Predicting protein phosphorylation sites in soybean using interpretable deep tabular learning network.

Phosphorylation of proteins is one of the most significant post-translational modifications (PTMs) and plays a crucial role in plant functionality due to its impact on signaling, gene expression, enzyme kinetics, protein stability and interactions. Accurate prediction of plant phosphorylation sites (p-sites) is vital as abnormal regulation of phosphorylation usually leads to plant diseases. However, current experimental methods for PTM prediction suffers from high-computational cost and are error-prone. The present study develops machine learning-based prediction techniques, including a high-performance interpretable deep tabular learning network (TabNet) to improve the prediction of protein p-sites in soybean. Moreover, we use a hybrid feature set of sequential-based features, physicochemical properties and position-specific scoring matrices to predict serine (Ser/S), threonine (Thr/T) and tyrosine (Tyr/Y) p-sites in soybean for the first time. The experimentally verified p-sites data of soybean proteins are collected from the eukaryotic phosphorylation sites database and database post-translational modification. We then remove the redundant set of positive and negative samples by dropping protein sequences with >40% similarity. It is found that the developed techniques perform >70% in terms of accuracy. The results demonstrate that the TabNet model is the best performing classifier using hybrid features and with window size of 13, resulted in 78.96 and 77.24% sensitivity and specificity, respectively. The results indicate that the TabNet method has advantages in terms of high-performance and interpretability. The proposed technique can automatically analyze the data without any measurement errors and any human intervention. Furthermore, it can be used to predict putative protein p-sites in plants effectively. The collected dataset and source code are publicly deposited at https://github.com/Elham-khalili/Soybean-P-sites-Prediction.

Machine learning-based approaches for ubiquitination site prediction in human proteins.

Protein ubiquitination is a critical post-translational modification (PTMs) involved in numerous cellular processes. Identifying ubiquitination sites (Ubi-sites) on proteins offers valuable insights into their function and regulatory mechanisms. Due to the cost- and time-consuming nature of traditional approaches for Ubi-site detection, there has been a growing interest in leveraging artificial intelligence for computer-aided Ubi-site prediction. In this study, we collected experimentally verified Ubi-sites of human proteins from the dbPTM database, then conducted comprehensive state-of-the art computational methods along with standard evaluation metrics and a proper validation strategy for Ubi-site prediction. We presented the effectiveness of our framework by comparing ten machine learning (ML) based approaches in three different categories: feature-based conventional ML methods, end-to-end sequence-based deep learning (DL) techniques, and hybrid feature-based DL models. Our results revealed that DL approaches outperformed the classical ML methods, achieving a 0.902 F1-score, 0.8198 accuracy, 0.8786 precision, and 0.9147 recall as the best performance for a DL model using both raw amino acid sequences and hand-crafted features. Interestingly, our experimental results disclosed that the performance of DL methods had a positive correlation with the length of amino acid fragments, suggesting that utilizing the entire sequence can lead to more accurate predictions in future research endeavors. Additionally, we developed a meticulously curated benchmark for Ubi-site prediction in human proteins. This benchmark serves as a valuable resource for future studies, enabling fair and accurate comparisons between different methods. Overall, our work highlights the potential of ML, particularly DL techniques, in predicting Ubi-sites and furthering our knowledge of protein regulation through ubiquitination in cells.

Thrombosis in COVID-19 infection: Role of platelet activation-mediated immunity.

