Google Research’s Post

View organization page for Google Research, graphic

215,973 followers

REGLE, a new method to understanding the genetic basis of organ function, leverages high-dimensional clinical data, requires no disease labels, and can incorporate expert-defined knowledge to reveal deeper insights into how our organs work. Learn more → https://goo.gle/3y5UdD7

  • REGLE consists of three steps: 1) learning the lower-dimensional embeddings, 2) performing GWAS on each coordinate of the embeddings, and 3) creating a polygenic disease risk score while requiring only a small number of disease labels.
William Wen

Founder at CodeIslands

2mo

A typical success case study of unsupervised deep learning👍 My basic understanding is: High-dimensional clinical data (HDCD) is compressed into a lower-dimensional latent space using Variational Autoencoders (VAEs). Then, based on gene associations and expert-defined features (EDFs), the data in the latent space is further manipulated and adjusted. 🤔

Like
Reply
Mirza Baig

WEF Davos 24 | Chief AI Officer | Open Source AI | AI for Good | USA, Canada, UK | DEI Co-Chair | 2x Founder

2mo
Prof Frederic Cadet

Co-founder & Chairman of the Board at PEACCEL

2mo

Very interesting Google Research

Like
Reply
See more comments

To view or add a comment, sign in

Explore topics