Lantern Pharma Inc. announced a series of important milestones related to the development, size, and advancement of RADR® -- its proprietary AI platform focused on transforming the cost, pace, and timeline of oncology drug development. The company plans to continue the expansion and growth of RADR® data with an increasingly automated, machine learning enabled process, that allows the collection, tagging, and curation of datasets from proprietary, collaborative, and public sources in a highly efficient manner. Lantern also expects that a meaningful amount of the new data will come from immuno-oncology (IO) studies, and IO clinical trials as well as from proprietary analysis aimed at molecular feature extraction from hundreds-of-thousands of molecules (both FDA approved and those under development).

Large-scale data expansion efforts were initially begun for RADR® in early 2019 when the platform had under 20 million data points, and grew to nearly 300 million data points by mid-2020 (at the time of the Lantern?s IPO) and have grown beyond 60 billion ? a 200x increase since the IPO and a nearly 3,000-fold increase since the start of the data-growth campaigns. This strategy has allowed data from thousands of previously siloed sources to be analyzed in a more comprehensive, complete, and productive manner and has aided in the development of new indications for LP-184 and the development of LP-284 in a highly compressed and cost-effective manner while also leading to several conference posters, and scientific publications by Lantern Pharma and its collaborators.

The current data-growth campaigns, which plan on the addition of antigen, immune-response, and protein data, are also enabling a more robust and powerful multi-omic analysis that is positioned to guide the use of LP-184, LP-284, and other similar synthetically lethal agents in combination with standard-of-care checkpoint inhibitors. These large-scale, machine-learning driven analyses can be critical in future efforts where AI can contribute more efficiently to drug development efforts by automatically creating its own models and testing combinations of drugs not previously being considered, including in rare and hard-to-treat oncology indications where conventional therapies have failed to show any measurable improvement or where patients often will develop resistance to these therapies and require new approaches.