16 papers
The paper introduces IFACE, a novel framework that unifies intrinsic geometry and chemical fields to compute a joint distance for protein surfaces, enabling more accurate separation of conformational variability from structural divergence and revealing conserved functional pockets within complex protein families.
This paper demonstrates that simple, local molecular fingerprints combined with LightGBM outperform complex graph neural networks and transformers across 132 peptide datasets, challenging the assumption that modeling long-range interactions is essential for accurate peptide function prediction.
CryoNet.Refine is a novel one-step diffusion model that automates and accelerates the refinement of atomic structures against cryo-EM density maps, outperforming traditional tools like Phenix in both model-map correlation and geometric quality while supporting diverse protein and nucleic acid complexes.
This paper introduces a novel representation of local protein environments derived from atomistic foundation models that effectively captures structural and chemical features, enabling the construction of data-driven priors and achieving state-of-the-art accuracy in physics-informed NMR chemical shift prediction.
This paper introduces Reverse Distillation, a framework that decomposes large protein language model representations into nested, orthogonal subspaces guided by smaller models to ensure consistent performance scaling and outperform existing baselines on ProteinGym benchmarks.
This paper introduces a thermodynamic model that learns low-dimensional, context-independent representations of intrinsically disordered protein (IDR) sequences to quantitatively predict their partitioning and multicomponent phase behavior in complex mixtures, providing a unified and interpretable framework for understanding biomolecular condensate formation.
This paper introduces a general sampling-based continuous optimization framework that iteratively refines parameterized distributions to design messenger RNA sequences, effectively navigating the vast synonymous space to optimize multiple coupled stability and performance objectives outperforming existing methods like LinearDesign and EnsembleDesign.
This paper introduces Quantifying Cross-Attention Interaction (QCAI), a novel post-hoc explainable AI method that interprets cross-attention mechanisms in encoder-decoder transformers to improve the understanding of TCR-pMHC binding, achieving state-of-the-art performance on the newly established TCR-XAI benchmark of 274 experimentally determined structures.
BInD is a knowledge-guided diffusion model that co-generates molecules and their interactions with target proteins to achieve balanced multi-objective optimization in structure-based drug design, outperforming existing methods across key criteria like binding affinity, molecular properties, and local geometry.
This paper critiques conventional aDNA methods for oversimplifying molecular origins and introduces the HSF posterior traceability framework, which utilizes first-principles analysis and a four-system classification to improve authenticity evaluation and reduce misassignment in complex, mixed-signal fossil samples.
This paper introduces a general inference-time optimization framework that generates experiment-grounded protein ensembles by optimizing latent representations and employing novel sampling schemes, thereby overcoming the limitations of current diffusion-based methods to produce thermodynamically plausible structures with improved agreement to experimental data while exposing vulnerabilities in existing confidence metrics.
This review surveys recent advances in using atomistic molecular dynamics simulations to characterize RNA conformational dynamics across various contexts, emphasizing the role of enhanced sampling, integrative approaches, and artificial intelligence in improving the precision and accuracy of structural ensembles.
The paper introduces HEroBM, a deep equivariant graph neural network that utilizes a hierarchical, local-principle-based approach to achieve accurate, transferable, and universal backmapping from coarse-grained to all-atom molecular representations across diverse chemical systems.
This study demonstrates that a statistical mechanics model, combining a linear model with an Ising model and parametrized by in vitro binding energy measurements of the transcription factor Klf4, accurately predicts its genome-wide occupancy across the human genome without additional fitting parameters.
FLOWR.root is an SE(3)-equivariant flow-matching foundation model that unifies structure-aware 3D ligand generation with multi-purpose affinity prediction and confidence estimation, achieving state-of-the-art performance through mixed-fidelity training and parameter-efficient finetuning for efficient, high-quality drug design.
Cryo-SWAN is a multi-scale wavelet-decomposition-inspired variational autoencoder that effectively learns robust 3D molecular density representations from voxelized data, outperforming state-of-the-art methods in reconstruction quality and enabling advanced applications like denoising and conditional shape generation for structural biology.