PT  - JOURNAL ARTICLE
AU  - Gil Kanfer
AU  - Shireen A. Sarraf
AU  - Yaakov Maman
AU  - Heather Baldwin
AU  - Kory R. Johnson
AU  - Michael E. Ward
AU  - Martin Kampmann
AU  - Jennifer Lippincott-Schwartz
AU  - Richard J. Youle
TI  - Image-based pooled whole genome CRISPR screening for Parkin and TFEB subcellular localization
AID  - 10.1101/2020.07.02.184390
DP  - 2020 Jan 01
TA  - bioRxiv
PG  - 2020.07.02.184390
4099  - http://biorxiv.org/content/early/2020/07/02/2020.07.02.184390.short
4100  - http://biorxiv.org/content/early/2020/07/02/2020.07.02.184390.full
AB  - Genome-wide CRISPR screens have transformed our ability to systematically interrogate human gene function, but are currently limited to a subset of cellular phenotypes. We report a novel pooled screening approach for a wider range of cellular and subtle subcellular phenotypes. Machine learning and convolutional neural network models are trained on the subcellular phenotype to be queried. Genome-wide screening then utilizes cells stably expressing dCas9 (CRISPRi), photoactivatable fluorescent protein (PA-mCherry), and a lentiviral guide RNA (gRNA) pool. Cells are screened by microscopy and classified by artificial intelligence (AI) algorithms, which precisely identify the genetically altered phenotype. Cells with the phenotype of interest are photoactivated, isolated via flow cytometry, and the gRNAs are identified by sequencing. A proof-of-concept screen accurately identified PINK1 as essential for Parkin recruitment to mitochondria. A genome-wide screen identified factors mediating TFEB relocation from the nucleus to the cytosol upon prolonged starvation. Twenty of the sixty-four hits called by the neural network model were independently validated, revealing new effectors of TFEB subcellular localization. This approach, AI-Photoswitchable Screening (AI-PS) offers a novel screening platform capable of classifying a broad range of mammalian subcellular morphologies, an approach largely unattainable with current methodologies at genome-wide scale.Competing Interest StatementThe authors have declared no competing interest.