FoldRec-C2C: protein fold recognition by combining cluster-to-cluster model and protein similarity network

ResCNNT-fold: Combining residual convolutional neural network and Transformer for protein fold recognition from language model embeddings

A comprehensive understanding of protein functions holds significant promise for disease research and drug development, and proteins with analogous tertiary structures tend to exhibit similar functions. Protein fold recognition stands as a classical approach in the realm of protein structure investigation. Despite significant advancements made by researchers in this field, the continuous updating of protein databases presents an ongoing challenge in accurately identifying protein fold types. In this study, we introduce a predictor, ResCNNT-fold, for protein fold recognition and employ the LE dataset for testing purpose. ResCNNT-fold leverages a pre-trained language model to obtain embedding representations for protein sequences, which are then processed by the ResCNNT feature extractor, a combination of residual convolutional neural network and Transformer, to derive fold-specific features. Subsequently, the query protein is paired with each protein whose structure is known in the template dataset. For each pair, the similarity score of their fold-specific features is calculated. Ultimately, the query protein is identified as the fold type of the template protein in the pair with the highest similarity score. To further validate the utility and efficacy of the proposed ResCNNT-fold predictor, we conduct a 2-fold cross-validation experiment on the fold level of the LE dataset. Remarkably, this rigorous evaluation yields an exceptional accuracy of 91.57%, which surpasses the best result among other state-of-the-art protein fold recognition methods by an approximate margin of 10%. The excellent performance unequivocally underscores the compelling advantages inherent to our proposed ResCNNT-fold predictor in the realm of protein fold recognition. The source code and data of ResCNNT-fold can be downloaded from https://github.com/Bioinformatics-Laboratory/ResCNNT-fold.

Predicting enhancer-promoter interaction based on epigenomic signals

Introduction: The physical interactions between enhancers and promoters are often involved in gene transcriptional regulation. High tissue-specific enhancer-promoter interactions (EPIs) are responsible for the differential expression of genes. Experimental methods are time-consuming and labor-intensive in measuring EPIs. An alternative approach, machine learning, has been widely used to predict EPIs. However, most existing machine learning methods require a large number of functional genomic and epigenomic features as input, which limits the application to different cell lines. Methods: In this paper, we developed a random forest model, HARD (H3K27ac, ATAC-seq, RAD21, and Distance), to predict EPI using only four types of features. Results: Independent tests on a benchmark dataset showed that HARD outperforms other models with the fewest features. Discussion: Our results revealed that chromatin accessibility and the binding of cohesin are important for cell-line-specific EPIs. Furthermore, we trained the HARD model in the GM12878 cell line and performed testing in the HeLa cell line. The cross-cell-lines prediction also performs well, suggesting it has the potential to be applied to other cell lines.

Enhancer-FRL: Improved and Robust Identification of Enhancers and Their Activities Using Feature Representation Learning

Enhancers are crucial for precise regulation of gene expression, while enhancer identification and strength prediction are challenging because of their free distribution and tremendous number of similar fractions in the genome. Although several bioinformatics tools have been developed, shortfalls in these models remain, and their performances need further improvement. In the present study, a two-layer predictor called Enhancer-FRL was proposed for identifying enhancers (enhancers or nonenhancers) and their activities (strong and weak). More specifically, to build an efficient model, the feature representation learning scheme was applied to generate a 50D probabilistic vector based on 10 feature encodings and five machine learning algorithms. Subsequently, the multiview probabilistic features were integrated to construct the final prediction model. Compared with the single feature-based model, Enhancer-FRL showed significant performance improvement and model robustness. Performance assessment on the independent test dataset indicated that the proposed model outperformed state-of-the-art available toolkits. The webserver Enhancer-FRL is freely accessible at http://lab.malab.cn/∼wangchao/softwares/Enhancer-FRL/, The code and datasets can be downloaded at the webserver page or at the Github https://github.com/wangchao-malab/Enhancer-FRL/.

Identification of adaptor proteins by incorporating deep learning and PSSM profiles

Adaptor proteins, also known as signal transduction adaptor proteins, are important proteins in signal transduction pathways, and play a role in connecting signal proteins for signal transduction between cells. Studies have shown that adaptor proteins are closely related to some diseases, such as tumors and diabetes. Therefore, it is very meaningful to construct a relevant model to accurately identify adaptor proteins. In recent years, many studies have used a position-specific scoring matrix (PSSM) and neural network methods to identify adaptor proteins. However, ordinary neural network models cannot correlate the contextual information in PSSM profiles well, so these studies usually process 20×N (N > 20) PSSM into 20×20 dimensions, which results in the loss of a large amount of protein information; This research proposes an efficient method that combines one-dimensional convolution (1-D CNN) and a bidirectional long short-term memory network (biLSTM) to identify adaptor proteins. The complete PSSM profiles are the input of the model, and the complete information of the protein is retained during the training process. We perform cross-validation during model training and test the performance of the model on an independent test set; in the data set with 1224 adaptor proteins and 11,078 non-adaptor proteins, five indicators including specificity, sensitivity, accuracy, area under the receiver operating characteristic curve (AUC) metric and Matthews correlation coefficient (MCC), were employed to evaluate model performance. On the independent test set, the specificity, sensitivity, accuracy and MCC were 0.817, 0.865, 0.823 and 0.465, respectively. Those results show that our method is better than the state-of-the art methods. This study is committed to improve the accuracy of adaptor protein identification, and laid a foundation for further research on diseases related to adaptor protein. This research provided a new idea for the application of deep learning related models in bioinformatics and computational biology.

