# Bison: Cross-Dataset Learning for Unseen-Compound Perturbation Prediction

arXiv: https://arxiv.org/abs/2609.32467 · HTML: https://mlsanity.com/paper/2609.32467/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 26 references that are in the map.
- First posted on arXiv 26 Sep 2026.

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

- [Simple and Effective Masked Diffusion Language Models](https://mlsanity.com/paper/2406.07524/) (2024)
- [Finite Scalar Quantization: VQ-VAE Made Simple](https://mlsanity.com/paper/2309.15505/) (2023)
- [Predicting Cellular Responses to Novel Drug Perturbations at a Single-Cell Resolution](https://mlsanity.com/paper/2204.13545/) (2022)
- [PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis](https://mlsanity.com/paper/2408.10609/) (2024)
- [In-silico biological discovery with large perturbation models](https://mlsanity.com/paper/2503.23535/) (2025)
- [Scalable Single-Cell Gene Expression Generation with Latent Diffusion Models](https://mlsanity.com/paper/2511.02986/) (2025)
- [Chem-PerturBridge: a harmonized compendium of small molecule perturbation transcriptomic effects](https://mlsanity.com/paper/2605.31522/) (2026)

## Abstract (arXiv)

Predicting transcriptional responses to unseen compounds is limited by fragmented chemical coverage and heterogeneous experimental platforms and gene panels. To assess molecular generalization across these settings, we build on Chem-PerturBridge to benchmark eight datasets with 16,771 compounds, withholding test compounds from every training dataset. This comparison reveals that high overall response agreement can coexist with weak prediction of drug-specific differences, despite reproducible signals across repeated measurements. To exploit complementary chemical supervision while targeting these differences, we introduce Bison: a shared gene representation connects native panels, while two discrete diffusion models compose context-dependent responses with molecular deviations learned through matched drug-contrast supervision. A single Bison model jointly trained across all eight datasets achieves the highest mean overall-response and drug-contrast Pearson correlations on the full benchmark in comparison with 11 methods trained independently per dataset. Compared with dataset-specific training of the same architecture, joint training increases mean drug-contrast correlation by 27.4%, with gains across all eight datasets and improvements in overall response prediction. These results demonstrate how matched drug contrasts turn complementary screens into shared molecular supervision for unseen-drug response prediction while preserving native gene measurements.