Protein Sequence Datasets Research Articles

TPGPred: A Mixed-Feature-Driven Approach for Identifying Thermophilic Proteins Based on GradientBoosting.

Thermophilic proteins maintain their stability and functionality under extreme high-temperature conditions, making them of significant importance in both fundamental biological research and biotechnological applications. In this study, we developed a machine learning-based thermophilic protein GradientBoosting prediction model, TPGPred, designed to predict thermophilic proteins by leveraging a large-scale dataset of both thermophilic and non-thermophilic protein sequences. By combining various machine learning algorithms with feature-engineering methods, we systematically evaluated the classification performance of the model, identifying the optimal feature combinations and classification models. Trained on a large public dataset of 5652 samples, TPGPred achieved an Accuracy score greater than 0.95 and an Area Under the Receiver Operating Characteristic Curve (AUROC) score greater than 0.98 on an independent test set of 627 samples. Our findings offer new insights into the identification and classification of thermophilic proteins and provide a solid foundation for their industrial application development.

Bi-SeqCNN: A Novel Light-weight Bi-directional CNN Architecture for Protein Function Prediction.

Deep learning approaches, such as convolution neural networks (CNNs) and deep recurrent neural networks (RNNs), have been the backbone for predicting protein function, with promising state-of-the-art (SOTA) results. RNNs with an in-built ability (i) focus on past information, (ii) collect both short-and-long range dependency information, and (iii) bi-directional processing offers a strong sequential processing mechanism. CNNs, however, are confined to focusing on short-term information from both the past and the future, although they offer parallelism. Therefore, a novel bi-directional CNN that strictly complies with the sequential processing mechanism of RNNs is introduced and is used for developing a protein function prediction framework, Bi-SeqCNN. This is a sub-sequence-based framework. Further, Bi-SeqCNN + is an ensemble approach to better the prediction results. To our knowledge, this is the first time bi-directional CNNs are employed for general temporal data analysis and not just for protein sequences. The proposed architecture produces improvements up to +5.5% over contemporary SOTA methods on three benchmark protein sequence datasets. Moreover, it is substantially lighter and attain these results with (0.50-0.70 times) fewer parameters than the SOTA methods.

Efficient Motif Discovery in Protein Sequences Using a Branch and Bound Algorithm.

Identifying motifs within sets of protein sequences constitutes a pivotal challenge in proteomics, imparting insights into protein evolution, function prediction, and structural attributes. Motifs hold the potential to unveil crucial protein aspects like transcription factor binding sites and protein-protein interaction regions. However, prevailing techniques for identifying motif sequences in extensive protein collections often entail significant time investments. Furthermore, ensuring the accuracy of obtained results remains a persistent motif discovery challenge. This paper introduces an innovative approach-a branch and bound algorithm-for exact motif identification across diverse lengths. This algorithm exhibits superior performance in terms of reduced runtime and enhanced result accuracy, as compared to existing methods. To achieve this objective, the study constructs a comprehensive tree structure encompassing potential motif evolution pathways. Subsequently, the tree is pruned based on motif length and targeted similarity thresholds. The proposed algorithm efficiently identifies all potential motif subsequences, characterized by maximal similarity, within expansive protein sequence datasets. Experimental findings affirm the algorithm's efficacy, highlighting its superior performance in terms of runtime, motif count, and accuracy, in comparison to prevalent practical techniques.

Effect of tokenization on transformers for biological sequences.

