On position-specific scoring matrix for protein function prediction

LGC-DBP: the method of DNA-binding protein identification based on PSSM and deep learning

The recognition of DNA Binding Proteins (DBPs) plays a crucial role in understanding biological functions such as replication, transcription, and repair. Although current sequence-based methods have shown some effectiveness, they often fail to fully utilize the potential of deep learning in capturing complex patterns. This study introduces a novel model, LGC-DBP, which integrates Long Short-Term Memory (LSTM), Gated Inception Convolution, and Improved Channel Attention mechanisms to enhance the prediction of DBPs. Initially, the model transforms protein sequences into Position Specific Scoring Matrices (PSSM), then processed through our deep learning framework. Within this framework, Gated Inception Convolution merges the concepts of gating units with the advantages of Graph Convolutional Network (GCN) and Dilated Convolution, significantly surpassing traditional convolution methods. The Improved Channel Attention mechanism substantially enhances the model's responsiveness and accuracy by shifting from a single input to three inputs and integrating three sigmoid functions along with an additional layer output. These innovative combinations have significantly improved model performance, enabling LGC-DBP to recognize and interpret the complex relationships within DBP features more accurately. The evaluation results show that LGC-DBP achieves an accuracy of 88.26% and a Matthews correlation coefficient of 0.701, both surpassing existing methods. These achievements demonstrate the model's strong capability in integrating and analyzing multi-dimensional data and mark a significant advancement over traditional methods by capturing deeper, nonlinear interactions within the data.

GNNGL-PPI: multi-category prediction of protein-protein interactions using graph neural networks based on global graphs and local subgraphs

Most proteins exert their functions by interacting with other proteins, making the identification of protein-protein interactions (PPI) crucial for understanding biological activities, pathological mechanisms, and clinical therapies. Developing effective and reliable computational methods for predicting PPI can significantly reduce the time-consuming and labor-intensive associated traditional biological experiments. However, accurately identifying the specific categories of protein-protein interactions and improving the prediction accuracy of the computational methods remain dual challenges. To tackle these challenges, we proposed a novel graph neural network method called GNNGL-PPI for multi-category prediction of PPI based on global graphs and local subgraphs. GNNGL-PPI consisted of two main components: using Graph Isomorphism Network (GIN) to extract global graph features from PPI network graph, and employing GIN As Kernel (GIN-AK) to extract local subgraph features from the subgraphs of protein vertices. Additionally, considering the imbalanced distribution of samples in each category within the benchmark datasets, we introduced an Asymmetric Loss (ASL) function to further enhance the predictive performance of the method. Through evaluations on six benchmark test sets formed by three different dataset partitioning algorithms (Random, BFS, DFS), GNNGL-PPI outperformed the state-of-the-art multi-category prediction methods of PPI, as measured by the comprehensive performance evaluation metric F1-measure. Furthermore, interpretability analysis confirmed the effectiveness of GNNGL-PPI as a reliable multi-category prediction method for predicting protein-protein interactions.

DeepAVP-TPPred: identification of antiviral peptides using transformed image-based localized descriptors and binary tree growth algorithm

MOTIVATION

Despite the extensive manufacturing of antiviral drugs and vaccination, viral infections continue to be a major human ailment. Antiviral peptides (AVPs) have emerged as potential candidates in the pursuit of novel antiviral drugs. These peptides show vigorous antiviral activity against a diverse range of viruses by targeting different phases of the viral life cycle. Therefore, the accurate prediction of AVPs is an essential yet challenging task. Lately, many machine learning-based approaches have developed for this purpose; however, their limited capabilities in terms of feature engineering, accuracy, and generalization make these methods restricted.

RESULTS

In the present study, we aim to develop an efficient machine learning-based approach for the identification of AVPs, referred to as DeepAVP-TPPred, to address the aforementioned problems. First, we extract two new transformed feature sets using our designed image-based feature extraction algorithms and integrate them with an evolutionary information-based feature. Next, these feature sets were optimized using a novel feature selection approach called binary tree growth Algorithm. Finally, the optimal feature space from the training dataset was fed to the deep neural network to build the final classification model. The proposed model DeepAVP-TPPred was tested using stringent 5-fold cross-validation and two independent dataset testing methods, which achieved the maximum performance and showed enhanced efficiency over existing predictors in terms of both accuracy and generalization capabilities.

AVAILABILITY AND IMPLEMENTATION

https://github.com/MateeullahKhan/DeepAVP-TPPred.

Prediction of drug-target binding affinity based on deep learning models

The prediction of drug-target binding affinity (DTA) plays an important role in drug discovery. Computerized virtual screening techniques have been used for DTA prediction, greatly reducing the time and economic costs of drug discovery. However, these techniques have not succeeded in reversing the low success rate of new drug development. In recent years, the continuous development of deep learning (DL) technology has brought new opportunities for drug discovery through the DTA prediction. This shift has moved the prediction of DTA from traditional machine learning methods to DL. The DL frameworks used for DTA prediction include convolutional neural networks (CNN), graph convolutional neural networks (GCN), and recurrent neural networks (RNN), and reinforcement learning (RL), among others. This review article summarizes the available literature on DTA prediction using DL models, including DTA quantification metrics and datasets, and DL algorithms used for DTA prediction (including input representation of models, neural network frameworks, valuation indicators, and model interpretability). In addition, the opportunities, challenges, and prospects of the application of DL frameworks for DTA prediction in the field of drug discovery are discussed.

DeepSS2GO: protein function prediction from secondary structure

Predicting protein function is crucial for understanding biological life processes, preventing diseases and developing new drug targets. In recent years, methods based on sequence, structure and biological networks for protein function annotation have been extensively researched. Although obtaining a protein in three-dimensional structure through experimental or computational methods enhances the accuracy of function prediction, the sheer volume of proteins sequenced by high-throughput technologies presents a significant challenge. To address this issue, we introduce a deep neural network model DeepSS2GO (Secondary Structure to Gene Ontology). It is a predictor incorporating secondary structure features along with primary sequence and homology information. The algorithm expertly combines the speed of sequence-based information with the accuracy of structure-based features while streamlining the redundant data in primary sequences and bypassing the time-consuming challenges of tertiary structure analysis. The results show that the prediction performance surpasses state-of-the-art algorithms. It has the ability to predict key functions by effectively utilizing secondary structure information, rather than broadly predicting general Gene Ontology terms. Additionally, DeepSS2GO predicts five times faster than advanced algorithms, making it highly applicable to massive sequencing data. The source code and trained models are available at https://github.com/orca233/DeepSS2GO.

iNGNN-DTI: prediction of drug-target interaction with interpretable nested graph neural network and pretrained molecule models

MOTIVATION

Drug-target interaction (DTI) prediction aims to identify interactions between drugs and protein targets. Deep learning can automatically learn discriminative features from drug and protein target representations for DTI prediction, but challenges remain, making it an open question. Existing approaches encode drugs and targets into features using deep learning models, but they often lack explanations for underlying interactions. Moreover, limited labeled DTIs in the chemical space can hinder model generalization.

