Abstract The emergence of technological innovations has created the opportunity to envision new approaches to discover therapeutics at scale. We combined advances in high content microscopy with arrayed CRISPR genome editing techniques and machine learning (ML) to build a rigorously controlled dataset enabling exploration of biology and chemistry at scale. Phenotypes from millions of perturbations in multiple cell types were embedded in a unified representation space and leveraged to accelerate discovery and reverse translation, ultimately yielding novel biological insights, and optimizing the advancement of lead molecular series through structure-activity relationships (SAR). Here, we demonstrate the capability of our platform to discover potential cancer therapies with distinct mechanisms of action. First, we describe the identification of a novel compound series that potentiates the effects of immunotherapy in syngeneic mouse models, producing complete responses and immunological memory, while also limiting peripheral inflammation. Specific novel chemical entities (NCEs) caused robust CD45+ cell influx into the tumor microenvironment and significantly attenuated exhausted T cells and immunosuppressive macrophages, thereby enhancing anti-tumor immunity. Strikingly, the same NCEs suppressed peripheral inflammation while sustaining elevated levels of intra-tumoral proinflammatory cytokines. Second, we highlight a novel and differentiated strategy to potentiate PARP inhibitor response in homologous repair deficient (HRD) - negative or HR-proficient ovarian cancers. NCEs altered the expression of genes within the DNA damage repair (DDR) network and cell cycle checkpoints to synergize with PARP inhibition in vivo and re-sensitized a PARP-resistant patient-derived xenograft (PDX) model. Collectively, we believe future efforts on the industrialization and integration of various technological innovations across biology, chemistry, automation, data science, and engineering will ultimately modernize drug discovery and radically improve patient lives. Citation Format: Jenny Rudnick, Kiran Nadella, Chase Neumann, Shane Rowley, Ethan Gardner, Shadi Swaidani, Aimee Iberg, Lu Chen, Daria Beshnova, Aurora Blucher, Rebecca Sarto Basso, Malini Rajan, Kevin Fales, Ashraf Saeed, Christopher Bailey, Weston Judd, Chrissy Egbert, Joel Ellis, John Ansede, Pouya Hadipour, Kevin Jessing, Janet Paulsen, Paul Rearden, Vamshi Manda, Sashi Kasimsetty, Sashi Kasimsetty, Michael Hancock, Harish Shankaran, Bryan Ellis, Meenakshy Iyer, Carl Brooks, Ashish Bhandari, Chris Gibson, Irit Rappley, Laura Schaevitz, Imran Haque, Hayley Donnella, Michael Cuccarese, Marie Evangelista. A phenomics platform combining imaging and artificial intelligence for rapid validation and advancement of novel oncology targets [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 2 (Clinical Trials and Late-Breaking Research); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(8_Suppl):Abstract nr LB071.