Search

Thermoalkaliphilic GH11 xylanases are largely favored for paper pulp biobleaching process. The present work aimed to comparatively investigate the molecular phylogeny, amino acid sequences, molecular structure, and enzyme–substrate interaction of six thermoalkaliphilic GH11 xylanases from different bacterial species (Oxalobacteraceae bacterium xylanase = ObXyl, Sphingomonas sp. xylanase = SsXyl, Hymenobacter sp. xylanase = HsXyl, Amycolatopsis vastitatis xylanase = AvXyl, Lentzea deserti xylanase = LdXyl, Streptomyces rubellomurinus xylanase = SrXyl). For this purpose, six bacterial thermoalkaliphilic GH11 xylanase sequences derived from unreviewed protein entries of UniProt/TrEMBL database were analyzed for their phylogenetic relationships and sequence similarities. Also, 3D predicted structures of the enzymes were built and computationally validated by different bioinformatics tools. The enzyme–substrate interactions were investigated by molecular docking analysis using various substrates. Phylogenetic analysis showed that six enzymes were grouped into two different clusters: the first cluster included ObXyl, SsXyl, and HsXyl, whereas the second cluster had AvXyl, LdXyl, and SrXyl. Multiple sequence alignment showed that the second cluster xylanases possessed longer N-terminal regions indicating higher thermostability, compared to the first cluster xylanases. The structural analyses showed that six predicted structures were largely conserved. Molecular docking results indicated that binding efficiency to xylotriose, xylotetraose, and xylopentaose was higher in second cluster enzymes than that in first cluster enzymes, exhibiting mostly above -8.0 kCal/mol of binding energy. Arginine in B8 β-strand was commonly involved in substrate interactions in all the second cluster xylanases, different from the first cluster ones. Thus, the present work predicted that the thermoalkaliphilic xylanases in the second cluster might be greater potential candidates for the paper pulp bleaching process. [ABSTRACT FROM AUTHOR]

Describes the circular DNA cloning and nucleotide sequences encoding of alpha-skeletal actin isoforms from walleye pollack. Amino acid sequence; Plaque hybridization; Reverse transcription-polymerase chain reaction; Use of terminal deoxynucleotidyl transferase.

Protein structure prediction (PSP) is a grand challenge in bioinformatics, drug discovery, and related fields. PSP is computationally challenging because of an astronomically large conformational space to be searched and an unknown very complex energy function to be minimised. To obtain a given protein's structure, template-based PSP approaches adopt a similar protein's known structure, while template-free PSP approaches work when no similar protein's structure is known. Currently, proteins with known structures are greatly outnumbered by proteins with unknown structures. Template-free PSP has obtained significant progress recently via machine learning and search-based optimisation approaches. However, very accurate structures for complex proteins are yet to be achieved at a level suitable for effective drug design. Moreover, ab initio prediction of a protein's structure only from its amino acid sequence remains unsolved. Furthermore, the number of protein sequences with unknown structures is growing rapidly. Hence, to make further progress in PSP, more sophisticated and advanced artificial intelligence (AI) approaches are needed. However, getting involved in PSP research is difficult for AI researchers because of the lack of a comprehensive understanding of the whole problem, along with the background and the literature of all related sub-problems. Unfortunately, existing PSP review papers cover PSP research at a very high level and only some parts of PSP and only from a particular singular viewpoint. Using a systematic approach, this review paper provides a comprehensive survey of the state-of-the-art template-free PSP research to fill this knowledge gap. Moreover, covering required PSP preliminaries and computational formulations, this paper presents PSP research from AI perspectives, discusses the challenges, provides our commentaries, and outlines future research directions. [ABSTRACT FROM AUTHOR]

Bitter taste is an unpleasant taste modality that affects food consumption. Bitter peptides are generated during enzymatic processes that produce functional, bioactive protein hydrolysates or during the aging process of fermented products such as cheese, soybean protein, and wine. Understanding the underlying peptide sequences responsible for bitter taste can pave the way for more efficient identification of these peptides. This paper presents BitterPep-GCN, a feature-agnostic graph convolution network for bitter peptide prediction. The graph-based model learns the embedding of amino acids in the bitter peptide sequences and uses mixed pooling for bitter classification. BitterPep-GCN was benchmarked using BTP640, a publicly available bitter peptide dataset. The latent peptide embeddings generated by the trained model were used to analyze the activity of sequence motifs responsible for the bitter taste of the peptides. Particularly, we calculated the activity for individual amino acids and dipeptide, tripeptide, and tetrapeptide sequence motifs present in the peptides. Our analyses pinpoint specific amino acids, such as F, G, P, and R, as well as sequence motifs, notably tripeptide and tetrapeptide motifs containing FF, as key bitter signatures in peptides. This work not only provides a new predictor of bitter taste for a more efficient identification of bitter peptides in various food products but also gives a hint into the molecular basis of bitterness. Scientific Contribution Our work provides the first application of Graph Neural Networks for the prediction of peptide bitter taste. The best-developed model, BitterPep-GCN, learns the embedding of amino acids in the bitter peptide sequences and uses mixed pooling for bitter classification. The embeddings were used to analyze the sequence motifs responsible for the bitter taste. [ABSTRACT FROM AUTHOR]

Secondary structure prediction is a key step in understanding protein function and biological properties and is highly important in the fields of new drug development, disease treatment, bioengineering, etc. Accurately predicting the secondary structure of proteins helps to reveal how proteins are folded and how they function in cells. The application of deep learning models in protein structure prediction is particularly important because of their ability to process complex sequence information and extract meaningful patterns and features, thus significantly improving the accuracy and efficiency of prediction. In this study, a combined model integrating an improved temporal convolutional network (TCN), bidirectional long short-term memory (BiLSTM), and a multi-head attention (MHA) mechanism is proposed to enhance the accuracy of protein prediction in both eight-state and three-state structures. One-hot encoding features and word vector representations of physicochemical properties are incorporated. A significant emphasis is placed on knowledge distillation techniques utilizing the ProtT5 pretrained model, leading to performance improvements. The improved TCN, achieved through multiscale fusion and bidirectional operations, allows for better extraction of amino acid sequence features than traditional TCN models. The model demonstrated excellent prediction performance on multiple datasets. For the TS115, CB513 and PDB (2018–2020) datasets, the prediction accuracy of the eight-state structure of the six datasets in this paper reached 88.2%, 84.9%, and 95.3%, respectively, and the prediction accuracy of the three-state structure reached 91.3%, 90.3%, and 96.8%, respectively. This study not only improves the accuracy of protein secondary structure prediction but also provides an important tool for understanding protein structure and function, which is particularly applicable to resource-constrained contexts and provides a valuable tool for understanding protein structure and function. [ABSTRACT FROM AUTHOR]

