Validation of Early Human Dose Prediction: A Key Metric for Compound Progression in Drug Discovery

Novel hydrazone compounds with broad-spectrum antiplasmodial activity and synergistic interactions with antimalarial drugs

The development of novel antiplasmodial compounds with broad-spectrum activity against different stages of Plasmodium parasites is crucial to prevent malaria disease and parasite transmission. This study evaluated the antiplasmodial activity of seven novel hydrazone compounds (referred to as CB compounds: CB-27, CB-41, CB-50, CB-53, CB-58, CB-59, and CB-61) against multiple stages of Plasmodium parasites. All CB compounds inhibited blood stage proliferation of drug-resistant or sensitive strains of Plasmodium falciparum in the low micromolar to nanomolar range. Interestingly, CB-41 exhibited prophylactic activity against hypnozoites and liver schizonts in Plasmodium cynomolgi, a primate model for Plasmodium vivax. Four CB compounds (CB-27, CB-41, CB-53, and CB-61) inhibited P. falciparum oocyst formation in mosquitoes, and five CB compounds (CB-27, CB-41, CB-53, CB-58, and CB-61) hindered the in vitro development of Plasmodium berghei ookinetes. The CB compounds did not inhibit the activation of P. berghei female and male gametocytes in vitro. Isobologram assays demonstrated synergistic interactions between CB-61 and the FDA-approved antimalarial drugs, clindamycin and halofantrine. Testing of six CB compounds showed no inhibition of Plasmodium glutathione S-transferase as a putative target and no cytotoxicity in HepG2 liver cells. CB compounds are promising candidates for further development as antimalarial drugs against multidrug-resistant parasites, which could also prevent malaria transmission.

Discovery of MK-1468: A Potent, Kinome-Selective, Brain-Penetrant Amidoisoquinoline LRRK2 Inhibitor for the Potential Treatment of Parkinson's Disease

Genetic mutation of the leucine-rich repeat kinase 2 (LRRK2) protein has been associated with Parkinson's disease (PD), a disabling and progressive neurodegenerative disorder that is devoid of efficacious disease-modifying therapies. Herein, we describe the invention of an amidoisoquinoline (IQ)-derived LRRK2 inhibitor lead chemical series. Knowledge-, structure-, and property-based drug design in concert with rigorous application of in silico calculations and presynthesis predictions enabled the prioritization of molecules with favorable CNS "drug-like" physicochemical properties. This resulted in the discovery of compound 8, which was profiled extensively before human ether-a-go-go (hERG) ion channel inhibition halted its progression. Strategic reduction of lipophilicity and basicity resulted in attenuation of hERG ion channel inhibition while maintaining a favorable CNS efflux transporter profile. Further structure- and property-based optimizations resulted in the discovery of preclinical candidate MK-1468. This exquisitely selective LRRK2 inhibitor has a projected human dose of 48 mg BID and a preclinical safety profile that supported advancement toward GLP toxicology studies.

Application of Physiologically Based Pharmacokinetic Modeling to Predict Drug-Drug Interactions between Elexacaftor/Tezacaftor/Ivacaftor and Tacrolimus in Lung Transplant Recipients

Elexacaftor/tezacaftor/ivacaftor (ETI) treatment has potential benefits in lung transplant recipients, including improvements in extrapulmonary manifestations, such as gastrointestinal and sinus disease; however, ivacaftor is an inhibitor of cytochrome P450 3A (CYP3A) and may, therefore, pose a risk for elevated systemic exposure to tacrolimus. The aim of this investigation is to determine the impact of ETI on tacrolimus exposure and devise an appropriate dosing regimen to manage the risk of this drug-drug interaction (DDI). The CYP3A-mediated DDI of ivacaftor-tacrolimus was evaluated using a physiologically based pharmacokinetic (PBPK) modeling approach, incorporating CYP3A4 inhibition parameters of ivacaftor and in vitro enzyme kinetic parameters of tacrolimus. To further support the findings in PBPK modeling, we present a case series of lung transplant patients who received both ETI and tacrolimus. We predicted a 2.36-fold increase in tacrolimus exposure when co-administered with ivacaftor, which would require a 50% dose reduction of tacrolimus upon initiation of ETI treatment to avoid the risk of elevated systemic exposure. Clinical cases (N = 13) indicate a median 32% (IQR: -14.30, 63.80) increase in the dose-normalized tacrolimus trough level (trough concentration/weight-normalized daily dose) after starting ETI. These results indicate that the concomitant administration of tacrolimus and ETI may lead to a clinically significant DDI, requiring the dose adjustment of tacrolimus.

