CaltechAUTHORS
  A Caltech Library Service

Harnessing an Artificial Intelligence Platform to Dynamically Individualize Combination Therapy for Treating Colorectal Carcinoma in a Rat Model

Ding, Xianting and Chang, Vincent H. S. and Li, Yulong and Li, Xin and Xu, Hongquan and Ho, Chih‐Ming and Ho, Dean and Yen, Yun (2020) Harnessing an Artificial Intelligence Platform to Dynamically Individualize Combination Therapy for Treating Colorectal Carcinoma in a Rat Model. Advanced Therapeutics, 3 (4). Art. No. 1900127. ISSN 2366-3987. https://resolver.caltech.edu/CaltechAUTHORS:20191120-102334275

[img] PDF - Supplemental Material
See Usage Policy.

961Kb
[img] Video (AVI) (Figure 2S) - Supplemental Material
See Usage Policy.

4Mb

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20191120-102334275

Abstract

Designing multi‐drug regimens often involves target‐ and synergy prediction‐based drug selection, and subsequent dose escalation to achieve the maximum tolerated dose (MTD) of each drug. This approach may improve efficacy, but not the optimal efficacy and often substantially increases toxicity. Drug interactions depend on many pathways in the omics networks and further complicate the design process. The virtually infinite drug–dose parameter space cannot be reconciled using conventional approaches, which are largely based on prediction. This barrier at least partially accounts for the low response rates that are observed with conventional mono‐ and combinatorial chemotherapy. A combination of nonstandard therapies for colorectal cancer (AGCH: adriamycin, gemcitabine, cisplatin, and herceptin) at ¼ MTD is used to treat the rats, the tumor response rates varied in a wide range. Some of the tumor response rates are close to that of control group. This work harnesses an artificial intelligence (AI) platform that is mechanism free and can dynamically optimize combinatorial therapy in rats. The individually optimized AGCH regimen reveal starkly different drug–dose parameters, which can converge each rat toward the same and low tumor response rate. Importantly, this AI‐based drug–dose optimization technology is an actionable platform, which can achieve N‐of‐1 therapy.


Item Type:Article
Related URLs:
URLURL TypeDescription
https://doi.org/10.1002/adtp.201900127DOIArticle
ORCID:
AuthorORCID
Ding, Xianting0000-0002-1549-3499
Yen, Yun0000-0003-0815-412X
Additional Information:© 2019 Wiley‐VCH Verlag GmbH & Co. KGaA, Weinheim. Issue Online: 17 April 2020; Version of Record online: 20 November 2019; Manuscript revised: 16 September 2019; Manuscript received: 01 July 2019. This article also appears in: Hot Topic: Artificial Intelligence and Machine Learning. The authors gratefully thank Prof. Vivian Y. Chang and Prof. Kuan Wang at Taipei Medical University for helpful discussions. The authors gratefully thank Dr. Bingsen Zhou and Ms. Tiffany Lin at City of Hope for cell culture studies. X.D. and Y.L. acknowledge support from Shanghai Municipal Science and Technology Project (17DZ2203400) and State key research and development plan (2017YFC0107603 and 2017ZX10203205‐006‐002). V.H.S.C. and Y.Y. acknowledge support from Sino‐American Cancer Foundation. C.‐M.H. acknowledges support from endowment fund of Ben Rich‐Lockheed Martin professorship. D.H. gratefully acknowledges support from a Ministry of Education Tier 1 FRC Grant, Singapore Ministry of Health's National Medical Research Council under its Open Fund‐Large Collaborative Grant (“OF‐LCG”) (MOH‐OFLCG18May‐0003), National Institutes of Health grant R21DK116140, Wallace H. Coulter Foundation, and startup funds from the National University of Singapore. This study is partially supported by the Health and welfare surcharge of tobacco products grant (Grant Numbers: MOHW108‐TDU‐B‐212‐124014, MOHW108‐TDU‐B‐212‐124026 and MOHW108‐TDU‐B‐212‐124020) and Ministry of Education (MOE) in Taiwan. The animal studies reported this manuscript were conducted in accordance with the relevant ethical guidelines in the United States of America. Conflict of Interest: X.D. and C.‐M.H. are inventors on pending and issued patents pertaining to patents (International Patent Application Serial No. PCT/US2014/012111 and PCT/US2015/058892) covering the technology described herein. C.‐M. H. is a co‐inventor of pending patent WO2015017449. D.H. and C.M.H. are co‐inventors of patents that also cover the technology described herein (US20170177834 and WO2016149529A1). Author Contributions: X.D., V.H.S.C., and Y.L. contributed equally to this work. X.D. and V.H.S.C. performed the preclinical experiments. X.D., H. X., and Y.L. performed the prospective PRS augmented AI optimization. X.D., Y.L., X.L., C.‐M.H., D.H., and Y.Y. performed the PRS augmented AI analysis. X.D., Y.L., C.‐M.H., D.H., and Y.Y. wrote and edited the paper.
Funders:
Funding AgencyGrant Number
Shanghai Municipal Science and Technology17DZ2203400
State Key Research and Development Plan2017YFC0107603
State Key Research and Development Plan2017ZX10203205‐006‐002
Sino‐American Cancer FoundationUNSPECIFIED
Ben Rich‐Lockheed Martin ProfessorshipUNSPECIFIED
Ministry of Education (Singapore)UNSPECIFIED
Ministry of Health (Singapore)MOH‐OFLCG18May‐0003
NIHR21DK116140
Wallace H. Coulter FoundationUNSPECIFIED
National University of SingaporeUNSPECIFIED
Ministry of Health and Welfare (Singapore)MOHW108‐TDU‐B‐212‐124014
Ministry of Health and Welfare (Singapore)MOHW108‐TDU‐B‐212‐124026
Ministry of Health and Welfare (Singapore)MOHW108‐TDU‐B‐212‐124020
Ministry of Education (Taipei)UNSPECIFIED
Subject Keywords:artificial intelligence medicine; colorectal carcinoma; personalized medicine; rats
Issue or Number:4
Record Number:CaltechAUTHORS:20191120-102334275
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20191120-102334275
Official Citation:Ding, X., Chang, V.H.S., Li, Y., Li, X., Xu, H., Ho, C.‐M., Ho, D. and Yen, Y. (2020), Harnessing an Artificial Intelligence Platform to Dynamically Individualize Combination Therapy for Treating Colorectal Carcinoma in a Rat Model. Adv. Therap., 3: 1900127. doi:10.1002/adtp.201900127
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:99953
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:20 Nov 2019 18:39
Last Modified:22 Apr 2020 18:03

Repository Staff Only: item control page