Protein-ligand binding affinity plays a pivotal role in drug development, particularly in identifying potential ligands for target disease-related proteins. Accurate affinity predictions can significantly reduce both the time and cost involved in drug development. However, highly precise affinity prediction remains a research challenge. A key to improve affinity prediction is to capture interactions between proteins and ligands effectively. Existing deep-learning-based computational approaches use 3D grids, 4D tensors, molecular graphs, or proximity-based adjacency matrices, which are either resource-intensive or do not directly represent potential interactions. In this paper, we propose atomic-level distance features and attention mechanisms to capture better specific protein-ligand interactions based on donor-acceptor relations, hydrophobicity, and π -stacking atoms. We argue that distances encompass both short-range direct and long-range indirect interaction effects while attention mechanisms capture levels of interaction effects. On the very well-known CASF-2016 dataset, our proposed method, named Distance plus Attention for Affinity Prediction (DAAP), significantly outperforms existing methods by achieving Correlation Coefficient (R) 0.909, Root Mean Squared Error (RMSE) 0.987, Mean Absolute Error (MAE) 0.745, Standard Deviation (SD) 0.988, and Concordance Index (CI) 0.876. The proposed method also shows substantial improvement, around 2% to 37%, on five other benchmark datasets. The program and data are publicly available on the website https://gitlab.com/mahnewton/daap. Scientific Contribution Statement This study innovatively introduces distance-based features to predict protein-ligand binding affinity, capitalizing on unique molecular interactions. Furthermore, the incorporation of protein sequence features of specific residues enhances the model's proficiency in capturing intricate binding patterns. The predictive capabilities are further strengthened through the use of a deep learning architecture with attention mechanisms, and an ensemble approach, averaging the outputs of five models, is implemented to ensure robust and reliable predictions. [ABSTRACT FROM AUTHOR]

Protein structure expectation is a particularly mind boggling issue that it is frequently assaulted and disintegrated using four distinct levels and they are: 1-D forecast of under- lying highlights along the essential succession of amino acids sequences, 2-D forecast of spatial connections between the sequence of amino acids, 3-D forecast of a tertiary structure of protein and quaternary structure of protein. This paper also try to introduce some assessment tools for finding the accuracy of result from applying ML and DL tools. And try to analyses and compare various algorithms based on deep learning methods verses machine learning methods used for sequence prediction. This paper also examines the turn of events and utilization of concealed Markov model, uphold vector machines, Bayesian techniques, and grouping strategies. This investigation will be helpful in creating future strategies to improve the exactness of protein auxiliary structure expectation. In this paper, also introduce and summarize the problem of quantum essential elements of: (1) Variational auto-encoder (2) GAN, generative adversarial network (3) RNN, recurrent neural (4) CNN, convolutional neural networks protein structure prediction. Later on also summarizes the evolution of predictive algorithms for 1-4D structure of protein from Amino Acid Sequences and summarize the deep learning ideas to prediction of structure of protein and learned algorithms of the last decade. [ABSTRACT FROM AUTHOR]

The design of binder proteins for specific target proteins using deep learning is a challenging task that has a wide range of applications in both designing therapeutic antibodies and creating new drugs. Machine learning-based solutions, as opposed to laboratory design, streamline the design process and enable the design of new proteins that may be required to address new and orphan diseases. Most techniques proposed in the literature necessitate either domain knowledge or some appraisal of the target protein's 3-D structure. This paper proposes an approach for designing binder proteins based solely on the amino acid sequence of the target protein and without recourse to domain knowledge or structural information. The sequences of the binders are generated with two new transformers, namely the AppendFormer and MergeFormer architectures. Because, in general, there is more than one binder for a given target protein, these transformers employ a binding score and a prior on the sequence of the binder to obtain a unique targeted solution. Our experimental evaluation confirms the strengths of this novel approach. The performance of the models was determined with 5-fold cross-validation and clearly indicates that our architectures lead to highly accurate results. In addition, scores of up to 0.98 were achieved in terms of Needleman-Wunsch and Smith-Waterman similarity metrics, which indicates that our solutions significantly outperform a seq2seq baseline model. [ABSTRACT FROM AUTHOR]

Protein structure prediction is one of the main research areas in the field of Bio-informatics. The importance of proteins in drug design attracts researchers for finding the accurate tertiary structure of the protein which is dependent on its secondary structure. In this paper, we focus on improving the accuracy of protein secondary structure prediction. To do so, a Multi-scale convolutional neural network with a Gated recurrent neural network (MCNN-GRNN) is proposed. The novel amino acid encoding method along with layered convolutional neural network and Gated recurrent neural network blocks helps to retrieve local and global relationships between features, which in turn effectively classify the input protein sequence into 3 and 8 states. We have evaluated our algorithm on CullPDB, CB513, PDB25, CASP10, CASP11, CASP12, CASP13, and CASP14 datasets. We have compared our algorithm with different state-of-the-art algorithms like DCNN-SS, DCRNN, MUFOLD-SS, DLBLS_SS, and CGAN-PSSP. The Q3 accuracy of the proposed algorithm is 82–87% and Q8 accuracy is 69–77% on different datasets. [ABSTRACT FROM AUTHOR]

Linear-B cell epitopes (LBCE) play a vital role in vaccine design; thus, efficiently detecting them from protein sequences is of primary importance. These epitopes consist of amino acids arranged in continuous or discontinuous patterns. Vaccines employ attenuated viruses and purified antigens. LBCE stimulate humoral immunity in the body, where B and T cells target circulating infections. To predict LBCE, the underlying protein sequences undergo a process of feature extraction, feature selection, and classification. Various system models have been proposed for this purpose, but their classification accuracy is only moderate. In order to enhance the accuracy of LBCE classification, this paper presents a novel 2-step metaheuristic variant-feature selection method that combines a linear support vector classifier (LSVC) with a Modified Genetic Algorithm (MGA). The feature selection model employs mono-peptide, dipeptide, and tripeptide features, focusing on the most diverse ones. These selected features are fed into a machine learning (ML)-based parallel ensemble classifier. The ensemble classifier combines correctly classified instances from various classifiers, including k-Nearest Neighbor (kNN), random forest (RF), logistic regression (LR), and support vector machine (SVM). The ensemble classifier came up with an impressively high accuracy of 99.3% as a result of its work. This accuracy is superior to the most recent models that are considered to be state-of-the-art for linear B-cell classification. As a direct consequence of this, the entire system model can now be utilised effectively in real-time clinical settings. [ABSTRACT FROM AUTHOR]

HIV-1 protease cleavage site prediction of an amino acid sequence of Human Immune Deficiency Virus (HIV-1) type 1 has been the subject of intense research for decades to increase the AUC value of the prediction without placing much attention to the accuracy metric by many researchers. Knowledge of the substrate specificity of HIV-1 protease has significant application in HIV-1 protease inhibitors development and in studying novel drug targets. Motivated by this, a multi-objective optimization (MOO)-based majority voting ensemble framework combining the outputs from multiple classifiers has been proposed in the current paper to increase both the prediction accuracy and AUC values simultaneously. The optimal set of classifiers that are considered for voting purposes at the time of combining the outputs is determined automatically using the search capability of MOO. Comparatively better results have been attained using various benchmark data sets with average accuracy and AUC (area under the ROC curve) values of 0.92 and 0.96, respectively. [ABSTRACT FROM AUTHOR]

