In the ongoing research exploring the therapeutic and mechanistic implications of altered metabolism of HIV medications caused by alcohol or alcohol/synthetic opioid combinations, Yan’s laboratory has uncovered a significant link between alcohol and ART interactions. The article titled, "Effect of alcohol exposure on the efficacy and safety of tenofovir alafenamide fumarate, a major medicine against human immunodeficiency virus" by Liu et al., sheds light on alcohols impact on tenofovir-medicines in HIV treatment efficacy and safety. Yan and coworkers conclude that alcohol drinking negatively impacts the efficacy and worsens the steatosis of tenofovir alafenamide fumarate (TAF). The mechanism he cites involves a transesterification reaction of TAF, leading to the formation of ethyl TAF when interacting with alcohol. Consequently, the formation of ethyl TAF reduces the production of the active metabolite, tenofovir diphosphate, compromising medication efficacy. Furthermore, the study identifies the alcohol-TAF interaction exacerbates toxicity through lipid retention and potentially leading to fatty liver.
While these findings are indeed significant, the “wet lab experiments” research methods employed in the paper lack efficiency and breadth compared to the synthetic data attainable through artificial intelligence (AI) and machine learning. Just imagine if these findings could be expanded upon, exploring a wide range of HIV treatments and even extending to other diseases and drug efficacies.
The methods used in the paper pose practical limitations to such endeavors. However, with the burgeoning opportunities presented by AI, the prospect of conducting more efficient and high-volume scientific research becomes increasingly promising. Traditional research methods often struggle to effectively or comprehensively analyze the intricacies of these complex interactions. Yet, with the advent of AI, particularly machine learning and deep learning, there is potential to streamline some of this research.
Currently, Yan’s laboratory aims to expand previous research with machine learning algorithms focused on how metabolism of HIV medications in certain organ systems is affected by alcohol and other substances. By leveraging AI-driven pattern recognition, researchers can identify intricate interactions between compounds within HIV treatment metabolism, shedding light on subtle nuances previously overlooked. Through continuous monitoring and feedback loops, AI enables dynamic parameter adjustments, ensuring optimal model performance in response to changing conditions.
A Semi-Modular Approach
AI algorithms are trained to predict compound interactions and dependencies, offering a comprehensive layer of analysis, with AI processing and training on datasets encompassing HIV medication metabolism, known cellular pathways, and chemical properties, we can expediate our understanding of alcohol-HIV drug interactions. Expanding upon this foundation, Yan and his team’s research aims to employ machine learning algorithms to delve deeper into the complexities of how alcohol and other substances impact the metabolism of HIV medications within specific organ systems. By employing techniques such as feature selection, model training, evaluation, and interpretation, we seek to uncover relationships and patterns to inform more effective treatment strategies and enhance patient outcomes.
These advancements refine current understanding of HIV treatment metabolism, empowering clinicians with actionable insights for personalized patient care. With AI, research can move more efficiently toward precision medicine, leading to optimized patient outcomes through tailored interventions.
Yan’s laboratory sets objectives:
• Investigate pharmacokinetic profiles of alcohol and ART
• Analyze pharmacodynamic effects on immune response and antiretroviral efficacy
• Explore potential synergistic or antagonistic interactions on molecular targets
• Develop an AI-driven prediction model for alcohol-ART interactions
The objectives include the updated and upgraded set of research goals and strategies that Yan and colleagues will be working within and striving to achieve. An evolution of the published data and previous studies as well as the current grant awarded in 2022. “Our ambitions have accelerated as we are moving forward with AI, to keep pace with the modern world”, Yan explained. Our purpose remains “Changing the game for HIV patient care”, Yan said.
Acknowledgement
This research is supported by the National Institutes of Health (Grant: R01 AA030486).
Thanks go to: Jason Blackard, Ph.D., Department of Internal Medicine, Division of Digestive Diseases, University of Cincinnati College of Medicine; Jaime Robertson, M.D., Department of Internal Medicine, Division of Infectious Diseases, University of Cincinnati College of Medicine; Jeffrey, Welge, Ph.D., Departments of Psychiatry and Environmental Health, University of Cincinnati College of Medicine; and Jenifer Brown, Ph.D., Department of Psychological Sciences, College of Health and Human Sciences, Purdue University for their comments and supports.
References
2. Liu, W., Yu, S., & Yan, B. (2022). Effect of alcohol exposure on the efficacy and safety of tenofovir alafenamide fumarate, a major medicine against human immunodeficiency virus. Biochemical Pharmacology, 204, 115224–115224.
3. Blackard, J. T., Brown, J. L., & Lyons, M. S. (2019). Synthetic Opioid Use and Common Injection-associated Viruses: Expanding the Translational Research Agenda. Current HIV research, 17(2), 94–101.
4. Kong, L., Shata, M. T. M., Brown, J. L., Lyons, M. S., Sherman, K. E., & Blackard, J. T. (2022). The synthetic opioid fentanyl increases HIV replication and chemokine co-receptor expression in vitro. Journal of neurovirology, 28(4-6), 583–594.
5. Xiang, Y., Du, J., Fujimoto, K., Li, F., Schneider, J., & Tao, C. (2022). Application of artificial intelligence and machine learning for HIV prevention interventions. The Lancet. HIV, 9(1), e54–e62.