Robotic data acquisition with deep learning enables cell image-based prediction of transcriptomic phenotypes

Single-cell whole-transcriptome analysis is the gold standard approach to identifying molecularly defined cell phenotypes. However, this approach cannot be used for dynam-ics measurements such as live-cell imaging. Here, we developed a multifunctional robot, the automated live imaging and cell picking system (ALPS) and used it to perform single-cell RNA sequencing for microscopically observed cells with multiple imaging modes. Using robotically obtained data that linked cell images and the whole transcrip-tome, we successfully predicted transcriptome-defined cell phenotypes in a noninvasive manner using cell image-based deep learning. This noninvasive approach opens a win-dow to determine the live-cell whole transcriptome in real time. Moreover, this work, which is based on a data-driven approach, is a proof of concept for determining the transcriptome-defined phenotypes (i.e., not relying on specific genes) of any cell from cell images using a model trained on linked datasets.

Automated summary

Developed a multifunctional robot system ALPS for single-cell RNA sequencing of cells observed under multiple imaging modes. Successfully predicted transcriptome-defined cell phenotypes using cell image-based deep learning. This work provides a new approach to determine live-cell whole transcriptome in real time.