Learning Protein Embedding to Improve Protein Fold Recognition Using Deep Metric Learning

Protein fold recognition refers to predicting the most likely fold type of the query protein and is a critical step of protein structure and function prediction. With the popularity of deep learning in bioinformatics, protein fold recognition has obtained impressive progress. In this study, to extract the fold-specific feature to improve protein fold recognition, we proposed a unified deep metric learning framework based on a joint loss function, termed NPCFold. In addition, we also proposed an integrated machine learning model based on the similarity of proteins in various properties, termed NPCFoldpro. Benchmark experiments show both NPCFold and NPCFoldpro outperform existing protein fold recognition methods at the fold level, indicating that our proposed strategies of fusing loss functions and fusing features could improve the fold recognition level.

Performing protein fold recognition by exploiting a stack convolutional neural network with the attention mechanism

Protein fold recognition is a critical step in protein structure and function prediction, and aims to ascertain the most likely fold type of the query protein. As a typical pattern recognition problem, designing a powerful feature extractor and metric function to extract relevant and representative fold-specific features from protein sequences is the key to improving protein fold recognition. In this study, we propose an effective sequence-based approach, called RattnetFold, to identify protein fold types. The basic concept of RattnetFold is to employ a stack convolutional neural network with the attention mechanism that acts as a feature extractor to extract fold-specific features from protein residue-residue contact maps. Moreover, based on the fold-specific features, we leverage metric learning to project fold-specific features into a subspace where similar proteins are closer together and name this approach RattnetFoldPro. Benchmarking experiments illustrate that RattnetFold and RattnetFoldPro enable the convolutional neural networks to efficiently learn the underlying subtle patterns in residue-residue contact maps, thereby improving the performance of protein fold recognition. An online web server of RattnetFold and the benchmark datasets are freely available at http://csbio.njust.edu.cn/bioinf/rattnetfold/.

An analysis of protein language model embeddings for fold prediction

The identification of the protein fold class is a challenging problem in structural biology. Recent computational methods for fold prediction leverage deep learning techniques to extract protein fold-representative embeddings mainly using evolutionary information in the form of multiple sequence alignment (MSA) as input source. In contrast, protein language models (LM) have reshaped the field thanks to their ability to learn efficient protein representations (protein-LM embeddings) from purely sequential information in a self-supervised manner. In this paper, we analyze a framework for protein fold prediction using pre-trained protein-LM embeddings as input to several fine-tuning neural network models, which are supervisedly trained with fold labels. In particular, we compare the performance of six protein-LM embeddings: the long short-term memory-based UniRep and SeqVec, and the transformer-based ESM-1b, ESM-MSA, ProtBERT and ProtT5; as well as three neural networks: Multi-Layer Perceptron, ResCNN-BGRU (RBG) and Light-Attention (LAT). We separately evaluated the pairwise fold recognition (PFR) and direct fold classification (DFC) tasks on well-known benchmark datasets. The results indicate that the combination of transformer-based embeddings, particularly those obtained at amino acid level, with the RBG and LAT fine-tuning models performs remarkably well in both tasks. To further increase prediction accuracy, we propose several ensemble strategies for PFR and DFC, which provide a significant performance boost over the current state-of-the-art results. All this suggests that moving from traditional protein representations to protein-LM embeddings is a very promising approach to protein fold-related tasks.

Distance-based support vector machine to predict DNA N6-methyladenine modification

Background:

DNA N6-methyladenine plays an important role in the restriction-modification system to isolate invasion from adventive DNA. The shortcomings of the high time-consumption and high costs of experimental methods have been exposed, and some computational methods have emerged. The support vector machine theory has received extensive attention in the bioinformatics field due to its solid theoretical foundation and many good characteristics.

Objective:

General machine learning methods include an important step of extracting features. The research has omitted this step and replaced with easy-to-obtain sequence distances matrix to obtain better results

Method:

First sequence alignment technology was used to achieve the similarity matrix. Then a novel transformation turned the similarity matrix into a distance matrix. Next, the similarity-distance matrix is made positive semi-definite so that it can be used in the kernel matrix. Finally, the LIBSVM software was applied to solve the support vector machine.

Results:

The five-fold cross-validation of this model on rice and mouse data has achieved excellent accuracy rates of 92.04% and 96.51%, respectively. This shows that the DB-SVM method has obvious advantages compared with traditional machine learning methods. Meanwhile this model achieved 0.943,0.982 and 0.818 accuracy,0.944, 0.982, and 0.838 Matthews correlation coefficient and 0.942, 0.982 and 0.840 F1 scores for the rice, M. musculus and cross-species genome datasets, respectively.

Conclusion:

These outcomes show that this model outperforms the iIM-CNN and csDMA in the prediction of DNA 6mA modification, which are the lastest research on DNA 6mA.

ATGPred-FL: sequence-based prediction of autophagy proteins with feature representation learning

Autophagy plays an important role in biological evolution and is regulated by many autophagy proteins. Accurate identification of autophagy proteins is crucially important to reveal their biological functions. Due to the expense and labor cost of experimental methods, it is urgent to develop automated, accurate and reliable sequence-based computational tools to enable the identification of novel autophagy proteins among numerous proteins and peptides. For this purpose, a new predictor named ATGPred-FL was proposed for the efficient identification of autophagy proteins. We investigated various sequence-based feature descriptors and adopted the feature learning method to generate corresponding, more informative probability features. Then, a two-step feature selection strategy based on accuracy was utilized to remove irrelevant and redundant features, leading to the most discriminative 14-dimensional feature set. The final predictor was built using a support vector machine classifier, which performed favorably on both the training and testing sets with accuracy values of 94.40% and 90.50%, respectively. ATGPred-FL is the first ATG machine learning predictor based on protein primary sequences. We envision that ATGPred-FL will be an effective and useful tool for autophagy protein identification, and it is available for free at http://lab.malab.cn/~acy/ATGPred-FL , the source code and datasets are accessible at https://github.com/jiaoshihu/ATGPred .