Deep-learning models are transforming biological research, including many bioinformatics and comparative genomics algorithms, such as sequence alignments, phylogenetic tree inference, and automatic classification of protein functions. Among these deep-learning algorithms, models for processing natural languages, developed in the natural language processing (NLP) community, were recently applied to biological sequences. However, biological sequences are different from natural languages, such as English, and French, in which segmentation of the text to separate words is relatively straightforward. Moreover, biological sequences are characterized by extremely long sentences, which hamper their processing by current machine-learning models, notably the transformer architecture. In NLP, one of the first processing steps is to transform the raw text to a list of tokens. Deep-learning applications to biological sequence data mostly segment proteins and DNA to single characters. In this work, we study the effect of alternative tokenization algorithms on eight different tasks in biology, from predicting the function of proteins and their stability, through nucleotide sequence alignment, to classifying proteins to specific families. We demonstrate that applying alternative tokenization algorithms can increase accuracy and at the same time, substantially reduce the input length compared to the trivial tokenizer in which each character is a token. Furthermore, applying these tokenization algorithms allows interpreting trained models, taking into account dependencies among positions. Finally, we trained these tokenizers on a large dataset of protein sequences containing more than 400 billion amino acids, which resulted in over a 3-fold decrease in the number of tokens. We then tested these tokenizers trained on large-scale data on the above specific tasks and showed that for some tasks it is highly beneficial to train database-specific tokenizers. Our study suggests that tokenizers are likely to be a critical component in future deep-network analysis of biological sequence data. Code, data, and trained tokenizers are available on https://github.com/technion-cs-nlp/BiologicalTokenizers.

GPCR-BERT: Interpreting Sequential Design of G Protein-Coupled Receptors Using Protein Language Models.

With the rise of transformers and large language models (LLMs) in chemistry and biology, new avenues for the design and understanding of therapeutics have been opened up to the scientific community. Protein sequences can be modeled as language and can take advantage of recent advances in LLMs, specifically with the abundance of our access to the protein sequence data sets. In this letter, we developed the GPCR-BERT model for understanding the sequential design of G protein-coupled receptors (GPCRs). GPCRs are the target of over one-third of Food and Drug Administration-approved pharmaceuticals. However, there is a lack of comprehensive understanding regarding the relationship among amino acid sequence, ligand selectivity, and conformational motifs (such as NPxxY, CWxP, and E/DRY). By utilizing the pretrained protein model (Prot-Bert) and fine-tuning with prediction tasks of variations in the motifs, we were able to shed light on several relationships between residues in the binding pocket and some of the conserved motifs. To achieve this, we took advantage of attention weights and hidden states of the model that are interpreted to extract the extent of contributions of amino acids in dictating the type of masked ones. The fine-tuned models demonstrated high accuracy in predicting hidden residues within the motifs. In addition, the analysis of embedding was performed over 3D structures to elucidate the higher-order interactions within the conformations of the receptors.

PseAAC2Vec protein encoding for TCR protein sequence classification

The classification and prediction of T-cell receptors (TCRs) protein sequences are of significant interest in understanding the immune system and developing personalized immunotherapies. In this study, we propose a novel approach using Pseudo Amino Acid Composition (PseAAC) protein encoding for accurate TCR protein sequence classification. The PseAAC2Vec encoding method captures the physicochemical properties of amino acids and their local sequence information, enabling the representation of protein sequences as fixed-length feature vectors. By incorporating physicochemical properties such as hydrophobicity, polarity, charge, molecular weight, and solvent accessibility, PseAAC2Vec provides a comprehensive and informative characterization of TCR protein sequences. To evaluate the effectiveness of the proposed PseAAC2Vec encoding approach, we assembled a large dataset of TCR protein sequences with annotated classes. We applied the PseAAC2Vec encoding scheme to each sequence and generated feature vectors based on a specified window size. Subsequently, we employed state-of-the-art machine learning algorithms, such as support vector machines (SVM) and random forests (RF), to classify the TCR protein sequences. Experimental results on the benchmark dataset demonstrated the superior performance of the PseAAC2Vec-based approach compared to existing methods. The PseAAC2Vec encoding effectively captures the discriminative patterns in TCR protein sequences, leading to improved classification accuracy and robustness. Furthermore, the encoding scheme showed promising results across different window sizes, indicating its adaptability to varying sequence contexts.

Computational prediction of allergenic proteins based on multi-feature fusion.

