RT Journal Article
SR Electronic
T1 Integrating deep learning and unbiased automated high-content screening to identify complex disease signatures in human fibroblasts
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 2020.11.13.380576
DO 10.1101/2020.11.13.380576
A1 Lauren Schiff
A1 Bianca Migliori
A1 Ye Chen
A1 Deidre Carter
A1 Caitlyn Bonilla
A1 Jenna Hall
A1 Minjie Fan
A1 Edmund Tam
A1 Sara Ahadi
A1 Brodie Fischbacher
A1 Anton Geraschenko
A1 Christopher J. Hunter
A1 Subhashini Venugopalan
A1 Sean DesMarteau
A1 Arunachalam Narayanaswamy
A1 Selwyn Jacob
A1 Zan Armstrong
A1 Peter Ferrarotto
A1 Brian Williams
A1 Geoff Buckley-Herd
A1 Jon Hazard
A1 Jordan Goldberg
A1 Marc Coram
A1 Reid Otto
A1 Edward A. Baltz
A1 Laura Andres-Martin
A1 Orion Pritchard
A1 Alyssa Duren-Lubanski
A1 Ameya Daigavane
A1 Kathryn Reggio
A1 NYSCF Global Stem Cell Array ® Team
A1 Phillip C. Nelson
A1 Michael Frumkin
A1 Susan L. Solomon
A1 Lauren Bauer
A1 Raeka S. Aiyar
A1 Elizabeth Schwarzbach
A1 Scott A. Noggle
A1 Frederick J. Monsma, Jr.
A1 Daniel Paull
A1 Marc Berndl
A1 Samuel J. Yang
A1 Bjarki Johannesson
YR 2022
UL http://biorxiv.org/content/early/2022/03/16/2020.11.13.380576.abstract
AB Drug discovery for diseases such as Parkinson’s disease are impeded by the lack of screenable cellular phenotypes. We present an unbiased phenotypic profiling platform that combines automated cell culture, high-content imaging, Cell Painting, and deep learning. We applied this platform to primary fibroblasts from 91 Parkinson’s disease patients and matched healthy controls, creating the largest publicly available Cell Painting image dataset to date at 48 terabytes. We use fixed weights from a convolutional deep neural network trained on ImageNet to generate deep embeddings from each image and train machine learning models to detect morphological disease phenotypes. Our platform’s robustness and sensitivity allow the detection of individual-specific variation with high fidelity across batches and plate layouts. Lastly, our models confidently separate LRRK2 and sporadic Parkinson’s disease lines from healthy controls (receiver operating characteristic area under curve 0.79 (0.08 standard deviation)), supporting the capacity of this platform for complex disease modeling and drug screening applications.Competing Interest StatementY.C., M.F., S.A., A.G., S.V., A.N., Z.A., B.W., J.K., M.C., E.A.B., O.P., A.D., P.C.N., M.F., M.B., and S.J.Y. were employed by Google. M.F., A.G., S.V., A.N., Z.A., B.W., J.K., M.C., E.A.B., O.P., P.C.N., M.F., M.B., and S.J.Y. own Alphabet stock. The remaining authors declare no competing interests.