Rhodopsins are light-sensitive proteins which universally exist in prokaryotes and eukaryotes. Type I rhodopsins exist in microbes and are known as microbial rhodopsins, which include various kinds such as bacteriorhodopsins (BR), halorhodopsins (HR), and sensory rhodopsins (SR). Type II rhodopsins, which belong to G-protein-coupled receptors (GPCR), exist in animals, and are collectively known as animal rhodopsins. Type III rhodopsins, also known as heliorhodopsins discovered by Alina Pushkarev in 2018, are distributed globally and exist in eukaryotes, prokaryotes, and even some viruses. Since type III rhodopsin is distinct in its protein sequence when compared to type I and II rhodopsins, it is not considered in this research. Past research has shown that there exists a clear evolution relationship between different kinds of microbial rhodopsins. However, the evolutionary relationship between microbial and animal rhodopsins hasn't been verified yet due to the huge difference between their sequences. Thus, this paper aims to explore the evolution process within microbial rhodopsins as well as the evolutionary relationship between microbial and animal rhodopsins, utilizing phylogenetic trees and transmembrane domain analysis. Results show that HR and SR both evolved from BR. Additionally, by comparing the phylogenetic tree of BR with phylogenetic tree of microbial 16S rRNA, it is discovered that evolution of microbial rhodopsins is significantly different from their host microbes. [ABSTRACT FROM AUTHOR]

Accurate prediction of drug–target interactions (DTIs), which is often used in the fields of drug discovery and drug repositioning, is regarded a key challenge in the study of drug science. In this paper, a new method called DeepStack-DTIs is proposed to predict DTIs. First, for the target protein, pseudo-position specific score matrix, pseudo amino acid composition and SPIDER3 are used to extract the different feature information of the target protein. Meanwhile, the path-based fingerprint features of each drug are extracted. Then, the synthetic minority oversampling technique (SMOTE) and light gradient boosting machine (LightGBM) are used for data balancing and feature selection, respectively. Finally, the processed features are input to the deep-stacked ensemble classifier composed of gated recurrent unit (GRU), deep neural network (DNN), support vector machine (SVM), eXtreme gradient boosting (XGBoost) and logistic regression (LR) to predict DTIs. Under the five-fold cross-validation and compared with existing methods, the proposed method achieves higher prediction accuracy on the gold standard dataset. To evaluate the predictive power of DeepStack-DTIs, we validate the method on another dataset and predict the drug–target interaction network. The results indicate that DeepStack-DTIs has excellent predictive ability than the other methods, and provides novel insights for the prediction of DTIs. A novel method DeepStack-DTIs for drug–target interactions prediction. PsePSSM, PseAAC, SPIDER3 and FP2 are fused to convert protein sequence and drug molecule information into digital information, respectively. The SMOTE algorithm is used to balance the dataset and LightGBM feature selection algorithm is employed to remove redundant and irrelevant features to select the optimal feature subset. This optimal feature subset is inputted into the deep-stacked ensemble classifier to predict drug–target interactions. The experimental results show DeepStack-DTIs method can significantly improve the prediction accuracy of drug–target interactions. [ABSTRACT FROM AUTHOR]

This document is a letter addressing errors in a published paper on van der Hoeve's syndrome, a form of osteogenesis imperfecta (OI). The authors of the paper incorrectly assumed that a single-nucleotide deletion in the COL1A1 gene would result in a stable mutant mRNA and a truncated protein. They also presented inaccurate descriptions of the causative variant and the classification of OI types. The letter corrects these errors and provides the appropriate terminology and classification. The document emphasizes the need for accurate scientific reporting and adherence to current practices in the field. [Extracted from the article]

An amendment to this paper has been published and can be accessed via a link at the top of the paper. [ABSTRACT FROM AUTHOR]

Insufficient research on the material basis and functional product development of horse bones has led to the waste of resources. This paper, as the by-product of horse meat bone marrow was the object, aimed to discover the flavor and antioxidant activity of novel collagen peptides. Two peptides, HBMP-1-1 and HBMP-2-1, were isolated and purified from horse bone marrow collagen protein (HBMP) hydrolysates. The combination of spectroscopic and chromatographic methods including SDS-PAGE, UV, FT-IR, CD, and SEM identified the structures of the peptides. The amino acid composition, flavor characteristics, and antioxidant activity were also evaluated. SDS-PAGE analysis showed that the molecular weight of the two peptides was concentrated under 4.1 kDa. The total amino acid contents of the HBMP-1-1 was up to 570.779 mg/g. Leucine, alanine, and glutamicacid were the predominant amino acids in HBMP-1-1 with high nutritional value, and it contained 10.07% β-folding, 46.39% β-turn, and 43.54% random coil structure. The peptide sequences IDDPTDSKPE, LNGKLTGM, ELDEGYVPK, AFQEDPDKF, and FVGKVVDPTQK with molecular weights of 1116.51, 833.45, 1049.51, 1096.49, and 1217.69 Da were detected using LC-MS/MS. The results of the antioxidant activity test showed that separation and purification significantly improved the bioactivity of the protein. The half-inhibition rate of HBMP-1-1 against DPPH, ABTS, and hydroxyl radicals were 0.054, 0.050, and 0.137 mg/mL, respectively. This article provides a scientific basis for clarifying the material basis of horse bone marrow collagen peptides. Also, it provides new approaches and ideas for exploring efficient and safe bone-derived lead compounds and products. [ABSTRACT FROM AUTHOR]

Protein pairs can interact with each other by physical connections through electrostatic forces or hydrophobic effects. Prediction of protein-protein interactions (PPIs) is critical in many biological applications, including protein function identification, drug design, and disease detection. In this paper, we propose a method of combining features for protein representation and PPI prediction directly from protein sequences. First, we utilized 5 protein sequence extractors including amino acid composition, pseudo-amino acid composition, amphiphilic pseudo-amino acid composition, quasi-sequence-order, and dipeptide composition to extract handcrafted features. Next, we applied a natural language processing technique, Word2vec, to generate learned features by embedding protein sequences into a feature space. Finally, a deep neural network architecture was employed for combining two types of features and identifying PPIs. The proposed method was evaluated on the Yeast core, Human, and eight independent datasets. The experimental results show that our method achieved 95.6% of accuracy on Yeast core, 99.2% of accuracy on Human, and 100% of accuracy on eight independent datasets, respectively. In addition, we also made extensive comparisons with other existing prediction methods, and the experimental results demonstrated the superior ability of our proposed method. The datasets and source code of our method can be downloaded at https://github.com/thnhan/DeepCF-PPI.git. [ABSTRACT FROM AUTHOR]

This paper outlines methods used to identify novel antigens for use in the development of serological assays. Specifically, we applied these methods to a neurogenic parasitic nematode of cervids called Parelaphostrongylus tenuis. This parasite is of particular concern in both wild and domestic ungulates as it causes significant neurological signs and definitive diagnosis is only possible post-mortem, necessitating the development of serologic assays for antemortem diagnosis. Proteins extracted from P. tenuis organisms were affinity isolated using antibodies enriched from seropositive moose (Alces alces). The proteins were analyzed using mass spectrometry and liquid chromatography to obtain amino acid sequences that were then cross-referenced to open reading frames predicted from an assembled transcriptome. An antigen of interest was assessed for immunogenic epitopes and subsequently synthesized into 10-mer synthetic overlapping peptides representing these regions. These synthetic peptides were then assessed for reactivity against positive and negative moose sera and demonstrated potential use as a serological assay in diagnostic laboratories. Known negative moose sera revealed significantly lower optical density when compared to the positive samples (p < 0.05). This method serves as a pipeline for the construction of diagnostic assays of pathogens in both human and veterinary medicine. [ABSTRACT FROM AUTHOR]