Building a Human Physiologically Based Pharmacokinetic Model for Aflatoxin B1 to Simulate Interactions with Drugs

Mycotoxins such as aflatoxin B1 (AFB1) are secondary fungal metabolites present in food commodities and part of one’s daily exposure, especially in certain regions, e.g., sub-Saharan Africa. AFB1 is mostly metabolised by cytochrome P450 (CYP) enzymes, namely, CYP1A2 and CYP3A4. As a consequence of chronic exposure, it is interesting to check for interactions with drugs taken concomitantly. A physiologically based pharmacokinetic (PBPK) model was developed based on the literature and in-house-generated in vitro data to characterise the pharmacokinetics (PK) of AFB1. The substrate file was used in different populations (Chinese, North European Caucasian and Black South African), provided by SimCYP® software (v21), to evaluate the impact of populations on AFB1 PK. The model’s performance was verified against published human in vivo PK parameters, with AUC ratios and Cmax ratios being within the 0.5–2.0-fold range. Effects on AFB1 PK were observed with commonly prescribed drugs in South Africa, leading to clearance ratios of 0.54 to 4.13. The simulations revealed that CYP3A4/CYP1A2 inducer/inhibitor drugs might have an impact on AFB1 metabolism, altering exposure to carcinogenic metabolites. AFB1 did not have effects on the PK of drugs at representative exposure concentrations. Therefore, chronic AFB1 exposure is unlikely to impact the PK of drugs taken concomitantly.

Artificial Intelligence and Machine Learning for Lead-to-Candidate Decision-Making and Beyond

The use of artificial intelligence (AI) and machine learning (ML) in pharmaceutical research and development has to date focused on research: target identification; docking-, fragment-, and motif-based generation of compound libraries; modeling of synthesis feasibility; rank-ordering likely hits according to structural and chemometric similarity to compounds having known activity and affinity to the target(s); optimizing a smaller library for synthesis and high-throughput screening; and combining evidence from screening to support hit-to-lead decisions. Applying AI/ML methods to lead optimization and lead-to-candidate (L2C) decision-making has shown slower progress, especially regarding predicting absorption, distribution, metabolism, excretion, and toxicology properties. The present review surveys reasons why this is so, reports progress that has occurred in recent years, and summarizes some of the issues that remain. Effective AI/ML tools to derisk L2C and later phases of development are important to accelerate the pharmaceutical development process, ameliorate escalating development costs, and achieve greater success rates.

Fighting Epilepsy with Nanomedicines-Is This the Right Weapon?

Epilepsy is a chronic and complex condition and is one of the most common neurological diseases, affecting about 50 million people worldwide. Pharmacological therapy has been, and is likely to remain, the main treatment approach for this disease. Although a large number of new antiseizure drugs (ASDs) has been introduced into the market in the last few years, many patients suffer from uncontrolled seizures, demanding the development of more effective therapies. Nanomedicines have emerged as a promising approach to deliver drugs to the brain, potentiating their therapeutic index. Moreover, nanomedicine has applied the knowledge of nanoscience, not only in disease treatment but also in prevention and diagnosis. In the current review, the general features and therapeutic management of epilepsy will be addressed, as well as the main barriers to overcome to obtain better antiseizure therapies. Furthermore, the role of nanomedicines as a valuable tool to selectively deliver drugs will be discussed, considering the ability of nanocarriers to deal with the less favourable physical-chemical properties of some ASDs, enhance their brain penetration, reduce the adverse effects, and circumvent the concerning drug resistance.

