Scalable in silico Simulation of Transdermal Drug Permeability: Application of BIOiSIM Platform

An AI Approach to Generating MIDD Assets Across the Drug Development Continuum

Model-informed drug development involves developing and applying exposure-based, biological, and statistical models derived from preclinical and clinical data sources to inform drug development and decision-making. Discrete models are generated from individual experiments resulting in a single model expression that is utilized to inform a single stage-gate decision. Other model types provide a more holistic view of disease biology and potentially disease progression depending on the appropriateness of the underlying data sources for that purpose. Despite this awareness, most data integration and model development approaches are still reliant on internal (within company) data stores and traditional structural model types. An AI/ML-based MIDD approach relies on more diverse data and is informed by past successes and failures including data outside a host company (external data sources) that may enhance predictive value and enhance data generated by the sponsor to reflect more informed and timely experimentation. The AI/ML methodology also provides a complementary approach to more traditional modeling efforts that support MIDD and thus yields greater fidelity in decision-making. Early pilot studies support this assessment but will require broader adoption and regulatory support for more evidence and refinement of this paradigm. An AI/ML-based approach to MIDD has the potential to transform regulatory science and the current drug development paradigm, optimize information value, and increase candidate and eventually product confidence with respect to safety and efficacy. We highlight early experiences with this approach using the AI compute platforms as representative examples of how MIDD can be facilitated with an AI/ML approach.

Opportunities and challenges in application of artificial intelligence in pharmacology

Artificial intelligence (AI) is a machine science that can mimic human behaviour like intelligent analysis of data. AI functions with specialized algorithms and integrates with deep and machine learning. Living in the digital world can generate a huge amount of medical data every day. Therefore, we need an automated and reliable evaluation tool that can make decisions more accurately and faster. Machine learning has the potential to learn, understand and analyse the data used in healthcare systems. In the last few years, AI is known to be employed in various fields in pharmaceutical science especially in pharmacological research. It helps in the analysis of preclinical (laboratory animals) and clinical (in human) trial data. AI also plays important role in various processes such as drug discovery/manufacturing, diagnosis of big data for disease identification, personalized treatment, clinical trial research, radiotherapy, surgical robotics, smart electronic health records, and epidemic outbreak prediction. Moreover, AI has been used in the evaluation of biomarkers and diseases. In this review, we explain various models and general processes of machine learning and their role in pharmacological science. Therefore, AI with deep learning and machine learning could be relevant in pharmacological research.

Machine learning and artificial intelligence in physiologically based pharmacokinetic modeling

Physiologically based pharmacokinetic (PBPK) models are useful tools in drug development and risk assessment of environmental chemicals. PBPK model development requires the collection of species-specific physiological, and chemical-specific absorption, distribution, metabolism, and excretion (ADME) parameters, which can be a time-consuming and expensive process. This raises a need to create computational models capable of predicting input parameter values for PBPK models, especially for new compounds. In this review, we summarize an emerging paradigm for integrating PBPK modeling with machine learning (ML) or artificial intelligence (AI)-based computational methods. This paradigm includes 3 steps (1) obtain time-concentration PK data and/or ADME parameters from publicly available databases, (2) develop ML/AI-based approaches to predict ADME parameters, and (3) incorporate the ML/AI models into PBPK models to predict PK summary statistics (eg, area under the curve and maximum plasma concentration). We also discuss a neural network architecture "neural ordinary differential equation (Neural-ODE)" that is capable of providing better predictive capabilities than other ML methods when used to directly predict time-series PK profiles. In order to support applications of ML/AI methods for PBPK model development, several challenges should be addressed (1) as more data become available, it is important to expand the training set by including the structural diversity of compounds to improve the prediction accuracy of ML/AI models; (2) due to the black box nature of many ML models, lack of sufficient interpretability is a limitation; (3) Neural-ODE has great potential to be used to generate time-series PK profiles for new compounds with limited ADME information, but its application remains to be explored. Despite existing challenges, ML/AI approaches will continue to facilitate the efficient development of robust PBPK models for a large number of chemicals.

In Silico Development of Combinatorial Therapeutic Approaches Targeting Key Signaling Pathways in Metabolic Syndrome

PURPOSE

Dysregulations of key signaling pathways in metabolic syndrome are multifactorial, eventually leading to cardiovascular events. Hyperglycemia in conjunction with dyslipidemia induces insulin resistance and provokes release of proinflammatory cytokines resulting in chronic inflammation, accelerated lipid peroxidation with further development of atherosclerotic alterations and diabetes. We have proposed a novel combinatorial approach using FDA approved compounds targeting IL-17a and DPP4 to ameliorate a significant portion of the clustered clinical risks in patients with metabolic syndrome. In our current research we have modeled the outcomes of metabolic syndrome treatment using two distinct drug classes.