iThermo: A Sequence-Based Model for Identifying Thermophilic Proteins Using a Multi-Feature Fusion Strategy

Thermophilic proteins have important application value in biotechnology and industrial processes. The correct identification of thermophilic proteins provides important information for the application of these proteins in engineering. The identification method of thermophilic proteins based on biochemistry is laborious, time-consuming, and high cost. Therefore, there is an urgent need for a fast and accurate method to identify thermophilic proteins. Considering this urgency, we constructed a reliable benchmark dataset containing 1,368 thermophilic and 1,443 non-thermophilic proteins. A multi-layer perceptron (MLP) model based on a multi-feature fusion strategy was proposed to discriminate thermophilic proteins from non-thermophilic proteins. On independent data set, the proposed model could achieve an accuracy of 96.26%, which demonstrates that the model has a good application prospect. In order to use the model conveniently, a user-friendly software package called iThermo was established and can be freely accessed at http://lin-group.cn/server/iThermo/index.html. The high accuracy of the model and the practicability of the developed software package indicate that this study can accelerate the discovery and engineering application of thermally stable proteins.

TMPpred: A support vector machine-based thermophilic protein identifier

MOTIVATION

The thermostability of proteins will cause them to break the temperature binding and play more functions. Using machine learning, we explored the mechanism of and reasons for protein thermostability characteristics.

RESULTS

Different from other methods that only pursue the performance of models, we aim to find important features so as to provide a powerful reference for in vitro experiments. We transformed this problem into a binary classification problem, that is, the distinction between thermophilic proteins and nonthermophilic proteins. Using support vector machine-based model construction and analysis, we inferred that Gly, Ala, Ser and Thr may be the most important components at the residue level that determine the thermal stability of proteins. It is also noteworthy that our proposed model obtains an Sn of 0.892, an Sp of 0.857, an ACC of 0.87566 and an AUC of 0.874. To facilitate other researchers, we wrapped our model and deployed it as a web server, which is accessible at http://112.124.26.17:7000/TMPpred/index.html.

The Characterization of Structure and Prediction for Aquaporin in Tumour Progression by Machine Learning

Recurrence and new cases of cancer constitute a challenging human health problem. Aquaporins (AQPs) can be expressed in many types of tumours, including the brain, breast, pancreas, colon, skin, ovaries, and lungs, and the histological grade of cancer is positively correlated with AQP expression. Therefore, the identification of aquaporins is an area to explore. Computational tools play an important role in aquaporin identification. In this research, we propose reliable, accurate and automated sequence predictor iAQPs-RF to identify AQPs. In this study, the feature extraction method was 188D (global protein sequence descriptor, GPSD). Six common classifiers, including random forest (RF), NaiveBayes (NB), support vector machine (SVM), XGBoost, logistic regression (LR) and decision tree (DT), were used for AQP classification. The classification results show that the random forest (RF) algorithm is the most suitable machine learning algorithm, and the accuracy was 97.689%. Analysis of Variance (ANOVA) was used to analyse these characteristics. Feature rank based on the ANOVA method and IFS strategy was applied to search for the optimal features. The classification results suggest that the 26th feature (neutral/hydrophobic) and 21st feature (hydrophobic) are the two most powerful and informative features that distinguish AQPs from non-AQPs. Previous studies reported that plasma membrane proteins have hydrophobic characteristics. Aquaporin subcellular localization prediction showed that all aquaporins were plasma membrane proteins with highly conserved transmembrane structures. In addition, the 3D structure of aquaporins was consistent with the localization results. Therefore, these studies confirmed that aquaporins possess hydrophobic properties. Although aquaporins are highly conserved transmembrane structures, the phylogenetic tree shows the diversity of aquaporins during evolution. The PCA showed that positive and negative samples were well separated by 54D features, indicating that the 54D feature can effectively classify aquaporins. The online prediction server is accessible at http://lab.malab.cn/∼acy/iAQP.

A SNARE Protein Identification Method Based on iLearnPlus to Efficiently Solve the Data Imbalance Problem

Machine learning has been widely used to solve complex problems in engineering applications and scientific fields, and many machine learning-based methods have achieved good results in different fields. SNAREs are key elements of membrane fusion and required for the fusion process of stable intermediates. They are also associated with the formation of some psychiatric disorders. This study processes the original sequence data with the synthetic minority oversampling technique (SMOTE) to solve the problem of data imbalance and produces the most suitable machine learning model with the iLearnPlus platform for the identification of SNARE proteins. Ultimately, a sensitivity of 66.67%, specificity of 93.63%, accuracy of 91.33%, and MCC of 0.528 were obtained in the cross-validation dataset, and a sensitivity of 66.67%, specificity of 93.63%, accuracy of 91.33%, and MCC of 0.528 were obtained in the independent dataset (the adaptive skip dipeptide composition descriptor was used for feature extraction, and LightGBM with proper parameters was used as the classifier). These results demonstrate that this combination can perform well in the classification of SNARE proteins and is superior to other methods.

Identify DNA-Binding Proteins Through the Extreme Gradient Boosting Algorithm

The exploration of DNA-binding proteins (DBPs) is an important aspect of studying biological life activities. Research on life activities requires the support of scientific research results on DBPs. The decline in many life activities is closely related to DBPs. Generally, the detection method for identifying DBPs is achieved through biochemical experiments. This method is inefficient and requires considerable manpower, material resources and time. At present, several computational approaches have been developed to detect DBPs, among which machine learning (ML) algorithm-based computational techniques have shown excellent performance. In our experiments, our method uses fewer features and simpler recognition methods than other methods and simultaneously obtains satisfactory results. First, we use six feature extraction methods to extract sequence features from the same group of DBPs. Then, this feature information is spliced together, and the data are standardized. Finally, the extreme gradient boosting (XGBoost) model is used to construct an effective predictive model. Compared with other excellent methods, our proposed method has achieved better results. The accuracy achieved by our method is 78.26% for PDB2272 and 85.48% for PDB186. The accuracy of the experimental results achieved by our strategy is similar to that of previous detection methods.