Discovery and Optimization of Potent, Selective, and Brain-Penetrant 1-Heteroaryl-1H-Indazole LRRK2 Kinase Inhibitors for the Treatment of Parkinson's Disease

Inhibition of leucine-rich repeat kinase 2 (LRRK2) kinase activity represents a genetically supported, chemically tractable, and potentially disease-modifying mechanism to treat Parkinson's disease. Herein, we describe the optimization of a novel series of potent, selective, central nervous system (CNS)-penetrant 1-heteroaryl-1H-indazole type I (ATP competitive) LRRK2 inhibitors. Type I ATP-competitive kinase physicochemical properties were integrated with CNS drug-like properties through a combination of structure-based drug design and parallel medicinal chemistry enabled by sp³-sp² cross-coupling technologies. This resulted in the discovery of a unique sp³-rich spirocarbonitrile motif that imparted extraordinary potency, pharmacokinetics, and favorable CNS drug-like properties. The lead compound, 25, demonstrated exceptional on-target potency in human peripheral blood mononuclear cells, excellent off-target kinase selectivity, and good brain exposure in rat, culminating in a low projected human dose and a pre-clinical safety profile that warranted advancement toward pre-clinical candidate enabling studies.

Analysis of Time-Dependent Pharmacokinetics Using In Vitro-In Vivo Extrapolation and Physiologically Based Pharmacokinetic Modeling

SCR430, a sorafenib derivative, is an investigational drug exhibiting anti-tumor action. This study aimed to have a mechanistic understanding of SCR430's time-dependent pharmacokinetics (TDPK) through an ex vivo study combined with an in vitro-in vivo extrapolation (IVIVE) and physiologically based pharmacokinetic (PBPK) modeling. A non-compartmental pharmacokinetic analysis was performed after intravenous SCR430 administration in female Sprague-Dawley rats for a control group (no treatment), a vehicle group (vehicle only, 14 days, PO), and a repeated-dosing group (SCR430, 30 mg/kg/day, 14 days, PO). In addition, hepatic uptake and metabolism modulation were investigated using isolated hepatocytes from each group of rats. The minimal PBPK model based on IVIVE was constructed to explain SCR430's TDPK. Repeated SCR430 administration decreased the systemic exposure by 4.4-fold, which was explained by increased hepatic clearance (4.7-fold). The ex vivo study using isolated hepatocytes from each group suggested that the increased hepatic uptake (9.4-fold), not the metabolic activity, contributes to the increased hepatic clearance. The minimal PBPK modeling based on an ex vivo study could explain the decreased plasma levels after the repeated doses. The current study demonstrates the TDPK after repeated dosing by hepatic uptake induction, not hepatic metabolism, as well as the effectiveness of an ex vivo approach combined with IVIVE and PBPK modeling to investigate the TDPK.

Towards the sustainable discovery and development of new antibiotics

An ever-increasing demand for novel antimicrobials to treat life-threatening infections caused by the global spread of multidrug-resistant bacterial pathogens stands in stark contrast to the current level of investment in their development, particularly in the fields of natural-product-derived and synthetic small molecules. New agents displaying innovative chemistry and modes of action are desperately needed worldwide to tackle the public health menace posed by antimicrobial resistance. Here, our consortium presents a strategic blueprint to substantially improve our ability to discover and develop new antibiotics. We propose both short-term and long-term solutions to overcome the most urgent limitations in the various sectors of research and funding, aiming to bridge the gap between academic, industrial and political stakeholders, and to unite interdisciplinary expertise in order to efficiently fuel the translational pipeline for the benefit of future generations.

Antimicrobial resistance is an increasing threat to public health and encouraging the development of new antimicrobials is one of the most important ways to address the problem. This Roadmap article aims to bring together industrial, academic and political partners, and proposes both short-term and long-term solutions to this challenge.

