Stem-cell based, machine learning approach for optimizing natural killer cell-based personalized immunotherapy for high-grade ovarian cancer

Abstract

Advanced high-grade serous ovarian cancer continues to be a therapeutic challenge for those affected using the current therapeutic interventions. There is an increasing interest in personalized cancer immunotherapy using activated natural killer (NK) cells. NK cells account for approximately 15% of circulating white blood cells. They are also an important element of the tumor microenvironment (TME) and the body's immune response to cancers. In the present study, DeepNEU-C2Rx, a machine learning platform, was first used to create validated artificially induced pluripotent stem cell simulations. These simulations were then used to generate wild-type artificially induced NK cells (aiNK-WT) and TME simulations. Once validated, the aiNK-WT simulations were exposed to artificially induced high-grade serous ovarian cancer represented by aiOVCAR3. Cytolytic activity of aiNK was evaluated in presence and absence of aiOVCAR3 and data were compared with the literature for validation. The TME simulations suggested 26 factors that could be evaluated based on their ability to enhance aiNK-WT cytolytic activity in the presence of aiOVCAR3. The addition of programmed cell death-1 inhibitor leads to significant reinvigoration of aiNK cytolytic activity. The combination of programmed cell death-1 and glycogen synthase kinase 3 inhibitors showed further improvement. Further addition of ascitic fluid factor inhibitors leads to optimal aiNK activation. Our data showed that NK cell simulations could be used not only to pinpoint novel immunotherapeutic targets to reinvigorate the activity of NK cells against cancers, but also to predict the outcome of targeting tumors with specific genetic expression and mutation profiles.