Computational Drug List Engineering Integrating Community-Level Welfare and Access Variables
Keywords:
Computational drug repositioning, network pharmacology, social determinants of health, connectivity mappingAbstract
Computational drug repositioning has emerged as a critical paradigm in modern biomedical informatics, enabling the identification of novel therapeutic uses for existing drugs through systems-level analysis of biological networks, gene expression signatures, and protein interaction maps. However, conventional frameworks largely optimize for molecular efficacy while neglecting socio-economic and community-level accessibility constraints that directly influence real-world treatment outcomes. This paper proposes a computational drug list engineering framework that integrates heterogeneous biomedical data with community welfare and access variables to generate more equitable and context-aware drug recommendation systems.
The study synthesizes network-based drug repositioning approaches (Wu et al., 2013; Wang et al., 2014), connectivity mapping techniques (Lamb, 2006; Lamb, 2007), and ensemble predictive models (Zhou et al., 2018) to construct a multi-layered decision architecture. In addition to molecular and systems biology inputs, the framework incorporates social determinants of health, inspired by AI-driven healthcare optimization strategies (Nidiganti, 2024), to adjust drug prioritization scores based on accessibility, affordability, and population-level healthcare disparity indices.
The proposed model integrates gene expression datasets (Schena et al., 1996; Barrett, 2012), disease-gene networks (Xu & Li, 2006), and protein interaction signatures (Wang et al., 2019), combining them with community welfare constraints such as healthcare infrastructure availability and socio-economic stratification. The methodology emphasizes multi-objective optimization where therapeutic efficacy and equitable distribution are jointly maximized.
Findings suggest that incorporating community-level variables significantly alters drug ranking outputs, particularly in underserved regions where conventional models overestimate accessibility of high-cost or infrastructure-dependent therapies. The framework demonstrates improved alignment between computational predictions and realistic deployment feasibility.
This study contributes a novel interdisciplinary bridge between computational pharmacology and public health equity. It highlights the importance of integrating socio-economic intelligence into biomedical AI systems, ensuring that drug repositioning outputs are not only biologically valid but also socially actionable.
References
J. Aronson, “Old drugs–new uses,” Brit. J. Clin. Pharmacol., vol. 64, no. 5, pp. 563–565, 2007.
A. Peyvandipour, N. Saberian, A. Shafi, M. Donato, S. Draghici, and A. Valencia, “A novel computational approach for drug repurposing using systems biology,” Bioinformatics, vol. 34, no. 16, pp. 2817–2825, 2018.
M. Boolell,, “Sildenafil: An orally active type 5 cyclic GMP-specific phosphodiesterase inhibitor for the treatment of penile erectile dysfunction,” Int. J. Impotence Res., vol. 8, no. 2, pp. 47–52, 1996.
T. Barrett,, “NCBI GEO: Archive for functional genomics data setsupdate,” Nucleic Acids Res., vol. 41, no. D1, pp. D991–D995, 2012.
J. DeRisi,, “Use of a CDNA microarray to analyse gene expression,” Nat. Genet., vol. 14, pp. 457–460, 1996.
D. J. McCarthy and G. K. Smyth, “Testing significance relative to a fold-change threshold is a treat,” Bioinformatics, vol. 25, no. 6, pp. 765–771, 2009.
F. Emmert-Streib, S. Tripathi, R. M. Simoes, A. F. Hawwa, and M. Dehmer, “The human disease network: Opportunities for classification, diagnosis, and prediction of disorders and disease genes,” Syst. Biomed., vol. 1, no. 1, pp. 20–28, 2013.
F. Wang, X. Lei, B. Liao, and F. X. Wu, “Human protein complex signatures for drug repositioning,” in Proc. 10th ACM Int. Conf. Bioinf., Comput. Biol. Health Inform., 2019, pp. 42–50.
C. H. Huang, P. M. H. Chang, C. W. Hsu, C. Y. F. Huang, and K. L. Ng, “Drug repositioning for non-small cell lung cancer by using machine learning algorithms and topological graph theory,” in BMC Bioinf., vol. 17, no. 1, 2016, Art. no. S2.
