bio.rodeo
ModelsOrganizationsProvidersLeaderboardAboutSign in
bio.rodeo

The authoritative source for evaluating biological foundation models. No hype, just honest analysis.

Categories
  • DNA & Gene
  • RNA
  • Protein
  • Small molecule
  • Single-cell
  • Spatial omics
  • Pathology
  • Imaging
  • Metabolomics
  • Biosignals
  • Language model
bio.rodeoModelsOrganizationsProvidersLeaderboardAboutFAQSubmit a modelTermsPrivacyContact
© 2026 Pulsatance. All rights reserved. ~
Built by Pulsatance
models / protein / bbflow
Protein
Max Planck Institute for Polymer ResearchHeidelberg Institute for Theoretical StudiesHeidelberg UniversityStockholm UniversityScience for Life LaboratoryKarlsruhe Institute of TechnologyReleased February 2025

BBFlow

Protein conformational ensemble generator conditioned on backbone geometry alone, sampling MD-like dynamics without MSAs or a folding model.

The short version

  • —Samples molecular-dynamics-like ensembles from one equilibrium backbone structure
  • —Generates ensembles for de novo designed proteins, where evolutionary information is absent
  • —Transfers to multi-chain proteins despite being trained only on monomers
  • —Conditions the flow matching prior itself on the input structure by geodesic interpolation
  • —Trains from scratch in a few GPU days with no folding-model weights to inherit
91Openness

Where to run it

No providers recorded yet. Browse all providers

BBFlow is a flow matching model that generates conformational ensembles of protein backbones, developed by the Gräter group across the Max Planck Institute for Polymer Research, the Heidelberg Institute for Theoretical Studies, and Heidelberg University, with collaborators at Stockholm University and the Karlsruhe Institute of Technology. It was posted in February 2025 and published at NeurIPS 2025.

Proteins are not single structures, and the ensembles molecular dynamics produces are often what a question actually requires — how flexible a loop is, whether a cryptic pocket opens, how two domains move together. MD is expensive enough that generative emulators have become an active alternative. The dominant approach, exemplified by AlphaFlow, fine-tunes a pretrained folding model and consumes evolutionary information as multiple sequence alignments or protein language model weights. That inheritance is costly at inference and carries a bias: for sequences with shallow alignments, and for de novo designed proteins with no evolutionary history at all, the conditioning signal is missing.

BBFlow drops the folding model entirely. Instead of predicting the fold from sequence, it takes the equilibrium backbone structure as input and generates fluctuations around it. The result is a model small enough to train from scratch in a few GPU days that runs an order of magnitude faster than its predecessor and works precisely where evolutionary conditioning fails.

#Key Features

  • Structure-conditioned generation: A geometric encoding of the equilibrium backbone conditions the flow, so no sequence alignment, language model embedding, or folding checkpoint is needed at inference.
  • Conditional prior: The prior is itself conditioned on the input protein through partial geodesic interpolation between pure noise and the equilibrium structure, shortening the distance the flow must travel.
  • De novo protein coverage: Ensembles for designed proteins with no evolutionary information are as accurate as for natural proteins, a regime where template-free AlphaFlow fails.
  • Multi-chain transfer: Although trained only on monomers, the model generalizes to multi-chain systems and reproduces their dynamic cross-correlation structure.
  • Simple deployment: A pretrained checkpoint loads with BBFlow.from_tag('latest') and samples through a Python API, a bbflow_sample CLI, or a Colab tutorial.

#Technical Details

A protein backbone is represented as a sequence of SE(3) frames, one rotation and translation per residue, and flow matching is formulated on the SE(3)^N manifold with geodesic interpolation paths. The network follows the GAFL architecture, an extension of FrameDiff and FrameFlow in which invariant point attention is replaced by Clifford frame attention; hyperparameters are inherited from those models. Conditioning enters as a distance embedding of the equilibrium structure, applied both to the learned vector field and to the prior distribution.

Training and evaluation use ATLAS, a curated set of three 100 ns all-atom MD trajectories for 1,390 structurally diverse proteins, under the same 1,265 / 39 / 82 split AlphaFlow used. Ensembles are scored on RMSF error and correlation, pairwise RMSD, dynamic cross-correlation matrices, a Wasserstein distance over principal components, and transient contact accuracy. On the ATLAS test set BBFlow matches AlphaFlow with templates on RMSF and principal components, beats it on pairwise RMSD and median RMSF — AlphaFlow-T systematically over-stabilizes and samples too close to the equilibrium structure — and outperforms template-free AlphaFlow, ESMFlow-T, two distilled variants, and ConfDiff on nearly every metric. Inference, measured per conformation of the 302-residue protein 7c45A on an A100-80GB, is about 40 times faster than AlphaFlow-T at length 300, with the margin widening for larger proteins. Ensemble generators targeting other distributions, such as BioEmu-1, are evaluated separately because they do not reproduce a fixed MD protocol.

#Applications

The natural use is annotating structures with dynamics at a scale MD cannot reach: screening candidate proteins for a target motion, flagging flexible loops or hinge regions before a design decision, or generating starting conformations for targeted simulations. Because it needs only a backbone, it slots directly downstream of a structure predictor or a design pipeline. Protein designers benefit most — a de novo backbone can be checked for unintended flexibility before synthesis, exactly the case where alignment-based ensemble methods have nothing to work with. The multi-chain capability extends this to oligomeric assemblies.

#Impact

BBFlow's argument is a useful negative result: neither pretrained folding weights nor evolutionary sequence information are needed to reproduce the conformational fluctuations seen in 300 ns of MD. That reframes ensemble generation as a structure-to-structure task rather than a folding task, and the efficiency gains follow from the smaller problem being solved. The code is released under the MIT license with a pretrained checkpoint, the preprocessed ATLAS dataset, and training scripts, though it depends on the separate GAFL and FrameFlow packages. Scope is bounded by the training distribution: the model emulates ensembles matching the temperature, force field, and 100 ns simulation length of ATLAS rather than the full Boltzmann distribution, and it generates backbones only, without side chains.

At a glance

Released
February 2025
Category
Protein
Organizations
Max Planck Institute for Polymer Research / Heidelberg Institute for Theoretical Studies / Heidelberg University / Stockholm University / Science for Life Laboratory / Karlsruhe Institute of Technology

Links

GitHub RepositoryResearch PaperGoogle Colab

Tags

conformational_ensemble_generationflow_matchinggenerativestructure_generation

Something wrong?

Much of this page is generated or calculated automatically. Flag anything that looks off and we will re-run it.