Utilizing structure based drug design and metabolic soft spot identification to optimize the in vitro potency and in vivo pharmacokinetic properties leading to the discovery of novel reversible Bruton's tyrosine kinase inhibitors

Bruton's tyrosine kinase (BTK) is an essential node on the BCR signaling in B cells, which are clinically validated to play a critical role in B-cell lymphomas and various auto-immune diseases such as Multiple Sclerosis (MS), Pemphigus, and rheumatoid arthritis (RA). Although non-selective irreversible BTK inhibitors have been approved for oncology, due to the emergence of drug resistance in B-cell lymphoma associated with covalent inhibitor, there an unmet medical need to identify reversible, selective, potent BTK inhibitor as viable therapeutics for patients. Herein, we describe the identification of Hits and subsequence optimization to improve the physicochemical properties, potency and kinome selectivity leading to the discovery of a novel class of BTK inhibitors. Utilizing Met ID and structure base design inhibitors were synthesized with increased in vivo metabolic stability and oral exposure in rodents suitable for advancing to lead optimization.

Optimization of brain-penetrant picolinamide derived leucine-rich repeat kinase 2 (LRRK2) inhibitors

The discovery of potent, kinome selective, brain penetrant LRRK2 inhibitors is the focus of extensive research seeking new, disease-modifying treatments for Parkinson's disease (PD). Herein, we describe the discovery and evolution of a picolinamide-derived lead series. Our initial optimization efforts aimed at improving the potency and CLK2 off-target selectivity of compound 1 by modifying the heteroaryl C-H hinge and linker regions. This resulted in compound 12 which advanced deep into our research operating plan (ROP) before heteroaryl aniline metabolite 14 was characterized as Ames mutagenic, halting its progression. Strategic modifications to our ROP were made to enable early de-risking of putative aniline metabolites or hydrolysis products for mutagenicity in Ames. This led to the discovery of 3,5-diaminopyridine 15 and 4,6-diaminopyrimidine 16 as low risk for mutagenicity (defined by a 3-strain Ames negative result). Analysis of key matched molecular pairs 17 and 18 led to the prioritization of the 3,5-diaminopyridine sub-series for further optimization due to enhanced rodent brain penetration. These efforts culminated in the discovery of ethyl trifluoromethyl pyrazole 23 with excellent LRRK2 potency and expanded selectivity versus off-target CLK2.

There is Only One Valid Definition of Clearance: Critical Examination of Clearance Concepts Reveals the Potential for Errors in Clinical Drug Dosing Decisions

Drug dosing decisions in clinical medicine and in introducing a drug to market for the past 60 years are based on the pharmacokinetic/clinical pharmacology concept of clearance. We used chemical reaction engineering models to demonstrate the limitations of presently employed clearance measurements based upon systemic blood concentration in reflecting organ clearance. The belief for the last 49 years that in vivo clearance is independent of the mechanistic model for organ clearance is incorrect. There is only one valid definition of clearance. Defining organ clearance solely on the basis of systemic blood concentrations can lead to drug dosing errors when drug effect sites reside either in an eliminating organ exhibiting incremental clearance or in a non-eliminating organ where intraorgan concentration is governed by transporter actions. Attempts to predict clearance are presently hampered by the lack of recognition that what we are trying to predict is a well-stirred model clearance.

Model-based Target Pharmacology Assessment (mTPA): An Approach Using PBPK/PD Modeling and Machine Learning to Design Medicinal Chemistry and DMPK Strategies in Early Drug Discovery

The optimal pharmacokinetic (PK) required for a drug candidate to elicit efficacy is highly dependent on the targeted pharmacology, a relationship that is often not well characterized during early phases of drug discovery. Generic assumptions around PK and potency risk misguiding screening and compound design toward nonoptimal absorption, distribution, metabolism, and excretion (ADME) or molecular properties and ultimately may increase attrition as well as hit-to-lead and lead optimization timelines. The present work introduces model-based target pharmacology assessment (mTPA), a computational approach combining physiologically based pharmacokinetic/pharmacodynamic (PBPK/PD) modeling, sensitivity analysis, and machine learning (ML) to elucidate the optimal combination of PK, potency, and ADME specific for the targeted pharmacology. Examples using frequently encountered PK/PD relationships are presented to illustrate its application, and the utility and benefits of deploying such an approach to guide early discovery efforts are discussed.

