In Vitro to In Vivo: Bidirectional and High-Precision Generation of In Vitro and In Vivo Neuronal Spike Data

Translational neuroscience relies on both in vitro slice recordings and in vivo record-ings. Their spontaneous population dynamics are observed under decisively different conditions, and across independent experiments there is typically no clear neuron-to-neuron correspondence. Here we formulate a time-resolved, bidirectional transfer task be-tween in vitro and in vivo multineuronal spike trains and provide a standardized evalua-tion procedure for generation across markedly different recording preparations. We train an autoregressive Transformer on 1-ms binned, 128-unit binary sequences and introduce Dice loss to directly optimize spike-event overlap under extreme class imbalance, compar-ing it with Binary Focal Cross-Entropy (γ = 2.0). Across 12 mouse datasets (6 in vitro HD-MEA sessions and 6 in vivo Neuropixels sessions), the method achieves strong within-domain performance and remains above chance for cross-domain generation (ROC-AUC 0.70±0.09 for in vitro→in vivo; 0.80±0.10 for in vivo→in vitro). Because spike events are ra-re, we report Precision–Recall curves and PR-AUC alongside ROC-AUC to reflect minori-ty-event quality. To our knowledge, this is the first demonstration of bidirectional, time-resolved generation between unpaired in vitro and in vivo population spike trains without assuming cell correspondence, and the framework can be adapted to other sparse neural event data and related event-based datasets when domain-specific validation criteria are defined.