Protein Structure and Dynamics

An Artificial Intelligence-based framework for protein interaction design with accelerated KAN-based Positive-Unlabeled learning

The paper introduces an AI framework for protein interaction design using KAN-based PU learning, achieving improved stability and validation metrics compared to traditional methods.

A peptide catalyst can replace an essential enzyme in a eukaryotic cell

This study shows a short peptide can replace an essential enzyme in yeast, demonstrating peptide-based catalysis as a possible precursor to modern protein enzymes.

The missing link between biomolecular condensates and amyloid fibrils

This paper identifies amphiphilic motifs that encode both fluid lyotropic phases and amyloid formation, linking functional condensation with pathological aggregation.

Multiple Protein Structure Alignment at Scale with FoldMason

FoldMason uses Foldseek's 3Di+AA alphabet for progressive multiple structure alignment, beating structure aligners' LDDT on AlphaFold DB clusters at near sequence-aligner speed, scaling to 100,000 structures.

Mapping targetable sites on the human surfaceome for the design of novel binders

The paper identifies 4,500 targetable sites on the human surfaceome and introduces binder seeds for protein design, validated through experimental approaches and supported by a database.

From Structure to Immunogenicity: Decoding Correlated Dynamics atthe Peptide MHC interface to Understand TCR Recognition

The paper decodes correlated dynamics at the pMHC interface to understand TCR recognition and immunogenicity using computational methods.

UdonPred: Untangling Protein Intrinsic Disorder Prediction

UdonPred predicts per-residue protein disorder from sequence using embeddings from ProstT5, showing that annotation quality, not model capacity, drives performance in continuous disorder prediction.

The Gaussian Network Model as a Framework for Allosteric Analysis: Dynamic Distance, Edge Centrality, and Entropy Sensitivity in KRAS

The paper introduces a framework using dynamic distance, edge centrality, and entropy sensitivity to analyze allosteric communication in KRAS, identifying key residue pairs that function as bottlenecks.

LocAlign: Local Protein Structural Alignment with Geometric Deep Learning

LocAlign uses geometric deep learning to align protein structures and identify functional motifs, achieving high accuracy for both similar and dissimilar folds.

Extending the MAD Toolbox: New Polymer Builder and Enhanced Martini Database

The paper updates the MAD web server with new tools and an enhanced database for building and simulating coarse-grained polymer models using the Martini force field.

CoEVFold suite: user friendly pipelines to visually represent protein coevolution

The paper introduces CoEVFold, a pipeline that identifies and visualizes protein coevolution using MSA data and provides tools for analyzing coevolution in proteins and complexes.

Surf2Spot: A Surface-Informed Geometry-Aware Model for Predicting Binder and Nanobody Design Hotspots

Surf2Spot predicts protein-protein and nanobody-antigen interaction hotspots using a deep learning model that integrates sequence, structure, and surface properties, improving performance over existing methods.

ESMDisPred: A Structure-Aware CNN-Transformer Architecture for Intrinsically Disordered Protein Prediction

ESMDisPred predicts intrinsically disordered proteins by integrating sequence embeddings with structural data, achieving high accuracy on benchmark datasets.

Improved Anisotropic Network Models for Membrane Protein Dynamics and Mechanosensitive Ion Channels

This paper introduces improved Anisotropic Network Models that incorporate Membrane Contact Probability to better predict membrane protein dynamics and mechanosensitivity, aligning with experimental findings.

FrustraMPNN: An ultra-fast deep learning tool for proteome-scale analysis of deep mutational single-residue local energetic frustration in proteins

FrustraMPNN rapidly predicts single-residue frustration in proteins at proteome scale with high accuracy, enabling new insights into protein function and dynamics.

Protein Language Models Trained on Biophysical Dynamics Inform Mutation Effects

This paper introduces two protein language models trained on dynamic biophysical data to better predict mutation effects and protein behavior.

High-Affinity Protein Binder Design via Flow Matching and In Silico Maturation

This paper designs high-affinity protein binders using a computational framework combining flow matching and in silico maturation, achieving picomolar and nanomolar affinities without experimental screening.

Atomistic simulation study reveals transduction of mechanical work generated by ATP hydrolysis onto myosin II functional loops

This paper uses atomistic simulations to show that ATP hydrolysis in myosin II stores mechanical energy in functional loops through hydrogen bond rearrangements, independent of heat release.

Constraint Network Analysis of Global and Local Rigidity in Wild-Type EGFR: Apo vs Gefitinib-Bound States

This study uses Constraint Network Analysis to compare the mechanical rigidity of wild-type EGFR in apo and gefitinib-bound states, finding that ligand binding causes localized rigidification without large-scale structural reorganization.

Amino acid homorepeats act as buffers to maintain proteostasis and constrain the compatible sequence space of proteomes

The paper evaluates the neutrality of amino acid homorepeats in yeast, finding hydrophobic repeats are harmful while hydrophilic repeats suppress proteotoxic stress and define compatible sequence space.

Fast Adversarial Generation of Molecular Dynamics Trajectories with Kinetic Fidelity

This paper introduces a GAN-based method to generate molecular dynamics trajectories with kinetic fidelity, enabling efficient sampling of rare events in complex systems.

A predicted structural interactome reveals binding interference from intrinsically disordered regions

The paper predicts protein-protein interactions in Drosophila using AlphaFold2-multimer, highlighting the role of intrinsically disordered regions and providing an interactive interface for exploration.

Protein Language Modeling beyond static folds reveals sequence-encoded flexibility

This paper introduces ProtProfileMD, a model that predicts protein dynamics from sequences, improving homology detection by capturing conformational changes through 3Di tokens.

Protein folding stability estimation with explicit consideration of unfolded states

IFUM is a deep learning model that improves folding stability prediction by jointly estimating free energy and unfolded state ensembles, showing better accuracy than previous methods.

Generating dynamic structures through physics-based sampling of trRosettaX2-predicted inter-residue geometries

This paper introduces trX2-D, a method that combines deep learning with physics-based sampling to predict protein dynamic structures and alternative conformations.

ProteinDJ: a high-performance and modular protein design pipeline

ProteinDJ is a high-performance protein design pipeline that enables efficient generation and testing of synthetic protein binders using HPC systems.

Allosteric Regulation of RNA Affinity by Motif V-VI Coupling in West Nile Virus NS3 Helicase

This study reveals ATP-dependent coupling between nucleotide and RNA affinity in WNV NS3h, showing how motif VIL residues modulate RNA binding through conformational changes.

Conformational State of Myosins Disordered Loop 2 Structure Mediates Actomyosin Association During Crossbridge Formation

The paper uses molecular dynamics simulations to show how conformational changes in loop 2 of myosin affect actomyosin association strength through electrostatic interactions.

Conformational Dynamics in Insulin Receptor Kinase Reveals a Type III Allosteric Pocket

This study identifies a type III allosteric pocket in the insulin receptor kinase through molecular dynamics simulations and shows its structural features and inhibitor binding dynamics.

Unifying constraints linking protein folding and native dynamics decoded from AlphaFold

The paper analyzes AlphaFold-predicted structures to show a relationship between folding topology and native dynamics across species.