Allergy is an autoimmune disorder described as an undesirable response of the immune system to typically innocuous substance in the environment. Studies have shown that the ability of proteins to trigger allergic reactions in susceptible individuals can be evaluated by bioinformatics tools. However, developing computational methods to accurately identify new allergenic proteins remains a vital challenge. This work aims to propose a machine learning model based on multi-feature fusion for predicting allergenic proteins efficiently. Firstly, we prepared a benchmark dataset of allergenic and non-allergenic protein sequences and pretested on it with a machine-learning platform. Then, three preferable feature extraction methods, including amino acid composition (AAC), dipeptide composition (DPC) and composition of k-spaced amino acid pairs (CKSAAP) were chosen to extract protein sequence features. Subsequently, these features were fused and optimized by Pearson correlation coefficient (PCC) and principal component analysis (PCA). Finally, the most representative features were picked out to build the optimal predictor based on random forest (RF) algorithm. Performance evaluation results via 5-fold cross-validation showed that the final model, called iAller (https://github.com/laihongyan/iAller), could precisely distinguish allergenic proteins from non-allergenic proteins. The prediction accuracy and AUC value for validation dataset achieved 91.4% and 0.97%, respectively. This model will provide guide for users to identify more allergenic proteins.

Improved prediction of MHC-peptide binding using protein language models.

Major histocompatibility complex Class I (MHC-I) molecules bind to peptides derived from intracellular antigens and present them on the surface of cells, allowing the immune system (T cells) to detect them. Elucidating the process of this presentation is essential for regulation and potential manipulation of the cellular immune system. Predicting whether a given peptide binds to an MHC molecule is an important step in the above process and has motivated the introduction of many computational approaches to address this problem. NetMHCPan, a pan-specific model for predicting binding of peptides to any MHC molecule, is one of the most widely used methods which focuses on solving this binary classification problem using shallow neural networks. The recent successful results of Deep Learning (DL) methods, especially Natural Language Processing (NLP-based) pretrained models in various applications, including protein structure determination, motivated us to explore their use in this problem. Specifically, we consider the application of deep learning models pretrained on large datasets of protein sequences to predict MHC Class I-peptide binding. Using the standard performance metrics in this area, and the same training and test sets, we show that our models outperform NetMHCpan4.1, currently considered as the-state-of-the-art.

Simplifying complex antibody engineering using machine learning.

Machine learning is transforming antibody engineering by enabling the generation of drug-like monoclonal antibodies with unprecedented efficiency. Unsupervised algorithms trained on massive and diverse protein sequence datasets facilitate the prediction of panels of antibody variants with native-like intrinsic properties (e.g., high stability), greatly reducing the amount of subsequent experimentation needed to identify specific candidates that also possess desired extrinsic properties (e.g., high affinity). Additionally, supervised algorithms, which are trained on deep sequencing datasets obtained after enrichment of invitro antibody libraries for one or more specific extrinsic properties, enable the prediction of antibody variants with desired combinations of extrinsic properties without the need for additional screening. Here we review recent advances using both machine learning approaches and how they are impacting the field of antibody engineering as well as key outstanding challenges and opportunities for these paradigm-changing methods.

MC-NN: An End-to-End Multi-Channel Neural Network Approach for Predicting Influenza A Virus Hosts and Antigenic Types

Influenza poses a significant threat to public health, particularly among the elderly, young children, and people with underlying diseases. The manifestation of severe conditions, such as pneumonia, highlights the importance of preventing the spread of influenza. An accurate and cost-effective prediction of the host and antigenic subtypes of influenza A viruses is essential to addressing this issue, particularly in resource-constrained regions. In this study, we propose a multi-channel neural network model to predict the host and antigenic subtypes of influenza A viruses from hemagglutinin and neuraminidase protein sequences. Our model was trained on a comprehensive data set of complete protein sequences and evaluated on various test data sets of complete and incomplete sequences. The results demonstrate the potential and practicality of using multi-channel neural networks in predicting the host and antigenic subtypes of influenza A viruses from both full and partial protein sequences.

Unsupervised Deep Learning Can Identify Protein Functional Groups from Unaligned Sequences.

Interpreting protein function from sequence data is a fundamental goal of bioinformatics. However, our current understanding of protein diversity is bottlenecked by the fact that most proteins have only been functionally validated in model organisms, limiting our understanding of how function varies with gene sequence diversity. Thus, accuracy of inferences in clades without model representatives is questionable. Unsupervised learning may help to ameliorate this bias by identifying highly complex patterns and structure from large datasets without external labels. Here we present DeepSeqProt, an unsupervised deep learning program for exploring large protein sequence datasets. DeepSeqProt is a clustering tool capable of distinguishing between broad classes of proteins while learning local and global structure of functional space. DeepSeqProt is capable of learning salient biological features from unaligned, unannotated sequences. DeepSeqProt is more likely to capture complete protein families and statistically significant shared ontologies within proteomes than other clustering methods. We hope this framework will prove of use to researchers and provide a preliminary step in further developing unsupervised deep learning in molecular biology.

