SelfTICA reformulates collective-variable discovery as contrastive dynamical representation learning on time-lagged data, decoupling feature learning from slow-mode extraction to produce reusable collective variables from limited or biased trajectories.
Equivariant graph neural networks for 3d macromolecular structure
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 5roles
background 1polarities
unclear 1representative citing papers
h-MINT improves ligand-protein binding affinity prediction by 2-4% and virtual screening metrics by 1-3% via overlapping fragment tokenization and hierarchical modeling.
ProHiFlo introduces hierarchical coarse-to-fine flow matching with functional guidance from pretrained predictors and an adaptive SE(3)-equivariant architecture, reporting higher success rates and fewer sampling steps than prior methods on protein generation tasks.
SITA performs scalable inference-time annealing of flow-based models on molecular systems by substituting energy-based surrogate likelihoods for divergence-based importance weights.
Diversity-regularized DPO fine-tuning of ProteinMPNN improves structural similarity scores by at least 8% over base model and sequence diversity by up to 20% over standard DPO for peptide inverse folding on OpenFold structures.
citing papers explorer
-
Contrastive learning of dynamical representations for enhanced molecular sampling
SelfTICA reformulates collective-variable discovery as contrastive dynamical representation learning on time-lagged data, decoupling feature learning from slow-mode extraction to produce reusable collective variables from limited or biased trajectories.
-
h-MINT: Modeling Pocket-Ligand Binding with Hierarchical Molecular Interaction Network
h-MINT improves ligand-protein binding affinity prediction by 2-4% and virtual screening metrics by 1-3% via overlapping fragment tokenization and hierarchical modeling.
-
ProHiFlo: Hierarchical Flow Matching with Functional Guidance for De Novo Protein Generation
ProHiFlo introduces hierarchical coarse-to-fine flow matching with functional guidance from pretrained predictors and an adaptive SE(3)-equivariant architecture, reporting higher success rates and fewer sampling steps than prior methods on protein generation tasks.
-
Scalable Inference-Time Annealing with Surrogate Likelihood Estimators
SITA performs scalable inference-time annealing of flow-based models on molecular systems by substituting energy-based surrogate likelihoods for divergence-based importance weights.
-
Improving Inverse Folding for Peptide Design with Diversity-regularized Direct Preference Optimization
Diversity-regularized DPO fine-tuning of ProteinMPNN improves structural similarity scores by at least 8% over base model and sequence diversity by up to 20% over standard DPO for peptide inverse folding on OpenFold structures.