Improving the therapeutic ratio of radiotherapy against radioresistant cancers: Leveraging on novel artificial intelligence-based approaches for drug combination discovery. (28th July 2021)

• Record Type: Journal Article
• Authors: Poon, Dennis Jun Jie; Tay, Li Min; Ho, Dean; Chua, Melvin Lee Kiang; Chow, Edward Kai-Hua; Yeo, Eugenia Li Ling
• Is Part Of: Cancer letters. Volume 511(2021)
• Page Start: 56
• Page End: 67
• Publication Date: 2021-07-28
• Subjects: Cancer radioresistance -- Machine learning -- Drug development -- Artificial intelligence -- Combinatorial therapeutics; Cancer -- Periodicals; Neoplasms -- Periodicals; Cancer -- Périodiques; Electronic journals; 616.994
• DOI: 10.1016/j.canlet.2021.04.019
• Languages: English
• ISSNs: 0304-3835

Abstract

Abstract (Max 250 words): Despite numerous advances in cancer radiotherapy, tumor radioresistance remain one of the major challenges limiting treatment efficacy of radiotherapy. Conventional strategies to overcome radioresistance involve understanding the underpinning molecular mechanisms, and subsequently using combinatorial treatment strategies involving radiation and targeted drug combinations against these radioresistant tumors. These strategies exploit and target the molecular fingerprint and vulnerability of the radioresistant clones to achieve improved efficacy in tumor eradication. However, conventional drug-screening approaches for the discovery of new drug combinations have been proven to be inefficient, limited and laborious. With the increasing availability of computational resources in recent years, novel approaches such as Quadratic Phenotypic Optimization Platform (QPOP), CURATE.AI and Drug Combination and Prediction and Testing (DCPT) platform have emerged to aid in drug combination discovery and the longitudinally optimized modulation of combination therapy dosing. These platforms could overcome the limitations of conventional screening approaches, thereby facilitating the discovery of more optimal drug combinations to improve the therapeutic ratio of combinatorial treatment. The use of better and more accurate models and methods with rapid turnover can thus facilitate a rapid translation in the clinic, hence, resulting in a better patient outcome. Here, we reviewed the clinical observations, molecular mechanisms and proposed treatment strategies for tumor radioresistance and discussed how novel approaches may be applied to enhance drug combination discovery, with the aim to further improve the therapeutic ratio and treatment efficacy of radiotherapy against radioresistant cancers. Highlights: Tumor radioresistance limit radiotherapy efficacy and is due to diverse biological mechanisms. Drug combinations targeting specific molecular vulnerabilities may have suboptimal efficacy. Exhaustive screening may discover new drug combinations but are costly and slow. Artificial intelligence (AI)-based approaches can prioritize drug combinations for testing. AI approaches can be used to rapidly develop personalized treatment for radioresistant cancers.