Probabilistic uncertainty in virtual spatial transcriptomics from histology is largely redundant with the predicted mean

Deep learning has enabled virtual spatial transcriptomics from histology, offering a scalable approach to molecular profiling of routinely archived tissue without molecular assays. However, reliable uncertainty estimates are essential for identifying potentially inaccurate predictions, and it remains unclear whether existing methods provide useful information about prediction reliability. Here, we present a systematic benchmark of uncertainty estimation for virtual spatial transcriptomics across three cancer cohorts spanning melanoma, lung, and kidney tumors. We evaluate aleatoric and epistemic uncertainty using probabilistic likelihoods and approximate Bayesian methods alongside histology-free and training-free baselines, assessing both calibration and error informativeness. Across cohorts and methods, uncertainty is associated with prediction error, but the predicted mean largely explains this association. After accounting for the mean, uncertainty provides only weak information about larger errors. Moreover, good calibration does not imply informative uncertainty, with simple distributions fitted without histology achieving comparable calibration. We therefore distinguish calibrated from informative uncertainty and argue that uncertainty should provide information about prediction error beyond the predicted mean. This benchmark provides a framework for systematic uncertainty evaluation in virtual spatial transcriptomics. Code availability: https://anonymous.4open.science/r/ST-uncertainty-benchmark