RT Journal Article
SR Electronic
T1 Functional immune mapping with deep-learning enabled phenomics applied to immunomodulatory and COVID-19 drug discovery
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 2020.08.02.233064
DO 10.1101/2020.08.02.233064
A1 Michael F. Cuccarese
A1 Berton A. Earnshaw
A1 Katie Heiser
A1 Ben Fogelson
A1 Chadwick T. Davis
A1 Peter F. McLean
A1 Hannah B. Gordon
A1 Kathleen-Rose Skelly
A1 Fiona L. Weathersby
A1 Vlad Rodic
A1 Ian K. Quigley
A1 Elissa D. Pastuzyn
A1 Brandon M. Mendivil
A1 Nathan H. Lazar
A1 Carl A. Brooks
A1 Joseph Carpenter
A1 Pamela Jacobson
A1 Seth W. Glazier
A1 Jes Ford
A1 James D. Jensen
A1 Nicholas D. Campbell
A1 Michael A. Statnick
A1 Adeline S. Low
A1 Kirk R. Thomas
A1 Anne E. Carpenter
A1 Sharath S. Hegde
A1 Ronald W. Alfa
A1 Mason L. Victors
A1 Imran S. Haque
A1 Yolanda T. Chong
A1 Christopher C. Gibson
YR 2020
UL http://biorxiv.org/content/early/2020/08/03/2020.08.02.233064.abstract
AB Development of accurate disease models and discovery of immune-modulating drugs is challenged by the immune system’s highly interconnected and context-dependent nature. Here we apply deep-learning-driven analysis of cellular morphology to develop a scalable “phenomics” platform and demonstrate its ability to identify dose-dependent, high-dimensional relationships among and between immunomodulators, toxins, pathogens, genetic perturbations, and small and large molecules at scale. High-throughput screening on this platform demonstrates rapid identification and triage of hits for TGF-β- and TNF-α-driven phenotypes. We deploy the platform to develop phenotypic models of active SARS-CoV-2 infection and of COVID-19-associated cytokine storm, surfacing compounds with demonstrated clinical benefit and identifying several new candidates for drug repurposing. The presented library of images, deep learning features, and compound screening data from immune profiling and COVID-19 screens serves as a deep resource for immune biology and cellular-model drug discovery with immediate impact on the COVID-19 pandemic.Competing Interest StatementWe declare competing interests. All authors were employees of or advisors to Recursion during the course of this work. All authors have real or potential ownership interest in Recursion.