BACKGROUND: Thrombosis plays an important role in the Coronavrus Disease 2019 (COVID-19) infection-related complications such as acute respiratory distress syndrome and myocardial infarction. Multiple factors such as oxygen demand injuries, endothelial cells injury related to infection, and plaque formation. MAIN BODY: Platelets obtained from the patients may have severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) RNA, showing that the increased activation potential recommends platelet can be hyper-activated in severely ill SARS-CoV-2 cases. Platelets contain multiple receptors that interact with specific ligands. Pathogen's receptors such as Toll-like receptors (TLRs), NOD-like receptor, C-type lectin receptor family, glycoprotein (GP) such as GPαIIbß3 and GPIbα which allow pathogens to interact with platelets. Platelet TLRs and NOD2 are involved in platelet activation and thrombosis. Accordingly, TLRs are critical receptors that could recognize various endogenous damage-associated molecular patterns and exogenous pathogen-associated molecular patterns (PAMPs). TLRs are considered as important components in the activation of innate immunity response against pathogenic and non-pathogenic components like damaged tissues. TLRs-1,-2,-4,-6,-7 expression on or within platelets has been reported previously. Various PAMPs were indicated to be capable of binding to platelet-TLRs and inducing both the activation and promotion of downstream proinflammatory signaling cascade. CONCLUSION: It is possible that the increased TLRs expression and TLR-mediated platelets activation during COVID-19 may enhance vascular and coronary thrombosis. It may be hypothesized using TLRs antagonist and monoclonal antibody against P-selectin, as the marker of leukocyte recruitment and platelet activation, besides viral therapy provide therapeutic advances in fighting against the thrombosis related complications in COVID-19.

Association of lymphotoxin-alpha gene polymorphisms (rs909253, rs1800683 and rs2229094) and risk of large-artery atherosclerosis stroke in Iranian population.

BACKGROUND: Lymphotoxin-alpha (LTA), a proinflammatory cytokine, is significantly associated with the progression of atherosclerosis as an independent hazard factor for stroke. According to new genetic studies, polymorphisms in the LTA gene that influence its expression or biological function may play a role in the progress of stroke; thus, the present case-control study investigated LTA gene polymorphisms (rs909253, rs1800683 and rs2229094) and the risk of large artery atherosclerosis stroke (LAA) in an Iranian population. METHODS: For 211 large artery atherosclerosis patients and 186 ischemic stroke-free controls, genotypes were determined using the tetra-primer amplification-refractory mutation system polymerase chain reaction method. Linkage disequilibrium and estimated haplotypes were analyzed using SNP Analyzer 2 software. The strength of the link between LTA gene polymorphisms (rs1800683, rs909253, and rs2229094) and the risk of stroke was determined using conditional logistic regression. RESULTS: Analysis revealed that the patterns of the rs1800683, rs909253 and rs2229094 genotypes showed no significant difference between the LAA and control group, although the distribution of the GAT (rs1800683G, rs909253A and rs2229094T) haplotype was significantly higher in the control group (odds ratio = 0.707, 95% confidence interval = 0.53-0.942, p = 0.0355). CONCLUSIONS: Our results indicate that the GAT haplotype in LTA gene is associated with a decreased risk of LAA incidence in a northeastern Iranian population.

Thromboxane A synthase 1 gene expression and promotor haplotypes are associated with risk of large artery-atherosclerosis stroke in Iranian population.

Large artery atherosclerosis (LAA) is known as an important cause of ischemic stroke (IS), which is a multifactorial disorder. Many candidate genes have been proposed for IS like (TBXAS1) that plays a significant role in LAA stroke pathogenesis. This is the first study on the evaluation of the association of the five single-nucleotide polymorphisms (SNPs) in TBXAS1 promoter region and the level of TBXAS1 transcript with large-artery atherosclerosis stroke. Five SNPs in TBXAS1 genes were investigated in 248 patients with large-artery atherosclerosis stroke and 199 healthy controls in Iranian population in this case-control study through using the high-resolution melting assay. In addition, the relationships between the selected SNPs with alteration of TBXAS1 gene expressions were investigated in terms of blood platelets through the reverse transcription-quantitative polymerase chain reaction. Multivariate logistic analysis with adjustments indicated that rs10256282CC, rs10237429CC, and rs4590360GG genotypes were associated with large-artery atherosclerosis stroke (adjusted odds ratio = 2.804, 2.872, and 2.432, respectively; P < 0.05, q < 0.05). Furthermore, the frequency of CACCG haplotype in the patients was greatly higher than that in the controls (OR = 1.424, 95% CI: 1.071-1.893, P = 0.014738). In addition, TBXAS1 expression was higher in patients compared to the controls (P = 0.021), and individuals with the homozygous mutated genotypes of these SNPs showed a higher expression level compared to other genotype (P < 0.05). In total, our findings indicate a significant association of TBXAS1 gene rs10256282CC, rs10237429CC, and rs4590360GG polymorphisms with large-artery atherosclerosis stroke susceptibility and the level of TBXAS1 expression, which was not previously reported in any population.

