Spectral Adaptive Repositioning for Flow-Based Single-Cell Perturbation Modeling
- 1Purdue University
Abstract
Predicting transcriptome-wide cellular responses to genetic and biomolecular perturbations is central to functional genomics and therapeutic target discovery. Existing methods assign gene positional encodings derived from arbitrary orderings or static co-expression masks built from unperturbed cells, and cannot capture the functional rewiring induced by perturbations. We present SPEAR, a generative framework built on two complementary positional mechanisms. Spectral positional encoding grounds each gene's position in the geometry of the co-expression network via continuous coordinates derived from the graph Laplacian. Adaptive repositioning then derives each gene's position from its perturbation-conditioned hidden state at every layer, allowing the attention genes exert on one another to reorganize without explicit supervision. Evaluated on genetic, pharmacological, and cytokine perturbation benchmarks, SPEAR demonstrates excellent recovery of differential gene-expression, distributional structure, and perturbation-specific identifiability. SPEAR also captures latent positional relationships that closely map to known transcription factor-target interactions. https://github.com/shouryaverma/SPEAR}{https://github.com/shouryaverma/SPEAR
Related
- DCAF: Unifying Data Validity, Evaluation Validity and Predictive Modeling for Single-cell Perturbation Simulation
- PopPert: Population-level Joint-Distribution Modeling for Single-Cell Perturbation Prediction
- PerturbBridge: Conditional Latent Schr\"{o}dinger Bridge for Single-Cell Perturbation Prediction
- Where single-cell foundation models help: a benchmark of annotation, perturbation and regulatory inference against simple baselines
- DELPHAI predicts heterogeneous perturbation responses with learned single-cell fitness
BibTeX
@misc{verma2026spectral,
title = {{Spectral Adaptive Repositioning for Flow-Based Single-Cell Perturbation Modeling}},
author = {S. Verma and M. Wang and S. D. Kadadi and N. A. Lanman and S. Mohammadi and A. Grama},
howpublished = {bioRxiv},
year = {2026},
month = nov,
doi = {10.64898/2026.11.02.763678},
url = {https://www.biorxiv.org/content/10.64898/2026.11.02.763678v1},
note = {CC BY-NC},
}
RIS
TY - UNPB
TI - Spectral Adaptive Repositioning for Flow-Based Single-Cell Perturbation Modeling
AU - S. Verma
AU - M. Wang
AU - S. D. Kadadi
AU - N. A. Lanman
AU - S. Mohammadi
AU - A. Grama
PY - 2026
DA - 2026/11/02
PB - bioRxiv
DO - 10.64898/2026.11.02.763678
UR - https://www.biorxiv.org/content/10.64898/2026.11.02.763678v1
AB - Predicting transcriptome-wide cellular responses to genetic and biomolecular perturbations is central to functional genomics and therapeutic target discovery. Existing methods assign gene positional encodings derived from arbitrary orderings or static co-expression masks built from unperturbed cells, and cannot capture the functional rewiring induced by perturbations. We present SPEAR, a generative framework built on two complementary positional mechanisms. Spectral positional encoding grounds each gene's position in the geometry of the co-expression network via continuous coordinates derived from the graph Laplacian. Adaptive repositioning then derives each gene's position from its perturbation-conditioned hidden state at every layer, allowing the attention genes exert on one another to reorganize without explicit supervision. Evaluated on genetic, pharmacological, and cytokine perturbation benchmarks, SPEAR demonstrates excellent recovery of differential gene-expression, distributional structure, and perturbation-specific identifiability. SPEAR also captures latent positional relationships that closely map to known transcription factor-target interactions. https://github.com/shouryaverma/SPEAR}{https://github.com/shouryaverma/SPEAR
ER -