RESULTS

We propose an interpretable nested graph neural network for DTI prediction (iNGNN-DTI) using pre-trained molecule and protein models. The analysis is conducted on graph data representing drugs and targets by using a specific type of nested graph neural network, in which the target graphs are created based on 3D structures using Alphafold2. This architecture is highly expressive in capturing substructures of the graph data. We use a cross-attention module to capture interaction information between the substructures of drugs and targets. To improve feature representations, we integrate features learned by models that are pre-trained on large unlabeled small molecule and protein datasets, respectively. We evaluate our model on three benchmark datasets, and it shows a consistent improvement on all baseline models in all datasets. We also run an experiment with previously unseen drugs or targets in the test set, and our model outperforms all of the baselines. Furthermore, the iNGNN-DTI can provide more insights into the interaction by visualizing the weights learned by the cross-attention module.

AVAILABILITY AND IMPLEMENTATION

The source code of the algorithm is available at https://github.com/syan1992/iNGNN-DTI.

Identification of DNA-protein binding residues through integration of Transformer encoder and Bi-directional Long Short-Term Memory

DNA-protein binding is crucial for the normal development and function of organisms. The significance of accurately identifying DNA-protein binding sites lies in its role in disease prevention and the development of innovative approaches to disease treatment. In the present study, we introduce a precise and robust identifier for DNA-protein binding residues. In the context of protein representation, we combine the evolutionary information of the protein, represented by its position-specific scoring matrix, with the spatial information of the protein's secondary structure, enriching the overall informational content. This approach initially employs a combination of Bi-directional Long Short-Term Memory and Transformer encoder to jointly extract the interdependencies among residues within the protein sequence. Subsequently, convolutional operations are applied to the resulting feature matrix to capture local features of the residues. Experimental results on the benchmark dataset demonstrate that our method exhibits a higher level of competitiveness when compared to contemporary classifiers. Specifically, our method achieved an MCC of 0.349, SP of 96.50%, SN of 44.03% and ACC of 94.59% on the PDNA-41 dataset.

Computational Protein Design - Where it goes?

Proteins have been playing a critical role in the regulation of diverse biological processes related to human life. With the increasing demand, functional proteins are sparse in this immense sequence space. Therefore, protein design has become an important task in various fields, including medicine, food, energy, materials, etc. Directed evolution has recently led to significant achievements. Molecular modification of proteins through directed evolution technology has significantly advanced the fields of enzyme engineering, metabolic engineering, medicine, and beyond. However, it is impossible to identify desirable sequences from a large number of synthetic sequences alone. As a result, computational methods, including data-driven machine learning and physics-based molecular modeling, have been introduced to protein engineering to produce more functional proteins. This review focuses on recent advances in computational protein design, highlighting the applicability of different approaches as well as their limitations.

Fusing Sequence and Structural Knowledge by Heterogeneous Models to Accurately and Interpretively Predict Drug-Target Affinity

Drug-target affinity (DTA) prediction is crucial for understanding molecular interactions and aiding drug discovery and development. While various computational methods have been proposed for DTA prediction, their predictive accuracy remains limited, failing to delve into the structural nuances of interactions. With increasingly accurate and accessible structure prediction of targets, we developed a novel deep learning model, named S2DTA, to accurately predict DTA by fusing sequence features of drug SMILES, targets, and pockets and their corresponding graph structural features using heterogeneous models based on graph and semantic networks. Experimental findings underscored that complex feature representations imparted negligible enhancements to the model's performance. However, the integration of heterogeneous models demonstrably bolstered predictive accuracy. In comparison to three state-of-the-art methodologies, such as DeepDTA, GraphDTA, and DeepDTAF, S2DTA's performance became more evident. It exhibited a 25.2% reduction in mean absolute error (MAE) and a 20.1% decrease in root mean square error (RMSE). Additionally, S2DTA showed some improvements in other crucial metrics, including Pearson Correlation Coefficient (PCC), Spearman, Concordance Index (CI), and R2, with these metrics experiencing increases of 19.6%, 17.5%, 8.1%, and 49.4%, respectively. Finally, we conducted an interpretability analysis on the effectiveness of S2DTA by bidirectional self-attention mechanism. The analysis results supported that S2DTA was an effective and accurate tool for predicting DTA.

In silico protein function prediction: the rise of machine learning-based approaches

Proteins function as integral actors in essential life processes, rendering the realm of protein research a fundamental domain that possesses the potential to propel advancements in pharmaceuticals and disease investigation. Within the context of protein research, an imperious demand arises to uncover protein functionalities and untangle intricate mechanistic underpinnings. Due to the exorbitant costs and limited throughput inherent in experimental investigations, computational models offer a promising alternative to accelerate protein function annotation. In recent years, protein pre-training models have exhibited noteworthy advancement across multiple prediction tasks. This advancement highlights a notable prospect for effectively tackling the intricate downstream task associated with protein function prediction. In this review, we elucidate the historical evolution and research paradigms of computational methods for predicting protein function. Subsequently, we summarize the progress in protein and molecule representation as well as feature extraction techniques. Furthermore, we assess the performance of machine learning-based algorithms across various objectives in protein function prediction, thereby offering a comprehensive perspective on the progress within this field.

Dual-Signal Feature Spaces Map Protein Subcellular Locations Based on Immunohistochemistry Image and Protein Sequence

Protein is one of the primary biochemical macromolecular regulators in the compartmental cellular structure, and the subcellular locations of proteins can therefore provide information on the function of subcellular structures and physiological environments. Recently, data-driven systems have been developed to predict the subcellular location of proteins based on protein sequence, immunohistochemistry (IHC) images, or immunofluorescence (IF) images. However, the research on the fusion of multiple protein signals has received little attention. In this study, we developed a dual-signal computational protocol by incorporating IHC images into protein sequences to learn protein subcellular localization. Three major steps can be summarized as follows in this protocol: first, a benchmark database that includes 281 proteins sorted out from 4722 proteins of the Human Protein Atlas (HPA) and Swiss-Prot database, which is involved in the endoplasmic reticulum (ER), Golgi apparatus, cytosol, and nucleoplasm; second, discriminative feature operators were first employed to quantitate protein image-sequence samples that include IHC images and protein sequence; finally, the feature subspace of different protein signals is absorbed to construct multiple sub-classifiers via dimensionality reduction and binary relevance (BR), and multiple confidence derived from multiple sub-classifiers is adopted to decide subcellular location by the centralized voting mechanism at the decision layer. The experimental results indicated that the dual-signal model embedded IHC images and protein sequences outperformed the single-signal models with accuracy, precision, and recall of 75.41%, 80.38%, and 74.38%, respectively. It is enlightening for further research on protein subcellular location prediction under multi-signal fusion of protein.

Identification of membrane protein types via deep residual hypergraph neural network

A membrane protein's functions are significantly associated with its type, so it is crucial to identify the types of membrane proteins. Conventional computational methods for identifying the species of membrane proteins tend to ignore two issues: High-order correlation among membrane proteins and the scenarios of multi-modal representations of membrane proteins, which leads to information loss. To tackle those two issues, we proposed a deep residual hypergraph neural network (DRHGNN), which enhances the hypergraph neural network (HGNN) with initial residual and identity mapping in this paper. We carried out extensive experiments on four benchmark datasets of membrane proteins. In the meantime, we compared the DRHGNN with recently developed advanced methods. Experimental results showed the better performance of DRHGNN on the membrane protein classification task on four datasets. Experiments also showed that DRHGNN can handle the over-smoothing issue with the increase of the number of model layers compared with HGNN. The code is available at https://github.com/yunfighting/Identification-of-Membrane-Protein-Types-via-deep-residual-hypergraph-neural-network.