Protein modification in neurodegenerative diseases.

Posttranslational modifications play a crucial role in governing cellular functions and protein behavior. Researchers have implicated dysregulated posttranslational modifications in protein misfolding, which results in cytotoxicity, particularly in neurodegenerative diseases such as Alzheimer disease, Parkinson disease, and Huntington disease. These aberrant posttranslational modifications cause proteins to gather in certain parts of the brain that are linked to the development of the diseases. This leads to neuronal dysfunction and the start of neurodegenerative disease symptoms. Cognitive decline and neurological impairments commonly manifest in neurodegenerative disease patients, underscoring the urgency of comprehending the posttranslational modifications' impact on protein function for targeted therapeutic interventions. This review elucidates the critical link between neurodegenerative diseases and specific posttranslational modifications, focusing on Tau, APP, α-synuclein, Huntingtin protein, Parkin, DJ-1, and Drp1. By delineating the prominent aberrant posttranslational modifications within Alzheimer disease, Parkinson disease, and Huntington disease, the review underscores the significance of understanding the interplay among these modifications. Emphasizing 10 key abnormal posttranslational modifications, this study aims to provide a comprehensive framework for investigating neurodegenerative diseases holistically. The insights presented herein shed light on potential therapeutic avenues aimed at modulating posttranslational modifications to mitigate protein aggregation and retard neurodegenerative disease progression.

Analysis and review of techniques and tools based on machine learning and deep learning for prediction of lysine malonylation sites in protein sequences.

The post-translational modifications occur as crucial molecular regulatory mechanisms utilized to regulate diverse cellular processes. Malonylation of proteins, a reversible post-translational modification of lysine/k residues, is linked to a variety of biological functions, such as cellular regulation and pathogenesis. This modification plays a crucial role in metabolic pathways, mitochondrial functions, fatty acid oxidation and other life processes. However, accurately identifying malonylation sites is crucial to understand the molecular mechanism of malonylation, and the experimental identification can be a challenging and costly task. Recently, approaches based on machine learning (ML) have been suggested to address this issue. It has been demonstrated that these procedures improve accuracy while lowering costs and time constraints. However, these approaches also have specific shortcomings, including inappropriate feature extraction out of protein sequences, high-dimensional features and inefficient underlying classifiers. As a result, there is an urgent need for effective predictors and calculation methods. In this study, we provide a comprehensive analysis and review of existing prediction models, tools and benchmark datasets for predicting malonylation sites in protein sequences followed by a comparison study. The review consists of the specifications of benchmark datasets, explanation of features and encoding methods, descriptions of the predictions approaches and their embedding ML or deep learning models and the description and comparison of the existing tools in this domain. To evaluate and compare the prediction capability of the tools, a new bunch of data has been extracted based on the most updated database and the tools have been assessed based on the extracted data. Finally, a hybrid architecture consisting of several classifiers including classical ML models and a deep learning model has been proposed to ensemble the prediction results. This approach demonstrates the better performance in comparison with all prediction tools included in this study (the source codes of the models presented in this manuscript are available in https://github.com/Malonylation). Database URL: https://github.com/A-Golshan/Malonylation.

An Update of Epigenetic Drugs for the Treatment of Cancers and Brain Diseases: A Comprehensive Review.

