# SCALE:Scalable Conditional Atlas-Level Endpoint transport for virtual cell perturbation prediction

arXiv: https://arxiv.org/abs/2603.17380 · HTML: https://mlsanity.com/paper/2603.17380/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 60 references that are in the map.
- First posted on arXiv 18 Mar 2026.

## Builds on (most cited first, 7 of 7)

- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Deep Sets](https://mlsanity.com/paper/1703.06114/) (2017)
- [How to Build the Virtual Cell with Artificial Intelligence: Priorities and Opportunities](https://mlsanity.com/paper/2409.11654/) (2024)
- [BioNeMo Framework: a modular, high-performance library for AI model development in drug discovery](https://mlsanity.com/paper/2411.10548/) (2024)
- [PerturbDiff: Functional Diffusion for Single-Cell Perturbation Modeling](https://mlsanity.com/paper/2602.19685/) (2026)
- [Diversity by Design: Addressing Mode Collapse Improves scRNA-seq Perturbation Modeling on Well-Calibrated Metrics](https://mlsanity.com/paper/2506.22641/) (2025)
- [Departures: Distributional Transport for Single-Cell Perturbation Prediction with Neural Schr"odinger Bridges](https://mlsanity.com/paper/2511.13124/) (2025)

## Abstract (arXiv)

Virtual-cell models aim to predict how cell populations respond to perturbations, but control and treated cells are measured as unpaired populations, complicating the learning of perturbation-specific effects. We present SCALE, a conditional transport model that represents cells as unordered sets and predicts treated populations without cell-level matching. A shared set-aware encoder and conditional DiT backbone learn latent transport, making endpoint supervision directly delta-aligned without an auxiliary delta objective. Across genetic, chemical, developmental and immune perturbations, SCALE recovered gene-expression changes, response directions and population structure. In CRISPR data with dominant cell-line effects, SCALE outperformed competing methods across seven metrics and maintained separation among gene-target representations rather than collapsing them into a shared region. SCALE further prioritized cytokines predicted to produce distinct immune activation and inflammatory responses. Experiments using matched PBMC samples from three donors confirmed these predicted differences. Together, SCALE enables perturbation-specific prediction from unpaired populations and supports experimental prioritization.