98%
921
2 minutes
20
The traditional process of antibody discovery is limited by inefficiency, high costs, and low success rates. Recent approaches employing artificial intelligence (AI) have been developed to optimize existing antibodies and generate antibody sequences in a target-agnostic manner. In this work, we present MAGE (Monoclonal Antibody GEnerator), a sequence-based Protein Language Model (PLM) fine-tuned for the task of generating paired human variable heavy and light chain antibody sequences against targets of interest. We show that MAGE can generate novel and diverse antibody sequences with experimentally validated binding specificity against SARS-CoV-2, an emerging avian influenza H5N1, and respiratory syncytial virus A (RSV-A). MAGE represents a first-in-class model capable of designing human antibodies against multiple targets with no starting template.
Download full-text PDF |
Source |
---|---|
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11870394 | PMC |
http://dx.doi.org/10.1101/2024.12.20.629482 | DOI Listing |
mBio
September 2025
Fred Hutchinson Cancer Center, Vaccine and Infectious Disease Division, Seattle, Washington, USA.
Accurate timing estimates of when participants acquire HIV in HIV prevention trials are necessary for determining antibody levels at acquisition. The Antibody-Mediated Prevention (AMP) Studies showed that a passively administered broadly neutralizing antibody can prevent the acquisition of HIV from a neutralization-sensitive virus. We developed a pipeline for estimating the date of detectable HIV acquisition (DDA) in AMP Study participants using diagnostic and viral sequence data.
View Article and Find Full Text PDFBackground: Eosinophilic pleural effusion (EPE), characterized by atypical symptoms and rarity, is easily over-looked and misdiagnosed.
Methods: The patient underwent comprehensive routine laboratory tests including blood analysis and pleural effusion examination, along with B-ultrasound and computed tomography (CT) imaging. Based on combined evaluation of the epidemiological history, serum-specific parasite antibody detection and targeted Next-Generation Sequencing were performed on the clinical specimens.
J Inflamm Res
September 2025
Department of the Head and Neck, The Third Affiliated Hospital of Kunming Medical University, Yunnan Cancer Hospital, Peking University Cancer Hospital Yunnan, Kunming, People's Republic of China.
Background: Immune escape of tumor cells is a common problem with tumor photothermal therapy utilizing gold nanorods (Au NRs). Whether CpG ODN, an immune adjuvant, can synergize with Au NRs to activate the immune response and its potential mechanism is not clear.
Methods: The effect of Au NRs combined with CpG ODN (Au NRs-C) on the activity of various immune-related cells, such as double-positive T cells, macrophages, NK cells, Th17, and Treg.
Hum Vaccin Immunother
December 2025
Department of Oncology, The Affiliated Hospital of Qingdao University, Qingdao, Shandong, China.
Trastuzumab-containing therapy remains a treatment option for patients with HER2-positive gastric cancer (GC). However, primary resistance to trastuzumab is a challenge. Therefore, it is essential to identify biomarkers for predicting the efficacy of trastuzumab-based treatment.
View Article and Find Full Text PDFEMBO Mol Med
September 2025
Institute of Physical Science and Information, Anhui University, 230039, Hefei, Anhui, China.
The global outbreak of the mpox in humans, caused by the mpox virus (MPXV), underscores the urgent need for safe and effective therapeutics. In this study, we characterized the dominant MPXV immunogens, M1R and B6R, by sequencing monoclonal antibodies (MAbs) from the immunized mice and analyzing their epitopes and functions through in vitro and in vivo assessments of binding and antiviral activities. Several broadly effective anti-M1R and anti-B6R neutralizing MAbs were identified and they exhibited enhanced antiviral effects against MPXV or vaccinia virus (VACV) when used in antibody cocktail and bispecific antibody designs.
View Article and Find Full Text PDF