METHODS

Targets were chosen based on the clustered clinical risks in metabolic syndrome: dyslipidemia, insulin resistance, impaired glucose control, and chronic inflammation. Drug development platform, BIOiSIM™, was used to narrow down two different drug classes with distinct modes of action and modalities. Pharmacokinetic and pharmacodynamic profiles of the most promising drugs were modeling showing predicted outcomes of combinatorial therapeutic interventions.

RESULTS

Preliminary studies demonstrated that the most promising drugs belong to DPP-4 inhibitors and IL-17A inhibitors. Evogliptin was chosen to be a candidate for regulating glucose control with long term collateral benefit of weight loss and improved lipid profiles. Secukinumab, an IL-17A sequestering agent used in treating psoriasis, was selected as a repurposed candidate to address the sequential inflammatory disorders that follow the first metabolic insult.

CONCLUSIONS

Our analysis suggests this novel combinatorial therapeutic approach inducing DPP4 and Il-17a suppression has a high likelihood of ameliorating a significant portion of the clustered clinical risk in metabolic syndrome.

Skin-on-a-Chip Technology for Testing Transdermal Drug Delivery-Starting Points and Recent Developments

During the last decades, several technologies were developed for testing drug delivery through the dermal barrier. Investigation of drug penetration across the skin can be important in topical pharmaceutical formulations and also in cosmeto-science. The state-of- the-art in the field of skin diffusion measurements, different devices, and diffusion platforms used, are summarized in the introductory part of this review. Then the methodologies applied at Pázmány Péter Catholic University are shown in detail. The main testing platforms (Franz diffusion cells, skin-on-a-chip devices) and the major scientific projects (P-glycoprotein interaction in the skin; new skin equivalents for diffusion purposes) are also presented in one section. The main achievements of our research are briefly summarized: (1) new skin-on-a-chip microfluidic devices were validated as tools for drug penetration studies for the skin; (2) P-glycoprotein transport has an absorptive orientation in the skin; (3) skin samples cannot be used for transporter interaction studies after freezing and thawing; (4) penetration of hydrophilic model drugs is lower in aged than in young skin; (5) mechanical sensitization is needed for excised rodent and pig skins for drug absorption measurements. Our validated skin-on-a-chip platform is available for other research groups to use for testing and for utilizing it for different purposes.

Gaultheria leucocarpa var. yunnanensis for Treating Rheumatoid Arthritis-An Assessment Combining Machine Learning-Guided ADME Properties Prediction, Network Pharmacology, and Pharmacological Assessment

Background: Dianbaizhu (Gaultheria leucocarpa var. yunnanensis), a traditional Chinese/ethnic medicine (TC/EM), has been used to treat rheumatoid arthritis (RA) for a long time. The anti-rheumatic arthritis fraction (ARF) of G. yunnanensis has significant anti-inflammatory and analgesic activities and is mainly composed of methyl salicylate glycosides, flavonoids, organic acids, and others. The effective ingredients and rudimentary mechanism of ARF remedying RA have not been elucidated to date. Purpose: The aim of the present study is to give an insight into the effective components and mechanisms of Dianbaizhu in ameliorating RA, based on the estimation of the absorption, distribution, metabolism, and excretion (ADME) properties, analysis of network pharmacology, and in vivo and in vitro validations. Study design and methods: The IL-1β-induced human fibroblast-like synoviocytes of RA (HFLS-RA) model and adjuvant-induced arthritis in the rat model were adopted to assess the anti-RA effect of ARF. The components in ARF were identified by using UHPLC-LTQ-Orbitrap-MSⁿ. The quantitative structure-activity relationship (QSAR) models were developed by using five machine learning algorithms, alone or in combination with genetic algorithms for predicting the ADME properties of ARF. The molecular networks and pathways presumably referring to the therapy of ARF on RA were yielded by using common databases and visible software, and the experimental validations of the key targets conducted in vitro. Results: ARF effectively relieved RA in vivo and in vitro. The five optimized QSAR models that were developed showed robustness and predictive ability. The characterized 48 components in ARF had good biological potency. Four key signaling pathways were obtained, which were related to both cytokine signaling and cell immune response. ARF suppressed IL-1β-induced expression of EGFR, MMP 9, IL2, MAPK14, and KDR in the HFLS-RA . Conclusions: ARF has good druggability and high exploitation potential. Methyl salicylate glycosides and flavonoids play essential roles in attuning RA. ARF may partially attenuate RA by regulating the expression of multi-targets in the inflammation-immune system. These provide valuable information to rationalize ARF and other TC/EMs in the treatment of RA.