Immunoglobulin Classification Based on FC* and GC* Features

Immunoglobulins have a pivotal role in disease regulation. Therefore, it is vital to accurately identify immunoglobulins to develop new drugs and research related diseases. Compared with utilizing high-dimension features to identify immunoglobulins, this research aimed to examine a method to classify immunoglobulins and non-immunoglobulins using two features, FC* and GC*. Classification of 228 samples (109 immunoglobulin samples and 119 non-immunoglobulin samples) revealed that the overall accuracy was 80.7% in 10-fold cross-validation using the J48 classifier implemented in Weka software. The FC* feature identified in this study was found in the immunoglobulin subtype domain, which demonstrated that this extracted feature could represent functional and structural properties of immunoglobulins for forecasting.

VTP-Identifier: Vesicular Transport Proteins Identification Based on PSSM Profiles and XGBoost

Vesicular transport proteins are related to many human diseases, and they threaten human health when they undergo pathological changes. Protein function prediction has been one of the most in-depth topics in bioinformatics. In this work, we developed a useful tool to identify vesicular transport proteins. Our strategy is to extract transition probability composition, autocovariance transformation and other information from the position-specific scoring matrix as feature vectors. EditedNearesNeighbours (ENN) is used to address the imbalance of the data set, and the Max-Relevance-Max-Distance (MRMD) algorithm is adopted to reduce the dimension of the feature vector. We used 5-fold cross-validation and independent test sets to evaluate our model. On the test set, VTP-Identifier presented a higher performance compared with GRU. The accuracy, Matthew's correlation coefficient (MCC) and area under the ROC curve (AUC) were 83.6%, 0.531 and 0.873, respectively.

AAPred-CNN: accurate predictor based on deep convolution neural network for identification of anti-angiogenic peptides

Recently, deep learning techniques have been developed for various bioactive peptide prediction tasks. However, there are only conventional machine learning-based methods for the prediction of anti-angiogenic peptides (AAP), which play an important role in cancer treatment. The main reason why no deep learning method has been involved in this field is that there are too few experimentally validated AAPs to support the training of deep models but researchers have believed that deep learning seriously depends on the amounts of labeled data. In this paper, as a tentative work, we try to predict AAP by constructing different classical deep learning models and propose the first deep convolution neural network-based predictor (AAPred-CNN) for AAP. Contrary to intuition, the experimental results show that deep learning models can achieve superior or comparable performance to the state-of-the-art model, although they are given a few labeled sequences to train. We also decipher the influence of hyper-parameters and training samples on the performance of deep learning models to help understand how the model work. Furthermore, we also visualize the learned embeddings by dimension reduction to increase the model interpretability and reveal the residue propensity of AAP through the statistics of convolutional features for different residues. In summary, this work demonstrates the powerful representation ability of AAPred-CNNfor AAP prediction, further improving the prediction accuracy of AAP.

SNAREs-SAP: SNARE Proteins Identification With PSSM Profiles

Soluble N-ethylmaleimide sensitive factor activating protein receptor (SNARE) proteins are a large family of transmembrane proteins located in organelles and vesicles. The important roles of SNARE proteins include initiating the vesicle fusion process and activating and fusing proteins as they undergo exocytosis activity, and SNARE proteins are also vital for the transport regulation of membrane proteins and non-regulatory vesicles. Therefore, there is great significance in establishing a method to efficiently identify SNARE proteins. However, the identification accuracy of the existing methods such as SNARE CNN is not satisfied. In our study, we developed a method based on a support vector machine (SVM) that can effectively recognize SNARE proteins. We used the position-specific scoring matrix (PSSM) method to extract features of SNARE protein sequences, used the support vector machine recursive elimination correlation bias reduction (SVM-RFE-CBR) algorithm to rank the importance of features, and then screened out the optimal subset of feature data based on the sorted results. We input the feature data into the model when building the model, used 10-fold crossing validation for training, and tested model performance by using an independent dataset. In independent tests, the ability of our method to identify SNARE proteins achieved a sensitivity of 68%, specificity of 94%, accuracy of 92%, area under the curve (AUC) of 84%, and Matthew’s correlation coefficient (MCC) of 0.48. The results of the experiment show that the common evaluation indicators of our method are excellent, indicating that our method performs better than other existing classification methods in identifying SNARE proteins.

CRBPDL: Identification of circRNA-RBP interaction sites using an ensemble neural network approach

Circular RNAs (circRNAs) are non-coding RNAs with a special circular structure produced formed by the reverse splicing mechanism. Increasing evidence shows that circular RNAs can directly bind to RNA-binding proteins (RBP) and play an important role in a variety of biological activities. The interactions between circRNAs and RBPs are key to comprehending the mechanism of posttranscriptional regulation. Accurately identifying binding sites is very useful for analyzing interactions. In past research, some predictors on the basis of machine learning (ML) have been presented, but prediction accuracy still needs to be ameliorated. Therefore, we present a novel calculation model, CRBPDL, which uses an Adaboost integrated deep hierarchical network to identify the binding sites of circular RNA-RBP. CRBPDL combines five different feature encoding schemes to encode the original RNA sequence, uses deep multiscale residual networks (MSRN) and bidirectional gating recurrent units (BiGRUs) to effectively learn high-level feature representations, it is sufficient to extract local and global context information at the same time. Additionally, a self-attention mechanism is employed to train the robustness of the CRBPDL. Ultimately, the Adaboost algorithm is applied to integrate deep learning (DL) model to improve prediction performance and reliability of the model. To verify the usefulness of CRBPDL, we compared the efficiency with state-of-the-art methods on 37 circular RNA data sets and 31 linear RNA data sets. Moreover, results display that CRBPDL is capable of performing universal, reliable, and robust. The code and data sets are obtainable at https://github.com/nmt315320/CRBPDL.git.