Sars-escape network for escape prediction of SARS-COV-2.

Viruses have coevolved with their hosts for over millions of years and learned to escape the host's immune system. Although not all genetic changes in viruses are deleterious, some significant mutations lead to the escape of neutralizing antibodies and weaken the immune system, which increases infectivity and transmissibility, thereby impeding the development of antiviral drugs or vaccines. Accurate and reliable identification of viral escape mutational sequences could be a good indicator for therapeutic design. We developed a computational model that recognizes significant mutational sequences based on escape feature identification using natural language processing along with prior knowledge of experimentally validated escape mutants. Our machine learning-based computational approach can recognize the significant spike protein sequences of severe acute respiratory syndrome coronavirus 2 using sequence data alone. This modelling approach can be applied to other viruses, such as influenza, monkeypox and HIV using knowledge of escape mutants and relevant protein sequence datasets. Complete source code and pre-trained models for escape prediction of severe acute respiratory syndrome coronavirus 2 protein sequences are available on Github at https://github.com/PremSinghBist/Sars-CoV-2-Escape-Model.git. The dataset is deposited to Zenodo at: doi: 10.5281/zenodo.7142638. The Python scripts are easy to run and customize as needed. premsing212@jbnu.ac.kr.

VPAgs-Dataset4ML: A Dataset to Predict Viral Protective Antigens for Machine Learning-Based Reverse Vaccinology

Reverse vaccinology (RV) is a computer-aided approach for vaccine development that identifies a subset of pathogen proteins as protective antigens (PAgs) or potential vaccine candidates. Machine learning (ML)-based RV is promising, but requires a dataset of PAgs (positives) and non-protective protein sequences (negatives). This study aimed to create an ML dataset, VPAgs-Dataset4ML, to predict viral PAgs based on PAgs obtained from Protegen. We performed seven steps to identify PAgs from the Protegen website and non-protective protein sequences from Universal Protein Resource (UniProt). The seven steps included downloading viral PAgs from Protegen, performing quality checks on PAgs using the standard BLASTp identity check ≤30% via MMseqs2, and computational steps running on Google Colaboratory and the Ubuntu terminal to retrieve and perform quality checks (similar to the PAgs) on non-protective protein sequences as negatives from UniProt. VPAgs-Dataset4ML contains 2145 viral protein sequences, with 210 PAgs in positive.fasta and 1935 non-protective protein sequences in negative.fasta. This dataset can be used to train ML models to predict antigens for various viral pathogens with the aim of developing effective vaccines.

Prediction of Bacterial Immunogenicity by Machine Learning Methods.

Prediction of bacterial immunogens is a prerequisite for the process of vaccine development through reverse vaccinology. The application of in silico methods allows significant reduction in time and cost for the discovery of potential vaccine candidates among proteins of a bacterial species. The steps in the prediction algorithm include collection of protein sequence datasets of known bacterial immunogens and non-immunogens, data preprocessing to transform the protein sequences into numerical matrices suitable for use as training and test sets for various machine learning methods, and derivation of predictive models. The performance of the derived models is evaluated by means of classification metrics.In this chapter, we present a protocol for predicting bacterial immunogenicity by applying machine learning methods. The protocol describes the process of model development from data collection and manipulation to training and validation of the derived models.

Deep embedding and alignment of protein sequences.

Protein sequence alignment is a key component of most bioinformatics pipelines to study the structures and functions of proteins. Aligning highly divergent sequences remains, however, a difficult task that current algorithms often fail to perform accurately, leaving many proteins or open reading frames poorly annotated. Here we leverage recent advances in deep learning for language modeling and differentiable programming to propose DEDAL (deep embedding and differentiable alignment), a flexible model to align protein sequences and detect homologs. DEDAL is a machine learning-based model that learns to align sequences by observing large datasets of raw protein sequences and of correct alignments. Once trained, we show that DEDAL improves by up to two- or threefold the alignment correctness over existing methods on remote homologs and better discriminates remote homologs from evolutionarily unrelated sequences, paving the way to improvements on many downstream tasks relying on sequence alignment in structural and functional genomics.