Intrinsic disorder may drive the interaction of PROS1 and MERTK in uveal melanoma

BACKGROUND

Class 2 uveal melanomas are associated with the inactivation of the BRCA1 ((breast cancer type 1 susceptibility protein)-associated protein 1 (BAP1)) gene. Inactivation of BAP1 promotes the upregulation of vitamin K-dependent protein S (PROS1), which interacts with the tyrosine-protein kinase Mer (MERTK) receptor on M2 macrophages to induce an immunosuppressive environment.

METHODS

We simulated the interaction of PROS1 with MERTK with ColabFold. We evaluated PROS1 and MERTK for the presence of intrinsically disordered protein regions (IDPRs) and disorder-to-order (DOT) regions to understand their protein-protein interaction (PPI). We first evaluated the structure of each protein with AlphaFold. We then analyzed specific sequence-based features of the PROS1 and MERTK with a suite of bioinformatics tools.

RESULTS

With high-resolution, moderate confidence, we successfully modeled the interaction between PROS1 and MERTK (predicted local distance difference test score (pDLLT) = 70.68). Our structural analysis qualitatively demonstrated IDPRs (i.e., spaghetti-like entities) in PROS1 and MERK. PROS1 was 23.37 % disordered, and MERTK was 23.09 % disordered, classifying them as moderately disordered and flexible proteins. PROS1 was significantly enriched in cysteine, the most order-promoting residue (p-value <0.05). Our IUPred analysis demonstrated that there are two disorder-to-order transition (DOT) regions in PROS1. MERTK was significantly enriched in proline, the most disorder-promoting residue (p-value <0.05), but did not contain DOT regions. Our STRING analysis demonstrated that the PPI network between PROS1 and MERTK is more complex than their assumed one-to-one binding (p-value <2.0 × 10-6).

CONCLUSION

Our findings present a novel prediction for the interaction between PROS1 and MERTK. Our findings show that PROS1 and MERTK contain elements of intrinsic disorder. PROS1 has two DOT regions that are attractive immunotherapy targets. We recommend that IDPRs and DOT regions found in PROS1 and MERTK should be considered when developing immunotherapies targeting this PPI.

PredLLPS_PSSM: a novel predictor for liquid-liquid protein separation identification based on evolutionary information and a deep neural network

The formation of biomolecular condensates by liquid-liquid phase separation (LLPS) has become a universal mechanism for spatiotemporal coordination of biological activities in cells and has been widely observed to directly regulate the key cellular processes involved in cancer cell pathology. However, the complexity of protein sequences and the diversity of conformations are inherently disordered, which poses great challenges for LLPS protein calculations and experimental research. Herein, we proposed a novel predictor named PredLLPS_PSSM for LLPS protein identification based only on sequence evolution information. Because finding real and reliable samples is the cornerstone of building predictors, we collected anew and collated the LLPS proteins from the latest versions of three databases. By comparing the performance of the position-specific score matrix (PSSM) and word embedding, PredLLPS_PSSM combined PSSM-based information and two deep learning frameworks. Independent tests using three existing independent test datasets and two newly constructed independent test datasets demonstrated the superiority of PredLLPS_PSSM compared with state-of-the-art methods. Furthermore, we tested PredLLPS_PSSM on nine experimentally identified LLPS proteins from three insects that were not included in any of the databases. In addition, the powerful Shapley Additive exPlanation algorithm and heatmap were applied to find the most critical amino acids relevant to LLPS.

DNA protein binding recognition based on lifelong learning

In recent years, research in the field of bioinformatics has focused on predicting the raw sequences of proteins, and some scholars consider DNA-binding protein prediction as a classification task. Many statistical and machine learning-based methods have been widely used in DNA-binding proteins research. The aforementioned methods are indeed more efficient than those based on manual classification, but there is still room for improvement in terms of prediction accuracy and speed. In this study, researchers used Average Blocks, Discrete Cosine Transform, Discrete Wavelet Transform, Global encoding, Normalized Moreau-Broto Autocorrelation and Pseudo position-specific scoring matrix to extract evolutionary features. A dynamic deep network based on lifelong learning architecture was then proposed in order to fuse six features and thus allow for more efficient classification of DNA-binding proteins. The multi-feature fusion allows for a more accurate description of the desired protein information than single features. This model offers a fresh perspective on the dichotomous classification problem in bioinformatics and broadens the application field of lifelong learning. The researchers ran trials on three datasets and contrasted them with other classification techniques to show the model's effectiveness in this study. The findings demonstrated that the model used in this research was superior to other approaches in terms of single-sample specificity (81.0%, 83.0%) and single-sample sensitivity (82.4%, 90.7%), and achieves high accuracy on the benchmark dataset (88.4%, 80.0%, and 76.6%).

Identification of DNA-binding protein based multiple kernel model

DNA-binding proteins (DBPs) play a critical role in the development of drugs for treating genetic diseases and in DNA biology research. It is essential for predicting DNA-binding proteins more accurately and efficiently. In this paper, a Laplacian Local Kernel Alignment-based Restricted Kernel Machine (LapLKA-RKM) is proposed to predict DBPs. In detail, we first extract features from the protein sequence using six methods. Second, the Radial Basis Function (RBF) kernel function is utilized to construct pre-defined kernel metrics. Then, these metrics are combined linearly by weights calculated by LapLKA. Finally, the fused kernel is input to RKM for training and prediction. Independent tests and leave-one-out cross-validation were used to validate the performance of our method on a small dataset and two large datasets. Importantly, we built an online platform to represent our model, which is now freely accessible via http://8.130.69.121:8082/.

Disto-TRP: An approach for identifying transient receptor potential (TRP) channels using structural information generated by AlphaFold

The ability to predict 3D protein structures computationally has significantly advanced biological research. The AlphaFold protein structure database, developed by DeepMind, has provided a wealth of predicted protein structures and has the potential to bring about revolutionary changes in the field of life sciences. However, directly determining the function of proteins from their structures remains a challenging task. The Distogram from AlphaFold is used in this study as a novel feature set to identify transient receptor potential (TRP) channels. Distograms feature vectors and pre-trained language model (BERT) features were combined to improve prediction performance for transient receptor potential (TRP) channels. The method proposed in this study demonstrated promising performance on many evaluation metrics. For five-fold cross-validation, the method achieved a Sensitivity (SN) of 87.00%, Specificity (SP) of 93.61%, Accuracy (ACC) of 93.39%, and a Matthews correlation coefficient (MCC) of 0.52. Additionally, on an independent dataset, the method obtained 100.00% SN, 95.54% SP, 95.73% ACC, and an MCC of 0.69. The results demonstrate the potential for using structural information to predict protein function. In the future, it is hoped that such structural information will be incorporated into artificial intelligence networks to explore more useful and valuable functional information in the biological field.

