MapPFN: Learning Causal Perturbation Maps in Context

Marvin Sextro; Weronika Kłos; Gabriel Dernbach

cs.LGJan 28, 2026

MapPFN: Learning Causal Perturbation Maps in Context

Authors: Marvin Sextro, Weronika Kłos, Gabriel Dernbach

Organizations: Machine Learning Group, Technische Universität Berlin, Berlin, Germany · Berlin Institute for the Foundations of Learning and Data (BIFOLD) · Aignostics, Berlin, Germany · Institute of Pathology, Charité - Universitätsmedizin Berlin, Berlin, Germany

Abstract

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 gene sets. Our results show that combining synthetic pre-training with fine-tuning on real single-cell data improves perturbation predictions across biological contexts. The code, model and data are available at https://marvinsxtr.github.io/MapPFN.

Figures & tables

Figure 1: MapPFN overview. MapPFN uses in-context learning (ICL) to predict perturbation effects in unseen biological contexts. During pre-training, we draw structural causal models (SCMs) or synthetic gene regulatory networks (GRNs)

\psi

to generate samples from the observational distribution

\mathbf{Y}^{\text{obs}}

and a context set of interventional distributions

\mathcal{C}=\{(t_{k},\mathbf{Y}^{\text{int}}_{k})\}_{k=1}^{K}

, where

t_{k}

denotes a perturbation (do-intervention). Given

\smash{\mathbf{Y}^{\text{obs}}}

and the context set

\mathcal{C}

, MapPFN predicts post-perturbation distributions

\mathbf{Y}^{\text{int}}_{q}

arising from unseen interventions

t_{q}

. During pre-training, MapPFN meta-learns how to map between pre- and post-perturbation distributions across many causal structures

\psi

by minimizing

\mathcal{L}(\hat{\mathbf{Y}}_{q}^{\text{int}},\mathbf{Y}^{\text{int}}_{q})

. At inference time, MapPFN predicts cell-level post-perturbation distributions

\mathbf{Y}^{\text{int}}_{q}\in\mathbb{R}^{\text{cells}\times\text{genes}}

in one step through amortized inference, without requiring knowledge of the underlying causal structure

\psi

Methods	Covariates	Observational	Interventional
CPA, CondOT, CellFlow	✓	✗	✗
MFM, STATE	✓	✓	✗
MapPFN (ours)	✓	✓	✓

Table 1: Overview of perturbation models by conditioning capability. Columns indicate whether a method conditions on covariates, observational populations, or interventional populations. While all baselines require interventional data as a supervision target, MapPFN uniquely conditions on interventional data via in-context learning.

Method	$\text{W}_{2}$ $\downarrow$	MMD ( $\times 10^{-3}$ ) $\downarrow$	RMSE $\downarrow$	PDS $\downarrow$	MR $\rightarrow 1$
CondOT [ 47 ]	$13.85\pm 0.12$	$5.14\pm 0.01$	$0.15\pm 0.00$	$0.11\pm 0.02$	$0.09\pm 0.01$
MFM [ 13 ]	$\resizebox{1492769}{422343}{{13.73}}\pm 0.16$	$4.81\pm 0.19$	$0.15\pm 0.01$	$0.09\pm 0.03$	$0.12\pm 0.00$
MapPFN (ours)	$\resizebox{1492769}{422343}{{13.69}}\pm 0.05$	$\resizebox{1165088}{422343}{{4.28}}\pm 0.06$	$\resizebox{1165088}{422343}{{0.14}}\pm 0.00$	$\resizebox{1165088}{422343}{{0.01}}\pm 0.01$	$\resizebox{1165088}{422343}{{0.99}}\pm 0.02$
Identity	$17.61\pm 0.14$	$12.98\pm 0.35$	$0.28\pm 0.01$	$0.49\pm 0.01$	$0.00\pm 0.00$
Observed	$9.82\pm 0.08$	$3.66\pm 0.06$	$0.07\pm 0.00$	$0.00\pm 0.00$	$1.00\pm 0.00$

Table 2: Evaluation of MapPFN within a prior of linear SCMs. Mean

\pm

std over three training seeds. Bold indicates results within one standard deviation of the best. In this controlled setting, MapPFN successfully meta-learns perturbation prediction.

