Benjamin Schubert

The study identifies over 27,000 unique epitope-reactive TCRs from immunized mice, showing that TCR diversity is not constrained by germline VJ combinations but by combinatorial pairing of segments and CDR3 sequences.

DextraDemixer improves identification of antigen-specific T cells from pMHC multimer data by using a Bayesian model and dynamic thresholding to reduce false discoveries.

This study identifies antigen-reactive CD4+ T cells after SARS-CoV-2 vaccination using single-cell RNA and TCR sequencing, revealing phenotypic differences between stimulated and unstimulated states.

The paper analyzes T cell responses to mRNA vaccination, finding that polyclonality and high, but not maximum, antigen receptor avidity correlate with response quality.

The paper benchmarks T-cell receptor-epitope predictors using ePytope-TCR, showing performance on datasets and highlighting biases in prediction scores across epitope classes.

P-TEAM predicts the effect of epitope mutations on T cell functionality using a Random Forest model trained on murine and human TCR-epitope interactions.

The paper introduces mvTCR, a multimodal generative model for integrating TCR and transcriptome data to improve analysis of single-cell immune profiling data.

This paper reviews proteasomal cleavage prediction methods, benchmarks deep learning architectures, and finds that dataset quality limits performance more than model choice.

The paper introduces meTCRs, a deep-learning method to embed TCR sequences for clustering and querying TCR-epitope databases.

This paper integrates missing data handling into KiMONo for multi-omics regulatory network inference and benchmarks its performance on different missing data scenarios.

scCODA is a Bayesian model for analyzing compositional single-cell data, improving detection of cell type changes in disease and other stimuli.

This paper presents a formal framework for epitope-based vaccine design that integrates all design phases into a single integer linear program to ensure optimal solutions.

This paper presents a computational method that jointly selects epitopes and designs spacers for string-of-beads vaccines to improve immunogenicity and processing efficiency.

The paper develops deep learning models to predict T-cell antigen specificity from TCR CDR3 sequences and finds categorical antigen modeling outperforms joint sequence modeling.

This study identifies 38 loci and 250 epistatic pairs affecting antibiotic resistance in Neisseria gonorrhoeae using evolutionary couplings.

The paper introduces EVcouplings, a Python framework for coevolutionary sequence analysis that enables structure prediction and mutation effect assessment.