DSAI-06 AI-DRIVEN METABOLOMICS AND SYNTHETIC DRUG DESIGN FOR TARGETING CNS METASTASES

Abstract CNS metastases affect ~30% of patients with advanced-stage cancers, however treatment is largely limited by the blood-brain barrier (BBB), which restricts drug penetration. Based on previous preclinical models, tumor cells adapt to the brain’s microenvironment through metabolic shifts, such as 2-3-fold increases in glutamine metabolism. Metabolomic profiling has identified biomarkers, including lactate, associated with tumor progression. Additionally, synthetic inhibitors that target metabolic enzymes, such as glutaminase, function by BBB permeation, emphasizing the optimization for tailored drug synthesis that maintains potency and pharmacokinetic properties. This study aims to analyze MRI image datasets from preclinical CNS metastasis models to identify biomarkers and propose optimized inhibitors to enhance drug efficacy.The data was collected from Stanford University’s BrainMetShare, and it includes 156 pre- and post- contrast brain MRI images in patients with≥1 CNS metastases. The primary tumors were lung (n=99), melanoma (n=7), breast (n=33), gastrointestinal (n=5), genitourinary (n=7), and miscellaneous (n=5). An in-house segmentation process via Matlab was used to segment the MRI images by slices/pixels and the tumor surfaces for each sample were reconstructed using the “isosurface” and gaussian kernel functions. The size, volume, and location of the tumors were calculated to identify morphological variables that can detect metabolite biomarkers. The initial MRI segmentation showed that the tumor ranges were between 2.0 cm^3 to 4.3 cm^3 (mean: 3.3 +/- 0.7 cm^3). A vast majority of the metastases were found in the cerebellum and brainstem with more advanced tumors being correlated with increased glutamine metabolism. This data will be used to determine effective concentrations for four inhibitors that previous studies have found to have promising BBB permeability: CB-839, BPTES, EPCG derivatives that inhibit LDHA, and 6-Diazo-5-oxo-L-norleucine (DON). Ongoing AI-driven analysis will be done to further evaluate the effectiveness of the inhibitors as plausible therapeutic approaches.