BepiPred-3.0: Improved B-cell epitope prediction using protein language models.

B-cell epitope prediction tools are of great medical and commercial interest due to their practical applications in vaccine development and disease diagnostics. The introduction of protein language models (LMs), trained on unprecedented large datasets of protein sequences and structures, tap into a powerful numeric representation that can be exploited to accurately predict local and global protein structural features from amino acid sequences only. In this paper, we present BepiPred-3.0, a sequence-based epitope prediction tool that, by exploiting LM embeddings, greatly improves the prediction accuracy for both linear and conformational epitope prediction on several independent test sets. Furthermore, by carefully selecting additional input variables and epitope residue annotation strategy, performance was further improved, thus achieving unprecedented predictive power. Our tool can predict epitopes across hundreds of sequences in minutes. It is freely available as a web server and a standalone package at https://services.healthtech.dtu.dk/service.php?BepiPred-3.0 with a user-friendly interface to navigate the results.

Meta-Analysis of the Public RNA-Seq Data of the Western Honeybee Apis mellifera to Construct Reference Transcriptome Data.

Simple SummaryThe honeybee is an economically and ecologically essential insect species and a critical social behavior model. It is vital to honey production and pollination. Therefore, it has been studied extensively in entomological research. The Western honeybee (Apis mellifera) is a representative species of honeybees. Reference transcriptome data are required to perform the meta-analyses using public RNA-Seq data and transcriptome analysis using newly sequenced RNA-Seq data. The reference transcriptome sequences were constructed, which consisted of 149,685 transcripts, and 194,174 predicted amino acid sequences. Half the predicted protein sequences were functionally annotated using protein sequence datasets for several model and insect species. We performed meta-analysis to search for novel immune-response-related transcripts. We identified 3–20 transcripts that were upregulated or downregulated in response to both viral and bacterial infections. However, the immune-related transcripts were not included among them. Autophagy-related protein 3 was downregulated by viral infections. The results suggested that autophagy was implicated in the viral immune responses, and autophagy was not regulated by the canonical immune pathways in A. mellifera. The results of the meta-analysis suggested that the reference transcriptome data could be used for transcriptome analysis in A. mellifera.The Western honeybee (Apis mellifera) is valuable in biological research and agriculture. Its genome sequence was published before those for other insect species. RNA-Seq data for A. mellifera have been applied in several recently published studies. Nevertheless, these data have not been prepared for use in subsequent meta-analyses. To promote A. mellifera transcriptome analysis, we constructed reference transcriptome data using the reference genome sequence and RNA-Seq data curated from about 1,000 runs of public databases. The new reference transcriptome data construct comprised 149,685 transcripts, and 194,174 protein sequences were predicted. Approximately 50–60% of the predicted protein sequences were functionally annotated using the protein sequence data for several model and insect species. Novel candidate immune-related transcripts were searched by meta-analysis using immune-response-related RNA-Seq and reference transcriptome data. Three to twenty candidate transcripts including autophagy-related protein 3 were upregulated or downregulated in response to both viral and bacterial infections. The constructed reference transcriptome data may facilitate future transcriptome analyses of A. mellifera.

Functional characterization of unknown protein sequences using Neuro-Fuzzy based machine learning approach and sequence augmented feature

Functional characterization of the Unknown Protein Sequence (UPS) is significant for biological research such as disease diagnosis and drug design. In this work Neuro-Fuzzy based machine learning framework is proposed with two levels of predictions, for functional characterization of UPS using augmented features and subcellular localization of the protein sequences. In the first level, Neuro-Fuzzy Approach (NFA) is applied for the categorization of UPS as bacterial or non-bacterial protein sequence. While NFA is capable to overcome the likelihood prediction problem of supervised learning algorithms with untrained samples such as UPS. In the next level functions of bacterial protein sequences are characterized using Protein Subcellular Localization (PSL) model. Physicochemical and evolutionary informations of the protein sequences are extracted and augmented as a protein feature vector that preserves the protein-residue-property and sequence-order-information. Various individual and ensemble classifiers such as Decision-Tree (C-4.5), k-Nearest-Neighbor (k-NN), Multi-Layer-Perceptron (MLP), Naïve-Bayes (NB), AdaBoost, and Gradient-Boosting-Machine (GBM) are used for the formation of the PSL model. PSL model is trained with augmented features of known Gram-Negative Bacterial Protein Sequence (GN_BPS) dataset with 10-fold cross-validation and 97.94% accuracy is achieved through C-4.5 classifier. Validated PSL model is further utilized for the functional characterization of the Unknown G- Bacterial Protein Sequences (Unk_GN_BPS) such as Unk_GN_156 and Unk_GN_61 datasets. The accuracy achieved for Unk_GN_156 is 78.20% with C-4.5 and 79.32% for the Unk_GN_61 through k-NN.

