David A. Baker

This paper designs de novo ligases that achieve site-specific ubiquitylation of a target protein with high selectivity and efficiency.

This study designs de novo amide ligases with a cysteine catalytic triad to selectively form amide bonds across diverse substrates, demonstrating high selectivity and applicability in synthesizing bioactive molecules.

The paper develops a computational framework to minimize CD8⁺ T cell immunogenicity in designed proteins while preserving function, using a de novo luciferase as a model.

Designed protein binders to conserved MYC regions reach low-nanomolar affinity, reduce MYC-MAX proximity in cells, and are depleted from MYC-dependent cancer cells in culture and mouse pancreatic tumors.

The paper designs and validates protein readers that specifically detect disease-related modifications in Tau and Abeta in Alzheimer's disease models and human samples.

Chaperone, a DataFrame-based framework and agent harness for protein design tools, cut tokens 86% and GPU-hours 64% while raising pass rate from 6% to 12%.

This study designs synthetic activators for programmable gene expression by engineering coactivator-binding proteins and demonstrates their enhanced transcriptional activation capabilities.

This paper designs enantioselective photoenzymes using deep learning methods to precisely position a photosensitizer and substrate, achieving high stereocontrol and regiocontrol.

The paper reports the crystal structure of HDAC6 CD2 complexed with a macrocyclic nonapeptide inhibitor, revealing key interactions that contribute to its inhibitory potency.

CaGE alternates guided structure prediction with sequence redesign, fading guidance each cycle, so sequences recover complex catalytic sites unaided; designed nonheme-iron and PLP-dependent enzymes were active.

This study designs de novo cysteine proteases with high activity and structural novelty, achieving 19% success rate and up to 3 x 10^7 rate enhancement over background reactions.

This paper designs de novo metalloproteases using RoseTTAFold Diffusion 2, achieving high activity and specificity for cleaving various substrates.

This study designs miniprotein inhibitors targeting bacterial adhesins to prevent and treat urinary tract infections.

This paper develops a computational method to design glycoproteins with controlled N-linked glycan composition by encoding glycan location and structure into amino acid sequences.

This paper describes a scalable recombinant pipeline for producing disulphide-stapled cyclic peptides, achieving high yields and enabling high-throughput screening.

This study designs protease-activatable cytokine prodrugs to reduce toxicity while maintaining antitumor efficacy in tumor models.

This paper computationally designs thermostable miniproteins that neutralize Nipah and Hendra viruses with subnanomolar affinity and potent in vitro antiviral activity.

This study designs allosterically controlled enzymes using denoising diffusion models, showing that activity can be activated or repressed by designed effectors.

RFOptimization improves all-atom biomolecular binder design by combining gradient-guided sequence optimization with orthogonal predictors to enhance in silico success rates.

This paper demonstrates that deep learning can accurately design RNA pseudoknots, achieving results comparable to human experts in a competition.

This paper presents a modular strategy to design programmable, highly porous protein crystals with tunable architectures and composition, enabling applications in catalysis and biomedicine.

This paper introduces scalable experimental and computational workflows to accelerate protein design by improving throughput, reducing costs, and enabling rapid validation of thousands of protein designs.

The paper designs de novo proteins that form autocatalytic isopeptide bonds, enabling rigid covalent protein assemblies through intramolecular and intermolecular crosslinking.

This paper designs proteins to reprogram T cell signaling pathways, improving CAR-T and TCR-T performance in solid tumor models.

The paper demonstrates that WRAP domains designed with deep learning can preserve weak interactions of membrane protein complexes in native mass spectrometry, enabling characterization of lipid and ligand interactions without detergent micelles.

This paper designs de novo integrated domains using AI tools to enable plant NLR receptors to recognize non-cognate pathogen effectors, demonstrating functional immune responses and structural fidelity.

This paper introduces a generative AI framework for designing transmembrane β-barrel nanopores with customizable properties for ion sensing, DNA translocation, and transport.

This study designs genetically encoded miniproteins to modulate FAK kinase activity, showing they can inhibit or activate FAK in vitro and in cells, and adapt them to target other kinases.

This paper designs and tests hyper-thermostable CO2 reductases with cobalt porphyrin cofactors, achieving high activity and suppressing competing reactions.

This study shows that computationally designed proteins can template and confine hydroxyapatite mineralization, providing a framework for programmable protein-guided mineralization.