Abstract
Abstract Combination therapy is critical to improving therapeutic options against cancer. This is particular true when striving to improve overall response rates for increasingly specific molecularly targeted therapeutics. As the number of therapeutic options increases, identifying an optimised drug combination from amongst a range of available drug sets is virtually impossible by conventional methods due to the large search space. Further complicating drug combination design and implementation in cancer is patient heterogeneity. Artificial intelligence (AI)-based tools are beginning to impact positively impact all facets of drug development and personalised medicine. Rather than aggregating large datasets from other sources (public/private data repositories, text-mining, etc.) to develop predictive models, we recently developed an experimentally-driven small dataset AI platform, Quantitative Parabolic Optimization Platform (QPOP), to identify and rank drug combinations from a specific drug set search space. Upon identifying the queried drug set as well as a desired biological system of interest to interrogate, QPOP can identify optimal drug combinations against specific systems of interests, including drug resistant cancers, utilising small datasets built from drug combination tests designed using orthogonal array composite design. QPOP does not rely on molecular mechanism modelling but rather uses specific quality controlled experimental data to rationally identify optimal drug combinations. In applications towards haematological malignancies, including multiple myeloma and lymphomas, novel epigenetic-based drug combinations were able to be identified against drug-resistant refractory/relapsed cases. Because of the efficiency of QPOP towards designing optimal drug combinations as well as the dosages within these combinations, this approach was applied across all levels of drug development, from in vitro and in vivo preclinical models to ex vivo patient sample analysis. Novel epigenetic-based drug combinations were validated to outperform standard of care in preclinical mouse models. Additionally, QPOP analysis of drug combination with ex vivo patient samples effectively ranked patient-specific drug combination sensitivities for both novel epigenetic-based drug combinations as well as standard of care drug combinations. The work presented in this study presents evidence for the use of QPOP toward faster and more efficient drug combination development as well as towards personalized oncology clinical decision support. The efficiency and flexible of QPOP reduces the time and costs associated drug combination design and evaluation, allowing for faster and cheaper implementation into both drug development and health technology applications. Citation Format: Edward Kai-Hua Chow. AI-driven drug combination design for drug-resistant hematological malignancies [abstract]. In: Proceedings of the AACR-NCI-EORTC International Conference on Molecular Targets and Cancer Therapeutics; 2019 Oct 26-30; Boston, MA. Philadelphia (PA): AACR; Mol Cancer Ther 2019;18(12 Suppl):Abstract nr B140. doi:10.1158/1535-7163.TARG-19-B140
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
