Martin Pačesa

This study shows that SERDs induce ER SUMOylation, which recruits co-repressors to suppress transcription, rather than relying on ER degradation for their activity.

This study identifies Avs5 systems as a conserved bacterial defense against jumbo phages, revealing their mechanism of recognizing and disrupting phage infection.

This paper introduces DiffTopo, a diffusion model for generating novel protein folds, and MirrorTopo, a pipeline to expand known fold space by mirroring native protein topologies.

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

BoltzDesign1 inverts AlphaFold3 to design protein binders for diverse targets without model finetuning, achieving high in silico success rates and structural diversity.

This paper designs proteins that target neosurfaces from protein-ligand complexes using a deep learning approach, validated experimentally against three drug-bound protein complexes.

Hallucinating binders by backpropagating through AlphaFold2 weights gave, across 12 targets, binders in 10-100% of the designs tested per target, mostly at nanomolar affinity.

Language models trained on over one million mined CRISPR operons generated Cas9-like effectors and matching guide RNAs, and an AI-designed editor is reported to edit the human genome precisely.

The paper predicts homo-oligomerization across four proteomes using AlphaFold2, finding that 50% of archaea, 45% of bacteria, and 20% of eukaryotes form homomers, with disease mutations enriched at interfaces.

This study designs soluble analogues of integral membrane proteins using deep learning, achieving high thermal stability and functional accuracy.