flashscenic: Accelerated GRN Analysis with RegDiffusion for Large-Scale Single-Cell Data
- 1Division of Engineering in Medicine, Department of Medicine, Brigham and Women's Hospital, Harvard Medical School; Gene and Cell Therapy Institute, Mass General
Abstract
Single-cell gene regulatory network (GRN) analysis via the SCENIC framework provides biologically interpretable cell-state representations through motif-validated transcription factor (TF) regulon activities. However, sequential, CPU-bound implementations (pySCENIC) constrain scalability to highly variable genes and make the repeated executions needed to resolve network stochasticity computationally prohibitive. Furthermore, while regulon activity is hypothesized to mitigate technical batch effects, its integration performance has never been quantitatively assessed against modern data integration benchmarks. We present flashscenic, an end-to-end GPU-accelerated framework that resolves these bottlenecks and expands the practical scope of single-cell regulatory genomics. By reformulating module construction, cisTarget motif pruning, and AUCell scoring into batched GPU tensor operations, flashscenic achieves a 12- to 27-fold downstream speedup over pySCENIC, while maintaining strict numerical equivalence (Pearson r = 0.9996). Leveraging this throughput, we conducted the first systematic benchmark of nine consensus aggregation strategies across multiple independent tissue cohorts, demonstrating that discrete post-pruning recurrence voting ([≥]50% recurrence, [≥]5 targets per regulon) maximizes biological fidelity. Finally, data integration benchmarking across a 116,043-cell acute myeloid leukemia (AML) atlas quantitatively demonstrates that uncorrected TF activity provides an intrinsic, unsupervised batch-integration benefit over raw PCA. Combining it with a standard batch integration method matches or outperforms canonical expression-based integration while accurately recovering lineage-defining and oncogenic regulators (CEBPA, HOXA9). flashscenic is available via pip install flashscenic, with source code and tutorials at https://github.com/haozhu233/flashscenic.
Related
- Copy number variants (CNVs) interfere with human accelerated regions (HARs) in neurodevelopmental disorders: a large-scale cohort study
- multiomeR: a pipeline for reproducible analysis of large-scale single-nucleus Epi Multiome datasets
- Large-scale integrated single-cell analysis reveals molecular subtypes and microenvironmental remodeling in cutaneous T cell lymphoma
- TorchGWAS 1.0: GPU-accelerated GWAS at scale.
- A Differentiable, GPU-Accelerated Finite-Element Formulation in JAX for Large-Deformation Shells with Contact: Application to Patient-Specific Aortic Valve Simulation
BibTeX
@misc{zhu2026flashscenic,
title = {{flashscenic: Accelerated GRN Analysis with RegDiffusion for Large-Scale Single-Cell Data}},
author = {H. Zhu and G. Cardenal-Antolin and X. Jin and J. S. Gootenberg and O. O. Abudayyeh and D. K. Slonim},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.26.761795},
url = {https://www.biorxiv.org/content/10.64898/2026.10.26.761795v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - flashscenic: Accelerated GRN Analysis with RegDiffusion for Large-Scale Single-Cell Data
AU - H. Zhu
AU - G. Cardenal-Antolin
AU - X. Jin
AU - J. S. Gootenberg
AU - O. O. Abudayyeh
AU - D. K. Slonim
PY - 2026
DA - 2026/10/26
PB - bioRxiv
DO - 10.64898/2026.10.26.761795
UR - https://www.biorxiv.org/content/10.64898/2026.10.26.761795v1
AB - Single-cell gene regulatory network (GRN) analysis via the SCENIC framework provides biologically interpretable cell-state representations through motif-validated transcription factor (TF) regulon activities. However, sequential, CPU-bound implementations (pySCENIC) constrain scalability to highly variable genes and make the repeated executions needed to resolve network stochasticity computationally prohibitive. Furthermore, while regulon activity is hypothesized to mitigate technical batch effects, its integration performance has never been quantitatively assessed against modern data integration benchmarks. We present flashscenic, an end-to-end GPU-accelerated framework that resolves these bottlenecks and expands the practical scope of single-cell regulatory genomics. By reformulating module construction, cisTarget motif pruning, and AUCell scoring into batched GPU tensor operations, flashscenic achieves a 12- to 27-fold downstream speedup over pySCENIC, while maintaining strict numerical equivalence (Pearson r = 0.9996). Leveraging this throughput, we conducted the first systematic benchmark of nine consensus aggregation strategies across multiple independent tissue cohorts, demonstrating that discrete post-pruning recurrence voting ([≥]50% recurrence, [≥]5 targets per regulon) maximizes biological fidelity. Finally, data integration benchmarking across a 116,043-cell acute myeloid leukemia (AML) atlas quantitatively demonstrates that uncorrected TF activity provides an intrinsic, unsupervised batch-integration benefit over raw PCA. Combining it with a standard batch integration method matches or outperforms canonical expression-based integration while accurately recovering lineage-defining and oncogenic regulators (CEBPA, HOXA9). flashscenic is available via pip install flashscenic, with source code and tutorials at https://github.com/haozhu233/flashscenic.
ER -