Noelia Ferruz

This paper introduces REXzyme, a model translating chemical reactions into enzyme sequences, and demonstrates its ability to generate active formate dehydrogenases for CO2 reduction.

ProtGPT3 is an open-source family of protein language models that enables controlled protein generation through alignment and prompting, showing effectiveness in generating functional proteins.

This study benchmarks ligand-conditioned protein generation using sequence-only data, revealing trade-offs between diversity and foldability based on dataset characteristics.

This paper introduces the EDEN family of foundation models for AI-programmable therapeutic design, demonstrating their ability to generate functional gene insertions, antibiotic peptides, and synthetic microbiomes.

The paper introduces SaprotHub, a platform that simplifies training and sharing of protein language models, enabling non-experts to build and collaborate on customized models.

The paper analyzes a crowdsourced protein design competition, showing participants designed EGFR binders with varying affinities and highlighting challenges in benchmarking and experimental design.

This study identifies interchain electrostatic interactions as critical for collagen triple helix folding, showing their conservation across domains of life and viruses.

This study uses generative language models to design de novo triosephosphate isomerases, which show catalytic activity in E. coli.

An enzyme-specific conditional language model generates active carbonic anhydrases and lactate dehydrogenases to user specification, some under 40% identity to natural proteins, with no retraining.

This paper reviews recent advances in deep learning for protein design, presents a practical pipeline for sequence-to-property analysis, and suggests a generated protein sequence for biosynthetic applications.

This paper introduces ProtGPT2, a deep unsupervised language model for protein design that generates de novo protein sequences with properties similar to natural proteins.

Protlego automates the design and structural analysis of chimeric proteins using Python, integrating fragment recombination and molecular dynamics simulations.