More and more evidences show that circular RNA can directly bind to proteins and participate in countless different biological processes. The calculation method can quickly and accurately predict the binding site of circular RNA and RBP. In order to identify the interaction of circRNA with 37 different types of circRNA binding proteins, we developed an integrated deep learning network based on hierarchical network, called CRBPDL. It can effectively learn high-level feature representations. The performance of the model was verified through comparative experiments of different feature extraction algorithms, different deep learning models and classifier models. Moreover, the CRBPDL model was applied to 31 linear RNAs, and the effectiveness of our method was proved by comparison with the results of current excellent algorithms. It is expected that the CRBPDL model can effectively predict the binding site of circular RNA-RBP and provide reliable candidates for further biological experiments.

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.

iAIPs: Identifying Anti-Inflammatory Peptides Using Random Forest

Recently, several anti-inflammatory peptides (AIPs) have been found in the process of the inflammatory response, and these peptides have been used to treat some inflammatory and autoimmune diseases. Therefore, identifying AIPs accurately from a given amino acid sequences is critical for the discovery of novel and efficient anti-inflammatory peptide-based therapeutics and the acceleration of their application in therapy. In this paper, a random forest-based model called iAIPs for identifying AIPs is proposed. First, the original samples were encoded with three feature extraction methods, including g-gap dipeptide composition (GDC), dipeptide deviation from the expected mean (DDE), and amino acid composition (AAC). Second, the optimal feature subset is generated by a two-step feature selection method, in which the feature is ranked by the analysis of variance (ANOVA) method, and the optimal feature subset is generated by the incremental feature selection strategy. Finally, the optimal feature subset is inputted into the random forest classifier, and the identification model is constructed. Experiment results showed that iAIPs achieved an AUC value of 0.822 on an independent test dataset, which indicated that our proposed model has better performance than the existing methods. Furthermore, the extraction of features for peptide sequences provides the basis for evolutionary analysis. The study of peptide identification is helpful to understand the diversity of species and analyze the evolutionary history of species.

Gene-Based Testing of Interactions Using XGBoost in Genome-Wide Association Studies

Among the myriad of statistical methods that identify gene–gene interactions in the realm of qualitative genome-wide association studies, gene-based interactions are not only powerful statistically, but also they are interpretable biologically. However, they have limited statistical detection by making assumptions on the association between traits and single nucleotide polymorphisms. Thus, a gene-based method (GGInt-XGBoost) originated from XGBoost is proposed in this article. Assuming that log odds ratio of disease traits satisfies the additive relationship if the pair of genes had no interactions, the difference in error between the XGBoost model with and without additive constraint could indicate gene–gene interaction; we then used a permutation-based statistical test to assess this difference and to provide a statistical p-value to represent the significance of the interaction. Experimental results on both simulation and real data showed that our approach had superior performance than previous experiments to detect gene–gene interactions.

ReRF-Pred: predicting amyloidogenic regions of proteins based on their pseudo amino acid composition and tripeptide composition

BACKGROUND

Amyloids are insoluble fibrillar aggregates that are highly associated with complex human diseases, such as Alzheimer's disease, Parkinson's disease, and type II diabetes. Recently, many studies reported that some specific regions of amino acid sequences may be responsible for the amyloidosis of proteins. It has become very important for elucidating the mechanism of amyloids that identifying the amyloidogenic regions. Accordingly, several computational methods have been put forward to discover amyloidogenic regions. The majority of these methods predicted amyloidogenic regions based on the physicochemical properties of amino acids. In fact, position, order, and correlation of amino acids may also influence the amyloidosis of proteins, which should be also considered in detecting amyloidogenic regions.

RESULTS

To address this problem, we proposed a novel machine-learning approach for predicting amyloidogenic regions, called ReRF-Pred. Firstly, the pseudo amino acid composition (PseAAC) was exploited to characterize physicochemical properties and correlation of amino acids. Secondly, tripeptides composition (TPC) was employed to represent the order and position of amino acids. To improve the distinguishability of TPC, all possible tripeptides were analyzed by the binomial distribution method, and only those which have significantly different distribution between positive and negative samples remained. Finally, all samples were characterized by PseAAC and TPC of their amino acid sequence, and a random forest-based amyloidogenic regions predictor was trained on these samples. It was proved by validation experiments that the feature set consisted of PseAAC and TPC is the most distinguishable one for detecting amyloidosis. Meanwhile, random forest is superior to other concerned classifiers on almost all metrics. To validate the effectiveness of our model, ReRF-Pred is compared with a series of gold-standard methods on two datasets: Pep-251 and Reg33. The results suggested our method has the best overall performance and makes significant improvements in discovering amyloidogenic regions.

CONCLUSIONS

The advantages of our method are mainly attributed to that PseAAC and TPC can describe the differences between amyloids and other proteins successfully. The ReRF-Pred server can be accessed at http://106.12.83.135:8080/ReRF-Pred/.

iTTCA-RF: a random forest predictor for tumor T cell antigens

BACKGROUND

Cancer is one of the most serious diseases threatening human health. Cancer immunotherapy represents the most promising treatment strategy due to its high efficacy and selectivity and lower side effects compared with traditional treatment. The identification of tumor T cell antigens is one of the most important tasks for antitumor vaccines development and molecular function investigation. Although several machine learning predictors have been developed to identify tumor T cell antigen, more accurate tumor T cell antigen identification by existing methodology is still challenging.

