addition, our method is also compared with other conventional machine learning methods, and the results show that our method can better complete the classification task of the vascular calcification risk.

EPSOL: sequence-based protein solubility prediction using multidimensional embedding

MOTIVATION

The heterologous expression of recombinant protein requires host cells, such as Escherichia coli, and the solubility of protein greatly affects the protein yield. A novel and highly accurate solubility predictor that concurrently improves the production yield and minimizes production cost, and that forecasts protein solubility in an E. coli expression system before the actual experimental work is highly sought.

RESULTS

In this paper, EPSOL, a novel deep learning architecture for the prediction of protein solubility in an E. coli expression system, which automatically obtains comprehensive protein feature representations using multidimensional embedding, is presented. EPSOL outperformed all existing sequence-based solubility predictors and achieved 0.79 in accuracy and 0.58 in Matthew's correlation coefficient. The higher performance of EPSOL permits large-scale screening for sequence variants with enhanced manufacturability and predicts the solubility of new recombinant proteins in an E. coli expression system with greater reliability.

AVAILABILITY AND IMPLEMENTATION

EPSOL's best model and results can be downloaded from GitHub (https://github.com/LiangYu-Xidian/EPSOL).

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

i4mC-EL: Identifying DNA N4-Methylcytosine Sites in the Mouse Genome Using Ensemble Learning

As one of important epigenetic modifications, DNA N4-methylcytosine (4mC) plays a crucial role in controlling gene replication, expression, cell cycle, DNA replication, and differentiation. The accurate identification of 4mC sites is necessary to understand biological functions. In the paper, we use ensemble learning to develop a model named i4mC-EL to identify 4mC sites in the mouse genome. Firstly, a multifeature encoding scheme consisting of Kmer and EIIP was adopted to describe the DNA sequences. Secondly, on the basis of the multifeature encoding scheme, we developed a stacked ensemble model, in which four machine learning algorithms, namely, BayesNet, NaiveBayes, LibSVM, and Voted Perceptron, were utilized to implement an ensemble of base classifiers that produce intermediate results as input of the metaclassifier, Logistic. The experimental results on the independent test dataset demonstrate that the overall rate of predictive accurate of i4mC-EL is 82.19%, which is better than the existing methods. The user-friendly website implementing i4mC-EL can be accessed freely at the following.

Amino Acid Reduction Can Help to Improve the Identification of Antimicrobial Peptides and Their Functional Activities

Antimicrobial peptides (AMPs) are considered as potential substitutes of antibiotics in the field of new anti-infective drug design. There have been several machine learning algorithms and web servers in identifying AMPs and their functional activities. However, there is still room for improvement in prediction algorithms and feature extraction methods. The reduced amino acid (RAA) alphabet effectively solved the problems of simplifying protein complexity and recognizing the structure conservative region. This article goes into details about evaluating the performances of more than 5,000 amino acid reduced descriptors generated from 74 types of amino acid reduced alphabet in the first stage and the second stage to construct an excellent two-stage classifier, Identification of Antimicrobial Peptides by Reduced Amino Acid Cluster (iAMP-RAAC), for identifying AMPs and their functional activities, respectively. The results show that the first stage AMP classifier is able to achieve the accuracy of 97.21 and 97.11% for the training data set and independent test dataset. In the second stage, our classifier still shows good performance. At least three of the four metrics, sensitivity (SN), specificity (SP), accuracy (ACC), and Matthews correlation coefficient (MCC), exceed the calculation results in the literature. Further, the ANOVA with incremental feature selection (IFS) is used for feature selection to further improve prediction performance. The prediction performance is further improved after the feature selection of each stage. At last, a user-friendly web server, iAMP-RAAC, is established at http://bioinfor.imu.edu. cn/iampraac.

A comprehensive review of the imbalance classification of protein post-translational modifications

Post-translational modifications (PTMs) play significant roles in regulating protein structure, activity and function, and they are closely involved in various pathologies. Therefore, the identification of associated PTMs is the foundation of in-depth research on related biological mechanisms, disease treatments and drug design. Due to the high cost and time consumption of high-throughput sequencing techniques, developing machine learning-based predictors has been considered an effective approach to rapidly recognize potential modified sites. However, the imbalanced distribution of true and false PTM sites, namely, the data imbalance problem, largely effects the reliability and application of prediction tools. In this article, we conduct a systematic survey of the research progress in the imbalanced PTMs classification. First, we describe the modeling process in detail and outline useful data imbalance solutions. Then, we summarize the recently proposed bioinformatics tools based on imbalanced PTM data and simultaneously build a convenient website, ImClassi_PTMs (available at lab.malab.cn/∼dlj/ImbClassi_PTMs/), to facilitate the researchers to view. Moreover, we analyze the challenges of current computational predictors and propose some suggestions to improve the efficiency of imbalance learning. We hope that this work will provide comprehensive knowledge of imbalanced PTM recognition and contribute to advanced predictors in the future.

ATSE: a peptide toxicity predictor by exploiting structural and evolutionary information based on graph neural network and attention mechanism

MOTIVATION

Peptides have recently emerged as promising therapeutic agents against various diseases. For both research and safety regulation purposes, it is of high importance to develop computational methods to accurately predict the potential toxicity of peptides within the vast number of candidate peptides.