Transdermal Delivery of Chemotherapeutics: Strategies, Requirements, and Opportunities

Chemotherapeutic drugs are primarily administered to cancer patients via oral or parenteral routes. The use of transdermal drug delivery could potentially be a better alternative to decrease the dose frequency and severity of adverse or toxic effects associated with oral or parenteral administration of chemotherapeutic drugs. The transdermal delivery of drugs has shown to be advantageous for the treatment of highly localized tumors in certain types of breast and skin cancers. In addition, the transdermal route can be used to deliver low-dose chemotherapeutics in a sustained manner. The transdermal route can also be utilized for vaccine design in cancer management, for example, vaccines against cervical cancer. However, the design of transdermal formulations may be challenging in terms of the conjugation chemistry of the molecules and the sustained and reproducible delivery of therapeutically efficacious doses. In this review, we discuss the nano-carrier systems, such as nanoparticles, liposomes, etc., used in recent literature to deliver chemotherapeutic agents. The advantages of transdermal route over oral and parenteral routes for popular chemotherapeutic drugs are summarized. Furthermore, we also discuss a possible in silico approach, Formulating for Efficacy™, to design transdermal formulations that would probably be economical, robust, and more efficacious.

A hybrid modeling approach for assessing mechanistic models of small molecule partitioning in vivo using a machine learning-integrated modeling platform

Prediction of the first-in-human dosing regimens is a critical step in drug development and requires accurate quantitation of drug distribution. Traditional in vivo studies used to characterize clinical candidate’s volume of distribution are error-prone, time- and cost-intensive and lack reproducibility in clinical settings. The paper demonstrates how a computational platform integrating machine learning optimization with mechanistic modeling can be used to simulate compound plasma concentration profile and predict tissue-plasma partition coefficients with high accuracy by varying the lipophilicity descriptor logP. The approach applied to chemically diverse small molecules resulted in comparable geometric mean fold-errors of 1.50 and 1.63 in pharmacokinetic outputs for direct tissue:plasma partition and hybrid logP optimization, with the latter enabling prediction of tissue permeation that can be used to guide toxicity and efficacy dosing in human subjects. The optimization simulations required to achieve these results were parallelized on the AWS cloud and generated outputs in under 5 h. Accuracy, speed, and scalability of the framework indicate that it can be used to assess the relevance of other mechanistic relationships implicated in pharmacokinetic-pharmacodynamic phenomena with a lower risk of overfitting datasets and generate large database of physiologically-relevant drug disposition for further integration with machine learning models.

Accelerated Repurposing and Drug Development of Pulmonary Hypertension Therapies for COVID-19 Treatment Using an AI-Integrated Biosimulation Platform

The COVID-19 pandemic has reached over 100 million worldwide. Due to the multi-targeted nature of the virus, it is clear that drugs providing anti-COVID-19 effects need to be developed at an accelerated rate, and a combinatorial approach may stand to be more successful than a single drug therapy. Among several targets and pathways that are under investigation, the renin-angiotensin system (RAS) and specifically angiotensin-converting enzyme (ACE), and Ca²⁺-mediated SARS-CoV-2 cellular entry and replication are noteworthy. A combination of ACE inhibitors and calcium channel blockers (CCBs), a critical line of therapy for pulmonary hypertension, has shown therapeutic relevance in COVID-19 when investigated independently. To that end, we conducted in silico modeling using BIOiSIM, an AI-integrated mechanistic modeling platform by utilizing known preclinical in vitro and in vivo datasets to accurately simulate systemic therapy disposition and site-of-action penetration of the CCBs and ACEi compounds to tissues implicated in COVID-19 pathogenesis.

In Silico Simulation of the Systemic Drug Exposure Following the Topical Application of Opioid Analgesics in Patients with Cutaneous Lesions

The use of opioid analgesics in treating severe pain is frequently associated with putative adverse effects in humans. Topical agents that are shown to have high efficacy with a favorable safety profile in clinical settings are great alternatives for pain management of multimodal analgesia. However, the risk of side effects induced by transdermal absorption and systemic exposure is of great concern as they are challenging to predict. The present study aimed to use "BIOiSIM" an artificial intelligence-integrated biosimulation platform to predict the transdermal disposition of opioid analgesics. The model successfully predicted their exposure following the topical application of central opioid agonist buprenorphine and peripheral agonist oxycodone in healthy human subjects with simulation of intra-skin exposure in subjects with burns and pressure wounds. The predicted plasma levels of analgesics were used to evaluate the safety of the therapeutic pain control in patients with the dermal structural impairments caused by acute (burns) or chronic cutaneous lesions (pressure wounds) with topical opioid analgesics.

Driving success in personalized medicine through AI-enabled computational modeling

The development of successful drugs is expensive and time-consuming because of high clinical attrition rates. This is caused partially by the rupture seen in the translatability of the drug from the bench to the clinic in the context of personalized medicine. Artificial intelligence (AI)-driven platforms integrated with mechanistic modeling have become instrumental in accelerating the drug development process by leveraging data ubiquitously across the various phases. AI can counter the deficiencies and ambiguities that arise during the classical drug development process while reducing human intervention and bridging the translational gap in discovering the connections between drugs and diseases.