Quackenbush, D. | Search bioRxiv

bioRxiv2024

A diffusion model conditioned on compound bioactivity profiles for predicting high-content images

High-content imaging (HCI) provides a rich snapshot of compound-induced phenotypic outcomes that augment our understanding of compound mechanisms in cellular systems. Generative imaging models for HCI provide a route towards anticipating the phenotypic outcomes of chemical perturbations in silico at unprecedented scale and speed. Here, we developed Profile-Diffusion (pDIFF), a generative method leveraging a latent diffusion model conditioned on in silico bioactivity profiles to predict high-content images displaying the cellular outcomes induced by compound treatment. We trained and evaluated a pDIFF model using high-content images from a Cell Painting assay profiling 3750 molecules with corresponding in silico bioactivity profiles. Using a realistic held-out set, we demonstrate that pDIFF provides improved predictions of phenotypic responses of compounds with low chemical similarity to compounds in the training set compared to generative models trained on chemical fingerprints only. In a virtual hit expansion scenario, pDIFF yielded significantly improved expansion outcomes, thus showcasing the potential of the methodology to speed up and improve the search for novel phenotypically active molecules.

bioinformatics↗

bioRxiv2022

A high-throughput COPD bronchosphere model for disease-relevant phenotypic compound screening

COPD is the third leading cause of death worldwide, but current therapies for COPD are only effective at treating the symptoms of the disease rather than targeting the underlying pathways that are driving the pathogenic changes. The lack of targeted therapies for COPD is in part due to a lack of knowledge about drivers of disease progression and the difficulty in building relevant and high throughput models that can recapitulate the phenotypic and transcriptomic changes associated with pathogenesis of COPD. To identify these drivers, we have developed a cigarette smoke extract (CSE)-treated bronchosphere assay in 384-well plate format that exhibits CSE-induced decreases in size and increase in luminal secretion of MUC5AC. Transcriptomic changes in CSE-treated bronchospheres resemble changes that occur in human smokers both with and without COPD compared to healthy groups, indicating that this model can capture human smoking signature. To identify new targets, we ran a small molecule compound deck screening with diversity in target mechanisms of action and identified hit compounds that attenuated CSE induced changes, either decreasing spheroid size or increasing secreted mucus. This work provides insight into the utility of this bronchosphere model in examining human respiratory diseases, the pathways implicated by CSE, and compounds with known mechanisms of action for therapeutic development.

cell biology↗