Dataset	Method	$\text{W}_{2}$ $\downarrow$	MMD ( $\times 10^{-3}$ ) $\downarrow$	RMSE $\downarrow$	PDS $\downarrow$	MR $\rightarrow 1$	AUPRC $\uparrow$
Melanoma	CPA [ 11 ]	$\resizebox{1492769}{422343}{{15.97}}\pm 0.82$	$152.13\pm 46.92$	$0.13\pm 0.01$	$0.49\pm 0.01$	$0.71\pm 0.07$	$0.03\pm 0.01$
	CondOT [ 47 ]	$22.19\pm 0.91$	$\resizebox{1165088}{422343}{{6.78}}\pm 0.33$	$\resizebox{1165088}{422343}{{0.10}}\pm 0.00$	$0.06\pm 0.02$	$0.04\pm 0.00$	$0.41\pm 0.05$
	MFM [ 13 ]	$20.75\pm 1.05$	$\resizebox{1165088}{422343}{{6.50}}\pm 0.46$	$\resizebox{1165088}{422343}{{0.09}}\pm 0.01$	$0.11\pm 0.05$	$0.11\pm 0.01$	$0.46\pm 0.07$
	CellFlow [ 12 ]	$22.28\pm 0.59$	$\resizebox{1165088}{422343}{{6.80}}\pm 0.49$	$\resizebox{1165088}{422343}{{0.10}}\pm 0.01$	$0.40\pm 0.02$	$0.02\pm 0.00$	$0.20\pm 0.06$
	STATE [ 14 ]	$20.79\pm 0.83$	$7.39\pm 1.19$	$\resizebox{1165088}{422343}{{0.09}}\pm 0.01$	$0.17\pm 0.18$	$\resizebox{1165088}{422343}{{0.95}}\pm 0.05$	$0.42\pm 0.23$
	MapPFN (pre-trained)	$22.25\pm 1.33$	$63.34\pm 17.79$	$0.32\pm 0.04$	$0.22\pm 0.04$	$\resizebox{1165088}{422343}{{1.01}}\pm 0.05$	$0.34\pm 0.07$

Table 3: Comparison of MapPFN against baselines across two single-cell perturbation datasets. Benchmark on a melanoma [ 4 ] and a leukemia [ 5 ] cell line. We report MapPFN (1) pre-trained on synthetic data and (2) fine-tuned on real data. MapPFN improves perturbation predictions across biological contexts by combining synthetic pre-training with fine-tuning on real single-cell data. The Mean and Linear baselines predict a single bulk profile per perturbation, so distributional metrics do not apply (

-

). Mean

\pm

std over five data splits (see Appendix D.1 ), each averaged over ten resampling seeds. Bold indicates results within one standard deviation of the best.

Configuration	$\text{W}_{2}$ $\downarrow$	MMD ( $\times 10^{-3}$ ) $\downarrow$	RMSE $\downarrow$	PDS $\downarrow$	MR $\rightarrow 1$	AUPRC $\uparrow$
MapPFN (pre-trained)	$22.25\pm 1.33$	$63.34\pm 17.79$	$0.32\pm 0.04$	$0.22\pm 0.04$	$1.01\pm 0.05$	$0.34\pm 0.07$
$-$ counterfactual prior	$69.15\pm 7.82$	$143.51\pm 7.78$	$0.94\pm 0.06$	$0.18\pm 0.02$	$3.16\pm 0.37$	$0.08\pm 0.03$
$-$ interventional context	$40.99\pm 4.93$	$101.05\pm 9.67$	$0.65\pm 0.06$	$0.29\pm 0.04$	$1.85\pm 0.18$	$0.25\pm 0.05$
MapPFN (fine-tuned)	$21.05\pm 0.62$	$6.57\pm 0.56$	$0.09\pm 0.01$	$0.02\pm 0.01$	$0.98\pm 0.01$	$0.62\pm 0.02$
MapPFN (random init)	$24.34\pm 0.90$	$52.33\pm 3.49$	$0.31\pm 0.02$	$0.19\pm 0.06$	$1.13\pm 0.02$	$0.09\pm 0.03$

Table 4: Ablation of the counterfactual paired prior, interventional context and synthetic pre-training on the melanoma dataset. Removing the counterfactual prior replaces paired data with unpaired interventional distributions. Removing the interventional context implies conditioning only on observational data. Random init trains the same architecture from scratch on real data, without synthetic pre-training. Mean

\pm

std over five data splits, each averaged over ten resampling seeds.

Appendix figures & tables8 assets

Supplementary material from the paper’s appendix.

Appendix

Symbol	Description	Range
$k$	Number of gene groups/modules	$\{1,2,3\}$
$p$	Sparsity term (avg. regulators per gene)	$[1.5,3.0]$
$\delta_{\text{in}}$	In-degree uniformity term	$[10,300]$
$\delta_{\text{out}}$	Out-degree uniformity term	$[1,30]$
$w$	Modularity term (within-group connectivity)	$[1,900]$

Appendix

Table 5: GRN structure parameters for the graph generator.

