Protein Data Bank

The Protein Data Bank (PDB) is a repository that contains three-dimensional structural data of biological macromolecules, which is used to evaluate and train models for generating atomic-level molecular dynamics trajectories.

Papers using Protein Data Bank (19)

Inference-time optimization for experiment-grounded protein ensemble generation2026 · 3 citesgRNAde: Geometric Deep Learning for 3D RNA inverse design2023 · 7 citesSimpleFold: Folding Proteins is Simpler than You Think2025 · 3 citesPETIMOT: A Novel Framework for Inferring Protein Motions from Sparse Data Using SE(3)-Equivariant Graph Neural Networks2025 · 1 citesAtomic Trajectory Modeling with State Space Models for Biomolecular Dynamics2026Classifying Metamorphic versus Single-Fold Proteins with Statistical Learning and AlphaFold22025Completion of partial structures using Patterson maps with the CrysFormer machine learning model2025Apo2Mol: 3D Molecule Generation via Dynamic Pocket-Aware Diffusion Models2025Torsion-Space Diffusion for Protein Backbone Generation with Geometric Refinement2025Monte Carlo Tree Diffusion with Multiple Experts for Protein Design2025RecCrysFormer: Refined Protein Structural Prediction from 3D Patterson Maps via Recycling Training Runs2025AlphaFold Meets Flow Matching for Generating Protein Ensembles2024 · 83 citesLanguage models can generate molecules, materials, and protein binding sites directly in three dimensions as XYZ, CIF, and PDB files2023 · 21 citesOpenProteinSet: Training data for structural biology at scale2023 · 15 citesSequence-Augmented SE(3)-Flow Matching For Conditional Protein Backbone Generation2024 · 7 citesEvaluating representation learning on the protein structure universe2024 · 6 citesxTrimoABFold: De novo Antibody Structure Prediction without MSA2022 · 5 cites3D Reconstruction of Protein Complex Structures Using Synthesized Multi-View AFM Images2022 · 1 citesImproving Protein-peptide Interface Predictions in the Low Data Regime2023