Imaging Seminar: Bridging Microscopy and Genomics with Machine Learning

<< Registration below >>

Abstract: 
Single-cell RNA-seq and other profiling assays have opened new windows into understanding cells' properties, regulation, dynamics, and function at unprecedented resolution and scale. However, these assays are inherently destructive, precluding us from tracking their temporal dynamics. Here, we present Raman2RNA (R2R), an experimental and computational framework to infer single-cell expression profiles in live cells through Raman microscopy images and domain translation using adversarial training. We demonstrate R2R in reprogramming mouse fibroblasts or differentiating mouse embryonic stem cells and show that their expression profiles can be accurately predicted in live cells. We also apply our method to other modalities, providing genomic interpretability to widely available modalities such as H&E stains. Our method should imply broad applications to understanding expression dynamics at scale in vitro and in vivo.

Bio: 
Koseki Kobayashi is a postdoc at MIT in Mechanical Engineering working with Drs. Peter So and Aviv Regev.
He's interested in the interface of genomics and spectroscopy, and his recent work demonstrated that genomics profiles of single live cells could be accurately predicted using machine learning and Raman microscopy, a label-free non-destructive micro-spectroscopy technique that can report on vibrational energy levels of molecules. The method, Raman2RNA, should have broad implications for understanding expression dynamics at scale in vitro and in vivo.

The seminar is followed by an aperitif. 

Registration appreciated
More info here