Circumventing glioblastoma resistance to temozolomide through optimal drug combinations designed by systems pharmacology and machine learning

A quantitative systems pharmacology model was developed to analyze resistance mechanisms in glioblastoma cells to temozolomide-based therapies.

• The model incorporates TMZ pharmacokinetics and dysregulated pathways in glioblastoma, validated with multi-type datasets.
• In silico screening identified drug combinations that may re-sensitize TMZ-resistant glioblastoma cells.
• Combining TMZ with inhibitors of DNA repair mechanisms is suggested as a potential strategy to overcome resistance.
• Machine learning was used to derive functional signatures that could assist in tailoring therapy for patients.

AI simplified