MAPS

MAPS is a software toolkit that utilizes deep learning to analyze high-content microscopy (HCM) images of cells to determine the functional status of newly discovered genetic variants. It was designed to address the challenge of keeping up with the rapid pace of genetic testing by providing a streamlined and cost-effective method for classifying variants. The toolkit leverages cloud-based deep learning services that are easy to train and deploy, allowing cell biologists to incorporate deep learning into their image analysis pipelines without requiring extensive coding knowledge. The effectiveness of the MAPS approach was demonstrated through a successful variant functionalization workflow that integrated HCM and MAPS to assess missense variants of PTEN, a tumor suppressor commonly mutated in both hereditary and somatic cancers. Overall, the MAPS toolkit offers a promising solution for improving the utility of genetic testing by quickly and accurately determining the functional status of newly discovered variants.