Computational array reconstruction with accumap for spatial transcriptomics

Several optics-free spatial transcriptomics assays that make use of diffusion of reads from beads have recently been developed, and provide a proof of principle for high-throughput, untargeted, spatial transcriptomics. These approaches leads to a challenging computational array reconstruction problem. We show that an statistical inference method, which we term accumap, outperforms the current approach which is to run UMAP on the bead count matrix. The accumap method makes use of predicted distances to reconstruct bead positions and can improve the accuracy of reconstruction by a factor of 3 in the diffusible Slide-Tag simulation framework.