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 modelContact
© 2026 Pulsatance. All rights reserved. ~
Built by Pulsatance
models / protein / confrover
Protein
ByteDance SeedReleased May 2025

ConfRover

Protein conformation and dynamics generation from MD data, sampling trajectories, independent ensembles, and interpolations between two known states.

63Openness

Where to run it

No providers recorded yet. Browse all providers

ConfRoverProteinByteDance Seed

Deep generative models trained on molecular dynamics data have split into two camps. Ensemble generators such as AlphaFlow and ConfDiff sample conformations that approximate a protein's equilibrium distribution but say nothing about the order in which those states are visited. Trajectory models capture temporal structure but cannot produce independent samples on demand. Neither formulation covers both, and the physical reality — a protein's accessible states and the paths between them — is a single object.

ConfRover, from ByteDance Seed, models conformation and dynamics together by treating an MD trajectory as an autoregressive sequence. Each frame is generated conditioned on the frames before it, using the causal transformer formulation familiar from language modeling. Because the conditioning context can be empty, a single frame, or a start-and-end pair, the same trained model supports forward simulation, time-independent sampling, and interpolation between two conformational states — the first model to do all three in one framework.

Trained on the ATLAS dataset with a test split by protein identity, ConfRover is evaluated on proteins whose structures and dynamics it has never seen. It was presented at NeurIPS 2025, with code and weights released under Apache-2.0.

#Key Features

  • Three sampling modes, one model: Forward simulation from a starting frame, independent identically distributed conformation sampling, and interpolation between two endpoint structures are all conditioning patterns over the same autoregressive factorization.
  • Modular three-stage architecture: A frozen folding-model encoder supplies protein representations, a causal transformer carries temporal context across frames, and an SE(3) diffusion decoder emits continuous 3D coordinates.
  • Multi-timescale training: Trajectories are sampled at strides spanning 1 to 1024 MD snapshots saved at 10 ps intervals, so the model learns motions across several orders of magnitude in time rather than one fixed step size.
  • Full-atom output: Backbone geometry comes from the SE(3) diffusion decoder, with a lightweight AngleResNet predicting seven torsional angles to reconstruct the backbone oxygen and side-chain atoms.
  • Hybrid training objective: Mixing trajectory and single-frame losses at a 1:1 ratio is what allows one checkpoint to be competitive at time-independent sampling as well as trajectory generation.

#Technical Details

The encoding layer draws single and pair representations from the Evoformer stack of a pretrained OpenFold model with frozen weights, after three recycling iterations; the diffusion decoder is initialized from ConfDiff and the remaining modules are trained from scratch. The released models carry 19.6M trainable parameters and are trained on the ATLAS set of roughly 1,300 proteins with triplicate 100 ns trajectories each, split by protein identity. A second checkpoint, ConfRover-interp, continues training the base model with a 1:1:1 mix of trajectory, single-frame, and interpolation objectives.

On a multi-start benchmark of about 2,700 generation conditions drawn from 82 held-out proteins, ConfRover's Pearson correlation with reference trajectory conformational change reaches 0.75 at the trajectory level and 0.63 at the frame level, against 0.56 and 0.47 for MDGen; in projected 2D PCA space the gap widens to 0.73 versus 0.18. On 100 ns simulation, state recovery improves to 0.51 Jensen-Shannon distance and 0.58 F1 against MDGen's 0.56 and 0.42, with an MD oracle at 0.31 and 0.79, and tICA-derived principal dynamic modes track the oracle closely. For time-independent sampling, ConfRover is comparable to AlphaFlow and ConfDiff, outperforming at least one of them on five of eight ensemble metrics despite not being specialized for that task.

#Applications

ConfRover offers a fast proxy for short MD runs in workflows that need conformational context rather than a single structure: identifying cryptic pockets and alternative binding-competent states for structure-based drug design, characterizing loop and domain flexibility, and generating starting ensembles for downstream docking or free-energy calculation. The interpolation mode targets a distinct question — sketching plausible paths between two known conformational states, such as apo and holo forms — where no comparable model for large proteins existed.

#Impact

By casting MD as next-frame prediction, ConfRover imports the training efficiency and conditioning flexibility of autoregressive sequence models into molecular simulation, and shows a general-purpose model can match specialists at their own task. The authors are direct about what remains: current checkpoints handle only single-chain proteins; ATLAS's 100 ns trajectories bias the learned dynamics toward short-timescale, local motions rather than large functional transitions; diffusion on backbone SE(3) space with reconstructed torsions loses accuracy for large rotamer changes; and the triangular updates in the structure module make scaling to larger proteins and longer trajectories computationally costly. A gap to MD-oracle fidelity in state recovery also persists.

At a glance

Parameters
19.6 Million
Released
May 2025
Category
Protein
Organization
ByteDance Seed

Links

GitHub RepositoryResearch PaperOfficial WebsiteHuggingFace Model

Tags

autoregressiveconformational_ensemble_generationdiffusiongenerativemolecular_dynamicstransformer

Something wrong?

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