Identification of DNA-binding proteins by Kernel Sparse Representation via L2,1-matrix norm

An understanding of DNA-binding proteins is helpful in exploring the role that proteins play in cell biology. Furthermore, the prediction of DNA-binding proteins is essential for the chemical modification and structural composition of DNA, and is of great importance in protein functional analysis and drug design. In recent years, DNA-binding protein prediction has typically used machine learning-based methods. The prediction accuracy of various classifiers has improved considerably, but researchers continue to spend time and effort on improving prediction performance. In this paper, we combine protein sequence evolutionary information with a classification method based on kernel sparse representation for the prediction of DNA-binding proteins, and based on the field of machine learning, a model for the identification of DNA-binding proteins by sequence information was finally proposed. Based on the confirmation of the final experimental results, we achieved good prediction accuracy on both the PDB1075 and PDB186 datasets. Our training result for cross-validation on PDB1075 was 81.37%, and our independent test result on PDB186 was 83.9%, both of which outperformed the other methods to some extent. Therefore, the proposed method in this paper is proven to be effective and feasible for predicting DNA-binding proteins.

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

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

Multi-View Kernel Sparse Representation for Identification of Membrane Protein Types

Membrane proteins are the main undertaker of biomembrane functions and play a vital role in many biological activities of organisms. Prediction of membrane protein types has a great help in determining the function of proteins and understanding the interactions of membrane proteins. However, the biochemical experiment is expensive and not suitable for the large-scale identification of membrane protein types. Therefore, computational methods were used to improve the efficiency of biological experiments. Most existing computational methods only use a single feature of protein, or use multiple features but do not integrate these well. In our study, the protein sequence is described via three different views (features), including amino acid composition, evolutionary information and physicochemical properties of amino acids. To exploit information among all views (features), we introduce a coupling strategy for Kernel Sparse Representation based Classification (KSRC) and construct a new model called Multi-view KSRC (MvKSRC). We implement our method on 4 benchmark data sets of membrane proteins. The comparison results indicate that our method is much superior to all existing methods.

HyperVR: a hybrid deep ensemble learning approach for simultaneously predicting virulence factors and antibiotic resistance genes

Infectious diseases emerge unprecedentedly, posing serious challenges to public health and the global economy. Virulence factors (VFs) enable pathogens to adhere, reproduce and cause damage to host cells, and antibiotic resistance genes (ARGs) allow pathogens to evade otherwise curable treatments. Simultaneous identification of VFs and ARGs can save pathogen surveillance time, especially in situ epidemic pathogen detection. However, most tools can only predict either VFs or ARGs. Few tools that predict VFs and ARGs simultaneously usually have high false-negative rates, are sensitive to the cutoff thresholds and can only identify conserved genes. For better simultaneous prediction of VFs and ARGs, we propose a hybrid deep ensemble learning approach called HyperVR. By considering both best hit scores and statistical gene sequence patterns, HyperVR combines classical machine learning and deep learning to simultaneously and accurately predict VFs, ARGs and negative genes (neither VFs nor ARGs). For the prediction of individual VFs and ARGs, in silico spike-in experiment (the VFs and ARGs in real metagenomic data), and pseudo-VFs and -ARGs (gene fragments), HyperVR outperforms the current state-of-the-art prediction tools. HyperVR uses only gene sequence information without strict cutoff thresholds, hence making prediction straightforward and reliable.

A review of visualisations of protein fold networks and their relationship with sequence and function

Proteins form arguably the most significant link between genotype and phenotype. Understanding the relationship between protein sequence and structure, and applying this knowledge to predict function, is difficult. One way to investigate these relationships is by considering the space of protein folds and how one might move from fold to fold through similarity, or potential evolutionary relationships. The many individual characterisations of fold space presented in the literature can tell us a lot about how well the current Protein Data Bank represents protein fold space, how convergence and divergence may affect protein evolution, how proteins affect the whole of which they are part, and how proteins themselves function. A synthesis of these different approaches and viewpoints seems the most likely way to further our knowledge of protein structure evolution and thus, facilitate improved protein structure design and prediction.

Computational Methods and Deep Learning for Elucidating Protein Interaction Networks

Protein interactions play a critical role in all biological processes, but experimental identification of protein interactions is a time- and resource-intensive process. The advances in next-generation sequencing and multi-omics technologies have greatly benefited large-scale predictions of protein interactions using machine learning methods. A wide range of tools have been developed to predict protein-protein, protein-nucleic acid, and protein-drug interactions. Here, we discuss the applications, methods, and challenges faced when employing the various prediction methods. We also briefly describe ways to overcome the challenges and prospective future developments in the field of protein interaction biology.

Drug-target binding affinity prediction method based on a deep graph neural network

The development of new drugs is a long and costly process, Computer-aided drug design reduces development costs while computationally shortening the new drug development cycle, in which DTA (Drug-Target binding Affinity) prediction is a key step to screen out potential drugs. With the development of deep learning, various types of deep learning models have achieved notable performance in a wide range of fields. Most current related studies focus on extracting the sequence features of molecules while ignoring the valuable structural information; they employ sequence data that represent only the elemental composition of molecules without considering the molecular structure maps that contain structural information. In this paper, we use graph neural networks to predict DTA based on corresponding graph data of drugs and proteins, and we achieve competitive performance on two benchmark datasets, Davis and KIBA. In particular, an MSE of 0.227 and CI of 0.895 were obtained on Davis, and an MSE of 0.127 and CI of 0.903 were obtained on KIBA.

Accurate Prediction of Human Essential Proteins Using Ensemble Deep Learning

Essential proteins are considered the foundation of life as they are indispensable for the survival of living organisms. Computational methods for essential protein discovery provide a fast way to identify essential proteins. But most of them heavily rely on various biological information, especially protein-protein interaction networks, which limits their practical applications. With the rapid development of high-throughput sequencing technology, sequencing data has become the most accessible biological data. However, using only protein sequence information to predict essential proteins has limited accuracy. In this paper, we propose EP-EDL, an ensemble deep learning model using only protein sequence information to predict human essential proteins. EP-EDL integrates multiple classifiers to alleviate the class imbalance problem and to improve prediction accuracy and robustness. In each base classifier, we employ multi-scale text convolutional neural networks to extract useful features from protein sequence feature matrices with evolutionary information. Our computational results show that EP-EDL outperforms the state-of-the-art sequence-based methods. Furthermore, EP-EDL provides a more practical and flexible way for biologists to accurately predict essential proteins. The source code and datasets can be downloaded from https://github.com/CSUBioGroup/EP-EDL.

TripletProt: Deep Representation Learning of Proteins Based On Siamese Networks

Pretrained representations have recently gained attention in various machine learning applications. Nonetheless, the high computational costs associated with training these models have motivated alternative approaches for representation learning. Herein we introduce TripletProt, a new approach for protein representation learning based on the Siamese neural networks. Representation learning of biological entities which capture essential features can alleviate many of the challenges associated with supervised learning in bioinformatics. The most important distinction of our proposed method is relying on the protein-protein interaction (PPI) network. The computational cost of the generated representations for any potential application is significantly lower than comparable methods since the length of the representations is significantly smaller than that in other approaches. TripletProt offers great potentials for the protein informatics tasks and can be widely applied to similar tasks. We evaluate TripletProt comprehensively in protein functional annotation tasks including sub-cellular localization (14 categories) and gene ontology prediction (more than 2000 classes), which are both challenging multi-class, multi-label classification machine learning problems. We compare the performance of TripletProt with the state-of-the-art approaches including a recurrent language model-based approach (i.e., UniRep), as well as a protein-protein interaction (PPI) network and sequence-based method (i.e., DeepGO). Our TripletProt showed an overall improvement of F1 score in the above mentioned comprehensive functional annotation tasks, solely relying on the PPI network. Availability: The source code and datasets are available at https://github.com/EsmaeilNourani/TripletProt.

