protein design

The paper improves a calreticulin-specific nanobody by framework engineering, resulting in higher yield, solubility, and binding affinity.

This study identifies PP2A as the main phosphatase for BAF dephosphorylation in interphase and shows PP4's role in maintaining centromeric BAF in an unphosphorylated state during mitosis.

The paper designs de novo TIM barrels with structural lids to create active sites for enzymatic function, achieving high catalytic efficiency.

The paper investigates how amino acid homorepeats (HRs) in proteins influence molecular outcomes through different mosaic configurations and identifies their functional implications.

ProMiSE evaluates protein multi-state prediction models using a curated dataset of biological conformational changes, revealing limitations in capturing functionally relevant dynamics.

Amylo-Pipe integrates mechanistic and kinetic prediction tools for protein and peptide aggregation, offering a web interface for assessing aggregation behavior and supporting protein engineering.

EditorForge refines inverse-folded protein sequences for enzyme and genome-editor domains by applying constraints and audits to ensure structural integrity and active-site protection.

This study designs proteins to control the phase, form, and function of metal-carbonate materials, demonstrating their use as electrocatalysts for alkaline water splitting.

This study identifies a loop-dependent inhibitory mechanism in AcrIIC1 anti-CRISPR proteins, showing how a unique loop enhances inhibition by disrupting sgRNA binding and R-loop maturation.

This paper applies entropy quantum computing to protein design, showing photonic solvers outperform classical methods for large instances.

The paper presents a computational framework to predict insertion sites in bacterial Type IV Pili for display, validated with experimental results showing improved display efficiency and surface patterning.

Promera is a generative model for biomolecular structure prediction, filtering, and design that improves binder filtering and controllable design compared to existing methods.

This work analyzes CAFA5 submissions, showing improved accuracy in protein function prediction and highlights the role of protein language models and 3D structures in performance gains.

The paper develops ESM3-PPISites, a model that identifies protein-protein interaction interfaces using multimodal representations, outperforming existing methods and improving docking accuracy.

NeoPep designs functional peptides de novo using a deep-learning framework that models biophysical principles, achieving high hit rates and structural accuracy across diverse targets.

This paper identifies residue W230 as a dynamic gate in b0,+AT that regulates arginine transport through side chain flipping, using molecular dynamics simulations.

ProtGPT3 is an open-source family of protein language models that enables controlled protein generation through alignment and prompting, showing effectiveness in generating functional proteins.

The paper shows that mRNA 3'UTRs act as chaperones for intrinsically disordered regions (IDRs) to regulate protein activity by promoting IDR-IDR interactions and preventing domain folding interference.

The paper improves antibody sequence design by combining a general inverse folding model with an antibody-specific language model, achieving better amino acid recovery and sequence diversity.

This paper introduces ProtHMSO, a heuristic multi-site optimization framework using masked protein language models to design functional protein sequences more efficiently than existing methods.

This study designs and characterizes de novo protein binders that specifically target the closed state of HSP90, showing their structural accuracy and functional properties.

The paper develops Indi2GO, an optical reporter system for benchmarking protein-protein interactions using split-indigoidine synthetase, demonstrating its utility in validating PPI tools and NRPS engineering.

This paper introduces ReCLIP, a transformer-based framework that models protein-protein interactions at the residue level, showing high accuracy in predicting mutation effects and peptide-MHC binding.

This paper describes a method to label affibodies with radiometals without using chelators, demonstrating stable metal binding and retention under various conditions.

The paper uses language modeling to create a comprehensive representation of protein biology, enabling structure prediction and discovery of high-affinity protein interactions.

This paper designs and validates a high-affinity peptide inhibitor targeting the HPV E1-E2 interface using computational methods, showing improved binding affinity and safety.

This paper introduces a method to modulate protein function through genetically encoded oxidative chemistry by using photosensitizers to generate reactive oxygen species and control protein activity.

ProNotch converts extracellular protease activity into programmable transcriptional outputs by using a modular receptor system that responds to protease cleavage.

The paper engineers a bacterial encapsulin into a nanoscaffold for controlled antigen display, demonstrating its utility in generating single- and multi-target nanovaccines for Alzheimer's disease.

This paper designs intrinsically disordered proteins using a physics-guided machine learning framework to encode complex signal processing and condensate properties.