Garyk Brixi

This paper demonstrates that a genomic language model can generate functional regulatory DNA sequences using few examples, showing improved performance in cell-type-specific gene expression and neuronal labeling.

This paper demonstrates that in-context learning in the genome language model Evo 2 enables efficient biological sequence design without additional training.

Minerva extracts RNA base-pairing, protein-contact and repeat maps from a genome language model without alignments, flagging unannotated structured loci and a phage ncRNA array reverse-transcribed into short cDNAs.

This paper introduces antiGen, a machine learning model that forecasts viral mutations from phylogenetic trees, achieving state-of-the-art results for SARS-CoV-2 and other viruses.

Fine-tuned Evo 1 and Evo 2 genome language models designed complete ΦX174-like phage genomes; 16 of 285 assembled designs were viable, and some outperformed ΦX174 in competition.

The paper introduces the Dayhoff Atlas, a resource with large protein sequence datasets and generative models to improve protein design and prediction.

A 40B-parameter DNA model trained on 9.3 trillion tokens scores coding and noncoding variants zero-shot, exposes interpretable sequence features, and writes chromosome-scale sequences.

7B-parameter convolution-attention DNA model with 131 kb context, trained on prokaryotic genomes, performs zero-shot fitness and essentiality prediction and generates Cas loci, transposons, and 650 kb sequences.

The paper investigates how ESM-2, a protein language model, predicts protein contacts by analyzing coevolving residue statistics and local sequence context.

This study identifies genetic loci associated with PCOS and shows genetic correlations with inflammation and sex hormones, improving PCOS prediction through polygenic risk scores.

This study generates functional ovarian granulosa-like cells from human iPSCs by overexpressing NR5A1 and RUNX1 or RUNX2, enabling the formation of ovary-like organoids with germ cells.

This study identifies key transcription factors that drive the rapid differentiation of human induced pluripotent stem cells into oogonia-like cells using a combinatorial approach and computational tools.

This paper designs peptides to degrade undruggable proteins using contrastive deep learning and experimental validation in human cells.