Symbol	Description	Range
Simulation parameters
$k$	Interaction strengths	$[1.0,5.0]$
$b$	Master regulator production rates	$[0.5,2.0]\cup[3.0,5.0]$
$\gamma$	Hill function coefficients (nonlinearity)	$[1.5,2.5]$
$\lambda$	Decay rates per gene	$[0.5,1.0]$
$\zeta$	Stochastic process noise scale	$[0.5,1.5]$

Appendix

Table 6: SERGIO simulation and technical noise parameters.

Figure 4: Data split. Each box represents a dataset

\mathbf{Y}^{\text{int}}_{ij}\in\mathbb{R}^{N\times d}

sampled from the SCM

\psi_{i}

under treatment

t_{j}

. Green boxes are part of the training data and purple boxes are withheld for evaluation.

Method	Hyperparameter	Search Range
MapPFN	Classifier-free guidance weight	$\{1.0,1.5,2.0,2.5,3.0\}$
CPA	Following the tuning protocol of PerturBench [ 51 ] .
CondOT	Hidden dimensions	$\{64,128,256\}$
	Hidden layers	$\{2,3,4\}$
	Learning rate	$\{10^{-3},10^{-4},10^{-5}\}$
MFM	k-nearest neighbors	$\{0,10,50,100\}$

Appendix

Table 7: Hyperparameter search ranges for each method.

Panel of Figure 5 — Figure 5: MapPFN scales with more data at inference time. Both the number of perturbation experiments in context and the number of cells per perturbation improve prediction quality, demonstrating that MapPFN adapts to the available data via in-context learning.

Figure 6: Coverage of the synthetic biological prior over real single-cell data distributions. Distributions of non-zero expression values (left) and log fold changes (right) for the synthetic biological prior, the melanoma [ 4 ] and leukemia [ 5 ] datasets. Log fold change values are clipped to the

[1,99]

percentile range for visualization.

Architecture	Parameters	$\text{W}_{2}$ $\downarrow$	MMD ( $\times 10^{-3}$ ) $\downarrow$	RMSE $\downarrow$	PDS $\downarrow$	MR $\rightarrow 1$	AUPRC $\uparrow$
MMDiT [ 22 ]	25.97M	$\resizebox{1492769}{422343}{{22.25}}\pm 1.33$	$\resizebox{1492769}{422343}{{63.34}}\pm 17.79$	$\resizebox{1165088}{422343}{{0.32}}\pm 0.04$	$\resizebox{1165088}{422343}{{0.22}}\pm 0.04$	$\resizebox{1165088}{422343}{{1.01}}\pm 0.05$	$\resizebox{1165088}{422343}{{0.34}}\pm 0.07$
DiT [ 43 ]	27.66M	$23.87\pm 1.58$	$\resizebox{1492769}{422343}{{51.47}}\pm 18.50$	$\resizebox{1165088}{422343}{{0.35}}\pm 0.06$	$\resizebox{1165088}{422343}{{0.19}}\pm 0.04$	$1.12\pm 0.04$	$0.22\pm 0.08$

Appendix

Table 8: Architecture ablation comparing MMDiT against DiT. Performance on the melanoma dataset [ 4 ] . Mean

\pm

std over five data splits, each averaged over ten resampling seeds. Bold indicates results within one standard deviation of the best.

Holdout	Method	$\text{W}_{2}$ $\downarrow$	MMD ( $\times 10^{-3}$ ) $\downarrow$	RMSE $\downarrow$	PDS $\downarrow$	MR $\rightarrow 1$	AUPRC $\uparrow$
IFN- $\gamma$	CondOT [ 47 ]	$22.19\pm 0.91$	$\resizebox{1165088}{422343}{{6.78}}\pm 0.33$	$\resizebox{1165088}{422343}{{0.10}}\pm 0.00$	$0.06\pm 0.02$	$0.04\pm 0.00$	$0.41\pm 0.05$
	STATE [ 14 ]	$\resizebox{1492769}{422343}{{20.79}}\pm 0.83$	$7.39\pm 1.19$	$\resizebox{1165088}{422343}{{0.09}}\pm 0.01$	$0.17\pm 0.18$	$\resizebox{1165088}{422343}{{0.95}}\pm 0.05$	$0.42\pm 0.23$
	MapPFN (pre-trained)	$22.25\pm 1.33$	$63.34\pm 17.79$	$0.32\pm 0.04$	$0.22\pm 0.04$	$\resizebox{1165088}{422343}{{1.01}}\pm 0.05$	$0.34\pm 0.07$
	MapPFN (fine-tuned)	$\resizebox{1492769}{422343}{{21.05}}\pm 0.62$	$\resizebox{1165088}{422343}{{6.57}}\pm 0.56$	$\resizebox{1165088}{422343}{{0.09}}\pm 0.01$	$\resizebox{1165088}{422343}{{0.02}}\pm 0.01$	$\resizebox{1165088}{422343}{{0.98}}\pm 0.01$	$\resizebox{1165088}{422343}{{0.62}}\pm 0.02$
TIL co-culture	CondOT [ 47 ]	$17.59\pm 0.41$	$8.86\pm 0.66$	$0.11\pm 0.01$	$\resizebox{1165088}{422343}{{0.06}}\pm 0.01$	$0.06\pm 0.01$	$0.49\pm 0.12$
	STATE [ 14 ]	$\resizebox{1492769}{422343}{{16.47}}\pm 0.36$	$\resizebox{1165088}{422343}{{8.28}}\pm 0.55$	$\resizebox{1165088}{422343}{{0.09}}\pm 0.01$	$0.15\pm 0.03$	$0.91\pm 0.01$	$0.50\pm 0.07$

