Efficient Identification of Novel Anti-Glioma Lead Compounds by Machine Learning Models

Glioblastoma multiforme is the most devastating and widespread primary central nervous system tumor. Pharmacological treatment of this malignance relies on a single drug, making the discovery of new compounds urgent despite the limitations imposed by the selective permeability of the blood-brain barrier (BBB).1 Aiming to discover new anti-glioma drugs, we developed robust machine learning models for predicting anti-proliferative activity and BBB penetration ability of new compounds. Using these models, we prioritized 41 compounds for further testing in vitro against three glioma cell lines and astrocytes. Subsequently, the most potent and selective among them were synthesized and tested in vivo using an orthotopic glioma model.2 This approach revealed that two lead compounds efficiently decreased malignant glioma development in mice, probably by inhibiting thioredoxin reductase activity. These compounds didn’t promote body weight reduction, death of animals, or altered hematological and toxicological markers, making then good candidates for lead optimization as anti-glioma candidates.