RESULTS

In this study, we proposed ATSE, a peptide toxicity predictor by exploiting structural and evolutionary information based on graph neural networks and attention mechanism. More specifically, it consists of four modules: (i) a sequence processing module for converting peptide sequences to molecular graphs and evolutionary profiles, (ii) a feature extraction module designed to learn discriminative features from graph structural information and evolutionary information, (iii) an attention module employed to optimize the features and (iv) an output module determining a peptide as toxic or non-toxic, using optimized features from the attention module.

CONCLUSION

Comparative studies demonstrate that the proposed ATSE significantly outperforms all other competing methods. We found that structural information is complementary to the evolutionary information, effectively improving the predictive performance. Importantly, the data-driven features learned by ATSE can be interpreted and visualized, providing additional information for further analysis. Moreover, we present a user-friendly online computational platform that implements the proposed ATSE, which is now available at http://server.malab.cn/ATSE. We expect that it can be a powerful and useful tool for researchers of interest.

iEnhancer-EBLSTM: Identifying Enhancers and Strengths by Ensembles of Bidirectional Long Short-Term Memory

Enhancers are regulatory DNA sequences that could be bound by specific proteins named transcription factors (TFs). The interactions between enhancers and TFs regulate specific genes by increasing the target gene expression. Therefore, enhancer identification and classification have been a critical issue in the enhancer field. Unfortunately, so far there has been a lack of suitable methods to identify enhancers. Previous research has mainly focused on the features of the enhancer's function and interactions, which ignores the sequence information. As we know, the recurrent neural network (RNN) and long short-term memory (LSTM) models are currently the most common methods for processing time series data. LSTM is more suitable than RNN to address the DNA sequence. In this paper, we take the advantages of LSTM to build a method named iEnhancer-EBLSTM to identify enhancers. iEnhancer-ensembles of bidirectional LSTM (EBLSTM) consists of two steps. In the first step, we extract subsequences by sliding a 3-mer window along the DNA sequence as features. Second, EBLSTM model is used to identify enhancers from the candidate input sequences. We use the dataset from the study of Quang H et al. as the benchmarks. The experimental results from the datasets demonstrate the efficiency of our proposed model.

Recent Advances in Predicting Protein S-Nitrosylation Sites

Protein S-nitrosylation (SNO) is a process of covalent modification of nitric oxide (NO) and its derivatives and cysteine residues. SNO plays an essential role in reversible posttranslational modifications of proteins. The accurate prediction of SNO sites is crucial in revealing a certain biological mechanism of NO regulation and related drug development. Identification of the sites of SNO in proteins is currently a very hot topic. In this review, we briefly summarize recent advances in computationally identifying SNO sites. The challenges and future perspectives for identifying SNO sites are also discussed. We anticipate that this review will provide insights into research on SNO site prediction.

prPred: A Predictor to Identify Plant Resistance Proteins by Incorporating k-Spaced Amino Acid (Group) Pairs

To infect plants successfully, pathogens adopt various strategies to overcome their physical and chemical barriers and interfere with the plant immune system. Plants deploy a large number of resistance (R) proteins to detect invading pathogens. The R proteins are encoded by resistance genes that contain cell surface-localized receptors and intracellular receptors. In this study, a new plant R protein predictor called prPred was developed based on a support vector machine (SVM), which can accurately distinguish plant R proteins from other proteins. Experimental results showed that the accuracy, precision, sensitivity, specificity, F1-score, MCC, and AUC of prPred were 0.935, 1.000, 0.806, 1.000, 0.893, 0.857, and 0.948, respectively, on an independent test set. Moreover, the predictor integrated the HMMscan search tool and Phobius to identify protein domain families and transmembrane protein regions to differentiate subclasses of R proteins. prPred is available at https://github.com/Wangys-prog/prPred. The tool requires a valid Python installation and is run from the command line.

eHSCPr discriminating the cell identity involved in endothelial to hematopoietic transition

MOTIVATION

Hematopoietic stem cells (HSCs) give rise to all blood cells and play a vital role throughout the whole lifespan through their pluripotency and self-renewal properties. Accurately identifying the stages of early HSCs is extremely important, as it may open up new prospects for extracorporeal blood research. Existing experimental techniques for identifying the early stages of HSCs development are time-consuming and expensive. Machine learning has shown its excellence in massive single-cell data processing and it is desirable to develop related computational models as good complements to experimental techniques.

RESULTS

In this study, we presented a novel predictor called eHSCPr specifically for predicting the early stages of HSCs development. To reveal the distinct genes at each developmental stage of HSCs, we compared F-score with three state-of-art differential gene selection methods (limma, DESeq2, edgeR) and evaluated their performance. F-score captured the more critical surface markers of endothelial cells and hematopoietic cells, and the area under receiver operating characteristic curve (ROC) value was 0.987. Based on SVM, the 10-fold cross-validation accuracy of eHSCpr in the independent dataset and the training dataset reached 94.84% and 94.19%, respectively. Importantly, we performed transcription analysis on the F-score gene set, which indeed further enriched the signal markers of HSCs development stages. eHSCPr can be a powerful tool for predicting early stages of HSCs development, facilitating hypothesis-driven experimental design and providing crucial clues for the in vitro blood regeneration studies.

AVAILABILITY

http://bioinfor.imu.edu.cn/ehscpr.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.