protein design

This paper designs a protein inhibitor for TEM-171 β-lactamase using deep learning and simulations, showing high stability and binding affinity.

This paper introduces SIMPLIFE, a computational workflow for designing optimal insertion sites for conjugation tags in proteins, demonstrating its use in augmenting T7 RNA polymerase function.

This study identifies a novel conserved protein, Pasovec, that interacts with the IFT-A complex to facilitate nuclear translocation of β-catenin in Wg/Wnt signaling.

The paper constructs allosteric maps for five human proteins to study how allostery evolves, finding conserved core interactions and protein-specific extensions.

This paper introduces RFpeptides, a deep learning framework for designing high-affinity macrocyclic peptides, achieving sub-nanomolar binding affinities and accurate structural predictions.

This study investigates the mechanisms of DNA and RNA strand transfer and protein exchange between SSB and RPA using smFRET, revealing dynamic interactions and length-dependent behavior.

This paper introduces TopoDiff, a diffusion-based framework for protein backbone generation that improves global geometry control and fold diversity through a structure encoder and latent sampler.

This paper presents a computational design of high-efficiency Kemp eliminases with unprecedented catalytic efficiency and stability through de novo enzyme design.

This paper introduces a cell-free combinatorial mutagenesis workflow using small oligos for high-iteration protein engineering, showing it is scalable and cost-effective.

This study compares the structural features of manganese catalase with other ferritin subtypes, highlighting differences in monomer structure, interface arrangement, and cage architecture that support its catalytic function.

AlphaDesign uses AlphaFold to design novel protein structures, including monomers, dimers, and higher-order complexes, showing structural integrity and conformational switching capabilities.

This study investigates SMCHD1's chromatin interactions and shows LRIF1 and ATPase activity are critical for its selective binding and epigenetic silencing functions.

This study introduces cycledesigner, a method combining RFdiffusion, ProteinMPNN, and HighFold to design cyclic peptide binders for specific targets, followed by scoring functions for screening.

GLIMPSE-1, a protein language model trained on human antibody sequences, improves antibody engineering for affinity, cross-reactivity, and developability by leveraging patterns in the human repertoire.

This paper designs cyclic peptide agonists for GCGR and GLP1R using EvoBind, achieving dual activation with EC50 values comparable to natural hormones.

This paper develops an mRNA system that allows translational regulation of synthetic mRNAs in response to extracellular ligands, demonstrating upregulation of anti-inflammatory signaling in response to PGE2.

This paper introduces BADASS, an optimization algorithm for protein design that improves fitness prediction and sequence diversity compared to existing methods.

The paper designs a protein that binds to multiple SARS-CoV-2 RBD variants with high affinity, demonstrating a strategy for broad-spectrum antiviral inhibitors.

This study benchmarks AI models for antibody CDR sequence design, finding that specialized models like AntiFold perform better in complex regions while general models struggle with antibody-specific nuances.

This study evaluates a bacteriophage P22 VLP system for encapsulating bioactive peptides in E. coli, showing it aids purification but does not significantly improve peptide yields.

The paper designs and characterizes ComMAND, a microRNA-based gene circuit that precisely controls transgene expression in diverse primary cells.

ProtMamba is a homology-aware, alignment-free protein language model that outperforms state-of-the-art models in homolog-conditioned sequence generation.

This paper introduces AiDTA, a deep reinforcement learning method for de novo design of protein-binding aptamers, achieving high-affinity DNA aptamers for disease-related proteins.

This study identifies Glu292 and Lys331 as critical residues in NctB's catalytic mechanism, showing that Glu292 optimizes Lys331's role in dioxygen activation despite lacking the conserved lysine found in other FAO enzymes.

The paper introduces an information-theoretic framework to identify key tuning residues in proteins by denoising sequence data, validated across multiple datasets with significant performance improvements.

The paper identifies novel protein and RNA interactions involving ORC subunits by integrating CRISPR screens, proximity labeling, proteomics, and structural predictions.

This paper designs hundreds of functional GPCR-targeting antibodies using a scaled generative model, achieving picomolar affinities and agonist activity for CXCR7.

This paper engineers Escherichia coli GapA to use NMN+ instead of NAD+, achieving a high cofactor specificity switch through rational design and mutagenesis.

The paper identifies a novel subclass of MgtE Mg2+ channels and demonstrates that de novo protein design can stabilize and enable structural analysis of otherwise unstable homologs.

The paper computationally designs monomeric Fc variants with distinct pH-responsive FcRn-binding profiles, showing enhanced binding at acidic pH and weak binding at neutral pH.