The Major Histocompatibility Complex (MHC) binds to the derived peptides from pathogens to present them to killer T cells on the cell surface. Developing computational methods for accurate, fast, and explainable peptide-MHC binding prediction can facilitate immunotherapies and vaccine development. Various deep learning-based methods rely on separate feature extraction from the peptide and MHC sequences and ignore their pairwise binding information. This paper develops a capsule neural network-based method to efficiently capture the peptide-MHC complex features to predict the peptide-MHC class I binding. Various evaluations confirmed our method outperformance over the alternative methods, while it can provide accurate prediction over less available data. Moreover, for providing precise insights into the results, we explored the essential features that contributed to the prediction. Since the simulation results demonstrated consistency with the experimental studies, we concluded that our method can be utilized for the accurate, rapid, and interpretable peptide-MHC binding prediction to assist biological therapies. A capsule neural network-based method captures pairwise information to accurately predict MHC-I and peptide binding. The comprehensive test of the model indicated both its superiority in performance and interpretability. [ABSTRACT FROM AUTHOR]

Protein structure prediction (PSP) has achieved significant progress lately via prediction of inter-residue distances using deep learning models and exploitation of the predictions during conformational search. In this context, prediction of large inter-residue distances and also prediction of distances between residues separated largely in the protein sequence remain challenging. To deal with these challenges, state-of-the-art inter-residue distance prediction algorithms have used large sets of coevolutionary and non-coevolutionary features. In this paper, we argue that the more the types of features used, the more the kinds of noises introduced and then the deep learning model has to overcome the noises to improve the accuracy of the predictions. Also, multiple features capturing similar underlying characteristics might not necessarily have significantly better cumulative effect. So we scrutinise the feature space to reduce the types of features to be used, but at the same time, we strive to improve the prediction accuracy. Consequently, for inter-residue real distance prediction, in this paper, we propose a deep learning model named scrutinised distance predictor (SDP), which uses only 2 coevolutionary and 3 non-coevolutionary features. On several sets of benchmark proteins, our proposed SDP method improves mean Local Distance Different Test (LDDT) scores at least by 10% over existing state-of-the-art methods. The SDP program along with its data is available from the website https://gitlab.com/mahnewton/sdp. [ABSTRACT FROM AUTHOR]

Drug discovery for a protein target is a laborious and costly process. Deep learning (DL) methods have been applied to drug discovery and successfully generated novel molecular structures, and they can substantially reduce development time and costs. However, most of them rely on prior knowledge, either by drawing on the structure and properties of known molecules to generate similar candidate molecules or extracting information on the binding sites of protein pockets to obtain molecules that can bind to them. In this paper, DeepTarget, an end-to-end DL model, was proposed to generate novel molecules solely relying on the amino acid sequence of the target protein to reduce the heavy reliance on prior knowledge. DeepTarget includes three modules: Amino Acid Sequence Embedding (AASE), Structural Feature Inference (SFI), and Molecule Generation (MG). AASE generates embeddings from the amino acid sequence of the target protein. SFI inferences the potential structural features of the synthesized molecule, and MG seeks to construct the eventual molecule. The validity of the generated molecules was demonstrated by a benchmark platform of molecular generation models. The interaction between the generated molecules and the target proteins was also verified on the basis of two metrics, drug–target affinity and molecular docking. The results of the experiments indicated the efficacy of the model for direct molecule generation solely conditioned on amino acid sequence. [ABSTRACT FROM AUTHOR]

Jiangxi is one of the provinces in China most seriously affected by the haemorrhagic fever with renal syndrome (HFRS) epidemic. The aim of this paper was to systematically explore the HFRS epidemic in Jiangxi from the perspective of Hantavirus (HV) prevalence in rodents and humans and virus molecular characteristics. Individual information on all HFRS cases in Jiangxi from 2005 to 2021 was extracted from the China Information System for Disease Control and Prevention. All S and M fragment sequences of the Seoul virus and Hantan virus strains uploaded by Jiangxi and its neighbouring provinces and some representative sequences from provinces in China or some countries of Southeast Asia with the highest HV prevalence were retrieved and downloaded from NCBI GenBank. Periodogram and spatial autocorrelation were adopted for temporal periodicity and spatial clustering analysis of the HFRS epidemic. Joinpoint regression was utilized to explore the changing morbidity trend patterns of HFRS. Multiple sequence alignment and amino acid variation analysis were used to explore the homology and variation of strain prevalence in Jiangxi. Based on monthly morbidity time series, the periodogram analysis showed that the prevalence of HFRS had periodicities of 6 months and 12 months. Spatial autocorrelation analysis showed that HFRS distributed in Jiangxi was not random, with a "High-High" clustering area around Gaoan County. HFRS morbidity among the 0 ~ 15-year-old and ~ 61-year-old or older populations in Jiangxi increased significantly during the period of 2008–2015. Generally, HFRS morbidity was significantly positively correlated with the index of rat with virus (IRV) (r = 0.742) in the counties surrounding Gaoan from 2005 to 2019. HTNV strains in Jiangxi were in one independent branch, while the SEOV strains in Jiangxi were relatively more diverse. Both the YW89-15 and GAW30/2021 strains shared approximately 85% nucleotide homology and approximately 97% amino acid homology with their corresponding standard strains and vaccine strains. GAW30/2021 and YW89-15 had some amino acid site variations in nucleoprotein, glycoprotein precursor and RNA-dependent polymerase with their corresponding vaccine strains Z10 (HTNV) and Z37 (SEOV). The HFRS epidemic in Jiangxi has obvious temporal periodicity and spatial clustering, and the significant increase in the non-Immunization Expanded Program (EPI) targeted population (children and elderly) suggests that HFRS vaccination in this population needs to be considered. Although applying the EPI played a certain role in curbing the incidence of HFRS in Jiangxi from the perspective of ecological epidemiology, HTNV and SEOV strains prevalent in Jiangxi have some amino acid site variations compared to their corresponding vaccine strains, suggesting that HV variation needs to be continuously monitored in the future to observe vaccine protective efficiency. [ABSTRACT FROM AUTHOR]

Multiple sequence alignment approaches refer to algorithmic solutions for the alignment of biological sequences. Since multiple sequence alignment has exponential time complexity when a dynamic programming approach is applied, a substantial number of parallel computing approaches have been implemented in the last two decades to improve their performance. In this paper, we present a systematic literature review of parallel computing approaches applied to multiple sequence alignment algorithms for proteins, published in the open literature from 1988 to 2022; we extracted articles from four scientific databases: ACM Digital Library, IEEE Xplore, Science Direct and SpringerLink, and four journals: Bioinformatics, PLOS Computational Biology, PLOS ONE, and Scientific Reports. Additionally, in order to cover other potential databases and journals, we performed a transversal search through Google Scholar. We conducted a selection process that yielded 106 research articles; then, we analyzed these articles and defined a classification framework. Additionally, we point out some directions and trends for parallel computing approaches for multiple sequence alignment, as well as some unsolved problems. [ABSTRACT FROM AUTHOR]

