SOFisher: Reinforcement Learning-Guided Experiment Designs for Spatial Omics

Spatial omics technologies enable the precise detection of proteins and RNAs at high spatial resolution. Designing spatial omics experiments requires careful consideration of "what" targets to measure and "where" to position the field of views (FOVs). Current FOV sampling strategies often involve acquiring densely sampled FOVs and stitching them together, which is time-consuming, resource-intensive, and sometimes impossible. To optimize FOV sampling strategies, we developed SOFisher, a reinforcement learning-based framework that harnesses the knowledge gained from the sequence of previously sampled FOVs to guide the selection of the next FOV position, to improve the efficiency of capturing more regions of interest. We rigorously evaluated SOFishers performance using comprehensive simulations based on real spatial datasets, and our results clearly demonstrated that SOFisher consistently outperformed the conventional approach across various metrics. SOFishers robustness and generalizability were further validated through cross-domain generalization tests and its adaptability to varying FOV sizes. On a real Alzheimers Disease (AD) dataset, SOFisher successfully guided the selection of FOVs containing neurofibrillary tangles and amyloid-{beta} plaques in both single and dual target tissue landmark scenarios. Remarkably, SOFisher-guided experiment design of spatial single-omics on limited tissue areas yielded insights into AD-related cell states, subtypes, and gene programs previously obtained through extensive spatial multi-omics experiments. SOFisher has the potential to revolutionize the experiment design of spatial biology.