Epigenetics has long been recognized as a significant field in biology and is defined as the investigation of any alteration in gene expression patterns that is not attributed to changes in the DNA sequences. Epigenetic marks, including histone modifications, non-coding RNAs, and DNA methylation, play crucial roles in gene regulation. Numerous studies in humans have been carried out on single-nucleotide resolution of DNA methylation, the CpG island, new histone modifications, and genome-wide nucleosome positioning. These studies indicate that epigenetic mutations and aberrant placement of these epigenetic marks play a critical role in causing the disease. Consequently, significant development has occurred in biomedical research in identifying epigenetic mechanisms, their interactions, and changes in health and disease conditions. The purpose of this review article is to provide comprehensive information about the different types of diseases caused by alterations in epigenetic factors such as DNA methylation and histone acetylation or methylation. Recent studies reported that epigenetics could influence the evolution of human cancer via aberrant methylation of gene promoter regions, which is associated with reduced gene function. Furthermore, DNA methyltransferases (DNMTs) in the DNA methylation process as well as histone acetyltransferases (HATs)/histone deacetylases (HDACs) and histone methyltransferases (HMTs)/demethylases (HDMs) in histone modifications play important roles both in the catalysis and inhibition of target gene transcription and in many other DNA processes such as repair, replication, and recombination. Dysfunction in these enzymes leads to epigenetic disorders and, as a result, various diseases such as cancers and brain diseases. Consequently, the knowledge of how to modify aberrant DNA methylation as well as aberrant histone acetylation or methylation via inhibitors by using epigenetic drugs can be a suitable therapeutic approach for a number of diseases. Using the synergistic effects of DNA methylation and histone modification inhibitors, it is hoped that many epigenetic defects will be treated in the future. Numerous studies have demonstrated a link between epigenetic marks and their effects on brain and cancer diseases. Designing appropriate drugs could provide novel strategies for the management of these diseases in the near future.

Epigenetic regulation in lung cancer.

Lung cancer is indeed a major cause of cancer-related deaths worldwide. The development of tumors involves a complex interplay of genetic, epigenetic, and environmental factors. Epigenetic mechanisms, including DNA methylation (DNAm), histone modifications, and microRNA expression, play a crucial role in this process. Changes in DNAm patterns can lead to the silencing of important genes involved in cellular functions, contributing to the development and progression of lung cancer. MicroRNAs and exosomes have also emerged as reliable biomarkers for lung cancer. They can provide valuable information about early diagnosis and treatment assessment. In particular, abnormal hypermethylation of gene promoters and its effects on tumorigenesis, as well as its roles in the Wnt signaling pathway, have been extensively studied. Epigenetic drugs have shown promise in the treatment of lung cancer. These drugs target the aberrant epigenetic modifications that are involved in the development and progression of the disease. Several factors have been identified as drug targets in non-small cell lung cancer. Recently, combination therapy has been discussed as a successful strategy for overcoming drug resistance. Overall, understanding the role of epigenetic mechanisms and their targeting through drugs is an important area of research in lung cancer treatment.

A Review of Machine Learning and Algorithmic Methods for Protein Phosphorylation Site Prediction.

Post-translational modifications (PTMs) have key roles in extending the functional diversity of proteins and, as a result, regulating diverse cellular processes in prokaryotic and eukaryotic organisms. Phosphorylation modification is a vital PTM that occurs in most proteins and plays a significant role in many biological processes. Disorders in the phosphorylation process lead to multiple diseases, including neurological disorders and cancers. The purpose of this review is to organize this body of knowledge associated with phosphorylation site (p-site) prediction to facilitate future research in this field. At first, we comprehensively review all related databases and introduce all steps regarding dataset creation, data preprocessing, and method evaluation in p-site prediction. Next, we investigate p-site prediction methods, which are divided into two computational groups: algorithmic and machine learning (ML). Additionally, it is shown that there are basically two main approaches for p-site prediction by ML: conventional and end-to-end deep learning methods, both of which are given an overview. Moreover, this review introduces the most important feature extraction techniques, which have mostly been used in p-site prediction. Finally, we create three test sets from new proteins related to the released version of the database of protein post-translational modifications (dbPTM) in 2022 based on general and human species. Evaluating online p-site prediction tools on newly added proteins introduced in the dbPTM 2022 release, distinct from those in the dbPTM 2019 release, reveals their limitations. In other words, the actual performance of these online p-site prediction tools on unseen proteins is notably lower than the results reported in their respective research papers.