A. K. Bera

De novo design of diverse small molecule binders and sensors using Shape Complementary Pseudocycles

The paper designs nanomolar binders for diverse small molecules using a pseudocycle-based shape complementarity method, enabling direct conversion into sensing systems.

Improving protein expression, stability, and function with ProteinMPNN

This paper introduces ProteinMPNN, a deep learning model that improves protein expression, stability, and function by incorporating evolutionary and structural information.

Rapid and automated design of two-component protein nanomaterials using ProteinMPNN

This study benchmarks ProteinMPNN against Rosetta in designing two-component protein nanomaterials, showing comparable success with significantly reduced computation and no manual refinement.

De novo design of highly selective miniprotein inhibitors of integrins αvβ6 and αvβ8

This paper designs highly selective miniprotein inhibitors for integrins αvβ6 and αvβ8 with picomolar affinity and therapeutic potential in a mouse fibrosis model.

Blueprinting expandable nanomaterials with standardized protein building blocks

This paper introduces standardized protein building blocks and geometric design principles to create expandable protein nanomaterials, validated through X-ray crystallography and electron microscopy.

Cyclic peptide structure prediction and design using AlphaFold

This paper modifies AlphaFold to predict and design cyclic peptides, achieving high accuracy in structure prediction and de novo design with experimental validation.

Design of stimulus-responsive two-state hinge proteins

This paper designs two-state hinge proteins that switch between structural states in response to ligands, demonstrating atomic-level accuracy and tunable kinetics and thermodynamics.

Precisely patterned nanofibers made from extendable protein multiplexes

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

Hallucinating protein assemblies

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

Improving the secretion of designed protein assemblies through negative design of cryptic transmembrane domains

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.

Large-scale design and refinement of stable proteins using sequence-only models

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.

Hierarchical design of multi-scale protein complexes by combinatorial assembly of oligomeric helical bundle and repeat protein building blocks

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.

A generative algorithm for de novo design of proteins with diverse pocket structures

This paper introduces a generative algorithm for designing de novo proteins with diverse small molecule binding pockets, validated through experimental testing and showing improved stability and diversity compared to natural proteins.

A revised mechanism of action of hyperaldosteronism-linked mutations in cytosolic domains of GIRK4 (KCNJ5).

This study shows that cytosolic domain mutations in GIRK4 (KCNJ5) cause loss-of-function rather than gain-of-function, challenging the existing mechanism of hyperaldosteronism.