Proteomics is a field dedicated to the analysis of proteins in cells, tissues, and organisms, aiming to gain insights into their structures, functions, and interactions. A crucial aspect within proteomics is protein family prediction, which involves identifying evolutionary relationships between proteins by examining similarities in their sequences or structures. This approach holds great potential for applications such as drug discovery and functional annotation of genomes. However, current methods for protein family prediction have certain limitations, including limited accuracy, high false positive rates, and challenges in handling large datasets. Some methods also rely on homologous sequences or protein structures, which introduce biases and restrict their applicability to specific protein families or structures. To overcome these limitations, researchers have turned to machine learning (ML) approaches that can identify connections between protein features and simplify complex high-dimensional datasets. This paper presents a comprehensive survey of articles that employ various ML techniques for predicting protein families. The primary objective is to explore and improve ML techniques specifically for protein family prediction, thus advancing future research in the field. Through qualitative and quantitative analyses of ML techniques, it is evident that multiple methods utilizing a range of classifiers have been applied for protein family prediction. However, there has been limited focus on developing novel classifiers for protein family classification, highlighting the urgent need for improved approaches in this area. By addressing these challenges, this research aims to enhance the accuracy and effectiveness of protein family prediction, ultimately facilitating advancements in proteomics and its diverse applications. [ABSTRACT FROM AUTHOR]

Bioinformatics is an interdisciplinary field that applies trending techniques in information technology, mathematics, and statistics in studying large biological data. Bioinformatics involves several computational techniques such as sequence and structural alignment, data mining, macromolecular geometry, prediction of protein structure and gene finding. Protein structure and sequence analysis are vital to the understanding of cellular processes. Understanding cellular processes contributes to the development of drugs for metabolic pathways. Protein sequence alignment is concerned with identifying the similarities and the relationships among different protein structures. In this paper, we target two well-known protein sequence alignment algorithms, the Needleman–Wunsch and the Smith–Waterman algorithms. These two algorithms are computationally expensive which hinders their applicability for large data sets. Thus, we propose a hybrid parallel approach that combines the capabilities of multi-core CPUs and the power of contemporary GPUs, and significantly speeds up the execution of the target algorithms. The validity of our approach is tested on real protein sequences. Moreover, the scalability of the approach is verified on randomly generated sequences with predefined similarity levels. The results showed that the proposed hybrid approach was up to 242 times faster than the sequential approach. [ABSTRACT FROM AUTHOR]

Three-dimensional protein structure prediction is one of the major challenges in bioinformatics. According to recent research findings, real-valued distance prediction plays a vital role in determining the unique three-dimensional protein structure. This paper proposes a novel methodology involving a deep residual dense network (DRDN) for predicting protein real-valued distance. The features extracted from the given query protein sequence and its corresponding homologous sequences are used for training the model. Multi-aligned homologous sequences for each query protein sequence are retrieved from five different databases using DeepMSA, HHblits, and HITS_PR_HHblits methods. The proposed method yielded outcomes of 3.89, 0.23, 0.45, and 0.63, respectively, corresponding to the evaluation metrics such as Absolute Error, Relative Error, High-accuracy Pairwise Distance Test (PDA), and Pairwise Distance Test (PDT). Further, the contact map is computed based on CASP criteria by converting the predicted real-valued distance, and it is evaluated using the precision metric. It is observed that precision of long-range top L/5 contact prediction on the CASP13 dataset by the proposed method, RaptorX, Zhang, trRosetta, JinboXu & JinLu, and Deepdist are 0.834, 0.657, 0.70, 0.785, 0.786, and 0.812, respectively. Also, Top-L/5 contact prediction on the CASP14 dataset evaluated using average precision resulted in 0.847, 0.707, 0.752, 0.783, 0.792, 0.817, and 0.825 respectively, corresponding to the proposed method, Zhang, RaptorX, trRosetta, Deepdist, JinboXu & JinLu, and Alphafold2. [ABSTRACT FROM AUTHOR]

One of the most popular measures in the analysis of protein sequence evolution is the ratio of nonsynonymous distance (dN) to synonymous distance (dS). Under the assumption that synonymous substitutions in the coding region are selectively neutral, the dN/dS ratio can be used to statistically detect the adaptive evolution (or purifying selection) if dN/dS > 1 (or dN/dS < 1) significantly. However, due to strong structural constraints and/or variable functional constraints imposed on amino acid sites, most encoding genes in most species have demonstrated dN/dS < 1. Consequently, the statistical power for testing dN/dS = 1 may be insufficient to distinguish between different selection modes. In this paper, we propose a more powerful test, called dN/dS-H, in which a new parameter H, a relative measure of rate variation among sites, was introduced. Given the condition of strong purifying selections at some sites, the dN/dS-H model predicts dN/dS = 1-H for neutral evolution, dN/dS < 1-H for nearly neutral selection, and dN/dS > 1-H for adaptive evolution. The potential of this new method for resolving the neutral-adaptive debates is illustrated by the protein sequence evolution in vertebrates, Drosophila and yeasts, as well as somatic cancer evolution (specialized as the CN/CS-H test). [ABSTRACT FROM AUTHOR]

The most challenging issue in diagnosing and treating neurological disorders is gene identification that causes the disease. Classification of the genes that cause or initiate different genes leading to diseases with neurological disorders like Parkinson's disease, is a grave challenge in biomedical research. Detecting neurological disorders has a significant contribution in genetics, which require the deployment of machine learning methods which are still in its infancy. For exploring protein sequences (genes), computational analysis is a vital technique, since a manual comparison of multiple sequences results in impracticality. It helps to find a gene in the sequence and to combine protein sequences into a class of similar sequence. There are many traditional methods available for detection of Parkinson's disease. However, relatively less comparative work is done on Machine Learning techniques using protein sequences for evaluation of Parkinson's disease. This paper demonstrates the comparison of multiple classification methods to identify Parkinson's disease using hydrophobicity and Amino Acid Composition as feature extraction methods. Classification methods are then combined to propose a 2-level ensemble method based on the false prediction rate. The performance of these methods is evaluated using Precision, Recall, F-Score and ROC curves. Experimental results have demonstrated that Random Forest, SVM, Neural Network (PCANNET) and Naïve Bayes classifiers individually performed best based on their performance metrics under 5-fold cross validation, whereas the proposed method outperforms Random Forest and SVM by 1.96%, NB by 1.1% and PCANNET by 1.68% respectively. Further, statistical analysis has been added to validate the proposed method. [ABSTRACT FROM AUTHOR]

Parkinson's disease (PD) genes identification plays an important role in improving the diagnosis and treatment of the disease. A number of machine learning methods have been proposed to identify disease-related genes, but only few of these methods are adopted for PD. This work puts forth a novel neural network-based ensemble (n-semble) method to identify Parkinson's disease genes. The artificial neural network is trained in a unique way to ensemble the multiple model predictions. The proposed n-semble method is composed of four parts: (1) protein sequences are used to construct feature vectors using physicochemical properties of amino acid; (2) dimensionality reduction is achieved using the t-Distributed Stochastic Neighbor Embedding (t-SNE) method, (3) the Jaccard method is applied to find likely negative samples from unknown (candidate) genes, and (4) gene prediction is performed with n-semble method. The proposed n-semble method has been compared with Smalter's, ProDiGe, PUDI and EPU methods using various evaluation metrics. It has been concluded that the proposed n-semble method outperforms the existing gene identification methods over the other methods and achieves significantly higher precision, recall and F Score of 88.9%, 90.9% and 89.8%, respectively. The obtained results confirm the effectiveness and validity of the proposed framework. [ABSTRACT FROM AUTHOR]

