Deep learning model enables the discovery of a novel immunotherapeutic agent regulating the kynurenine pathway

Background: Kynurenine (Kyn) is a key inducer of an immunosuppressive tumor microenvironment (TME). Although indoleamine 2,3-dioxygenase (IDO)-selective inhibitors have been developed to suppress the Kyn pathway, the results were not satisfactory due to the presence of various opposing mechanisms. Here, we employed an orally administered novel Kyn pathway regulator to overcome the limitation of anti-tumor immune response.Methods: We identified a lead compound through the development of a deep learning model to predict compound-target interaction. Inhibitory activity of the lead compound against both IDO and tryptophan 2,3-dioxygenase (TDO) was evaluated using enzyme- and cell-based assays. CT26 colon cancer-bearing mice were treated with the lead compound and/or immune checkpoint inhibitors. Tumor samples were analyzed using histological, flow cytometry, and immune profiling assays.Results: We identified a novel core structure that inhibited both IDO and TDO. An orally available lead compound, STB-C017 (designated hereafter as STB), was then selected via validation of structural modification and in vitro assays. STB effectively inhibited the enzymatic and cellular activity of IDO and TDO in vitro. Moreover, it potently suppressed Kyn levels in both the plasma and tumor in vivo. The dose and schedule of STB administration were optimized based on the immunotherapeutic efficacy and toxicity. STB monotherapy increased the infiltration of CD8+ T cells into TME. In addition, it elicited an anti-cancer immune response with a strong activation of T cell immunity. STB reprogrammed the TME with widespread changes in immune-mediated gene signatures. Notably, STB-based combination immunotherapy elicited the most potent anti-tumor efficacy through concurrent treatment with immune checkpoint inhibitors (ɑPD-1 and/or ɑCTLA-4), leading to complete tumor regression and long-term overall survival.Conclusions: Our study demonstrated that a novel Kyn pathway regulator derived using deep learning technology can activate T cell immunity and potentiate immune checkpoint blockade by overcoming an immunosuppressive TME.