bio.rodeo
ModelsOrganizationsLeaderboardAbout
bio.rodeo

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

AboutFAQSubmit a modelContact
© 2026 Pulsatance. All rights reserved. ~
Built by Pulsatance
Single-cell

Chreode

University of North Carolina at Chapel Hill / University of Texas at Austin / University of Pennsylvania

A cell world model pretrained on a 2.4M-cell mouse embryonic atlas that predicts one-step transcriptional state transitions and transfers to perturbation prediction.

Released: May 2026

Chreode is a "cell world model" that learns to predict how single cells move through transcriptional state space, both as they follow developmental signals and as they respond to genetic perturbations. Introduced as a 2026 preprint by researchers at the University of North Carolina at Chapel Hill, the University of Texas at Austin, and the University of Pennsylvania, it is framed as a contribution to the emerging "AI Virtual Cell" agenda: building models that can simulate cellular behavior the way physical world models simulate environments. The name evokes Waddington's idea of a chreode — a canalized developmental pathway that cells are guided along.

The central problem Chreode addresses is one-step temporal dynamics: given a cell's current transcriptional state, where does it go next? Rather than treating this as an unstructured regression or a generic diffusion sampling task, Chreode parameterizes the transition with a structured residual transition operator that decomposes cell-state change into three interpretable components — a downhill landscape flow toward attractor states, a rotational in-tangent term that captures cyclic or curved motion along the developmental manifold, and a stochastic spread term modeling biological noise. This decomposition is designed to mirror the geometry of Waddington-style developmental landscapes while remaining trainable at scale.

Chreode's second contribution is transfer: a model pretrained purely on unperturbed developmental dynamics generalizes to perturbation prediction through transfer learning, without redesigning the downstream training procedure. This positions it between trajectory-inference methods and perturbation-response models, suggesting that developmental dynamics and perturbation responses can share a common learned substrate.

#Key Features

  • Structured residual transition operator: State transitions are decomposed into downhill landscape flow, rotational in-tangent dynamics, and stochastic spread, giving the dynamics an interpretable geometric structure rather than a black-box update.
  • One-step temporal prediction: Chreode predicts the next transcriptional state directly in a single step, avoiding the long iterative sampling chains typical of diffusion-based dynamics models.
  • Developmental pretraining at atlas scale: The model is pretrained self-supervised on a 2.4M-cell mouse embryonic atlas assembled from seven datasets, learning broad developmental dynamics before any task-specific tuning.
  • Transfer to perturbation prediction: Weights learned from unperturbed development transfer to genetic perturbation tasks, yielding a roughly 12.4% relative improvement without modifying the downstream training procedure.
  • scVI + DiT architecture: A shared scVI variational encoder maps expression into a latent space where a diffusion-transformer (DiT) backbone models the transition operator.

#Technical Details

Chreode couples a shared scVI encoder — a variational autoencoder widely used to denoise and embed scRNA-seq counts — with a diffusion-transformer (DiT) backbone that learns the residual transition operator in the latent space. Pretraining uses a 2.4M-cell mouse embryonic atlas drawn from seven datasets, exposing the model to a wide range of developmental cell states and transitions. On developmental benchmarks, Chreode reports reduced Sinkhorn (optimal-transport) distance between predicted and observed populations on hematopoiesis and islet differentiation tasks, improving over trajectory-prediction baselines such as PRESCIENT. For perturbation prediction, transferring the pretrained model to the Norman Perturb-seq dataset lowers the DE20 mean-squared error (computed over the top 20 differentially expressed genes) from 0.2121 to 0.1858 — about a 12.4% relative improvement — while leaving the downstream training recipe unchanged. The preprint states that the codebase is released under an open research license; pretrained weights are not released with this submission.

#Applications

Chreode targets computational and developmental biologists who want to forecast how cell populations evolve and how they will respond to genetic interventions. Predicting one-step transcriptional dynamics supports developmental-trajectory and cell-fate analyses in systems such as hematopoiesis and pancreatic islet differentiation, while the perturbation-transfer capability is relevant to designing and interpreting Perturb-seq and CRISPR screens — for example, prioritizing perturbations or anticipating differential-expression responses before running an experiment. As a "virtual cell" component, it could serve as a dynamics module within larger simulation pipelines.

#Impact

Chreode is a recent preprint, so its downstream influence and adoption are not yet established. Its main conceptual contribution is showing that a model pretrained only on unperturbed developmental dynamics can transfer to perturbation prediction, and that imposing an interpretable geometric structure (flow, rotation, and noise) on cell-state transitions can improve predictive accuracy over less-structured baselines such as PRESCIENT. Key limitations include reliance on a mouse embryonic training corpus, which may constrain generalization to human or adult tissues; the absence of released pretrained weights, which limits immediate reuse; and benchmarks reported on a focused set of differentiation and perturbation tasks rather than across a broad, standardized suite. As an unreviewed preprint, its results await independent validation.

Citation

Preprint

DOI: 10.48550/arXiv.2605.28111

DOI: 10.48550/arXiv.2605.28111

Openness

Unclassified
Missing required components

Tags

cell_fate_predictioncrispr_perturbationdevelopmental_trajectory_modelingdiffusion_transformergenerativemouse_embryoperturbation_predictionself_supervisedtranscriptomicsvariational_autoencoderworld_model

Resources

Research Paper