Protein hot spot residues are functional sites in protein–protein interactions. Biological experimental methods are traditionally used to identify hot spot residues, which is laborious and time-consuming. Thus a variety of computational methods were widely used in recent years. Despite the success of computational methods in hot spot identification, most of them are impractical in reality because they can recognize hot spot residues only from known protein–protein interface residues. Therefore, identifying hot spots from whole protein sequence is a meaningful and interesting issue. However, it will bring extreme imbalance between positive and negative samples. Hot spot residues only account for about 1–2% of whole protein sequences. To address the issue, this paper proposes a two-step ensemble model for identifying hot spot residues from extremely unbalanced data set. The model is composed of 134 classifiers constructed by base KNN and SVM. Compared to the previous methods, our model yields good performance with an F1 score of 0.593 on the BID test set. Furthermore, to validate the robustness of our model, it was tested on other three independent test sets and also achieved good predictions. More importantly, the performance of our model tested on unbalanced data set is comparable with other methods tested on balanced hot spot data set. [ABSTRACT FROM AUTHOR]

In biological research, alignment of protein sequences by computer is often needed to find similarities between them. Although results can be computed in a reasonable time for alignment of two sequences, it is still very central processing unit (CPU) time-consuming when solving massive sequences alignment problems such as protein database search. In this paper, an optimized protein database search method is presented and tested with Swiss-Prot database on graphic processing unit (GPU) devices, and further, the power of CPU multi-threaded computing is also involved to realize a GPU-based heterogeneous parallelism. In our proposed method, a hybrid alignment approach is implemented by combining Smith-Waterman local alignment algorithm with Needleman-Wunsch global alignment algorithm, and parallel database search is realized with compute unified device architecture (CUDA) parallel computing framework. In the experiment, the algorithm is tested on a lower-end and a higher-end personal computers equipped with GeForce GTX 750 Ti and GeForce GTX 1070 graphics cards, respectively. The results show that the parallel method proposed in this paper can achieve a speedup up to 138.86 times over the serial counterpart, improving efficiency and convenience of protein database search significantly. [ABSTRACT FROM AUTHOR]

Protein Secondary Structure (PSS) prediction emerges as a hot topic in the area of bioinformatics.PSS helps to predict the tertiary structure and helps to understand its structures, which in turn helps to design various drugs. The existing PSS prediction techniques are capable of achieving Q3 accuracy of nearly 80% and have no improvement till now. In this paper, we propose a novel technique that uses amino acid sequences alone as an input feature and the respected feature vector matrix is given through the deep learning model (DLM) for PSS prediction. We use OneHotEncoding and LSTM (Long Short Term Memory) technique to forecast PSS that helps to achieve more accuracy. The OneHotEncoder is used to extract the local contexts of amino-acid sequences, and LSTM captures the long-distance interdependencies among aminoacids. The overall implementation is carried in MATLAB 2020a. The performance of this model is evaluated in terms of precision, recall, F1-score, and by the percentage of accuracy of both Q3 and Q8 secondary structure predictions. The Q3 structure of the proposed scheme gained 86.54, 85.2 and 85.7%CullPDB, CASP10, and CASP11 and the accuracy of Q8 is 77.8, 72.5 and 74.9% on the benchmark datasets such as CullPDB, CASP10, and CASP11 respectively. Some of the advantages of the proposed scheme are minimize the computation time and achieves better accuracy when compared to the other baseline models in the prediction of PSS. [ABSTRACT FROM AUTHOR]

How we choose to represent our data has a fundamental impact on our ability to subsequently extract information from them. Machine learning promises to automatically determine efficient representations from large unstructured datasets, such as those arising in biology. However, empirical evidence suggests that seemingly minor changes to these machine learning models yield drastically different data representations that result in different biological interpretations of data. This begs the question of what even constitutes the most meaningful representation. Here, we approach this question for representations of protein sequences, which have received considerable attention in the recent literature. We explore two key contexts in which representations naturally arise: transfer learning and interpretable learning. In the first context, we demonstrate that several contemporary practices yield suboptimal performance, and in the latter we demonstrate that taking representation geometry into account significantly improves interpretability and lets the models reveal biological information that is otherwise obscured. "Representation learning plays an increasing role in protein sequence analysis. This paper seeks to clarify how to ensure that such representations are meaningful, proposing best practices both for the choice of methods and the subsequence analysis [ABSTRACT FROM AUTHOR]

Lysine malonylation is one of the most important post-translational modifications (PTMs). It affects the functionality of cells. Malonylation site prediction in proteins can unfold the mechanisms of cellular functionalities. Experimental methods are one of the due prediction approaches. But they are typically costly and time-consuming to implement. Recently, methods based on machine-learning solutions have been proposed to tackle this problem. Such practices have been shown to reduce costs and time complexities and increase accuracy. However, these approaches also have specific shortcomings, including inappropriate feature extraction out of protein sequences, high-dimensional features, and inefficient underlying classifiers. A machine learning-based method is proposed in this paper to cope with these problems. In the proposed approach, seven different features are extracted. Then, the extracted features are combined, ranked based on the Fisher's score (F-score), and the most efficient ones are selected. Afterward, malonylation sites are predicted using various classifiers. Simulation results show that the proposed method has acceptable performance compared with some state-of-the-art approaches. In addition, the XGBOOST classifier, founded on extracted features such as TFCRF, has a higher prediction rate than the other methods. The codes are publicly available at: https://github.com/jimy2020/Malonylation-site-prediction [ABSTRACT FROM AUTHOR]

Numerous protein sequences are evolving with advances in high-throughput technologies and genomic projects. Functional characterization of the variable length unknown protein sequence (VLUPS) provides valuable insights into the disease diagnosis and drug design. In this paper, subcellular localization-based deep learning framework has been proposed for the functional characterization of VLUPS using ensemble of shallow and deep features. Pseudo-amino acid composition and pseudo-position specific scoring matrix features of protein sequences are established as shallow feature. Deep feature and Prot_Seq of the raw protein sequences are extracted through one-hot encoding and convolutional neural network. Next, shallow and deep features are embedded as hybrid feature vector while preserving the sequence-order-information and protein residue properties. To handle the skewed and variable length protein sequence data, ensemble deep learning model has been formed using feature subset ensemble and long short-term memory. The proposed model is trained and tested using subsets of shallow, deep, and hybrid features of Gram-positive (G+) and Gram-negative (G-) datasets with 5-fold cross-validation. Accuracy attained by the model is 96.77% with known G+ dataset and 98.32% using G- dataset. Achieved accuracy for VLUPS is 79.29% with the G+ dataset and 76.84% for G- dataset. [ABSTRACT FROM AUTHOR]

The diversification of the characteristic sequences of anti-cancer peptides has imposed difficulties on research. To effectively predict new anti-cancer peptides, this paper proposes a more suitable feature grouping sequence and spatial dimension-integrated network algorithm for anti-cancer peptide sequence prediction called GRCI-Net. The main process is as follows: First, we implemented the fusion reduction of binary structure features and K-mer sparse matrix features through principal component analysis and generated a set of new features; second, we constructed a new bidirectional long- and short-term memory network. We used traditional convolution and dilated convolution to acquire features in the spatial dimension using the memory network's grouping sequence model, which is designed to better handle the diversification of anti-cancer peptide feature sequences and to fully learn the contextual information between features. Finally, we achieved the fusion of grouping sequence features and spatial dimensional integration features through two sets of dense network layers, achieved the prediction of anti-cancer peptides through the sigmoid function, and verified the approach with two public datasets, ACP740 (accuracy reached 0.8230) and ACP240 (accuracy reached 0.8750). The following is a link to the model code and datasets mentioned in this article: https://github.com/ YouHongfeng101/ACP-DL. [ABSTRACT FROM AUTHOR]

