Machine learning identifies experimental brain metastasis subtypes based on their influence on neural circuits

• Published in: Cancer cell Vol. 41; no. 9; pp. 1637 - 1649.e11
• Main Authors: Sanchez-Aguilera, Alberto, Masmudi-Martín, Mariam, Navas-Olive, Andrea, Baena, Patricia, Hernández-Oliver, Carolina, Priego, Neibla, Cordón-Barris, Lluís, Alvaro-Espinosa, Laura, García, Santiago, Martínez, Sonia, Lafarga, Miguel, Sobrino, Cecilia, Ajenjo, Nuria, Artiga, Maria-Jesus, Ortega-Paino, Eva, García-Calvo, Virginia, Pérez-Núñez, Angel, González-León, Pedro, Jiménez-Roldán, Luis, Moreno, Luis Miguel, Esteban, Olga, Sepúlveda, Juan Manuel, Toldos, Oscar, Laín, Aurelio Hernández, Arenas, Alicia, Blasco, Guillermo, Alén, José Fernández, Zaragoza, Adolfo de la Lama, Núñez, Antía Domínguez, Calero, Lourdes, Valverde, Concepción Fiaño, Piñeiro, Ana González, Delgado López, Pedro David, Pascual, Mar, Ahicart, Gerard Plans, Otín, Begoña Escolano, Lin, Michael Z, Al-Shahrour, Fátima, Menendez de la Prida, Liset, Valiente, Manuel
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 11.09.2023; Cell Press
• Subjects: biomarkers; Brain; brain circuit impact; brain metastasis; Brain Neoplasms - genetics; cancer neuroscience; decision trees; electrophysiology; elta oscillations; gamma oscillations; Gene Expression Profiling; Humans; Machine Learning; Mutation; brain circuit impact; electrophysiology; biomarkers; gamma oscillations; decision trees; brain metastasis; cancer neuroscience; elta oscillations
• ISSN: 1535-6108; 1878-3686
• DOI: 10.1016/j.ccell.2023.07.010

A high percentage of patients with brain metastases frequently develop neurocognitive symptoms; however, understanding how brain metastasis co-opts the function of neuronal circuits beyond a tumor mass effect remains unknown. We report a comprehensive multidimensional modeling of brain functional analyses in the context of brain metastasis. By testing different preclinical models of brain metastasis from various primary sources and oncogenic profiles, we dissociated the heterogeneous impact on local field potential oscillatory activity from cortical and hippocampal areas that we detected from the homogeneous inter-model tumor size or glial response. In contrast, we report a potential underlying molecular program responsible for impairing neuronal crosstalk by scoring the transcriptomic and mutational profiles in a model-specific manner. Additionally, measurement of various brain activity readouts matched with machine learning strategies confirmed model-specific alterations that could help predict the presence and subtype of metastasis. [Display omitted] •Brain metastasis experimental models recapitulate neuronal impact heterogeneity•The underlying mechanism cannot be explained by the tumor mass effect•A molecular signature is enriched in models imposing high neural impact•Altered brain activity patterns predict the presence and subtype of metastasis Patients with brain metastasis experience neurocognitive impairment. Until now, the mass effect of the tumor was the only underlying cause. Sanchez-Aguilera et al. demonstrate that, independently on the size, number, and location, a machine learning approach correctly classifies different models of brain metastasis based on their impact on brain activity.