Generative modeling reveals the connection between cellular morphology and gene expression

Shuo Wen, Ramon Viñas Torné, Johannes Bues, Camille Lambert, Nadia Grenningloh, Timothee Ferrari, Elisa Bugani, Joern Pezoldt, Jillian Love, Wouter Karthaus, Bart Deplancke, Maria Brbic

Track: Full / long paper (5-8 pages)

Keywords: Multimodal generative modeling, Single-cell transcriptomics, Cellular morphology, Imaging–transcriptomics integration

Abstract: The understanding of how transcriptional programs give rise to cellular morphology, and how morphological features reflect and influence cell identity and function remains limited. This is due in part to the lack of large-scale datasets pairing the two modalities, as well as the absence of computational frameworks capable of modeling their cross-modal structure. Here, we introduce COSMIC, a bidirectional generative framework that enables quantitative decomposition of transcriptional variance reflected in morphology and morphological variance explained by gene expression. COSMIC builds on a foundation model trained on over 21 million segmented nuclei and couples it with existing transcriptomic embeddings. To enable cross-modal learning, we leveraged a newly generated multimodal dataset acquired using IRIS, a technology that captures high-resolution images and transcriptomes from the same single cells at scale. COSMIC accurately modeled cell type identity, establishing a quantitative link between morphological phenotypes and underlying gene expression. In prostate cancer cells, COSMIC identified morphological and transcriptomic differences between chemotherapy drug treatment-responsive and -resistant cells. Together, these results demonstrate that generative modeling powered by paired single-cell measurements can capture the bidirectional flow of information between cellular form and gene expression, opening new avenues for mechanistic discovery and predictive modeling in both basic and translational cell biology.

Anonymization: This submission has been anonymized for double-blind review via the removal of identifying information such as names, affiliations, and identifying URLs.

Submission Number: 22