METHODS

In this study, we used a non-redundant dataset of 592 tumor T cell antigens (positive samples) and 393 tumor T cell antigens (negative samples). Four types feature encoding methods have been studied to build an efficient predictor, including amino acid composition, global protein sequence descriptors and grouped amino acid and peptide composition. To improve the feature representation ability of the hybrid features, we further employed a two-step feature selection technique to search for the optimal feature subset. The final prediction model was constructed using random forest algorithm.

RESULTS

Finally, the top 263 informative features were selected to train the random forest classifier for detecting tumor T cell antigen peptides. iTTCA-RF provides satisfactory performance, with balanced accuracy, specificity and sensitivity values of 83.71%, 78.73% and 88.69% over tenfold cross-validation as well as 73.14%, 62.67% and 83.61% over independent tests, respectively. The online prediction server was freely accessible at http://lab.malab.cn/~acy/iTTCA .

CONCLUSIONS

We have proven that the proposed predictor iTTCA-RF is superior to the other latest models, and will hopefully become an effective and useful tool for identifying tumor T cell antigens presented in the context of major histocompatibility complex class I.

Recent development of machine learning methods in sumoylation sites prediction

Sumoylation of proteins is an important reversible post-translational modification of proteins and mediates a variety of cellular processes. Sumo-modified proteins can change their subcellular localization, activity and stability. In addition, it also plays an important role in various cellular processes such as transcriptional regulation and signal transduction. The abnormal sumoylation is involved in many diseases, including neurodegeneration and immune-related diseases, as well as the development of cancer. Therefore, identification of the sumoylation site (SUMO site) is fundamental to understanding their molecular mechanisms and regulatory roles. In contrast to labor-intensive and costly experimental approaches, computational prediction of sumoylation sites in silico also attracted much attention for its accuracy, convenience and speed. At present, many computational prediction models have been used to identify SUMO sites, but these contents have not been comprehensively summarized and reviewed. Therefore, the research progress of relevant models is summarized and discussed in this paper. We will briefly summarize the development of bioinformatics methods on sumoylation site prediction. We will mainly focus on the benchmark dataset construction, feature extraction, machine learning method, published results and online tools. We hope the review will provide more help for wet-experimental scholars.

A Survey for Predicting ATP Binding Residues of Proteins Using Machine Learning Methods

Protein-ligand interactions are necessary for majority protein functions. Adenosine-5'-triphosphate (ATP) is one such ligand that plays vital role as a coenzyme in providing energy for cellular activities, catalyzing biological reaction and signaling. Knowing ATP binding residues of proteins is helpful for annotation of protein function and drug design. However, due to the huge amounts of protein sequences influx into databases in the post-genome era, experimentally identifying ATP binding residues is cost-ineffective and time-consuming. To address this problem, computational methods have been developed to predict ATP binding residues. In this review, we briefly summarized the application of machine learning methods in detecting ATP binding residues of proteins. We expect this review will be helpful for further research.

rBPDL:Predicting RNA-Binding Proteins Using Deep Learning

RNA-binding protein (RBP) is a powerful and wide-ranging regulator that plays an important role in cell development, differentiation, metabolism, health and disease. The prediction of RBPs provides valuable guidance for biologists. Although experimental methods have made great progress in predicting RBP, they are time-consuming and not flexible. Therefore, we developed a network model, rBPDL, by combining a convolutional neural network and long short-term memory for multilabel classification of RBPs. Moreover, to achieve better prediction results, we used a voting algorithm for ensemble learning of the model. We compared rBPDL with state-of-the-art methods and found that rBPDL significantly improved identification performance for the RBP68 dataset, with a macro-Area Under Curve (AUC), micro-AUC, and weighted AUC of 0.936, 0.962, and 0.946, respectively. Furthermore, through AUC statistical analysis of the RBP domain, we analyzed the performance of rBPDL and found that the RBP identification performance in the same domain was similar. In addition, we analyzed the performance preferences and physicochemical properties of the binding protein amino acids and explored the characteristics that affect the binding by using the RBP86 dataset.

ProtRe-CN: Protein Remote Homology Detection by Combining Classification Methods and Network Methods via Learning to Rank

Protein remote homology detection is one of fundamental research tasks for downstream analysis (i.e., protein structure and function prediction). Many advanced methods are proposed from different views with complementary detection ability, such as the classification method, the network method, and the ranking method. A framework integrating these heterogeneous methods is urgently desired to reduce the false positive rate and predictive bias. We propose a novel ranking method called ProtRe-CN by fusing the classification methods and network methods via Learning to Rank. Experimental results on the benchmark dataset and the independent dataset show that ProtRe-CN outperforms other existing state-of-the-art predictors. ProtRe-CN improves the detective performance via correcting the false positives in the ranking list by combining the heterogeneous methods. The web server of ProtRe-CN can be accessed at http://bliulab.net/ProtRe-CN.

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.

Prediction of presynaptic and postsynaptic neurotoxins based on feature extraction

A neurotoxin is essentially a protein that mainly acts on the nervous system; it has a selective toxic effect on the central nervous system and neuromuscular nodes, can cause muscle paralysis and respiratory paralysis, and has strong lethality. According to their principle of action, neurotoxins are divided into presynaptic neurotoxins and postsynaptic neurotoxins. Correctly identifying presynaptic and postsynaptic nerve toxins provides important clues for future drug development and the discovery of drug targets. Therefore, a predictive model, Neu_LR, was constructed in this paper. The monoMonokGap method was used to extract the frequency characteristics of presynaptic and postsynaptic neurotoxin sequences and carry out feature selection, then, based on the important features obtained after dimensionality reduction, the prediction model Neu_LR was constructed using a logistic regression algorithm, and ten-fold cross-validation and independent test set validation were used. The final accuracy rates were 99.6078 and 94.1176%, respectively, which proved that the Neu_LR model had good predictive performance and robustness, and could meet the prediction requirements of presynaptic and postsynaptic neurotoxins. The data and source code of the model can be freely download from https://github.com/gyx123681/.

