Uğur Şahin

This study demonstrates that lipid nanoparticle-formulated RNA encoding a potent HIV-1 neutralizing antibody can durably suppress viremia in humanized mice.

This paper presents an RNA-encoded bNAb platform for in vivo production of PGT121-LS, showing prolonged half-life and potent neutralization in mice and non-human primates.

This study evaluates the immunogenicity of an LP.8.1-adapted BNT162b2 vaccine against JN.1 sublineages, showing higher neutralizing antibody responses compared to other adapted vaccines.

This study identifies a CD8+ T cell molecular signature specific to small cell lung cancer, showing its prognostic value and potential for immunotherapy.

This paper describes two mRNA vaccines for tuberculosis that are immunogenic, well-tolerated, and effective in rodent models, entering clinical trials.

This study shows that lung-targeted cytokine RNA-lipoplexes enhance anti-tumor immunity by activating T and NK cells and reducing Tregs, with efficacy in murine models and human lung tumor cultures.

Omicron JN.1- and KP.2-adapted BNT162b2 mRNA vaccines elicit stronger neutralizing antibody responses against circulating sublineages than previous vaccines, supporting annual strain updates.

The paper introduces SegmentNT, a DNA foundation model for genome annotation, achieving state-of-the-art performance in identifying 14 genic and regulatory elements across species.

The paper investigates how immunodominance affects CD8+ T cell differentiation and hierarchy after RNA vaccination, finding that dominant responses influence subdominant ones through cross-competition.

ChatNT is a conversational agent that understands biological sequences and achieves state-of-the-art results on genomics tasks while being accessible to non-coders.

This paper introduces splice2neo, a tool to identify tumor-specific splice junctions from somatic mutations, which can generate neoantigen candidates for immunotherapy.

FrameDiPT is a diffusion model for protein structure inpainting that recovers masked sections using sequence and structural context, achieving comparable accuracy to existing models with limited data.

LightMHC predicts full-atom pMHC structures from sequences using a lightweight model with attention mechanisms, achieving comparable performance to AlphaFold 2 and ESMFold with faster speed.

The monovalent Omicron XBB.1.5-adapted BNT162b2 mRNA vaccine elicits stronger neutralizing antibody responses against XBB.1.5 and related sublineages than the bivalent Wild Type + Omicron BA.4/5 vaccine.

This study uses multiple instance learning to predict immune checkpoint blockade efficacy based on qualitative neoantigen profiles, showing better performance than quantitative approaches.

A COVID-19 Early Warning System combines structural modelling with machine learning to detect and monitor high risk SARS-CoV-2 variants, identifying all 16 WHO designated variants on average more than one and a half months in advance by selecting on average less than 0.3% of the weekly novel variants.

The paper introduces a graph neural network for peptide-MHC structure prediction, achieving accuracy comparable to AlphaFold 2 with significantly fewer parameters.

The paper analyzes SARS-CoV-2 genome data to show increasing mutation rates in spike protein variants over time and highlights the need for continuous viral surveillance.