Artificial Intelligence-Guided Prioritization and Experimental Evaluation of Synergistic Target Combinations for...

Background/Objectives: Breast cancer exhibits substantial molecular heterogeneity, resulting in diverse therapeutic vulnerabilities and limiting the efficacy of single-agent therapies. Although multi-target strategies may offer improved therapeutic benefit, the systematic identification of synergistic higher-order target combinations remains challenging. This study aimed to identify and validate effective higher-order target combinations for heterogeneous breast cancer. Methods: DeepMDS, a previously developed deep learning-based multi-compound synergy prediction model, was used to prioritize candidate target combinations for breast cancer. Exhaustive two-target and three-target combinations were ranked in the gene-expression contexts of ER-positive luminal-like MCF-7 and triple-negative MDA-MB-231 breast cancer cells. The top-ranked target combinations were evaluated using single, pairwise, and triple small interfering RNA (siRNA) perturbations. Representative inhibitors were subsequently assessed in fixed-ratio combinations in MCF-7, MDA-MB-231, and 4T1 cells and in a 4T1 syngeneic mouse experiment. Results: BIRC5-NAMPT-TOP1 ranked first in both cell lines. Triple siRNA co-transfection targeting BIRC5, NAMPT, and TOP1 produced the strongest antiproliferative effects, with inhibition rates of 62.94% in MCF-7 cells and 55.62% in MDA-MB-231 cells. The corresponding inhibitors, LQZ-7I, FK866, and topotecan, exhibited synergistic antiproliferative activity at multiple molar ratios, with combination index values below 1. The optimized 2.5:10:1 molar ratio showed strong synergy in MCF-7, MDA-MB-231, and 4T1 cells, with combination index values of 0.26, 0.19, and 0.15, respectively. In tumor-bearing mice model, the triple-inhibitor regimen achieved a tumor inhibition rate of 62.05%. Topotecan-containing groups showed hematological alterations, whereas no statistically detectable elevations were observed in the measured terminal serum hepatic or renal biomarkers. Conclusions: The BIRC5-NAMPT-TOP1 combination showed reproducible phenotypic activity in the tested genetic and pharmacological models. These findings support the use of DeepMDS as a hypothesis-generation tool for higher-order target prioritization.