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.
AlphaFold meets flow matching for generating protein ensembles
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
q-bio.BM 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
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.
A review summarizing AI techniques for protein conformation generation, trajectory modeling, Boltzmann generators, machine learning potentials, and related challenges in scalability and physical consistency.
citing papers explorer
-
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.
-
Learning Structure, Energy, and Dynamics: A Survey of Artificial Intelligence for Protein Dynamics
A review summarizing AI techniques for protein conformation generation, trajectory modeling, Boltzmann generators, machine learning potentials, and related challenges in scalability and physical consistency.