Evaluation of deep learning techniques for identification of sarcoma-causing carcinogenic mutations

The abnormal growth of human healthy cells is called cancer. One of the major types of cancer is sarcoma, mostly found in human bones and soft tissue cells. It commonly occurs in children. According to a survey of the United States of America, there are more than 17,000 sarcoma patients registered each year which is 15% of all cancer cases. Recognition of cancer at its early stage saves many lives. The proposed study developed a framework for the early detection of human sarcoma cancer using deep learning Recurrent Neural Network (RNN) algorithms. The DNA of a human cell is made up of 25,000 to 30,000 genes. Each gene is represented by sequences of nucleotides. The nucleotides in a sequence of a driver gene can change which is termed as mutations. Some mutations can cause cancer. There are seven types of a gene whose mutation causes sarcoma cancer. The study uses the dataset which has been taken from more than 134 samples and includes 141 mutations in 8 driver genes. On these gene sequences RNN algorithms Long and Short-Term Memory (LSTM), Gated Recurrent Units and Bi-directional LSTM (Bi-LSTM) are used for training. Rigorous testing techniques such as Self-consistency testing, independent set testing, 10-fold cross-validation test are applied for the validation of results. These validation techniques yield several metrics such as Area Under the Curve (AUC), sensitivity, specificity, Mathew's correlation coefficient, loss, and accuracy. The proposed algorithm exhibits an accuracy of 99.6% with an AUC value of 1.00.

Identifying SNARE Proteins Using an Alignment-Free Method Based on Multiscan Convolutional Neural Network and PSSM Profiles

Background: SNARE proteins play a vital role in membrane fusion and cellular physiology and pathological processes. Many potential therapeutics for mental diseases or even cancer based on SNAREs are also developed. Therefore, there is a dire need to predict the SNAREs for further manipulation of these essential proteins, which demands new and efficient approaches. Methods: Some computational frameworks were proposed to tackle the hurdles of biological methods, which take plenty of time and budget to conduct the identification of SNAREs. However, the performances of existing frameworks were insufficiently satisfied, as they failed to retain the SNARE sequence order and capture the mass hidden features from SNAREs. This paper proposed a novel model constructed on the multiscan convolutional neural network (CNN) and position-specific scoring matrix (PSSM) profiles to address these limitations. We employed and trained our model on the benchmark dataset with fivefold cross-validation and two different independent datasets. Results: Overall, the multiscan CNN was cross-validated on the training set and excelled in the SNARE classification reaching 0.963 in AUC and 0.955 in AUPRC. On top of that, with the sensitivity, specificity, accuracy, and MCC of 0.842, 0.968, 0.955, and 0.767, respectively, our proposed framework outperformed previous models in the SNARE recognition task. Conclusions: It is truly believed that our model can contribute to the discrimination of SNARE proteins and general proteins.

Identifying Transcription Factors That Prefer Binding to Methylated DNA Using Reduced G-Gap Dipeptide Composition

Transcription factors (TFs) play an important role in gene expression and regulation of 3D genome conformation. TFs have ability to bind to specific DNA fragments called enhancers and promoters. Some TFs bind to promoter DNA fragments which are near the transcription initiation site and form complexes that allow polymerase enzymes to bind to initiate transcription. Previous studies showed that methylated DNAs had ability to inhibit and prevent TFs from binding to DNA fragments. However, recent studies have found that there were TFs that could bind to methylated DNA fragments. The identification of these TFs is an important steppingstone to a better understanding of cellular gene expression mechanisms. However, as experimental methods are often time-consuming and labor-intensive, developing computational methods is essential. In this study, we propose two machine learning methods for two problems: (1) identifying TFs and (2) identifying TFs that prefer binding to methylated DNA targets (TFPMs). For the TF identification problem, the proposed method uses the position-specific scoring matrix for data representation and a deep convolutional neural network for modeling. This method achieved 90.56% sensitivity, 83.96% specificity, and an area under the receiver operating characteristic curve (AUC) of 0.9596 on an independent test set. For the TFPM identification problem, we propose to use the reduced g-gap dipeptide composition for data representation and the support vector machine algorithm for modeling. This method achieved 82.61% sensitivity, 64.86% specificity, and an AUC of 0.8486 on another independent test set. These results are higher than those of other studies on the same problems.

DeepCPPred: A Deep Learning Framework for the Discrimination of Cell-Penetrating Peptides and Their Uptake Efficiencies

Cell-penetrating peptides (CPPs) are special peptides capable of carrying a variety of bioactive molecules, such as genetic materials, short interfering RNAs and nanoparticles, into cells. Recently, research on CPP has gained substantial interest from researchers, and the biological mechanisms of CPPS have been assessed in the context of safe drug delivery agents and therapeutic applications. Correct identification and synthesis of CPPs using traditional biochemical methods is an extremely slow, expensive and laborious task particularly due to the large volume of unannotated peptide sequences accumulating in the World Bank repository. Hence, a powerful bioinformatics predictor that rapidly identifies CPPs with a high recognition rate is urgently needed. To date, numerous computational methods have been developed for CPP prediction. However, the available machine-learning (ML) tools are unable to distinguish both the CPPs and their uptake efficiencies. This study aimed to develop a two-layer deep learning framework named DeepCPPred to identify both CPPs in the first phase and peptide uptake efficiency in the second phase. The DeepCPPred predictor first uses four types of descriptors that cover evolutionary, energy estimation, reduced sequence and amino-acid contact information. Then, the extracted features are optimized through the elastic net algorithm and fed into a cascade deep forest algorithm to build the final CPP model. The proposed method achieved 99.45 percent overall accuracy with the CPP924 benchmark dataset in the first layer and 95.43 percent accuracy in the second layer with the CPPSite3 dataset using a 5-fold cross-validation test. Thus, our proposed bioinformatics tool surpassed all the existing state-of-the-art sequence-based CPP approaches.

An Ensemble Tf-Idf Based Approach to Protein Function Prediction via Sequence Segmentation

This paper explores the use of variants of tf-idf-based descriptors, namely length-normalized-tf-idf and log-normalized-tf-idf, combined with a segmentation technique, for efficient modeling of variable-length protein sequences. The proposed solution, ProtVecGen-Ensemble, is an ensemble of three models trained on differently segmented datasets constructed from an input dataset containing complete protein sequences. Evaluations using biological process (BP) and molecular function (MF) datasets demonstrate that the proposed feature set is not only superior to its contemporaries but also produces more consistent results with respect to variation in sequence lengths. Improvements of +6.07% (BP) and +7.56% (MF) over state-of-the-art tf-idf-based MLDA feature set were obtained. The best results were achieved when ProtVecGen-Ensemble was combined with ProtVecGen-Plus - the state-of-the-art method for protein function prediction - resulting in improvements of +8.90% (BP) and +11.28% (MF) over MLDA and +1.49% (BP) and +2.07% (MF) over ProtVecGen-Plus+MLDA. To capture the performance consistency with respect to sequence lengths, we have defined a variance-based metric, with lower values indicating better performance. On this metric, the proposed ProtVecGen-Ensemble+ProtVecGen-Plus framework resulted in reductions of 56.85 percent (BP) and 56.08 percent (MF) over MLDA and 10.37 percent (BP) and 26.48 percent (MF) over ProtVecGenPlus+MLDA.

