Virtual experiments bridge sequence and microscopy with generative models
- 1University of California, San Francisco
Abstract
Large-scale screening and mapping efforts have produced vast libraries of perturbation-readout data. Converting these measurements into mechanistic insights requires models that link perturbation and genetic input to phenotypes, i.e., labels from experimental readouts, which are usually task specific. We propose a different, virtual experiment modeling approach: train generative models to recreate readouts conditioned on the experimental context, and then let established downstream models extract phenotypes from the synthetic data. As an illustrative case, we develop a bidirectional sequence-image generative framework, CELL-FM, that maps protein sequence and cellular context to fluorescence microscopy images and back, enabling in silico localization prediction, image-conditioned functional motif analysis and generation, and large-scale virtual mutagenesis revealing the amino acid features controlling condensate formation of intrinsically disordered peptides. This approach decouples representation learning from task-specific annotation, reuses rich experimental modalities across many downstream tasks, and preserves the spatial and organizational detail that hand-crafted labels often discard.
Related
- Supervised 3D Virtual Fluorescence and Pseudo-H&E Staining of Fresh Bulk Tissues via Multimodal qOBM and Fluorescence Microscopy
- PRAXIS-VirtualCell: A Programmable and Trustworthy Framework for Agentic Virtual Cell Experiments
- Speciesformer learns conserved cellular states for cross-species generative virtual cell modeling
- Diffusion MR Microscopy of the Human Hippocampus at 50 μm Resolution at 14.1 T for 3D Virtual Histology
- On doubting image quality assessment metrics for microscopy virtual staining
BibTeX
@misc{zheng2026virtual,
title = {{Virtual experiments bridge sequence and microscopy with generative models}},
author = {D. Zheng and K. Hong and B. Huang},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.13.751243},
url = {https://www.biorxiv.org/content/10.64898/2026.09.13.751243v1},
note = {CC BY-NC},
}
RIS
TY - UNPB
TI - Virtual experiments bridge sequence and microscopy with generative models
AU - D. Zheng
AU - K. Hong
AU - B. Huang
PY - 2026
DA - 2026/09/13
PB - bioRxiv
DO - 10.64898/2026.09.13.751243
UR - https://www.biorxiv.org/content/10.64898/2026.09.13.751243v1
AB - Large-scale screening and mapping efforts have produced vast libraries of perturbation-readout data. Converting these measurements into mechanistic insights requires models that link perturbation and genetic input to phenotypes, i.e., labels from experimental readouts, which are usually task specific. We propose a different, virtual experiment modeling approach: train generative models to recreate readouts conditioned on the experimental context, and then let established downstream models extract phenotypes from the synthetic data. As an illustrative case, we develop a bidirectional sequence-image generative framework, CELL-FM, that maps protein sequence and cellular context to fluorescence microscopy images and back, enabling in silico localization prediction, image-conditioned functional motif analysis and generation, and large-scale virtual mutagenesis revealing the amino acid features controlling condensate formation of intrinsically disordered peptides. This approach decouples representation learning from task-specific annotation, reuses rich experimental modalities across many downstream tasks, and preserves the spatial and organizational detail that hand-crafted labels often discard.
ER -