RESUMEN
Cancer is a complex disease involving the deregulation of intricate cellular systems beyond genetic aberrations and, as such, requires sophisticated computational approaches and high-dimensional data for optimal interpretation. While conventional artificial intelligence (AI) models excel in many prediction tasks, they often lack interpretability and are blind to the scientific hypotheses generated by researchers to enable cancer discoveries. Here we propose that hypothesis-driven AI, a new emerging class of AI algorithm, is an innovative approach to uncovering the complex etiology of cancer from big omics data. This review exemplifies how hypothesis-driven AI is different from conventional AI by citing its application in various areas of oncology including tumor classification, patient stratification, cancer gene discovery, drug response prediction, and tumor spatial organization. Our aim is to stress the feasibility of incorporating domain knowledge and scientific hypotheses to craft the design of new AI algorithms. We showcase the power of hypothesis-driven AI in making novel cancer discoveries that can be overlooked by conventional AI methods. Since hypothesis-driven AI is still in its infancy, open questions such as how to better incorporate new knowledge and biological perspectives to ameliorate bias and improve interpretability in the design of AI algorithms still need to be addressed. In conclusion, hypothesis-driven AI holds great promise in the discovery of new mechanistic and functional insights that explain the complexity of cancer etiology and potentially chart a new roadmap to improve treatment regimens for individual patients.
RESUMEN
Survival of dormant, disseminated breast cancer cells contributes to tumor relapse and metastasis. Women with a body mass index greater than 35 have an increased risk of developing metastatic recurrence. Herein, we investigated the effect of diet-induced obesity (DIO) on primary tumor growth and metastatic progression using both metastatic and systemically dormant mouse models of breast cancer. This approach led to increased PT growth and pulmonary metastasis. We developed a novel protocol to induce obesity in Balb/c mice by combining dietary and hormonal interventions with a thermoneutral housing strategy. In contrast to standard housing conditions, ovariectomized Balb/c mice fed a high-fat diet under thermoneutral conditions became obese over a period of 10 weeks, resulting in a 250% gain in fat mass. Obese mice injected with the D2.OR model developed macroscopic pulmonary nodules compared with the dormant phenotype of these cells in mice fed a control diet. Analysis of the serum from obese Balb/c mice revealed increased levels of FGF2 as compared with lean mice. We demonstrate that serum from obese animals, exogenous FGF stimulation, or constitutive stimulation through autocrine and paracrine FGF2 is sufficient to break dormancy and drive pulmonary outgrowth. Blockade of FGFR signaling or specific depletion of FGFR1 prevented obesity-associated outgrowth of the D2.OR model. IMPLICATIONS: Overall, this study developed a novel DIO model that allowed for demonstration of FGF2:FGFR1 signaling as a key molecular mechanism connecting obesity to breakage of systemic tumor dormancy and metastatic progression.
