Protein Structure and Dynamics

This paper introduces a distance-restraint-guided diffusion model to sample protein conformational changes and ligand dissociation pathways, achieving uniform coverage and high structural quality.

The paper investigates the role of a dynamic loop in AvPAL by engineering disulfide bonds to restrict its mobility, revealing its regulatory function in substrate specificity.

This study evaluates refolding metrics in protein design, showing they are limited by evolutionary information and structural flexibility, reducing their reliability for filtering design candidates.

The paper uses chiral inversion mutagenesis to identify geometrically constrained residues in LCDs that affect self-association.

The paper fine-tunes a protein language model using synthetic metalloprotein sequences to improve recovery of metal-binding motifs and identifies novel metal-binding sites.

The paper explores random protein sequence space to identify physical phenotypes and shows that sequence-based models can predict experimentally observed properties.

This study reveals that PDZ1 in the Syntenin-1 tandem domain exhibits intrinsic conformational diversity, contrasting with PDZ2's structural conservation, and suggests functional specialization for ligand recognition and domain stabilization.

This paper introduces Genie 3, a diffusion model that improves protein design by combining SE(3)-equivariance with hallucination, achieving state-of-the-art results in binder design and motif scaffolding.

DOMINO generates multidomain proteins by learning domain co-occurrence patterns and using them to design novel sequences with high structural confidence.

The paper introduces SNI, a framework to identify atypical protein assemblies, and applies it to NLRs, finding an undecameric assembly in NRC7 orthologs.

This study shows how a designed generalist binding protein can evolve into specific functions like a fluorophore binder and an efficient enzyme through weak, promiscuous interactions.

This paper introduces ASCG, a framework for coarse-graining molecular dynamics that learns reduced variables from atomistic simulations, achieving accurate free energy surfaces and faster timesteps with less training data.

This paper introduces DPLM, a dynamics-aware protein language model that integrates molecular dynamics simulations with sequence data to improve predictions of protein properties.

CTGoMartini simulates protein conformational transitions using G[o]-Martini models, enabling the study of functional state changes in membrane proteins.

This paper introduces InvDNA, a deep learning method for designing single-stranded DNA sequences from backbone coordinates, achieving better sequence recovery and structural accuracy than existing methods.

The paper uses statistical crystallography to model correlated motions in SARS-CoV-2 Mpro and shows how dimerization affects catalytic activity through structural links.

This study investigates how functional and conformational substates change during enzyme evolution using single-molecule kinetic assays and simulations, showing coordinated shifts in substate equilibria that optimize catalytic efficiency.

This paper shows that protein language models can detect local structural similarities from sequence data without 3D models, identifying aligned regions through cosine similarity of residue embeddings.

This paper introduces DynamicsPLM, a protein language model that uses conformational ensembles to improve predictions of protein interactions, localization, and function.

InversePep generates peptides with target structural geometries using a diffusion model, outperforming existing methods in producing geometry-consistent sequences.

This paper introduces a secondary structure distance metric to analyze protein evolution, showing structural divergence can differ from sequence-based phylogeny, especially in proteins with ordered and disordered regions.

InterMap accelerates interaction fingerprint detection in large molecular ensembles, achieving significant reductions in runtime and memory usage compared to existing tools.

This paper introduces an Allosteric Logic Gate (ALG) that converts two independent deformations into a Boolean-like conformational output, demonstrating non-linear logic operations through optimized spring constants.

This study evaluates four protein-ligand cofolding methods using a new benchmark dataset, finding they primarily memorize ligand poses rather than predict them de novo.

This study introduces a computational pipeline using secondary structure elements to detect protein symmetry and structural rearrangements, identifying 17,130 circularly related proteins and 26,739 proteins with indel mutations.

AnewSampling is a generative model that accurately samples all-atom equilibrium distributions of biomolecular interactions, outperforming prior methods and enabling efficient exploration of conformational landscapes.

This study identifies evolutionary changes in protein disorder in naked mole rats that contribute to their unique physiological traits.

This paper designs sequence-specific DNA binding proteins using deep learning, achieving a 100-fold improvement in success rates over previous methods.

AlphaFold-NMR reveals hidden conformational states of proteins using AI-driven sampling and Bayesian validation, uncovering structural heterogeneity in Gaussia luciferase and Cyclin-Dependent Kinase 2-Associated Protein 1.

This paper introduces AFLF, a method to generate diverse protein conformations from sequence using AlphaFold's latent space, showing it captures structural fluctuations and binding sites.