SHERLOCK: Structured representation learning and causal inference of downstream perturbation effects

Abstract

Understanding the effects of genetic, molecular, and experimental perturbations is essential for decoding cellular mechanisms and guiding biomedical interventions. Existing computational approaches are typically designed for individual tasks, such as predicting perturbation responses, characterizing downstream transcriptional effects, or modeling perturbation combinations, and therefore do not provide a unified framework for learning interpretable perturbation representations while enabling causal analysis of downstream effects and characterization of condition-dependent responses. We present SHERLOCK, an interpretable deep generative framework for single-cell perturbation analysis that represents perturbation effects as structured interventions on a latent baseline cellular state. SHERLOCK learns correlated and sparse perturbation representations that organize genetic and pharmacological perturbations according to shared transcriptional responses. % By formulating perturbations as interventions within a structural causal model, it enables counterfactual estimation of their downstream transcriptional effects under explicit identifiability assumptions. The same framework quantifies how perturbation responses vary across conditions and compositionally models combinatorial perturbations, enabling prediction of held-out combinations and classification of genetic interactions. Across genome-scale CRISPR, chemical, and spatial perturbation datasets, SHERLOCK recovers perturbation relationships concordant with known biological pathways and pharmacological properties, identifies condition-dependent responses, and predicts combinatorial perturbation effects. Together, SHERLOCK provides a unified framework for interpretable and causal analysis of perturbation effects across diverse single-cell perturbation experiments.

Transcriptional perturbation effects remain structured beyond the leading global trend
Q. Liu, Q. Zhang, Y. Chen +3
bioRxiv5 Oct 2026PreprintCC BY-NC-NDFull textGenetics & genomicsbioRxiv
Where single-cell foundation models help: a benchmark of annotation, perturbation and regulatory inference against simple baselines
F. A. Cupaioli, I. Merelli
bioRxiv3 Nov 2026PreprintAll rights reservedFull textBioinformatics & computational biologybioRxiv
MRFlow: Mechanism-Structured Residual Flow Matching for Virtual Cell Perturbation Prediction
Haojie Yang, Ran Su
arXiv1 Oct 2026PreprintCC BY 4.0Full textBioinformatics & computational biologyarXiv
Change in the demographic dynamics of a spatially structured population of a colonial waterbird after a perturbation affecting a large colony.
Killian A Gregory, Odin Rumianowski, Jean-Dominique Lebreton +2
Proceedings. Biological sciences1 Oct 2026Peer-reviewedCC BYFull textEcologyEurope PMC
A biological-response compound representation allows chemical perturbation prediction across cell lines
L. Le Breton, L. Kaufmann, E. Carraz-Billat +2
bioRxiv28 Sep 2026PreprintCC BYFull textBioinformatics & computational biologybioRxiv

Cite

BibTeX RIS

BibTeX

@misc{zhang2026sherlock,
  title = {{SHERLOCK: Structured representation learning and causal inference of downstream perturbation effects}},
  author = {M. Zhang and J. D. Myers and L. Shi and R. M. Giglio and S. Chatterjee and J. L. McFaline-Figueroa and E. Azizi},
  howpublished = {bioRxiv},
  year = {2026},
  month = sep,
  doi = {10.64898/2026.09.25.754573},
  url = {https://www.biorxiv.org/content/10.64898/2026.09.25.754573v1},
  note = {CC BY-NC-ND},
}

RIS

TY  - UNPB
TI  - SHERLOCK: Structured representation learning and causal inference of downstream perturbation effects
AU  - M. Zhang
AU  - J. D. Myers
AU  - L. Shi
AU  - R. M. Giglio
AU  - S. Chatterjee
AU  - J. L. McFaline-Figueroa
AU  - E. Azizi
PY  - 2026
DA  - 2026/09/25
PB  - bioRxiv
DO  - 10.64898/2026.09.25.754573
UR  - https://www.biorxiv.org/content/10.64898/2026.09.25.754573v1
AB  - Understanding the effects of genetic, molecular, and experimental perturbations is essential for decoding cellular mechanisms and guiding biomedical interventions. Existing computational approaches are typically designed for individual tasks, such as predicting perturbation responses, characterizing downstream transcriptional effects, or modeling perturbation combinations, and therefore do not provide a unified framework for learning interpretable perturbation representations while enabling causal analysis of downstream effects and characterization of condition-dependent responses. We present SHERLOCK, an interpretable deep generative framework for single-cell perturbation analysis that represents perturbation effects as structured interventions on a latent baseline cellular state. SHERLOCK learns correlated and sparse perturbation representations that organize genetic and pharmacological perturbations according to shared transcriptional responses. % By formulating perturbations as interventions within a structural causal model, it enables counterfactual estimation of their downstream transcriptional effects under explicit identifiability assumptions. The same framework quantifies how perturbation responses vary across conditions and compositionally models combinatorial perturbations, enabling prediction of held-out combinations and classification of genetic interactions. Across genome-scale CRISPR, chemical, and spatial perturbation datasets, SHERLOCK recovers perturbation relationships concordant with known biological pathways and pharmacological properties, identifies condition-dependent responses, and predicts combinatorial perturbation effects. Together, SHERLOCK provides a unified framework for interpretable and causal analysis of perturbation effects across diverse single-cell perturbation experiments.
ER  -

Abstract

Related

Cite