Appendix

Table 9: Performance across three holdout cell states of the melanoma dataset. Mean

\pm

std over five data splits, each averaged over ten resampling seeds. Bold indicates results within one standard deviation of the best for each holdout.

Single-Cell Perturbation Modeling

Single-cell perturbation modeling predicts how genetic or chemical interventions change cellular states across cells and contexts.

See all 61 papers

Causal Cellular Context Transfer Learning (C3TL): An Efficient Architecture for Prediction of Unseen Perturbation Effects
Mar 13, 2026Michael Scholkemper, Sach MukherjeeTransfer Learning Cross-Domain Transfer Learning
Statistics and Machine Learning, German Center for Neurodegenerative Diseases (DZNE), Bonn, Germany. · Statistics and Machine Learning, German Center for Neurodegenerative Diseases (DZNE) Bonn, Germany, University of Bonn, Germany & University of Cambridge, United Kingdom.
PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling
Jul 26, 2026Yuche Gao, José Miguel Hernández-Lobato, Siyuan GuoSynthetic Data Pretraining Structural Causal Models
University of Cambridge, Cambridge, United Kingdom · Prior Labs, Freiburg, Germany
PerturbMap: Cross-Context Transfer of Single-Cell Perturbation Responses
Jul 30, 2026Panpan Cui, Yiqi Liu, Wenhao SunSingle-Cell Perturbation Modeling Cross-Domain Transfer Learning
School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences · Institute of Computing Technology, CAS; University of Chinese Academy of Sciences · 3Hong Kong University of Science and Technology

Mar 13, 2026J/K move · Enter open · S save

Causal Cellular Context Transfer Learning (C3TL): An Efficient Architecture for Prediction of Unseen Perturbation Effects

Michael Scholkemper, Sach Mukherjee

Statistics and Machine Learning, German Center for Neurodegenerative Diseases (DZNE), Bonn, Germany. · Statistics and Machine Learning, German Center for Neurodegenerative Diseases (DZNE) Bonn, Germany, University of Bonn, Germany & University of Cambridge, United Kingdom.

Transfer Learning Cross-Domain Transfer Learning Causal Inference

Open paper AskPDF arXiv

Predicting the effects of chemical and genetic perturbations on quantitative cell states is a central challenge in computational biology, molecular medicine and drug discovery. Recent work has leveraged large-scale single-cell data and massive foundation models to address this task. However, such computational resources and extensive datasets are not always accessible in academic or clinical settings, hence limiting utility. Here we propose a lightweight framework for perturbation effect prediction that exploits the structured nature of biological interventions and specific inductive biases/invariances. Our approach leverages available information concerning perturbation effects to allow generalization to novel contexts and requires only widely-available bulk molecular data. Extensive testing, comparing predictions of context-specific perturbation effects against real, large-scale interventional experiments, demonstrates accurate prediction in new contexts. The proposed approach is competitive with SOTA foundation models but requires simpler data, much smaller model sizes and less time. Focusing on robust bulk signals and efficient architectures, we show that accurate prediction of perturbation effects is possible without proprietary hardware or very large models, hence opening up ways to leverage causal learning approaches in biomedicine generally.

Abstract

Single-Cell Perturbation Modeling

Explore similar work

Causal Cellular Context Transfer Learning (C3TL): An Efficient Architecture for Prediction of Unseen Perturbation Effects

PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling

PerturbMap: Cross-Context Transfer of Single-Cell Perturbation Responses