IDRBP-PPCT: Identifying Nucleic Acid-Binding Proteins Based on Position-Specific Score Matrix and Position-Specific Frequency Matrix Cross Transformation

DNA-binding proteins (DBPs) and RNA-binding proteins (RBPs) are two important nucleic acid-binding proteins (NABPs), which play important roles in biological processes such as replication, translation and transcription of genetic material. Some proteins (DRBPs) bind to both DNA and RNA, also play a key role in gene expression. Identification of DBPs, RBPs and DRBPs is important to study protein-nucleic acid interactions. Computational methods are increasingly being proposed to automatically identify DNA- or RNA-binding proteins based only on protein sequences. One challenge is to design an effective protein representation method to convert protein sequences into fixed-dimension feature vectors. In this study, we proposed a novel protein representation method called Position-Specific Scoring Matrix (PSSM) and Position-Specific Frequency Matrix (PSFM) Cross Transformation (PPCT) to represent protein sequences. This method contains the evolutionary information in PSSM and PSFM, and their correlations. A new computational predictor called IDRBP-PPCT was proposed by combining PPCT and the two-layer framework based on the random forest algorithm to identify DBPs, RBPs and DRBPs. The experimental results on the independent dataset and the tomato genome proved the effectiveness of the proposed method. A user-friendly web-server of IDRBP-PPCT was constructed, which is freely available at http://bliulab.net/IDRBP-PPCT.

Comparative Analysis on Alignment-Based and Pretrained Feature Representations for the Identification of DNA-Binding Proteins

The interaction between DNA and protein is vital for the development of a living body. Previous numerous studies on in silico identification of DNA-binding proteins (DBPs) usually include features extracted from the alignment-based (pseudo) position-specific scoring matrix (PSSM), leading to limited application due to its time-consuming generation. Few researchers have paid attention to the application of pretrained language models at the scale of evolution to the identification of DBPs. To this end, we present comprehensive insights into a comparison study on alignment-based PSSM and pretrained evolutionary scale modeling (ESM) representations in the field of DBP classification. The comparison is conducted by extracting information from PSSM and ESM representations using four unified averaging operations and by performing various feature selection (FS) methods. Experimental results demonstrate that the pretrained ESM representation outperforms the PSSM-derived features in a fair comparison perspective. The pretrained feature presentation deserves wide application to the area of in silico DBP identification as well as other function annotation issues. Finally, it is also confirmed that an ensemble scheme by aggregating various trained FS models can significantly improve the classification performance of DBPs.

Identifying Membrane Protein Types Based on Lifelong Learning With Dynamically Scalable Networks

Membrane proteins are an essential part of the body's ability to maintain normal life activities. Further research into membrane proteins, which are present in all aspects of life science research, will help to advance the development of cells and drugs. The current methods for predicting proteins are usually based on machine learning, but further improvements in prediction effectiveness and accuracy are needed. In this paper, we propose a dynamic deep network architecture based on lifelong learning in order to use computers to classify membrane proteins more effectively. The model extends the application area of lifelong learning and provides new ideas for multiple classification problems in bioinformatics. To demonstrate the performance of our model, we conducted experiments on top of two datasets and compared them with other classification methods. The results show that our model achieves high accuracy (95.3 and 93.5%) on benchmark datasets and is more effective compared to other methods.

PSSMCOOL: A Comprehensive R Package for Generating Evolutionary-based Descriptors of Protein Sequences from PSSM Profiles

Position-specific scoring matrix (PSSM), also called profile, is broadly used for representing the evolutionary history of a given protein sequence. Several investigations reported that the PSSM-based feature descriptors can improve the prediction of various protein attributes such as interaction, function, subcellular localization, secondary structure, disorder regions, and accessible surface area. While plenty of algorithms have been suggested for extracting evolutionary features from PSSM in recent years, there is not any integrated standalone tool for providing these descriptors. Here, we introduce PSSMCOOL, a flexible comprehensive R package that generates 38 PSSM-based feature vectors. To our best knowledge, PSSMCOOL is the first PSSM-based feature extraction tool implemented in R. With the growing demand for exploiting machine-learning algorithms in computational biology, this package would be a practical tool for machine-learning predictions.

Development of peptide vaccine candidate using highly antigenic PE-PGRS family proteins to stimulate the host immune response against Mycobacterium tuberculosis H37Rv: an immuno-informatics approach

Tuberculosis (TB) is a fast spreading; transmissible disease caused by the Mycobacterium tuberculosis (M. tuberculosis). M. tuberculosis has a high death rate in its endemic regions due to a lack of appropriate treatment and preventative measures. We have used a vaccinomics strategy to create an effective multi-epitope vaccine against M. tuberculosis. The antigenic proteins with the highest antigenicity were utilised to predict cytotoxic T-lymphocyte (CTL), helper T-lymphocyte (HTL), and linear B-lymphocyte (LBL) epitopes. CTL and HTL epitopes were covered in 99.97% of the population. Seven epitopes each of CTL, HTL, and LBL were ultimately selected and utilised to develop a multi-epitope vaccine. A vaccine design was developed by combining these epitopes with suitable linkers and LprG adjuvant. The vaccine chimera was revealed to be highly immunogenic, non-allergenic, and non-toxic. To ensure a better expression within the Escherichia coli K12 (E. coli K12) host system, codon adaptation and in silico cloning were accomplished. Following that, various validation studies were conducted, including molecular docking, molecular dynamics simulation, and immunological simulation, all of which indicated that the designed vaccine would be stable in the biological environment and effective against M. tuberculosis infection. The immune simulation revealed higher levels of T-cell and B-cell activity, which corresponded to the actual immune response. Exposure simulations were repeated several times, resulting in increased clonal selection and faster antigen clearance. These results suggest that, if proposed vaccine chimera would test both in-vitro and in-vivo, it could be a viable treatment and preventive strategy for TB.Communicated by Ramaswamy H. Sarma.

PWM2Vec: An Efficient Embedding Approach for Viral Host Specification from Coronavirus Spike Sequences

Simple Summary

The family of coronaviruses comprises a diverse set of strains and variants which cause diseases from the common cold to COVID-19. Moreover, they infect a wide array of hosts from bats, camels, birds, to humans. Studying coronaviruses through the lens of host specificity provides a unique perspective to understanding the evolution, diversity and dynamics of this family. In particular, this can reveal groups of different hosts infected by similar strains, giving clues on strains which were more likely to have evolved to jump from one host to another. In this work, we frame host specificity as a classification task, in designing a very compact numerical representation of the spike sequences of different coronaviruses. Based on this numerical representation, classification methods are able to detect the target host with high accuracy. Such an approach can used to efficiently scale to large volumes of sequences, in order to unveil trends in the host specificity of different coronavirus strains.

