D. Baker

RPXDock enables fast, flexible protein docking for symmetric architectures, supporting diverse applications in nanomaterial design.

The paper designs extendable protein multiplexes with symmetric architectures to create precisely patterned nanofibers through controlled repeat propagation and hydrophilic patch placement.

Deep network-based protein design generates symmetric homo-oligomers with high structural accuracy, demonstrating the potential for creating novel nanomachines and biomaterials.

This study identifies cryptic transmembrane domains in designed protein nanoparticles that hinder secretion and introduces a computational tool, Degreaser, to remove them while maintaining stability, improving secretion efficiency.

This paper improves de novo protein binder design by using deep learning models to assess design success rates and computational efficiency.

A deep learning method for protein sequence design shows high performance in both simulations and experiments, applicable to various design challenges.

This paper describes a remote cohort-based curriculum for undergraduate students to learn computational protein design, enhancing their research skills and connecting them with the lab.

This study demonstrates that Notch ligand dimers mediate cis-inhibition of Notch receptor activity, introducing a new model of Notch signaling that distinguishes between ligand monomer-driven transactivation and dimer-mediated cis-inhibition.

The paper shows that the Phage Nucleus of {phi}PA3 forms a self-assembling, 2D crystalline lattice with adaptable inter-tetramer contacts and functional channels.

The paper shows that inducing Par complex cortical polarity with designed proteins causes cytoskeletal symmetry breaking and asymmetric cell division features in unpolarized cells.

The paper introduces randomized sorting in sort-seq assays to eliminate systematic bias, validated through simulation and experiments, and extends the method for variance estimation and multi-bin sorting.

This paper introduces design rules for immunoglobulin-like domains and demonstrates the de novo creation of stable, functional scaffolds with improved biophysical properties.

The paper uses coevolution analysis and deep learning to model core eukaryotic protein complexes in yeast, identifying 104 new assemblies and structurally characterizing 608 previously unknown complexes.

This paper introduces two deep learning methods for designing proteins with specific functional sites, showing they can generate diverse proteins with desired properties.

This study identifies Rxfp4-expressing hypothalamic neurons as regulators of food intake and preference in mice through genetic and pharmacological manipulations.

The paper uses covariation analysis of AHL synthase and receptor sequences to identify selectivity elements in quorum sensing systems and demonstrates their role in signal specificity.

The paper presents two neural network models for predicting and generating stable proteins based on amino acid sequences, showing improved stability in both expert-designed and model-generated proteins.

The paper designs and evaluates 30,000 de novo proteins to explore shape diversity, identifies 6,200 stable proteins, and develops a classifier for stability prediction.

This study evaluates the protective efficacy of modified miniproteins against SARS-CoV-2 in mice, showing reduced viral burden and prevention of lung disease.

The paper uses cryoEM to analyze polyclonal antibody responses to HIV Env immunogens in rhesus macaques, revealing structural differences in antibody binding and immunogenicity of engineered mutations and glycan sites.

The paper designs modular nanocages that assemble antibodies into precise geometries, enhancing signaling and neutralization compared to free antibodies.

This paper designs proteins with discontinuous functional sites using deep learning, eliminating the need for pre-defined secondary structures and enabling diverse scaffold generation.

This study designs a family of stable de novo TIM barrels with diverse thermodynamic properties and identifies epistatic effects influencing their stability.

The paper investigates how the valency of F-domain scaffolds affects signaling through the angiopoietin pathway, finding that higher valency mimics Ang1's pro-angiogenic effects while lower valency mimics Ang2's antagonistic effects.

The paper improves protein-ligand docking by optimizing force field parameters using small-molecule crystal structures, achieving better binding structure prediction.

This paper describes a hierarchical method to design multi-scale symmetric protein complexes using repeat proteins and helical bundles, resulting in large symmetric assemblies like an icosahedral nanocage.

This paper designs protein sequences by optimizing an energy landscape to ensure they fold into a desired structure, showing improved performance over traditional methods.

The paper uses deep networks to design new proteins by inverting structure prediction models, resulting in 27 stable folded proteins with diverse structures.

Nanoparticle immunogens with four seasonal influenza hemagglutinins elicit neutralizing antibodies against both the head and stem, providing broad protection against diverse influenza strains.

This paper uses deep learning and computational methods to determine an almost-complete atomic model of the Fanconi Anemia core complex from a low-resolution cryoEM map.