Summary
UniCell: Deconvolve (UCD), a pre-trained, interpretable, deep learning model to deconvolve cell 10 type fractions and predict cell identity across Spatial Transcriptomic, bulk-RNA-Seq, and scRNA-Seq datasets without contextualized reference data. UCD is trained on 10 million pseudo-mixtures from the world's largest fully-integrated scRNA-Seq training database comprising 28 million annotated single cells spanning 840 unique cell types from 899 studies.
Form Instruction
The UniCell package is currently in the alpha stage. Complete the form below in order to receive an API access token in order to leverage UniCell for your transcriptomics projects.