Talip Uçar

BoltzProt-1: Towards Efficient De Novo Binder Design with Good Developability

BoltzProt-1 improves nanobody design for protein targets by increasing hit rates and developability compared to existing methods.

BoltzGen: Toward Universal Binder Design

An all-atom diffusion model unifying biomolecular structure prediction and sequence-structure generation designs experimentally validated nanobodies, mini-proteins, and linear or cyclic peptides across 26 diverse targets.

BLOSUM Is All You Learn - Generative Antibody Models Reflect Evolutionary Priors

This paper shows that BLOSUM similarity scores correlate with antibody binding affinity, suggesting generative models implicitly learn evolutionary priors.

Exploring Log-Likelihood Scores for Ranking Antibody Sequence Designs

The paper benchmarks generative models for antibody sequence design using log-likelihood scores and finds they correlate with binding affinities, suggesting their potential for ranking.

IgBlend: Unifying 3D Structures and Sequences in Antibody Language Models

IgBlend integrates 3D structures and sequences for antibody language models, outperforming existing models in benchmarks and showing correlation with binding affinities.