Abstract

The study of host specificity has important connections to the question about the origin of SARS-CoV-2 in humans which led to the COVID-19 pandemic—an important open question. There are speculations that bats are a possible origin. Likewise, there are many closely related (corona)viruses, such as SARS, which was found to be transmitted through civets. The study of the different hosts which can be potential carriers and transmitters of deadly viruses to humans is crucial to understanding, mitigating, and preventing current and future pandemics. In coronaviruses, the surface (S) protein, or spike protein, is important in determining host specificity, since it is the point of contact between the virus and the host cell membrane. In this paper, we classify the hosts of over five thousand coronaviruses from their spike protein sequences, segregating them into clusters of distinct hosts among birds, bats, camels, swine, humans, and weasels, to name a few. We propose a feature embedding based on the well-known position weight matrix (PWM), which we call PWM2Vec, and we use it to generate feature vectors from the spike protein sequences of these coronaviruses. While our embedding is inspired by the success of PWMs in biological applications, such as determining protein function and identifying transcription factor binding sites, we are the first (to the best of our knowledge) to use PWMs from viral sequences to generate fixed-length feature vector representations, and use them in the context of host classification. The results on real world data show that when using PWM2Vec, machine learning classifiers are able to perform comparably to the baseline models in terms of predictive performance and runtime—in some cases, the performance is better. We also measure the importance of different amino acids using information gain to show the amino acids which are important for predicting the host of a given coronavirus. Finally, we perform some statistical analyses on these results to show that our embedding is more compact than the embeddings of the baseline models.

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.

Machine and Deep Learning for Prediction of Subcellular Localization

Protein subcellular localization prediction (PSLP), which plays an important role in the field of computational biology, identifies the position and function of proteins in cells without expensive cost and laborious effort. In the past few decades, various methods with different algorithms have been proposed in solving the problem of subcellular localization prediction; machine learning and deep learning constitute a large portion among those proposed methods. In order to provide an overview about those methods, the first part of this article will be a brief review of several state-of-the-art machine learning methods on subcellular localization prediction; then the materials used by subcellular localization prediction is described and a simple prediction method, that takes protein sequences as input and utilizes a convolutional neural network as the classifier, is introduced. At last, a list of notes is provided to indicate the major problems that may occur with this method.

Identification of DNA-Binding Proteins via Hypergraph Based Laplacian Support Vector Machine

Background:

The identification of DNA binding proteins (DBP) is an important research field. Experiment-based methods are time-consuming and labor-intensive for detecting DBP.

Objective:

To solve the problem of large-scale DBP identification, some machine learning methods are proposed. However, these methods have insufficient predictive accuracy. Our aim is to develop a sequence- based machine learning model to predict DBP.

Methods:

In our study, we extracted six types of features (including NMBAC, GE, MCD, PSSM-AB, PSSM-DWT, and PsePSSM) from protein sequences. We used Multiple Kernel Learning based on Hilbert- Schmidt Independence Criterion (MKL-HSIC) to estimate the optimal kernel. Then, we constructed a hypergraph model to describe the relationship between labeled and unlabeled samples. Finally, Laplacian Support Vector Machines (LapSVM) is employed to train the predictive model. Our method is tested on PDB186, PDB1075, PDB2272 and PDB14189 data sets.

Result:

Compared with other methods, our model achieved best results on benchmark data sets.

Conclusion:

The accuracy of 87.1% and 74.2% are achieved on PDB186 (Independent test of PDB1075) and PDB2272 (Independent test of PDB14189), respectively.

Prediction of Protein-Protein Interaction Sites Based on Stratified Attentional Mechanisms

Proteins are the basic substances that undertake human life activities, and they often perform their biological functions through interactions with other biological macromolecules, such as cell transmission and signal transduction. Predicting the interaction sites between proteins can deepen the understanding of the principle of protein interactions, but traditional experimental methods are time-consuming and labor-intensive. In this study, a new hierarchical attention network structure, named HANPPIS, by adding six effective features of protein sequence, position-specific scoring matrix (PSSM), secondary structure, pre-training vector, hydrophilic, and amino acid position, is proposed to predict protein–protein interaction (PPI) sites. The experiment proved that our model has obtained very effective results, which was better than the existing advanced calculation methods. More importantly, we used the double-layer attention mechanism to improve the interpretability of the model and to a certain extent solved the problem of the “black box” of deep neural networks, which can be used as a reference for location positioning on the biological level.

Predicting the multi-label protein subcellular localization through multi-information fusion and MLSI dimensionality reduction based on MLFE classifier

MOTIVATION

Multi-label (ML) protein subcellular localization (SCL) is an indispensable way to study protein function. It can locate a certain protein (such as the human transmembrane protein that promotes the invasion of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)) or expression product at a specific location in a cell, which can provide a reference for clinical treatment of diseases such as coronavirus disease 2019 (COVID-19).

RESULTS

The article proposes a novel method named ML-locMLFE. First of all, six feature extraction methods are adopted to obtain protein effective information. These methods include pseudo amino acid composition, encoding based on grouped weight, gene ontology, multi-scale continuous and discontinuous, residue probing transformation and evolutionary distance transformation. In the next part, we utilize the ML information latent semantic index method to avoid the interference of redundant information. In the end, ML learning with feature-induced labeling information enrichment is adopted to predict the ML protein SCL. The Gram-positive bacteria dataset is chosen as a training set, while the Gram-negative bacteria dataset, virus dataset, newPlant dataset and SARS-CoV-2 dataset as the test sets. The overall actual accuracy of the first four datasets are 99.23%, 93.82%, 93.24% and 96.72% by the leave-one-out cross validation. It is worth mentioning that the overall actual accuracy prediction result of our predictor on the SARS-CoV-2 dataset is 72.73%. The results indicate that the ML-locMLFE method has obvious advantages in predicting the SCL of ML protein, which provides new ideas for further research on the SCL of ML protein.

AVAILABILITY AND IMPLEMENTATION

The source codes and datasets are publicly available at https://github.com/QUST-AIBBDRC/ML-locMLFE/.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

FTWSVM-SR: DNA-Binding Proteins Identification via Fuzzy Twin Support Vector Machines on Self-Representation

Due to the high cost of DNA-binding proteins (DBPs) detection, many machine learning algorithms (ML) have been utilized to large-scale process and detect DBPs. The previous methods took no count of the processing of noise samples. In this study, a fuzzy twin support vector machine (FTWSVM) is employed to detect DBPs. First, multiple types of protein sequence features are formed into kernel matrices; Then, multiple kernel learning (MKL) algorithm is utilized to linear combine multiple kernels; next, self-representation-based membership function is utilized to estimate membership value (weight) of each training sample; finally, we feed the integrated kernel matrix and membership values into the FTWSVM-SR model for training and testing. On comparison with other predictive models, FTWSVM based on SR (FTWSVM-SR) obtains the best performance of Matthew's correlation coefficient (MCC): 0.7410 and 0.5909 on two independent testing sets (PDB186 and PDB2272 datasets), respectively. The results confirm that our method can be an effective DBPs detection tool. Before the biochemical experiment, our model can screen and analyze DBPs on a large scale.

PScL-HDeep: image-based prediction of protein subcellular location in human tissue using ensemble learning of handcrafted and deep learned features with two-layer feature selection

Protein subcellular localization plays a crucial role in characterizing the function of proteins and understanding various cellular processes. Therefore, accurate identification of protein subcellular location is an important yet challenging task. Numerous computational methods have been proposed to predict the subcellular location of proteins. However, most existing methods have limited capability in terms of the overall accuracy, time consumption and generalization power. To address these problems, in this study, we developed a novel computational approach based on human protein atlas (HPA) data, referred to as PScL-HDeep, for accurate and efficient image-based prediction of protein subcellular location in human tissues. We extracted different handcrafted and deep learned (by employing pretrained deep learning model) features from different viewpoints of the image. The step-wise discriminant analysis (SDA) algorithm was applied to generate the optimal feature set from each original raw feature set. To further obtain a more informative feature subset, support vector machine-based recursive feature elimination with correlation bias reduction (SVM-RFE + CBR) feature selection algorithm was applied to the integrated feature set. Finally, the classification models, namely support vector machine with radial basis function (SVM-RBF) and support vector machine with linear kernel (SVM-LNR), were learned on the final selected feature set. To evaluate the performance of the proposed method, a new gold standard benchmark training dataset was constructed from the HPA databank. PScL-HDeep achieved the maximum performance on 10-fold cross validation test on this dataset and showed a better efficacy over existing predictors. Furthermore, we also illustrated the generalization ability of the proposed method by conducting a stringent independent validation test.

