Alex Rubinsteyn

The paper reports the discovery of TCRs specific to vaccine peptides in a patient with osteosarcoma following personalized neoantigen vaccination and in vitro expansion.

This paper explores the use of LLM-based coding agents in scientific computing, presenting case studies in the life sciences and discussing their potential and challenges.

The paper predicts pMHC-I binding stability using a protein language model, showing improved performance over existing methods and demonstrating its utility in immunogenicity and antigen-presentation modeling.

The paper introduces vmwhere, a tool for analyzing tetrameric microsatellites from long-read sequencing data, and shows its application in linking GGAA repeat structure to chromatin state in Ewing sarcoma.

This study identifies PRAME as a therapeutic target in NUT carcinoma, showing its high expression and susceptibility to T-cell mediated cytotoxicity via PRAME epitopes presented by HLA Class I molecules.

TCR-TRANSLATE generates antigen-specific TCR sequences using seq2seq models, achieving validated CDR3β sequences for unseen antigens but with limitations in validation scope and focus.

This pilot study tested antisense oligonucleotides targeting NUTM1 in NUT carcinoma cell lines but found no selective inhibition, highlighting the need for further ASO optimization.

ACE optimizes ELISpot assay design by using an epitope similarity model to reduce false positives and improve efficiency.

The paper evaluates long-read and short-read fusion detection tools using simulated data and identifies LongGF as the most effective long-read tool.

Vaxrank selects neoantigen vaccine peptides from tumor mutations, RNA data, and HLA type to design personalized cancer vaccines.

The paper describes a computational pipeline for a personalized neoantigen vaccine trial, including tools for variant calling, peptide selection, and sequence reconstruction.

The paper develops an allele-specific MHC peptide binding predictor using imputed training data, achieving performance comparable to existing methods.