Quantum mechanics-based multi-tensor AI/ML correctly predicts - glioblastoma patients' overall survival, gene targets to sensitize the tumors, and the tumors' response to their targeting - from their whole genomes

Despite the growth in targeted therapy development, the drug failure rate has increased to ~95%. As clinical trials demonstrated, the targeted gene alone does not predict whether patients would have longer life expectancy in response to a drug. As studies with model organisms showed, the effect of the drug, and the mechanisms underlying it, depend on the entire multi-ome. But multi-omic data are small-cohort, noisy, and high-dimensional, i.e., extremely difficult to model. We have developed our quantum mechanics-based artificial intelligence and machine learning (AI/ML) to overcome these challenges [doi: 10.1158/1538-7445.AM2025-CT227]. We demonstrated our algorithms in the unsupervised modeling of, e.g., whole genomes of 85 astrocytoma patients. Mechanistic interpretation showed that the model blindly removed batch effects, separated normal demographic variations, and discovered a disease-specific genome-wide pattern of DNA copy-number alterations. This pattern was used to derive an actionable predictor of patients' overall survival (OS) and gene targets to sensitize their tumors. We computationally validated both the predictor and the modeling in federated studies of mutually-exclusive sets of ~50-250 patients. The modeling repeatedly discovered a representation of the predictor in every study, in astrocytoma grades II, III, and IV, i.e., glioblastoma (GBM), patients. We experimentally validated the predictor in a clinical trial in 79 GBM patients, initially retrospectively, and, in a four-year follow up, also prospectively [doi: 10.1063/1.5142559, 10.1145/3624062.3624078]. In all the cohorts, the predictor, with 75-95% concordance with survival, was more accurate than all standard-of-care indicators. With 100% reproducibility among Complete Genomics, Illumina, and Ultima whole-genome sequencing, and >99% when including Affymetrix and Agilent DNA microarrays, the predictor was also the most precise. Here, we describe functional genomics experimental validation of both a gene target predicted to sensitize the tumors, as well as the predicted tumors' response level. Guide RNAs were designed and a lentiviral CRISPR-Cas9 all-in-one vector was utilized to knock out the candidate target. Knockout validation at the protein level was performed using Western blot. Knockout in patient-derived GBM cell lines resulted in significantly attenuated cell viability and proliferation. The level of attenuation was significantly different between the cell lines, in agreement with their whole genome-based predicted response. We conclude that our quantum mechanics-based multi-tensor AI/ML solved the 75-year-old problem of correctly predicting - GBM patients' OS, gene targets to sensitize the tumors, and the tumors' response to their targeting - from their whole genomes.