Current status and future prospects of drug-target interaction prediction

Drug-target interaction prediction is important for drug development and drug repurposing. Many computational methods have been proposed for drug-target interaction prediction due to their potential to the time and cost reduction. In this review, we introduce the molecular docking and machine learning-based methods, which have been widely applied to drug-target interaction prediction. Particularly, machine learning-based methods are divided into different types according to the data processing form and task type. For each type of method, we provide a specific description and propose some solutions to improve its capability. The knowledge of heterogeneous network and learning to rank are also summarized in this review. As far as we know, this is the first comprehensive review that summarizes the knowledge of heterogeneous network and learning to rank in the drug-target interaction prediction. Moreover, we propose three aspects that can be explored in depth for future research.

Application of Machine Learning for Drug-Target Interaction Prediction

Exploring drug–target interactions by biomedical experiments requires a lot of human, financial, and material resources. To save time and cost to meet the needs of the present generation, machine learning methods have been introduced into the prediction of drug–target interactions. The large amount of available drug and target data in existing databases, the evolving and innovative computer technologies, and the inherent characteristics of various types of machine learning have made machine learning techniques the mainstream method for drug–target interaction prediction research. In this review, details of the specific applications of machine learning in drug–target interaction prediction are summarized, the characteristics of each algorithm are analyzed, and the issues that need to be further addressed and explored for future research are discussed. The aim of this review is to provide a sound basis for the construction of high-performance models.

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.

Computational identification of N4-methylcytosine sites in the mouse genome with machine-learning method

N4-methylcytosine (4mC) is a kind of DNA modification which could regulate multiple biological processes. Correctly identifying 4mC sites in genomic sequences can provide precise knowledge about their genetic roles. This study aimed to develop an ensemble model to predict 4mC sites in the mouse genome. In the proposed model, DNA sequences were encoded by k-mer, enhanced nucleic acid composition and composition of k-spaced nucleic acid pairs. Subsequently, these features were optimized by using minimum redundancy maximum relevance (mRMR) with incremental feature selection (IFS) and five-fold cross-validation. The obtained optimal features were inputted into random forest classifier for discriminating 4mC from non-4mC sites in mouse. On the independent dataset, our model could yield the overall accuracy of 85.41%, which was approximately 3.8% -6.3% higher than the two existing models, i4mC-Mouse and 4mCpred-EL respectively. The data and source code of the model can be freely download from https://github.com/linDing-groups/model_4mc.

Application of Multilayer Network Models in Bioinformatics

Multilayer networks provide an efficient tool for studying complex systems, and with current, dramatic development of bioinformatics tools and accumulation of data, researchers have applied network concepts to all aspects of research problems in the field of biology. Addressing the combination of multilayer networks and bioinformatics, through summarizing the applications of multilayer network models in bioinformatics, this review classifies applications and presents a summary of the latest results. Among them, we classify the applications of multilayer networks according to the object of study. Furthermore, because of the systemic nature of biology, we classify the subjects into several hierarchical categories, such as cells, tissues, organs, and groups, according to the hierarchical nature of biological composition. On the basis of the complexity of biological systems, we selected brain research for a detailed explanation. We describe the application of multilayer networks and chronological networks in brain research to demonstrate the primary ideas associated with the application of multilayer networks in biological studies. Finally, we mention a quality assessment method focusing on multilayer and single-layer networks as an evaluation method emphasizing network studies.

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.

Prediction of lncRNA-Protein Interactions via the Multiple Information Integration

The long non-coding RNA (lncRNA)-protein interaction plays an important role in the post-transcriptional gene regulation, such as RNA splicing, translation, signaling, and the development of complex diseases. The related research on the prediction of lncRNA-protein interaction relationship is beneficial in the excavation and the discovery of the mechanism of lncRNA function and action occurrence, which are important. Traditional experimental methods for detecting lncRNA-protein interactions are expensive and time-consuming. Therefore, computational methods provide many effective strategies to deal with this problem. In recent years, most computational methods only use the information of the lncRNA-lncRNA or the protein-protein similarity and cannot fully capture all features to identify their interactions. In this paper, we propose a novel computational model for the lncRNA-protein prediction on the basis of machine learning methods. First, a feature method is proposed for representing the information of the network topological properties of lncRNA and protein interactions. The basic composition feature information and evolutionary information based on protein, the lncRNA sequence feature information, and the lncRNA expression profile information are extracted. Finally, the above feature information is fused, and the optimized feature vector is used with the recursive feature elimination algorithm. The optimized feature vectors are input to the support vector machine (SVM) model. Experimental results show that the proposed method has good effectiveness and accuracy in the lncRNA-protein interaction prediction.

Sequence representation approaches for sequence-based protein prediction tasks that use deep learning

Deep learning has been increasingly used in bioinformatics, especially in sequence-based protein prediction tasks, as large amounts of biological data are available and deep learning techniques have been developed rapidly in recent years. For sequence-based protein prediction tasks, the selection of a suitable model architecture is essential, whereas sequence data representation is a major factor in controlling model performance. Here, we summarized all the main approaches that are used to represent protein sequence data (amino acid sequence encoding or embedding), which include end-to-end embedding methods, non-contextual embedding methods and embedding methods that use transfer learning and others that are applied for some specific tasks (such as protein sequence embedding based on extracted features for protein structure predictions and graph convolutional network-based embedding for drug discovery tasks). We have also reviewed the architectures of various types of embedding models theoretically and the development of these types of sequence embedding approaches to facilitate researchers and users in selecting the model that best suits their requirements.

