Applying Optimization Algorithms to Tuberculosis Antibiotic Treatment Regimens
Tuberculosis (TB), one of the most common infectious diseases, requires treatment with multiple antibiotics taken over at least 6 months. This long treatment often results in poor patient-adherence, which can lead to the emergence of multi-drug resistant TB. New antibiotic treatment strategies are sorely needed. New antibiotics are being developed or repurposed to treat TB, but as there are numerous potential antibiotics, dosing sizes and potential schedules, the regimen design space for new treatments is too large to search exhaustively. Here we propose a method that combines an agent-based multi-scale model capturing TB granuloma formation with algorithms for mathematical optimization to identify optimal TB treatment regimens.
We define two different single-antibiotic treatments to compare the efficiency and accuracy in predicting optimal treatment regimens of two optimization algorithms: genetic algorithms (GA) and surrogate-assisted optimization through radial basis function (RBF) networks. We also illustrate the use of RBF networks to optimize double-antibiotic treatments.
We found that while GAs can locate optimal treatment regimens more accurately, RBF networks provide a more practical strategy to TB treatment optimization with fewer simulations, and successfully estimated optimal double-antibiotic treatment regimens.
Our results indicate surrogate-assisted optimization can locate optimal TB treatment regimens from a larger set of antibiotics, doses and schedules, and could be applied to solve optimization problems in other areas of research using systems biology approaches. Our findings have important implications for the treatment of diseases like TB that have lengthy protocols or for any disease that requires multiple drugs.
KeywordsTuberculosis Antibiotics Agent-based modeling Genetic algorithm Surrogate-assisted optimization
Radial basis function
Ordinary differential equation
Partial differential equation
Latin hypercube sampling
This research was supported by the following grants from the National Institutes of Health: U01HL131072, R01AI123093 and R01HL110811. This research also used resources of the National Energy Research Scientific Computing Center, which is supported by the Office of Science of the U.S. Department of Energy under Contract No. DE-AC02-05CH11231 and the Extreme Science and Engineering Discovery Environment (XSEDE), which is supported by National Science Foundation Grant Number MCB140228. We thank Paul Wolberg for computational assistance and Chang Gong for initial efforts on the GA and Fig. 1 calculations.
Conflict of interest
Joseph M. Cicchese, Elsje Pienaar, Denise E. Kirschner, and Jennifer J. Linderman declare that they have no conflicts of interest.
No human or animal studies were performed by the authors for this article.
- 1.Akhtar, T., and C.A. Shoemaker. Multi objective optimization of computationally expensive multi-modal functions with RBF surrogates and multi-rule selection. J. Glob. Optim. Springer US, 64:17–32, 2016.Google Scholar
- 5.CDC. Treatment of Tuberculosis. Arch. Intern. Med., 2003.Google Scholar
- 11.Diaz-Manriquez, A., G. Toscano-Pulido, and W. Gomez-Flores. On the selection of surrogate models in evolutionary optimization algorithms. 2011 IEEE Congr. Evol. Comput. CEC 2155–2162, 2011.Google Scholar
- 14.Finley, S.D., L.-H. Chu, and A.S. Popel. Computational systems biology approaches to anti-angiogenic cancer therapeutics. Drug Discov. Today Elsevier Ltd, 20:187–197, 2015.Google Scholar
- 24.Kia, R., F. Khaksar-Haghani, N. Javadian, and R. Tavakkoli-Moghaddam. Solving a multi-floor layout design model of a dynamic cellular manufacturing system by an efficient genetic algorithm. J. Manuf. Syst. The Society of Manufacturing Engineers, 33:218–232, 2014.Google Scholar
- 28.Lee, B.-Y. et al. Drug regimens identified and optimized by output-driven platform markedly reduce tuberculosis treatment time. Nat. Commun. 8, 2017.Google Scholar
- 30.Linderman, J.J., N.A. Cilfone, E. Pienaar, C. Gong, and D.E. Kirschner. A multi-scale approach to designing therapeutics for tuberculosis. Integr. Biol. Royal Society of Chemistry, 7:591–609, 2015.Google Scholar
- 37.Melin, P., and O. Castillo. A review on type-2 fuzzy logic applications in clustering, classification and pattern recognition. Appl. Soft Comput. J. Elsevier B.V., 21:568–577, 2014.Google Scholar
- 42.Orr, M.J.L. Introduction to radial basis function networks., 1996. Available from: http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.133.7043.
- 44.Pienaar, E. et al. A computational tool integrating host immunity with antibiotic dynamics to study tuberculosis treatment. J. Theor. Biol. Elsevier, 367:166–179, 2015. Available from: http://dx.doi.org/10.1016/j.jtbi.2014.11.021.
- 54.WHO. Integrated PK-PD and agent-based modeling in oncology. J. Pharmacokinet. Pharmacodyn. 42:179–189, 2016.Google Scholar
- 55.Zumla, A., P. Nahid, and S.T. Cole. Advances in the development of new tuberculosis drugs and treatment regimens. Nat. Rev. Drug Discov. Nature Publishing Group, 12:388–404, 2013.Google Scholar
- 56.Zumla, A.I. et al. New antituberculosis drugs, regimens, and adjunct therapies: Needs, advances, and future prospects. Lancet Infect. Dis. Elsevier Ltd, 14:327–340, 2014.Google Scholar