Mechanism-based organization of neural networks to emulate systems biology and pharmacology models.

Deep learning neural networks are often described as black boxes, as it is difficult to trace model outputs back to model inputs due to a lack of clarity over the internal mechanisms. This is even true for those neural networks designed to emulate mechanistic models, which simply learn a mapping between the inputs and outputs of mechanistic models, ignoring the underlying processes. Using a mechanistic model studying the pharmacological interaction between opioids and naloxone as a proof-of-concept example, we demonstrated that by reorganizing the neural networks' layers to mimic the structure of the mechanistic model, it is possible to achieve better training rates and prediction accuracy relative to the previously proposed black-box neural networks, while maintaining the interpretability of the mechanistic simulations. Our framework can be used to emulate mechanistic models in a large parameter space and offers an example on the utility of increasing the interpretability of deep learning networks.

Physiologically based modeling reveals different risk of respiratory depression after fentanyl overdose between adults and children.

Despite a rapid increase in pediatric mortality rate from prescription and illicit opioids, there is limited research on the dose-dependent impact of opioids on respiratory depression in children, the leading cause of opioid-associated death. In this article, we extend a previously developed translational model to cover pediatric populations by incorporating age-dependent pharmacokinetic, pharmacodynamic, and physiological changes compared to adults. Our model reproduced previous perioperative clinical findings that adults and children have similar risk of respiratory depression at the same plasma fentanyl concentration when specific endpoints (minute ventilation, CO2 tension in the blood) were used. However, our model points to a potential caveat that, in a perioperative setting, routine use of mechanical ventilation and supplemental oxygen maintained the blood and tissue oxygen partial pressures in patients and prevented the use of oxygen-related endpoints to evaluate the consequences of respiratory depression. In a community setting when such oxygenation procedures are not immediately available, our model suggests that the higher oxygen demand and reduced cerebrovascular reactivity could make children more susceptible to severe hypoxemia and brain hypoxia, even with the same plasma fentanyl concentration as adults. Our work indicates that when developing intervention strategies to protect children from opioid overdose in a community setting, these pediatric-specific factors may need to be considered.

Intranasal Naloxone Repeat Dosing Strategies and Fentanyl Overdose: A Simulation-Based Randomized Clinical Trial.

Importance: Questions have emerged as to whether standard intranasal naloxone dosing recommendations (ie, 1 dose with readministration every 2-3 minutes if needed) are adequate in the era of illicitly manufactured fentanyl and its derivatives (hereinafter, fentanyl). Objective: To compare naloxone plasma concentrations between different intranasal naloxone repeat dosing strategies and to estimate their effect on fentanyl overdose. Design, Setting, and Participants: This unblinded crossover randomized clinical trial was conducted with healthy participants in a clinical pharmacology unit (Spaulding Clinical Research, West Bend, Wisconsin) in March 2021. Inclusion criteria included age 18 to 55 years, nonsmoking status, and negative test results for the presence of alcohol or drugs of abuse. Data analysis was performed from October 2021 to May 2023. Intervention: Naloxone administered as 1 dose (4 mg/0.1 mL) at 0, 2.5, 5, and 7.5 minutes (test), 2 doses at 0 and 2.5 minutes (test), and 1 dose at 0 and 2.5 minutes (reference). Main Outcomes and Measures: The primary outcome was the first prespecified time with higher naloxone plasma concentration. The secondary outcome was estimated brain hypoxia time following simulated fentanyl overdoses using a physiologic pharmacokinetic-pharmacodynamic model. Naloxone concentrations were compared using paired tests at 3 prespecified times across the 3 groups, and simulation results were summarized using descriptive statistics. Results: This study included 21 participants, and 18 (86%) completed the trial. The median participant age was 34 years (IQR, 27-50 years), and slightly more than half of participants were men (11 [52%]). Compared with 1 naloxone dose at 0 and 2.5 minutes, 1 dose at 0, 2.5, 5, and 7.5 minutes significantly increased naloxone plasma concentration at 10 minutes (7.95 vs 4.42 ng/mL; geometric mean ratio, 1.95 [1-sided 97.8% CI, 1.28-∞]), whereas 2 doses at 0 and 2.5 minutes significantly increased the plasma concentration at 4.5 minutes (2.24 vs 1.23 ng/mL; geometric mean ratio, 1.98 [1-sided 97.8% CI, 1.03-∞]). No drug-related serious adverse events were reported. The median brain hypoxia time after a simulated fentanyl 2.97-mg intravenous bolus was 4.5 minutes (IQR, 2.1-∞ minutes) with 1 naloxone dose at 0 and 2.5 minutes, 4.5 minutes (IQR, 2.1-∞ minutes) with 1 naloxone dose at 0, 2.5, 5, and 7.5 minutes, and 3.7 minutes (IQR, 1.5-∞ minutes) with 2 naloxone doses at 0 and 2.5 minutes. Conclusions and Relevance: In this clinical trial with healthy participants, compared with 1 intranasal naloxone dose administered at 0 and 2.5 minutes, 1 dose at 0, 2.5, 5, and 7.5 minutes significantly increased naloxone plasma concentration at 10 minutes, whereas 2 doses at 0 and 2.5 minutes significantly increased naloxone plasma concentration at 4.5 minutes. Additional research is needed to determine optimal naloxone dosing in the community setting. Trial Registration: ClinicalTrials.gov Identifier: NCT04764630.