Investigating the Theoretical Basis for In Vitro-In Vivo Extrapolation (IVIVE) in Predicting Drug Metabolic Clearance and Proposing Future Experimental Pathways

Extensive studies have been conducted to predict in vivo metabolic clearance from in vitro human liver metabolism parameters (i.e., in vitro-in vivo extrapolation (IVIVE)) with little success. Here, deriving IVIVE from first principles, we show that the product of fraction unbound in the blood and the predicted in vivo intrinsic clearance determined from hepatocyte or microsomal incubations is the lower boundary condition for in vivo hepatic clearance and the prerequisite for IVIVE predictions to be valid, regardless of extraction ratio. For 60-80% of drugs evaluated here, this product is markedly less than the in vivo measured clearance, a result that violates the lower boundary of the predictive relationship. This can only be explained by (a) suboptimal in vitro metabolic stability assay conditions, (b) significant error in the assumption that in vitro intrinsic clearance determinations will predict in vivo intrinsic clearance simply by scaling-up the amount of enzyme (in vitro incubation to in vivo liver), and/or (c) the methods of determining fraction unbound are incorrect. We further suggest that widely employed organ blood flow values underpredict the effective blood flow within the organ by approximately 2.5-fold, thus impacting IVIVE of high clearance compounds. We propose future pathways that should be investigated in terms of the relationship to experimentally measured clearance values, rather than model-dependent intrinsic clearance. IVIVE outcome can be improved by estimating the ratio of unbound drug concentration in the liver tissue to the liver plasma, examining the assumption of the free drug theory (i.e., there are no transporter effects at the blood cell membrane) and the finding that the upper limit of organ clearance may be greater than blood flow entering the organ.

In Silico Models of Human PK Parameters. Prediction of Volume of Distribution Using an Extensive Data Set and a Reduced Number of Parameters

A novel, descriptor-parsimonious in silico model to predict human VDss (volume of distribution at steady-state) has been derived and thoroughly tested in a quasi-prospective regimen using an independent test set of 213 compounds. The model performs on par with a former benchmark model that relied on far more descriptors. As a result, the new random forest model relying on only six descriptors allows for interpretations that help chemists to design compounds with desired human VDss values. A comparison of in silico predictions of VDss with models using in vitro derived descriptors or in vivo scaling methods supports the strength of the in-silico approach, considering its resource- and animal-sparing nature. The strong performance of the in silico VDss models on structurally novel compounds supports the high degree of confidence that can be placed in using in silico human VDss predictions for compound design and human dose predictions.

A Fully Integrated Assay Panel for Early Drug Metabolism and Pharmacokinetics Profiling

Evaluation and optimization of physicochemical and metabolic properties of compounds are a crucial component of the drug development process. Continuous access to this information during the design-make-test-analysis cycle enables identification of chemical entities with suitable properties for efficient project progression. In this study, we describe an integrated and automated assay panel (DMPK Wave 1) that informs weekly on lipophilicity, solubility, human plasma protein binding, and metabolic stability in rat hepatocytes and human liver microsomes. All assays are running in 96-well format with ultraperformance liquid chromatography-mass spectrometry (MS)/MS as read-out. A streamlined overall workflow has been developed by optimizing all parts of the process, including shipping of compounds between sites, use of fit-for-purpose equipment and information systems, and technology for compound requesting, data analysis, and reporting. As a result, lead times can be achieved that well match project demands across sites independently of where compounds are synthesized. This robust screening strategy is run on a weekly basis and enables optimization of structure-activity relationships in parallel with DMPK properties to allow efficient and informed decision making.

The evolution of strategies to minimise the risk of human drug-induced liver injury (DILI) in drug discovery and development

Early identification of toxicity associated with new chemical entities (NCEs) is critical in preventing late-stage drug development attrition. Liver injury remains a leading cause of drug failures in clinical trials and post-approval withdrawals reflecting the poor translation between traditional preclinical animal models and human clinical outcomes. For this reason, preclinical strategies have evolved over recent years to incorporate more sophisticated human in vitro cell-based models with multi-parametric endpoints. This review aims to highlight the evolution of the strategies adopted to improve human hepatotoxicity prediction in drug discovery and compares/contrasts these with recent activities in our lab. The key role of human exposure and hepatic drug uptake transporters (e.g. OATPs, OAT2) is also elaborated.