DeepNEC: a novel alignment-free tool for the identification and classification of nitrogen biochemical network-related enzymes using deep learning.

Nitrogen is essential for life and its transformations are an important part of the global biogeochemical cycle. Being an essential nutrient, nitrogen exists in a range of oxidation states from +5 (nitrate) to -3 (ammonium and amino-nitrogen), and its oxidation and reduction reactions catalyzed by microbial enzymes determine its environmental fate. The functional annotation of the genes encoding the core nitrogen network enzymes has a broad range of applications in metagenomics, agriculture, wastewater treatment and industrial biotechnology. This study developed an alignment-free computational approach to determine the predicted nitrogen biochemical network-related enzymes from the sequence itself. We propose deepNEC, a novel end-to-end feature selection and classification model training approach for nitrogen biochemical network-related enzyme prediction. The algorithm was developed using Deep Learning, a class of machine learning algorithms that uses multiple layers to extract higher-level features from the raw input data. The derived protein sequence is used as an input, extracting sequential and convolutional features from raw encoded protein sequences based on classification rather than traditional alignment-based methods for enzyme prediction. Two large datasets of protein sequences, enzymes and non-enzymes were used to train the models with protein sequence features like amino acid composition, dipeptide composition (DPC), conformation transition and distribution, normalized Moreau-Broto (NMBroto), conjoint and quasi order, etc. The k-fold cross-validation and independent testing were performed to validate our model training. deepNEC uses a four-tier approach for prediction; in the first phase, it will predict a query sequence as enzyme or non-enzyme; in the second phase, it will further predict and classify enzymes into nitrogen biochemical network-related enzymes or non-nitrogen metabolism enzymes; in the third phase, it classifies predicted enzymes into nine nitrogen metabolism classes; and in the fourth phase, it predicts the enzyme commission number out of 20 classes for nitrogen metabolism. Among all, the DPC + NMBroto hybrid feature gave the best prediction performance (accuracy of 96.15% in k-fold training and 93.43% in independent testing) with an Matthews correlation coefficient (0.92 training and 0.87 independent testing) in phase I; phase II (accuracy of 99.71% in k-fold training and 98.30% in independent testing); phase III (overall accuracy of 99.03% in k-fold training and 98.98% in independent testing); phase IV (overall accuracy of 99.05% in k-fold training and 98.18% in independent testing), the DPC feature gave the best prediction performance. We have also implemented a homology-based method to remove false negatives. All the models have been implemented on a web server (prediction tool), which is freely available at http://bioinfo.usu.edu/deepNEC/.

FEGS: a novel feature extraction model for protein sequences and its applications

BackgroundFeature extraction of protein sequences is widely used in various research areas related to protein analysis, such as protein similarity analysis and prediction of protein functions or interactions.ResultsIn this study, we introduce FEGS (Feature Extraction based on Graphical and Statistical features), a novel feature extraction model of protein sequences, by developing a new technique for graphical representation of protein sequences based on the physicochemical properties of amino acids and effectively employing the statistical features of protein sequences. By fusing the graphical and statistical features, FEGS transforms a protein sequence into a 578-dimensional numerical vector. When FEGS is applied to phylogenetic analysis on five protein sequence data sets, its performance is notably better than all of the other compared methods.ConclusionThe FEGS method is carefully designed, which is practically powerful for extracting features of protein sequences. The current version of FEGS is developed to be user-friendly and is expected to play a crucial role in the related studies of protein sequence analyses.