Many pore-forming proteins originating from pathogenic bacteria are toxic against agricultural pests. They are the key ingredients in several pesticidal products for agricultural use, including transgenic crops. There is an urgent need to identify novel pore-forming proteins to combat development of resistance in pests to existing products, and to develop products that are effective against a broader range of pests. Existing computational methodologies to search for these proteins rely on sequence homology-based approaches. These approaches are based on similarities between protein sequences, and thus are limited in their usefulness for discovering novel proteins. In this paper, we outline a novel deep learning model trained on pore-forming proteins from the public domain. We compare different ways of encoding protein information during training, and contrast it with traditional approaches. We show that our model is capable of identifying known pore formers with no sequence similarity to the proteins used to train the model, and therefore holds promise for identifying novel pore formers. [ABSTRACT FROM AUTHOR]

Deep learning techniques are found very useful to classify sequential data in recent times. The protein sequences belong to the functional classes based on the structure of their sequences. The annotation task of protein sequences into corresponding functional classes is multi-label in nature. The primary structure of protein contains a notable amount of vast data compared to the other secondary, tertiary, and quaternary structures. The clustering-based techniques require expert domain knowledge from the extensive data samples. Traditional methods use the n-gram features of amino acids while ignoring the relationship of motifs and amino acid sequence. This paper proposes an efficient method to classify the proteins into their functional classes using a convolution neural network based on heuristic rules. The proposed approach works on the primary structure of protein sequences which considers the relationship among motifs and amino acids. The proposed approach also takes into account the amino acid locations in the protein sequence. The proposed approach considers the affinity information between amino acids and motifs. Along with achieving high performance in the classification of protein sequences, we propose a heuristic approach to improve the precision and recall of the individual functional classes. The proposed heuristic approach improves the performance and handles the data imbalance problem. The proposed approach is compared with other competitive approaches, and our approach provides better performance metrics in terms of precision, recall, AUC, and subset accuracy. The greatest challenge with multi-label classification is to handle the data imbalance, which appears due to variance in frequencies of the labels in the data. This data imbalance is dealt with weight modulation in the loss function to influence the learning process. [ABSTRACT FROM AUTHOR]

The rapid spread of coronavirus disease (COVID-19) has become a worldwide pandemic and affected more than 15 million patients reported in 27 countries. Therefore, the computational biology carrying this virus that correlates with the human population urgently needs to be understood. In this paper, the classification of the human protein sequences of COVID-19, according to the country, is presented based on machine learning algorithms. The proposed model is based on distinguishing 9238 sequences using three stages, including data preprocessing, data labeling, and classification. In the first stage, data preprocessing's function converts the amino acids of COVID-19 protein sequences into eight groups of numbers based on the amino acids' volume and dipole. It is based on the conjoint triad (CT) method. In the second stage, there are two methods for labeling data from 27 countries from 0 to 26. The first method is based on selecting one number for each country according to the code numbers of countries, while the second method is based on binary elements for each country. According to their countries, machine learning algorithms are used to discover different COVID-19 protein sequences in the last stage. The obtained results demonstrate 100% accuracy, 100% sensitivity, and 90% specificity via the country-based binary labeling method with a linear support vector machine (SVM) classifier. Furthermore, with significant infection data, the USA is more prone to correct classification compared to other countries with fewer data. The unbalanced data for COVID-19 protein sequences is considered a major issue, especially as the US's available data represents 76% of a total of 9238 sequences. The proposed model will act as a prediction tool for the COVID-19 protein sequences in different countries. [ABSTRACT FROM AUTHOR]

RNA-binding proteins play an important role in the biological process. However, the traditional experiment technology to predict RNA-binding residues is time-consuming and expensive, so the development of an effective computational approach can provide a strategy to solve this issue. In recent years, most of the computational approaches are constructed on protein sequence information, but the protein structure has not been considered. In this paper, we use a novel computational model of RNA-binding residues prediction, using protein sequence and structure information. Our hybrid features are encoded by local sequence and structure feature extraction models. Our predictor is built by employing the Granular Multiple Kernel Support Vector Machine with Repetitive Under-sampling (GMKSVM-RU). In order to evaluate our method, we use fivefold cross-validation on the RBP129, our method achieves better experimental performance with MCC of 0.3367 and accuracy of 88.84%. In order to further evaluate our model, an independent data set (RBP60) is employed, and our method achieves MCC of 0.3921 and accuracy of 87.52%. Above results demonstrate that integrating sequence and structure information is beneficial to improve the prediction ability of RNA-binding residues. [ABSTRACT FROM AUTHOR]

This paper presents genetic data on the full genome analysis of A/chicken/Tajikistan/2379/2018 H9N2 influenza virus isolated in September 2018 from chicken pathological material received from poultry farms of the Republic of Tajikistan and subtyped as H9N2 by serological and molecular methods. According to the results of hemagglutinin gene sequencing, the amino acid sequence of the cleavage site was RSSR/GLF, which is typical for low-virulent avian influenza virus. Phylogenetic analysis of the nucleotide sequence of a hemagglutinin gene fragment (nt 1-1539 of the open reading frame) showed that the A/chicken/Tajikistan/2379/2018 H9N2 isolate belongs to the Y280 genetic group of low-virulent A/H9 influenza virus, which is widespread in Southeast Asia. The complete nucleotide sequence of the viral genome was determined. Comparative analysis of all genomic segments revealed that the A/chicken/Tajikistan/2379/2018 H9N2 virus is closely related to an A/H9 influenza virus isolated in the Far East of the Russian Federation in 2018. Genetic similarity (97.1-99% identity in four out of eight viral genes) was found to isolates of an H7N9 subtype virus recovered in the Inner Mongolia and Hebei regions of China in 2017. According to the analysis of the predicted amino acid sequence of the studied isolate, the positions of some molecular markers indicate possible adaptation of the virus to mammals. Further genetic analysis showed that this virus belongs to genotype G57. [ABSTRACT FROM AUTHOR]

The rapid spread of multi-drug resistant microbes has lead researchers to discover natural alternative remedies such as antimicrobial peptides (AMPs). In the first line of defense, AMPs display a broad spectrum of potent activity against multi-resistant pathogenic bacteria, viruses, fungi, and even cancer. AMPs can be further characterised into families according to amino acid composition, secondary structure, and function. However, despite recent advancements in rapid computational methods for AMP prediction from various mammalian, aquatic, and terrestrial species, there is limited information regarding their presence, functional roles, and family type from marine macroalgae. In this paper, we present a promising two-tier ensemble of heterogeneous machine learning models that integrates seven well-known machine learning classifiers to predict AMPs from macroalgae. The first tier of the ensemble consists of a suite of binary classifiers that identify AMPs from protein sequence data which are then forwarded to a second-tier multi-class ensemble to characterise their functional family type. The two-tier ensemble was successfully used to identify 39 putative AMP sequences in 12 macroalgae species from three different phyla groups. The approach we describe is not limited to AMPs and can also be applied to search sequence data for other types of proteins. [ABSTRACT FROM AUTHOR]