Structure-Based Screening of Plasmodium berghei Glutathione S-Transferase Identifies CB-27 as a Novel Antiplasmodial Compound

Plasmodium falciparum parasites are increasingly drug-resistant, requiring the search for novel antimalarials with distinct modes of action. Enzymes in the glutathione pathway, including glutathione S-transferase (GST), show promise as novel antimalarial targets. This study aims to better understand the biological function of Plasmodium GST, assess its potential as a drug target, and identify novel antiplasmodial compounds using the rodent model P. berghei. By using reverse genetics, we provided evidence that GST is essential for survival of P. berghei intra-erythrocytic stages and is a valid target for drug development. A structural model of the P. berghei glutathione S-transferase (PbGST) protein was generated and used in a structure-based screening of 900,000 compounds from the ChemBridge Hit2Lead library. Forty compounds were identified as potential inhibitors and analyzed in parasite in vitro drug susceptibility assays. One compound, CB-27, exhibited antiplasmodial activity with an EC50 of 0.5 μM toward P. berghei and 0.9 μM toward P. falciparum multidrug-resistant Dd2 clone B2 parasites. Moreover, CB-27 showed a concentration-dependent inhibition of the PbGST enzyme without inhibiting the human ortholog. A shape similarity screening using CB-27 as query resulted in the identification of 24 novel chemical scaffolds, with six of them showing antiplasmodial activity ranging from EC50 of 0.6-4.9 μM. Pharmacokinetic and toxicity predictions suggest that the lead compounds have drug-likeness properties. The antiplasmodial potency, the absence of hemolytic activity, and the predicted drug-likeness properties position these compounds for lead optimization and further development as antimalarials.

Prediction of active human dose: learnings from 20 years of Merck KGaA experience, illustrated by case studies

High-quality dose predictions based on a good understanding of target engagement is one of the main translational goals in drug development. Here, we systematically evaluate active human dose predictions for 15 Merck KGaA/EMD Serono assets spanning several modalities and therapeutic areas. Using case studies, we illustrate the value of adhering to the translational best practices of having an exposure-response relationship in an appropriate animal model; having validated, translatable pharmacodynamic (PD) biomarkers measurable in Phase I populations in the right tissue; having a deeper understanding of biology; and capturing uncertainties in predictions. Given the gap in publications on the subject, we believe that the learnings from this unique diverse data set, which are generic to the industry, will trigger actions to improve future predictions.

Application and Impact of Human Dose Projection from Discovery to Early Drug Development

The application and impact of human dose projection (HDP) has been well recognized in the late drug development phase, with increasing appreciation earlier during discovery and early development. This commentary describes the perspective of pharmaceutical scientists on the evolving application and impact of HDP at various phases from discovery to early development, including lead generation, lead optimization, lead up to candidate nomination, and early drug development. The underlying fundamental concepts and key input parameters for HDP are briefly discussed. A broad overview of phase-specific tools and approaches commonly utilized for human dose projection in the pharmaceutical industry is provided. A discussion of phase-appropriate implementation strategies, associated limitations/assumptions and continuous refinement for HDP from discovery to early development is presented. The authors describe the phase-specific applications of human dose projection to facilitate key assessments and relative impact on decision points.