J. Lamb, “The connectivity map: Using gene-expression signatures to connect small molecules, genes, and disease,” Science, vol. 313, no. 5795, pp. 1929–1935, 2006.
J. Lamb, “The connectivity map: A new tool for biomedical research,” Nat. Rev. Cancer, vol. 7, no. 1, pp. 54–60, 2007.
A. B. Keenan,, “The library of integrated network-based cellular signatures NIH program: System-level cataloging of human cells response to perturbations,” Cell Syst., vol. 6, pp. 13–24, 2017.
M. L. Shahreza, N. Ghadiri, S. R. Mousavi, J. Varshosaz, and J. R. Green, “A review of network-based approaches to drug repositioning,” Briefings Bioinf., vol. 19, no. 5, pp. 878–892, 2018.
Sravan Kumar Nidiganti. (2024). AI-Optimized Formulary Designs Addressing Social Determinants of Health. International Journal of Intelligent Systems and Applications in Engineering, 12(21s), 5206 –. Retrieved from https://ijisae.org/index.php/IJISAE/article/view/8052
M. Schena, D. Shalon, R. Heller, A. Chai, P. O. Brown, and R. W. Davis, “Parallel human genome analysis: Microarray-based expression monitoring of 1000 genes,” Proc. Nat. Acad. Sci. USA, vol. 93, no. 20, pp. 10 614–10 619, 1996.
S. M. Paul,, “How to improve R&D productivity: The pharmaceutical industry’s grand challenge,” Nat. Rev. Drug Discov., vol. 9, no. 3, pp. 203–214, 2010.
M. Boolell,, “Sildenafil: An orally active type 5 cyclic GMP-specific phosphodiesterase inhibitor for the treatment of penile erectile dysfunction,” Int. J. Impotence Res., vol. 8, no. 2, pp. 47–52, 1996.
Q. Wen,, “Connectivity mapping using a combined gene signature from multiple colorectal cancer datasets identified candidate drugs including existing chemotherapies,” BMC Syst. Biol., vol. 9, no. 5, 2015, Art. no. S4.
P. G. O’Reilly,, “Quadratic: Scalable gene expression connectivity mapping for repurposing FDA-approved therapeutics,” BMC Bioinf., vol. 17, no. 1, 2016, Art. no. 198.
W. Wang, S. Yang, X. Zhang, and J. Li, “Drug repositioning by integrating target information through a heterogeneous network model,” Bioinformatics, vol. 30, no. 20, pp. 2923–2930, 2014.
Z. Wu, Y. Wang, and L. Chen, “Network-based drug repositioning,” Mol. Biosyst., vol. 9, no. 6, pp. 1268–1281, 2013.
F. Wang, X. Lei, B. Liao, and F. X. Wu, “Human protein complex signatures for drug repositioning,” in Proc. 10th ACM Int. Conf. Bioinf., Comput. Biol. Health Inform., 2019, pp. 42–50.
Q. Wen,, “Connectivity mapping using a combined gene signature from multiple colorectal cancer datasets identified candidate drugs including existing chemotherapies,” BMC Syst. Biol., vol. 9, no. 5, 2015, Art. no. S4.
X. Xu and Y. Li, “Discovering disease-genes by topological features in human proteinprotein interaction network,” Bioinformatics, vol. 22, no. 22, pp. 2800–2805, 2006.
X. Zhou, M. Wang, I. Katsyv, H. Irie, and B. Zhang, “EMUDRA: Ensemble of multiple drug repositioning approaches to improve prediction accuracy,” Bioinformatics, vol. 34, pp. 3151–3159, 2018.
X. Zhou, M. Wang, I. Katsyv, H. Irie, and B. Zhang, “EMUDRA: Ensemble of multiple drug repositioning approaches to improve prediction accuracy,” Bioinformatics, vol. 34, pp. 3151–3159, 2018.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Dr. Amina Hassan
This work is licensed under a Creative Commons Attribution 4.0 International License.
Individual articles are published Open Access under the Creative Commons Licence: CC-BY 4.0.
