MapPFN: Learning Causal Perturbation Maps in Context
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914538474962944 |
|---|---|
| author | Sextro, Marvin Kłos, Weronika Dernbach, Gabriel |
| author_facet | Sextro, Marvin Kłos, Weronika Dernbach, Gabriel |
| contents | Planning effective interventions in biological systems requires treatment-effect models that adapt to unseen biological contexts by identifying their specific underlying mechanisms. Yet single-cell perturbation datasets span only a handful of biological contexts, and existing methods cannot leverage new interventional evidence at inference time to adapt beyond their training data. To meta-learn a perturbation effect estimator, we present MapPFN, a prior-data fitted network (PFN) pre-trained on a synthetic biological prior with causal interventions, decoupling pre-training from limited wet-lab data. Unlike existing methods, MapPFN uses in-context learning to map a sequence of experiments to a post-perturbation distribution, enabling a single pre-trained model to adapt to new datasets and arbitrary gene sets at inference time. Zero-shot, MapPFN identifies differentially expressed genes on par with models trained on real single-cell data, and fine-tuning further improves predictions across biological contexts. Our code, model and data are available at https://marvinsxtr.github.io/MapPFN. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_21092 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MapPFN: Learning Causal Perturbation Maps in Context Sextro, Marvin Kłos, Weronika Dernbach, Gabriel Machine Learning Planning effective interventions in biological systems requires treatment-effect models that adapt to unseen biological contexts by identifying their specific underlying mechanisms. Yet single-cell perturbation datasets span only a handful of biological contexts, and existing methods cannot leverage new interventional evidence at inference time to adapt beyond their training data. To meta-learn a perturbation effect estimator, we present MapPFN, a prior-data fitted network (PFN) pre-trained on a synthetic biological prior with causal interventions, decoupling pre-training from limited wet-lab data. Unlike existing methods, MapPFN uses in-context learning to map a sequence of experiments to a post-perturbation distribution, enabling a single pre-trained model to adapt to new datasets and arbitrary gene sets at inference time. Zero-shot, MapPFN identifies differentially expressed genes on par with models trained on real single-cell data, and fine-tuning further improves predictions across biological contexts. Our code, model and data are available at https://marvinsxtr.github.io/MapPFN. |
| title | MapPFN: Learning Causal Perturbation Maps in Context |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2601.21092 |