Oncological drug discovery: AI meets structure-based computational research

• Published in: Drug discovery today Vol. 27; no. 6; pp. 1661 - 1670
• Main Authors: Gorostiola González, Marina, Janssen, Antonius P.A., IJzerman, Adriaan P., Heitman, Laura H., van Westen, Gerard J.P.
• Format: Journal Article
• Language: English
• Published: England Elsevier Ltd 01.06.2022
• Subjects: Artificial intelligence; Cancer; Hallmarks of cancer; Machine learning; Structure-based drug design; Structure-based drug design; AI; TCGA; DHODH; SB; FEP; Hallmarks of cancer; RF; QSAR; Machine learning; MD; Artificial intelligence; VS; Cancer; ML
• ISSN: 1359-6446; 1878-5832
• DOI: 10.1016/j.drudis.2022.03.005

•AI approaches integrated with structure-based methods are used in all aspects of oncological drug discovery.•The level of integration is variable, with few truly integrated methods being used.•Virtual screening is themost common use case scenario and shows real benefits.•Data availability and computational power are the most important bottlenecks. The integration of machine learning and structure-based methods has proven valuable in the past as a way to prioritize targets and compounds in early drug discovery. In oncological research, these methods can be highly beneficial in addressing the diversity of neoplastic diseases portrayed by the different hallmarks of cancer. Here, we review six use case scenarios for integrated computational methods, namely driver prediction, computational mutagenesis, (off)-target prediction, binding site prediction, virtual screening, and allosteric modulation analysis. We address the heterogeneity of integration approaches and individual methods, while acknowledging their current limitations and highlighting their potential to bring drugs for personalized oncological therapies to the market faster.