Research

at the
frontier

Fine-tuned protein language models capture T cell receptor stochasticity

The combinatorial explosion of T cell receptor (TCRs) sequences enables our immune systems to recognise and respond to an enormous diversity of pathogens. Modelling the highly stochastic TCR generation and selection processes at both sequence and repertoire levels is important for disease detection and advancing therapeutic research.

Training-Free Guidance with Applications to Protein Engineering

Diffusion models facilitate powerful control over the generative process. Here we introduce training-free guidance, a method for sampling from a broad class of conditional distributions that can be considered generalisations of inpainting.

Protein-Protein Affinity Prediction

Accurate prediction of protein–protein binding affinity is vital for understanding molecular interactions and designing therapeutics. We adapt Boltz-2, a state-of-the-art structure-based protein–ligand affinity predictor, for protein–protein affinity regression and evaluate it on two datasets, TCR3d and PPB-affinity. Our results echo known biases associated with training with structural data and suggest that current structure-based representations are not primed for performant affinity prediction.

AACR25: Immunoengineering by design

Combining state of the art generative AI with high throughput screening approaches empowers a TCR design process that considers both selectivity and specificity, opening up the next generation of TCR-based therapeutics.

Exploring the Synergy of Machine Learning and Physics-Based Computational Chemistry to Accelerate Drug Discovery

Synteny’s lab-in-the-loop AI platform is optimised for the discovery of novel TCR-based therapies. Physics-based priors may improve the fidelity of our systems. Here we explore the value of molecular dynamics (MD) coupled with MM-PBSA for predicting TCR-pMHC binding free energies.

Building Synteny’s Data Foundry to solve molecular recognition

The challenge of mapping genotype to phenotype defines much of modern biology. From the protein folding problem, where sequence determines structure, to emerging virtual cell models, these efforts reveal how sequence encodes function across molecular and cellular scales.

Inference Time Control of Diffusion Models in Drug Discovery

Drug discovery can be viewed as a constrained statistical sampling problem. Like composing a sentence, designing molecules and protein sequences demands precise control over both semantics and syntax.

Protein–Protein Affinity Prediction: the data landscapes of sequence and structure

Binding affinity – the strength with which two molecules interact – sits at the heart of biology. Whether a small molecule inhibitor nestles in a protein’s catalytic site, a T cell receptor recognises a tumour antigen, or an engineered bispecific antibody coaxes immune cells towards their targets, affinity drives functional biological events.

Using AI and multiplexed library assays to estimate TCR affinity at scale

We are entering the era of generative biology. At Synteny, we rationally explore biological design space in order to develop programmable protein therapeutics. We move beyond inefficient screening processes, making TCR-based therapeutics scalable and accessible.

A fully programmable immune system

If you’ve been watching the explosion of immune therapies over the past decade, you might think we’ve already mapped the immune system’s potential. CAR-Ts, checkpoint inhibitors, antibody drugs, they’ve all changed medicine.