Deep learning-enabled natural language processing to identify directional pharmacokinetic drug-drug interactions.

BACKGROUND: During drug development, it is essential to gather information about the change of clinical exposure of a drug (object) due to the pharmacokinetic (PK) drug-drug interactions (DDIs) with another drug (precipitant). While many natural language processing (NLP) methods for DDI have been published, most were designed to evaluate if (and what kind of) DDI relationships exist in the text, without identifying the direction of DDI (object vs. precipitant drug). Here we present a method for the automatic identification of the directionality of a PK DDI from literature or drug labels. METHODS: We reannotated the Text Analysis Conference (TAC) DDI track 2019 corpus for identifying the direction of a PK DDI and evaluated the performance of a fine-tuned BioBERT model on this task by following the training and validation steps prespecified by TAC. RESULTS: This initial attempt showed the model achieved an F-score of 0.82 in identifying sentences as containing PK DDI and an F-score of 0.97 in identifying object versus precipitant drugs in those sentences. DISCUSSION AND CONCLUSION: Despite a growing list of NLP methods for DDI extraction, most of them use a common set of corpora to perform general purpose tasks (e.g., classifying a sentence into one of several fixed DDI categories). There is a lack of coordination between the drug development and biomedical informatics method development community to develop corpora and methods to perform specific tasks (e.g., extract clinical exposure changes due to PK DDI). We hope that our effort can encourage such a coordination so that more "fit for purpose" NLP methods could be developed and used to facilitate the drug development process.

Calibration and Validation of a Mechanistic COVID-19 Model for Translational Quantitative Systems Pharmacology - A Proof-of-Concept Model Development for Remdesivir.

With the ongoing global pandemic of coronavirus disease 2019 (COVID-19), there is an urgent need to accelerate the traditional drug development process. Many studies identified potential COVID-19 therapies based on promising nonclinical data. However, the poor translatability from nonclinical to clinical settings has led to failures of many of these drug candidates in the clinical phase. In this study, we propose a mechanism-based, quantitative framework to translate nonclinical findings to clinical outcome. Adopting a modularized approach, this framework includes an in silico disease model for COVID-19 (virus infection and human immune responses) and a pharmacological component for COVID-19 therapies. The disease model was able to reproduce important longitudinal clinical data for patients with mild and severe COVID-19, including viral titer, key immunological cytokines, antibody responses, and time courses of lymphopenia. Using remdesivir as a proof-of-concept example of model development for the pharmacological component, we developed a pharmacological model that describes the conversion of intravenously administered remdesivir as a prodrug to its active metabolite nucleoside triphosphate through intracellular metabolism and connected it to the COVID-19 disease model. After being calibrated with the placebo arm data, our model was independently and quantitatively able to predict the primary endpoint (time to recovery) of the remdesivir clinical study, Adaptive Covid-19 Clinical Trial (ACTT). Our work demonstrates the possibility of quantitatively predicting clinical outcome based on nonclinical data and mechanistic understanding of the disease and provides a modularized framework to aid in candidate drug selection and clinical trial design for COVID-19 therapeutics.

Development of a Translational Model to Assess the Impact of Opioid Overdose and Naloxone Dosing on Respiratory Depression and Cardiac Arrest.

In response to a surge of deaths from synthetic opioid overdoses, there have been increased efforts to distribute naloxone products in community settings. Prior research has assessed the effectiveness of naloxone in the hospital setting; however, it is challenging to assess naloxone dosing regimens in the community/first-responder setting, including reversal of respiratory depression effects of fentanyl and its derivatives (fentanyls). Here, we describe the development and validation of a mechanistic model that combines opioid mu receptor binding kinetics, opioid agonist and antagonist pharmacokinetics, and human respiratory and circulatory physiology, to evaluate naloxone dosing to reverse respiratory depression. Validation supports our model, which can quantitatively predict displacement of opioids by naloxone from opioid mu receptors in vitro, hypoxia-induced cardiac arrest in vivo, and opioid-induced respiratory depression in humans from different fentanyls. After validation, overdose simulations were performed with fentanyl and carfentanil followed by administration of different intramuscular naloxone products. Carfentanil induced more cardiac arrest events and was more difficult to reverse than fentanyl. Opioid receptor binding data indicated that carfentanil has substantially slower dissociation kinetics from the opioid receptor compared with nine other fentanyls tested, which likely contributes to the difficulty in reversing carfentanil. Administration of the same dose of naloxone intramuscularly from two different naloxone products with different formulations resulted in differences in the number of virtual patients experiencing cardiac arrest. This work provides a robust framework to evaluate dosing regimens of opioid receptor antagonists to reverse opioid-induced respiratory depression, including those caused by newly emerging synthetic opioids.