Identification of Methicillin-Resistant Staphylococcus Aureus From Methicillin-Sensitive Staphylococcus Aureus and Molecular Characterization in Quanzhou, China

To distinguish Methicillin-Resistant Staphylococcus aureus (MRSA) from Methicillin-Sensitive Staphylococcus aureus (MSSA) in the protein sequences level, test the susceptibility to antibiotic of all Staphylococcus aureus isolates from Quanzhou hospitals, define the virulence factor and molecular characteristics of the MRSA isolates. MRSA and MSSA Pfam protein sequences were used to extract feature vectors of 188D, n-gram and 400D. Weka software was applied to classify the two Staphylococcus aureus and performance effect was evaluated. Antibiotic susceptibility testing of the 81 Staphylococcus aureus was performed by the Mérieux Microbial Analysis Instrument. The 65 MRSA isolates were characterized by Panton-Valentine leukocidin (PVL), X polymorphic region of Protein A (spa), multilocus sequence typing test (MLST), staphylococcus chromosomal cassette mec (SCCmec) typing. After comparing the results of Weka six classifiers, the highest correctly classified rates were 91.94, 70.16, and 62.90% from 188D, n-gram and 400D, respectively. Antimicrobial susceptibility test of the 81 Staphylococcus aureus: Penicillin-resistant rate was 100%. No resistance to teicoplanin, linezolid, and vancomycin. The resistance rate of the MRSA isolates to clindamycin, erythromycin and tetracycline was higher than that of the MSSAs. Among the 65 MRSA isolates, the positive rate of PVL gene was 47.7% (31/65). Seventeen sequence types (STs) were identified among the 65 isolates, and ST59 was the most prevalent. SCCmec type III and IV were observed at 24.6 and 72.3%, respectively. Two isolates did not be typed. Twenty-one spa types were identified, spa t437 (34/65, 52.3%) was the most predominant type. MRSA major clone type of molecular typing was CC59-ST59-spa t437-IV (28/65, 43.1%). Overall, 188D feature vectors can be applied to successfully distinguish MRSA from MSSA. In Quanzhou, the detection rate of PVL virulence factor was high, suggesting a high pathogenic risk of MRSA infection. The cross-infection of CA-MRSA and HA-MRSA was presented, the molecular characteristics were increasingly blurred, HA-MRSA with typical CA-MRSA molecular characteristics has become an important cause of healthcare-related infections. CC59-ST59-spa t437-IV was the main clone type in Quanzhou, which was rare in other parts of mainland China.

A Method for Identifying Vesicle Transport Proteins Based on LibSVM and MRMD

With the development of computer technology, many machine learning algorithms have been applied to the field of biology, forming the discipline of bioinformatics. Protein function prediction is a classic research topic in this subject area. Though many scholars have made achievements in identifying protein by different algorithms, they often extract a large number of feature types and use very complex classification methods to obtain little improvement in the classification effect, and this process is very time-consuming. In this research, we attempt to utilize as few features as possible to classify vesicular transportation proteins and to simultaneously obtain a comparative satisfactory classification result. We adopt CTDC which is a submethod of the method of composition, transition, and distribution (CTD) to extract only 39 features from each sequence, and LibSVM is used as the classification method. We use the SMOTE method to deal with the problem of dataset imbalance. There are 11619 protein sequences in our dataset. We selected 4428 sequences to train our classification model and selected other 1832 sequences from our dataset to test the classification effect and finally achieved an accuracy of 71.77%. After dimension reduction by MRMD, the accuracy is 72.16%.

Identification and Classification of Enhancers Using Dimension Reduction Technique and Recurrent Neural Network

Enhancers are noncoding fragments in DNA sequences, which play an important role in gene transcription and translation. However, due to their high free scattering and positional variability, the identification and classification of enhancers have a higher level of complexity than those of coding genes. In order to solve this problem, many computer studies have been carried out in this field, but there are still some deficiencies in these prediction models. In this paper, we use various feature extraction strategies, dimension reduction technology, and a comprehensive application of machine model and recurrent neural network model to achieve an accurate prediction of enhancer identification and classification with the accuracy of was 76.7% and 84.9%, respectively. The model proposed in this paper is superior to the previous methods in performance index or feature dimension, which provides inspiration for the prediction of enhancers by computer technology in the future.

ProtFold-DFG: protein fold recognition by combining Directed Fusion Graph and PageRank algorithm

As one of the most important tasks in protein structure prediction, protein fold recognition has attracted more and more attention. In this regard, some computational predictors have been proposed with the development of machine learning and artificial intelligence techniques. However, these existing computational methods are still suffering from some disadvantages. In this regard, we propose a new network-based predictor called ProtFold-DFG for protein fold recognition. We propose the Directed Fusion Graph (DFG) to fuse the ranking lists generated by different methods, which employs the transitive closure to incorporate more relationships among proteins and uses the KL divergence to calculate the relationship between two proteins so as to improve its generalization ability. Finally, the PageRank algorithm is performed on the DFG to accurately recognize the protein folds by considering the global interactions among proteins in the DFG. Tested on a widely used and rigorous benchmark data set, LINDAHL dataset, experimental results show that the ProtFold-DFG outperforms the other 35 competing methods, indicating that ProtFold-DFG will be a useful method for protein fold recognition. The source code and data of ProtFold-DFG can be downloaded from http://bliulab.net/ProtFold-DFG/download.