Active spot selection does not clearly beat random sampling in spatial transcriptomics
Benchmarking Active Spot Selection for Cost-Efficient Spatial Transcriptomics
Computer Vision and Pattern RecognitionMachine Learning
Summary
Spatial transcriptomics measures gene activity across different regions in tissue, but it can be expensive to collect data everywhere. The authors tested smarter ways to pick spots to measure so they could save costs. Using two public datasets, they found that these smarter methods did not consistently give better results than just picking spots randomly. The effectiveness depended on how many spots were sampled and the measurement used to judge performance.
What this means in practice
- •For biotech sequencing teams: Evaluate active learning spot selection to optimize sequencing cost-effectiveness in spatial gene expression studies with diverse tissue types.
- •For medical imaging analysts: Incorporate spatially aware sampling strategies cautiously when linking tissue morphology to gene expression in imaging data.
Authors
Zheyu Zhu, Junchao Zhu, Fengbei Liu, Tianyuan Yao, Gelei Xu, John Cannon, Haichun Yang, Yuankai Huo, Mert R. Sabuncu, Ruining Deng
Abstract
Spatial transcriptomics (ST) measures gene expression in tissue context, but dense capture grids can be costly and may repeatedly sample morphologically similar regions. Most active learning strategies were developed for categorical labels and independent samples. We conduct a retrospective pool-based benchmark of active learning versus uniform Random sampling for ST, where expression vectors are high-dimensional and continuous and candidates are spatially correlated. Using two fully profiled public ST cohorts, we mask candidate expression vectors and simulate multi-round selection with uncertainty-based Monte Carlo dropout (MC-dropout) and temporal output discrepancy (TOD), and diversity-based CoreSet and TypiClust-inspired selection. We compare 160 completed configurations at 5%, 10%, 30%, and 50% of the fold-wide training spot pool under patient-level cross-validation, with a separate full-label reference. Within each budget, strategies share the selection schedule, morphology-to-expression predictor, and optimization protocol. We assess mean per-gene within-slide Pearson correlation coefficient (PCC), expression-cluster agreement, and Moran's I fidelity. On HER2-positive breast cancer, pooled mean PCC differences from Random across the four active strategies were -0.0176, -0.0117, +0.0056, and +0.0057 at 5%, 10%, 30%, and 50%, respectively. On cutaneous squamous cell carcinoma (cSCC), three strategies were below Random at 5%, and all four were below Random at 10%. On HER2-positive breast cancer, CoreSet and MC-dropout had lower PCC but higher expression-cluster agreement than Random at the two smallest budgets; this pattern did not reproduce on cSCC. Under the reported fixed training horizons, the evaluated active strategies do not consistently improve on Random at small budgets, and rankings depend on the evaluation measure.