Ensembits is the first tokenizer of protein conformational ensembles that outperforms static tokenizers on RMSF prediction and matches them on function and mutation tasks while using less pretraining data.
Alphafold meets flow matching for generating protein ensembles
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
other 1
citation-polarity summary
verdicts
UNVERDICTED 4roles
other 1polarities
unclear 1representative citing papers
Derives a conditional-marginal entropy-rate objective for bridge-aware discretization that yields U-shaped schedules and improves low-NFE sample quality on 2D, CIFAR-10, and protein tasks.
ConforNets use channel-wise affine transforms on pre-Pairformer pair latents in OpenFold3 to achieve state-of-the-art unsupervised generation of alternate protein states and supervised conformational transfer across families.
DynaProt predicts per-residue 3x3 covariance matrices for local flexibility and scalar pairwise covariances for dynamic coupling from static protein structures using an SE(3)-invariant Gaussian framework, achieving high RMSF accuracy with far fewer parameters than prior methods.
citing papers explorer
-
ENSEMBITS: an alphabet of protein conformational ensembles
Ensembits is the first tokenizer of protein conformational ensembles that outperforms static tokenizers on RMSF prediction and matches them on function and mutation tasks while using less pretraining data.
-
Entropy Across the Bridge: Conditional-Marginal Discretization for Flow and Schr\"odinger Samplers
Derives a conditional-marginal entropy-rate objective for bridge-aware discretization that yields U-shaped schedules and improves low-NFE sample quality on 2D, CIFAR-10, and protein tasks.
-
ConforNets: Latents-Based Conformational Control in OpenFold3
ConforNets use channel-wise affine transforms on pre-Pairformer pair latents in OpenFold3 to achieve state-of-the-art unsupervised generation of alternate protein states and supervised conformational transfer across families.
-
Learning residue level protein dynamics with multiscale Gaussians
DynaProt predicts per-residue 3x3 covariance matrices for local flexibility and scalar pairwise covariances for dynamic coupling from static protein structures using an SE(3)-invariant Gaussian framework, achieving high RMSF accuracy with far fewer parameters than prior methods.