A gene encoding phzR was isolated from a phenazine-producing bacterium Pseudomonas aeruginosa 2016NX1. This paper provided the full-length cDNA encoding phzR (GenBank Accession no., MW143078). The cDNA of the phzR contained an open reading frame (ORF) of 714 bp. The potential regulatory elements were predicted in the phzR promoter region. The deduced amino acid sequence of P. aeruginosa phzR showed significant homology to the known phzRs from different organisms. Gene overexpression analysis showed that the phenazine content was improved (44.39%) in comparison to wild-type 2016NX1. [ABSTRACT FROM AUTHOR]

In the digital era, massive growth in Wireless Multimedia Sensor Networks (WMSNs) can be used in various applications such as environmental and industrial monitoring, disaster management. WMSN comprises many low-power camera sensor nodes that may have overlapping field of view for enhancing the accuracy of the monitored environment. Hence, huge volume of redundant data which make it inefficient in terms of network lifetime and energy. It needs to establish a tremendous suitable approach to communicate images over WMSN that handle critical factors such as maximize QoS and minimize energy consumption efficiently. There is a need for energy efficient image processing and transmission over WMSN. So aggregating multi-view images using cluster based distributed routing approaches with QoS constraints have received significant research interest. The Distributed Two-Layer Cluster framework is used in this paper for transmitting aggregated data by local cluster head (LCH) and master cluster head from various clusters to base station in multi-hop basis. This aggregated data are generated from multi-view images captured by correlated camera sensor nodes of local cluster (LC) and master cluster (MC) using first level data aggregation (FLDA) and second level data aggregation (SLDA) algorithms respectively. In FLDA, less complex novel protein sequence alignment based patch matching algorithm is used to reduce inter-view redundancy of multi-view images. Then, this first level aggregated data transmission of LC is reduced using Varying Bit Encoding based on Arithmetic Operations algorithm by combining multi-view images together and achieves its compression ratio of about 2.54. In SLDA, Higher-Order SVD is used to aggregate FLDA data from LCH for reducing MC transmission rate and achieves its compression ratio of about 9.1. The comparison of network performance results with existing cluster based routing algorithms exhibit the improvement of the proposed system in terms of performance metrices such as energy consumption, packet delivery ratio, end-to-end delay and network lifetime. This results show that PSA based TLDA performs better and average energy consumption of processing and transmitting multi-view images per round is considerably minimized to 0.320 J. Thus the proposed system prolongs the network lifetime by 35%, 6% when compared with DFRP and GRAD-CORR based TLDA in terms of number of rounds. [ABSTRACT FROM AUTHOR]

Pectin methylesterase (PME) is a type of protein encoded by a multi-gene family and participates in seed germination, fruit ripening and stress response. To further study the function of the PME gene family in potato, this paper screened and identified potato PME gene family by bioinformatics methods, and analysed the structure, physicochemical properties, conserved domains and evolutionary relationships of the gene sequences. The results showed that the identified 54 potato PME genes can be divided into Group I (only PME domain) and Group II (both PME domain and PMEI domain). The phylogenetic tree constructed by the maximum likelihood method indicated that potato PME genes consisted of five subfamilies. The protein sequences of potato PME genes were compared with clustalx2.1 software. Most of these sequences were identified to have five conserved structural regions including Gx Yx E (Region I), QAVAxR (Region II), QDTL (Region III), GxxDFIFG (Region IV) and YLGRxWx (Region V). Conserved motifs of potato PME amino acid sequences were analysed by MEME online software. Motif1 contains three of the five conserved structural regions and motif2 and motif8 each contain one, indicating that these sequences are more conservative. The structure of 54 potato PME gene sequences was analysed by the GSDS website. It was found that there were only two parts, exon or coding sequence (CDS) between untranslated regions (UTRs), without intron structures in these sequences, indicating that the structure is relatively simple. It will provide a reference for the study on the function of potato PME gene. [ABSTRACT FROM AUTHOR]

The paper presents qualitative and quantitative composition of the nucleotide sequences of the 5'‑region of the first subunit of the mitochondrial cytochrome oxidase (COI) gene (decoded in the framework of the International DNA Barcoding Project) and the variability of the corresponding amino acid sequences in the genus Jordanita Verity, 1946. The number of variable positions in the COI region (219 amino acid residues) is 14.2% that significantly exceeds the data for other Lepidoptera. Thirty one amino acid variable positions were revealed, and two of them are localized near the active site of the enzyme. [ABSTRACT FROM AUTHOR]

Cellobiose is one of the most abundant carbohydrates available in nature which can be used as biofuel in various applications such as food industry, energy production, paper production, etc. with no harm to the environment. One way for a safe decomposition the cellobiose is enzymatic hydrolysis. Cellobiohydrolase enzyme, which is naturally present in some yeasts and bacteria, is capable of decomposing carbohydrates. Because of its low production in its original organism and also high volumes of requirements to this enzyme for industrial usage, there is strong desired to mass-produce of this enzyme using biotechnological approaches. In this study, several signal peptide sequences with Lactococcus originality, with the aim of binding to the cellobiohydrolase gene, were evaluated. In this regard, signalP server, a valid and accurate online tool, was used to determine the most important details including N-terminal (n), hydrophobic (h) and carboxy-terminal (c) regions of signal peptides and their probability. Thereafter, Portparam and Solpro online tools were used to investigate the physico-chemical properties of each signal peptide. Finally, the best peptide signal with the best specificity and the highest D-score was selected for binding to the cellobiohydrolase gene sequence aimed at expression in the Gram-positive bacterium Lactococcus lactis. Final frame of target gen was synthetized and ligated in pBU003 expression vector using double digestion by SalI and XhoI restriction enzymes. Recombinant expression vector was transferred to MC1061 for replication and then transferred into the MG1363 as expressing strain of Lacticoccus lactis. Recombinant proteins were purified from M17 medium using the Ni-NTA Agarose column. Their quantification and qualification examined through Bradford assay and 12% SDS-PAGE respectively. Phosphoric acid-treated cotton as a substrate was used to determine the Ce16B cellobiohydrolase activity at 450 nm absorbance. In silico investigating the signal peptides have led to the choice of the USP45 signal peptide as a powerful secretory signal. Recombinant proteins were successfully expressed in Lactococcus lactis. The concentration of each recombinant protein was determined 0.7 g/l (R2 = 0.989). In vitro assessment of enzymatic activity or recombinant proteins on PC showed 1.89 U (R2: 9941). [ABSTRACT FROM AUTHOR]

Many domains have a stake in the development of reliable systems for automatic protein classification. Of particular interest in recent studies of automatic protein classification is the exploration of new methods for extracting features from a protein that enhance classification for specific problems. These methods have proven very useful in one or two domains, but they have failed to generalize well across several domains (i.e. classification problems). In this paper, we evaluate several feature extraction approaches for representing proteins with the aim of sequence-based protein classification. Several protein representations are evaluated, those starting from: the position specific scoring matrix (PSSM) of the proteins; the amino-acid sequence; a matrix representation of the protein, of dimension (length of the protein) ×20, obtained using the substitution matrices for representing each amino-acid as a vector. A valuable result is that a texture descriptor can be extracted from the PSSM protein representation which improves the performance of standard descriptors based on the PSSM representation. Experimentally, we develop our systems by comparing several protein descriptors on nine different datasets. Each descriptor is used to train a support vector machine (SVM) or an ensemble of SVM. Although different stand-alone descriptors work well on some datasets (but not on others), we have discovered that fusion among classifiers trained using different descriptors obtains a good performance across all the tested datasets. Matlab code/Datasets used in the proposed paper are available at [ABSTRACT FROM AUTHOR]