Abstract 6375: Augmented intelligence to define drug targets associated with triple negative breast cancer (TNBC) metabolic reprogramming

Abstract

Abstract Introduction: Basal-like breast cancer (BLBC; TNBC) cells use aerobic glycolysis at a higher rate than Luminal A (LumA) cells. Metabolic reprogramming using aerobic glycolysis (Warburg effect), is correlated with increased aggressiveness of cancer cells and poor outcome in patients. Therefore, genes involved in this pathway are promising targets for developing cancer therapeutics. Method: MIMs has developed a unique platform of augmented intelligence that combines bioinformatics, systems biology and artificial intelligence. It integrates multi-layered omics data with a knowledge-base that aggregates structured data from more than 140 databases as well as unstructured data from the scientific literature. Using this approach a genetic interaction graph (GI-Graph) is inferred per patient, capturing functional relationships between genes in the specific context of the tumor. The GI-Graphs are subsequently used to train supervised machine learning algorithms for predicting gene functionality and potential as a target. Preliminary analysis was performed on transcriptomic data from 321 LumA and 162 TNBC samples, from the TCGA Data Portal and a predictive model was developed using two GI-Graphs from the two subgroups. Briefly, subgraphs, containing genes with functional interactions with the known genes in OXPHOS and glycolysis pathways, were used to extract gene attributes, and to build an algorithm that predicts involvement of a gene in the Warburg effect. Using a testing gene set extracted from the literature the performance of the model was assessed, which showed a true positive rate of 18% and a false positive rate of 0.36%, and outperformed 5-times the classical bioinformatics tools. Results: This model predicted 108 genes as the top 1% genes being involved in the metabolic reprogramming of TNBC. Additional information from MIMs’ platform, including differential gene expression between LumA and TNBC, gene pleiotropy and essentiality and the topological metrics, enabled the life scientists to further refine the gene lists, based on the expected characteristics of a good target in oncology. Following this process, 30 genes were selected as potential targets controlling the metabolic reprogramming of TNBC, among which 4 genes were already evaluated in TNBC clinical trials. Conclusion: Our preliminary data strongly supports that the predictive model based on the GI-Graphs has the potential to identify promising therapeutic targets for TNBC. Citation Format: Sarah Jenna, Benjamin Boucher, Liebaut Dudragne, Abdoulaye Baniré Diallo. Augmented intelligence to define drug targets associated with triple negative breast cancer (TNBC) metabolic reprogramming [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 6375.