AI Article Synopsis
- The study aims to link protein amino acid sequences to their ability to produce an antibody response, while also enhancing a computational method for predicting linear B-cell epitopes (LBE).
- A deep maxout network (DMN) utilizing dropout training was developed for this prediction, with GPU technology speeding up the training process.
- The DMN-LBE model demonstrated a 68.33% accuracy and a 0.743 AUC score during a rigorous 10-fold cross-validation, outpacing existing prediction methods, and is now available as a free online tool to aid in vaccine research, antibody production, and disease management.
Article Abstract
To establish a relation between an protein amino acid sequence and its tendencies to generate antibody response, and to investigate an improved in silico method for linear B-cell epitope (LBE) prediction. We present a sequence-based LBE predictor developed using deep maxout network (DMN) with dropout training techniques. A graphics processing unit (GPU) was used to reduce the training time of the model. A 10-fold cross-validation test on a large, non-redundant and experimentally verified dataset (Lbtope_Fixed_ non_redundant) was performed to evaluate the performance. DMN-LBE achieved an accuracy of 68.33% and an area under the receiver operating characteristic curve (AUC) of 0.743, outperforming other prediction methods in the field. A web server, DMN-LBE, of the improved prediction model has been provided for public free use. We anticipate that DMN-LBE will be beneficial to vaccine development, antibody production, disease diagnosis, and therapy.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.3967/bes2015.065 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Hyperreactive B cells instruct their elimination by T cells to curb autoinflammation and lymphomagenesis.
Immunity
December 2024
Institute of Experimental Hematology, School of Medicine, Technical University of Munich, 81675 Munich, Germany; Center for Translational Cancer Research (TranslaTUM), School of Medicine, Technical University of Munich, 81675 Munich, Germany; German Cancer Consortium (DKTK), 69120 Heidelberg, Germany; Max-Planck Institute of Biochemistry, 82152 Planegg, Germany. Electronic address:
B cell immunity carries the inherent risk of deviating into autoimmunity and malignancy, which are both strongly associated with genetic variants or alterations that increase immune signaling. Here, we investigated the interplay of autoimmunity and lymphoma risk factors centered around the archetypal negative immune regulator TNFAIP3/A20 in mice. Counterintuitively, B cells with moderately elevated sensitivity to stimulation caused fatal autoimmune pathology, while those with high sensitivity did not.
View Article and Find Full Text PDFDeveloping a universal multi-epitope protein vaccine candidate for enhanced borna virus pandemic preparedness.
Front Immunol
December 2024
School of Basic Medicine, Guangzhou Medical University, Guangzhou, China.
Introduction: Borna disease virus 1 (BoDV-1) is an emerging zoonotic RNA virus that can cause severe acute encephalitis with high mortality. Currently, there are no effective countermeasures, and the potential risk of a future outbreak requires urgent attention. To address this challenge, the complete genome sequence of BoDV-1 was utilized, and immunoinformatics was applied to identify antigenic peptides suitable for vaccine development.
View Article and Find Full Text PDFDevelopment, validation, and clinical application of LC-MS/MS method for simultaneous determination of ibrutinib, zanubrutinib, orelabrutinib, acalabrutinib, and their active metabolites in patients with B-cell lymphoma.
Anal Bioanal Chem
December 2024
Department of Pharmacy, Peking University Third Hospital, Beijing, 100191, China.
Bruton's tyrosine kinase inhibitors (BTKis) exhibit significant interindividual pharmacokinetics, making therapeutic drug monitoring (TDM) a promising approach for personalized therapy. However, simultaneous quantification of multiple BTKis poses technical challenges. A unified protocol for BTKis detection would be clinically desirable.
View Article and Find Full Text PDFEvaluating predictive patterns of antigen-specific B cells by single-cell transcriptome and antibody repertoire sequencing.
Cell Syst
December 2024
Department of Biosystems Science and Engineering, ETH Zurich, 4057 Basel, Switzerland; Botnar Institute of Immune Engineering, 4056 Basel, Switzerland. Electronic address:
The field of antibody discovery typically involves extensive experimental screening of B cells from immunized animals. Machine learning (ML)-guided prediction of antigen-specific B cells could accelerate this process but requires sufficient training data with antigen-specificity labeling. Here, we introduce a dataset of single-cell transcriptome and antibody repertoire sequencing of B cells from immunized mice, which are labeled as antigen specific or non-specific through experimental selections.
View Article and Find Full Text PDFDesign of multi-epitope-based therapeutic vaccine candidates from HBc and HBx proteins of hepatitis B virus using reverse vaccinology and immunoinformatics approaches.
PLoS One
December 2024
School of Life Science and Technology, Institut Teknologi Bandung, Bandung, West Java, Indonesia.
The major problem in cases of chronic hepatitis B (CHB) is the failure of the patient's immune response to eliminate the covalently closed circular DNA (cccDNA) minichromosome of hepatitis B virus (HBV). Epigenetic regulation involving the HBV core protein (HBc) and HBV X protein (HBx) influences the transcription and stability of the cccDNA minichromosome. The HBc and/or HBx-based therapeutic vaccines that have been developed cannot accommodate differences between HBV genotypes.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!