TRP-BERT: Discrimination of transient receptor potential (TRP) channels using contextual representations from deep bidirectional transformer based on BERT

Transient receptor potential (TRP) channels are non-selective cation channels that act as ion channels and are primarily found on the plasma membrane of numerous animal cells. These channels are involved in the physiology and pathophysiology of a wide variety of biological processes, including inhibition and progression of cancer, pain initiation, inflammation, regulation of pressure, thermoregulation, secretion of salivary fluid, and homeostasis of Ca²⁺ and Mg²⁺. Increasing evidences indicate that mutations in the gene encoding TRP channels play an essential role in a broad array of diseases. Therefore, these channels are becoming popular as potential drug targets for several diseases. The diversified role of these channels demands a prediction model to classify TRP channels from other channel proteins (non-TRP channels). Therefore, we presented an approach based on the Support Vector Machine (SVM) classifier and contextualized word embeddings from Bidirectional Encoder Representations from Transformers (BERT) to represent protein sequences. BERT is a deeply bidirectional language model and a neural network approach to Natural Language Processing (NLP) that achieves outstanding performance on various NLP tasks. We apply BERT to generate contextualized representations for every single amino acid in a protein sequence. Interestingly, these representations are context-sensitive and vary for the same amino acid appearing in different positions in the sequence. Our proposed method showed 80.00% sensitivity, 96.03% specificity, 95.47% accuracy, and a 0.56 Matthews correlation coefficient (MCC) for an independent test set. We suggest that our proposed method could effectively classify TRP channels from non-TRP channels and assist biologists in identifying new potential TRP channels.

Protein Secondary Structure Prediction With a Reductive Deep Learning Method

Protein secondary structures have been identified as the links in the physical processes of primary sequences, typically random coils, folding into functional tertiary structures that enable proteins to involve a variety of biological events in life science. Therefore, an efficient protein secondary structure predictor is of importance especially when the structure of an amino acid sequence fragment is not solved by high-resolution experiments, such as X-ray crystallography, cryo-electron microscopy, and nuclear magnetic resonance spectroscopy, which are usually time consuming and expensive. In this paper, a reductive deep learning model MLPRNN has been proposed to predict either 3-state or 8-state protein secondary structures. The prediction accuracy by the MLPRNN on the publicly available benchmark CB513 data set is comparable with those by other state-of-the-art models. More importantly, taking into account the reductive architecture, MLPRNN could be a baseline for future developments.

A sequence-based multiple kernel model for identifying DNA-binding proteins

BACKGROUND

DNA-Binding Proteins (DBP) plays a pivotal role in biological system. A mounting number of researchers are studying the mechanism and detection methods. To detect DBP, the tradition experimental method is time-consuming and resource-consuming. In recent years, Machine Learning methods have been used to detect DBP. However, it is difficult to adequately describe the information of proteins in predicting DNA-binding proteins. In this study, we extract six features from protein sequence and use Multiple Kernel Learning-based on Centered Kernel Alignment to integrate these features. The integrated feature is fed into Support Vector Machine to build predictive model and detect new DBP.

RESULTS

In our work, date sets of PDB1075 and PDB186 are employed to test our method. From the results, our model obtains better results (accuracy) than other existing methods on PDB1075 ([Formula: see text]) and PDB186 ([Formula: see text]), respectively.

CONCLUSION

Multiple kernel learning could fuse the complementary information between different features. Compared with existing methods, our method achieves comparable and best results on benchmark data sets.

Component Parts of Bacteriophage Virions Accurately Defined by a Machine-Learning Approach Built on Evolutionary Features

Antimicrobial resistance (AMR) continues to evolve as a major threat to human health, and new strategies are required for the treatment of AMR infections. Bacteriophages (phages) that kill bacterial pathogens are being identified for use in phage therapies, with the intention to apply these bactericidal viruses directly into the infection sites in bespoke phage cocktails. Despite the great unsampled phage diversity for this purpose, an issue hampering the roll out of phage therapy is the poor quality annotation of many of the phage genomes, particularly for those from infrequently sampled environmental sources. We developed a computational tool called STEP³ to use the “evolutionary features” that can be recognized in genome sequences of diverse phages. These features, when integrated into an ensemble framework, achieved a stable and robust prediction performance when benchmarked against other prediction tools using phages from diverse sources. Validation of the prediction accuracy of STEP³ was conducted with high-resolution mass spectrometry analysis of two novel phages, isolated from a watercourse in the Southern Hemisphere. STEP³ provides a robust computational approach to distinguish specific and universal features in phages to improve the quality of phage cocktails and is available for use at http://step3.erc.monash.edu/.

IMPORTANCE In response to the global problem of antimicrobial resistance, there are moves to use bacteriophages (phages) as therapeutic agents. Selecting which phages will be effective therapeutics relies on interpreting features contributing to shelf-life and applicability to diagnosed infections. However, the protein components of the phage virions that dictate these properties vary so much in sequence that best estimates suggest failure to recognize up to 90% of them. We have utilized this diversity in evolutionary features as an advantage, to apply machine learning for prediction accuracy for diverse components in phage virions. We benchmark this new tool showing the accurate recognition and evaluation of phage component parts using genome sequence data of phages from undersampled environments, where the richest diversity of phage still lies.

Robust ensemble of handcrafted and learned approaches for DNA-binding proteins

Purpose

Automatic DNA-binding protein (DNA-BP) classification is now an essential proteomic technology. Unfortunately, many systems reported in the literature are tested on only one or two datasets/tasks. The purpose of this study is to create the most optimal and universal system for DNA-BP classification, one that performs competitively across several DNA-BP classification tasks.

Design/methodology/approach

Efficient DNA-BP classifier systems require the discovery of powerful protein representations and feature extraction methods. Experiments were performed that combined and compared descriptors extracted from state-of-the-art matrix/image protein representations. These descriptors were trained on separate support vector machines (SVMs) and evaluated. Convolutional neural networks with different parameter settings were fine-tuned on two matrix representations of proteins. Decisions were fused with the SVMs using the weighted sum rule and evaluated to experimentally derive the most powerful general-purpose DNA-BP classifier system.

Findings

The best ensemble proposed here produced comparable, if not superior, classification results on a broad and fair comparison with the literature across four different datasets representing a variety of DNA-BP classification tasks, thereby demonstrating both the power and generalizability of the proposed system.

Originality/value

Most DNA-BP methods proposed in the literature are only validated on one (rarely two) datasets/tasks. In this work, the authors report the performance of our general-purpose DNA-BP system on four datasets representing different DNA-BP classification tasks. The excellent results of the proposed best classifier system demonstrate the power of the proposed approach. These results can now be used for baseline comparisons by other researchers in the field.