EMBER: Contextualized gene representations enable compositional prediction across cellular perturbations
- 1Carnegie Mellon University
Abstract
Predicting the effects of individual and combined perturbations is central to identifying context-specific vulnerabilities and designing targeted interventions. Yet learning gene representations that integrate functional relationships with cellular state and transfer across perturbation tasks remains challenging. Here, we present EMBER, a gene-centric foundation model that learns context-dependent functional representations of genes. EMBER combines interaction-guided contrastive learning with masked expression reconstruction during pretraining on a single-cell corpus curated for diversity and balanced sampling across cell types and experimental batches. EMBER decouples gene representation learning from task-specific prediction through a composable embedding framework: the pretrained encoder remains frozen, while lightweight probes combine contextualized gene embeddings to predict individual and combined perturbation effects. The same pretrained representations support single-gene perturbation-response prediction, digenic interaction prediction, and multi-target drug-response prediction. EMBER improves cross-context perturbation-response prediction and genetic-interaction ranking relative to evaluated baselines. EMBER also prioritized SCFD1, a mediator of autophagosome-lysosome fusion, as a candidate dependency during mTOR inhibition. Together, these results establish contextualized gene embeddings as reusable building blocks for modeling genetic and pharmacological perturbations, supporting the prioritization of genetic interactions and context-specific interventions for experimental testing.
Related
- Regulon-informed cellular representations reveal task-dependent generalization in drug combination prediction
- Intrinsic cellular persistent firing sustains hippocampal spatial representations during working memory
- Stable-Shift: Biologically Structured Prediction of Transcriptional Responses to Unseen Gene Perturbations
- Beyond the Final Layer: Evaluating Single-Cell Foundation Model Representations for Molecular Prediction
- The recoverable resolution of cellular perturbation-response prediction
BibTeX
@misc{ho2026ember,
title = {{EMBER: Contextualized gene representations enable compositional prediction across cellular perturbations}},
author = {N. Ho and E. P. Xing and J. Ma},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.28.762655},
url = {https://www.biorxiv.org/content/10.64898/2026.10.28.762655v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - EMBER: Contextualized gene representations enable compositional prediction across cellular perturbations
AU - N. Ho
AU - E. P. Xing
AU - J. Ma
PY - 2026
DA - 2026/10/28
PB - bioRxiv
DO - 10.64898/2026.10.28.762655
UR - https://www.biorxiv.org/content/10.64898/2026.10.28.762655v1
AB - Predicting the effects of individual and combined perturbations is central to identifying context-specific vulnerabilities and designing targeted interventions. Yet learning gene representations that integrate functional relationships with cellular state and transfer across perturbation tasks remains challenging. Here, we present EMBER, a gene-centric foundation model that learns context-dependent functional representations of genes. EMBER combines interaction-guided contrastive learning with masked expression reconstruction during pretraining on a single-cell corpus curated for diversity and balanced sampling across cell types and experimental batches. EMBER decouples gene representation learning from task-specific prediction through a composable embedding framework: the pretrained encoder remains frozen, while lightweight probes combine contextualized gene embeddings to predict individual and combined perturbation effects. The same pretrained representations support single-gene perturbation-response prediction, digenic interaction prediction, and multi-target drug-response prediction. EMBER improves cross-context perturbation-response prediction and genetic-interaction ranking relative to evaluated baselines. EMBER also prioritized SCFD1, a mediator of autophagosome-lysosome fusion, as a candidate dependency during mTOR inhibition. Together, these results establish contextualized gene embeddings as reusable building blocks for modeling genetic and pharmacological perturbations, supporting the prioritization of genetic interactions and context-specific interventions for experimental testing.
ER -