Prediction of Fraction Unbound in Microsomal and Hepatocyte Incubations: A Comparison of Methods across Industry Datasets

The fraction unbound in the incubation, f_u,inc, is an important parameter to consider in the evaluation of intrinsic clearance measurements performed in vitro in hepatocytes or microsomes. Reliable estimates of f_u,inc based on a compound's structure have the potential to positively impact the screening timelines in drug discovery. Previous works suggested that f_u,inc is primarily driven by passive processes and can be described using physicochemical properties such as lipophilicity and the protonation state of the molecule. While models based on these principles proved predictive in relatively small datasets that included marketed drugs, their applicability domain has not been extensively explored. The work presented here from the in silico ADME discussion group (part of the International Consortium for Innovation through Quality in Pharmaceutical Development, the IQ consortium) describes the accuracy of these models in large proprietary datasets that include several thousand of compounds across chemical space. Overall, the models do well for compounds with low lipophilicity. In other words, the equations correctly predict that f_u,inc is, in general, above 0.5 for compounds with a calculated logP of less than 3. When applied to lipophilic compounds, the models failed to produce quantitatively accurate predictions of f_u,inc, with a high risk of underestimating binding properties. These models can, therefore, be used quantitatively for less lipophilic compounds. On the other hand, internal machine-learning models using a company's own proprietary dataset also predict compounds with higher lipophilicity reasonably well. Additionally, the data shown indicate that microsomal binding is, in general, a good proxy for hepatocyte binding.

Discovery of Potent and Orally Bioavailable Inverse Agonists of the Retinoic Acid Receptor-Related Orphan Receptor C2

The further optimization of a recently disclosed series of inverse agonists of the nuclear receptor RORC2 is described. Investigations into the left-hand side of compound 1, guided by X-ray crystal structures, led to the substitution of the 4-aryl-thiophenyl residue with the hexafluoro-2-phenyl-propan-2-ol moiety. This change resulted in to compound 28, which combined improved drug-like properties with good cell potency and a significantly lower dose, using an early dose to man prediction. Target engagement in vivo was demonstrated in the thymus of mice by a reduction in the number of double positive T cells after oral dosing.

Opportunities and challenges using artificial intelligence in ADME/Tox

A recent conference organized a panel of scientists representing small and big pharma companies, who work at the interface of machine learning (ML) and absorption, distribution, metabolism, excretion, and toxicology (ADME/Tox). With the recent rebirth of AI related to pharma, it is timely to present this collaborative commentary to capture the diverging opinions on the past, present and future role of AI for ADME/Tox and how it can be applied in newer areas such as nanomaterials.

Accelerated drug discovery by rapid candidate drug identification

The eventual candidate drug (CD) is often already synthesized during early drug discovery but not nominated until much later. To facilitate the rapid identification of a potential CD, a thoroughly worked-out CD target profile (CDTP) with criteria acceptable for the disease target product profile (TPP) is required at the start of lead generation (LG). In addition to driving the compound property optimization, the preclinical project team has to understand the ultimate goal to be able to rapidly identify and progress a potential CD. A screening cascade with meaningful and well-balanced progression criteria based on the CDTP is required to rapidly filter out unwanted compounds and to progress a potential CD through the cascade to candidate selection.

Recent applications of machine learning in medicinal chemistry

In recent decades, artificial intelligence and machine learning have played a significant role in increasing the efficiency of processes across a wide spectrum of industries. When it comes to the pharmaceutical and biotechnology sectors, numerous tools enabled by advancement of computer science have been developed and are now routinely utilized. However, there are many aspects of the drug discovery process, which can further benefit from refinement of computational methods and tools, as well as improvement of accessibility of these new technologies. In this review, examples of recent developments in machine learning application are described, which have the potential to impact different parts of the drug discovery and development flow scheme. Notably, new deep learning-based approaches across compound design and synthesis, prediction of binding, activity and ADMET properties, as well as applications of genetic algorithms are highlighted.

Strategy for Extending Half-life in Drug Design and Its Significance

Preclinical optimization of compounds toward viable drug candidates requires an integrated understanding of properties that impact predictions of the clinically efficacious dose. The importance of optimizing half-life, unbound clearance, and potency and how they impact dose predictions are discussed in this letter. Modest half-life improvements for short half-life compounds can dramatically lower the efficacious dose. The relationship between dose and half-life is nonlinear when unbound clearance is kept constant, whereas the relationship between dose and unbound clearance is linear when half-life is kept constant. Due to this difference, we show that dose is more sensitive to changes in half-life than changes in unbound clearance when half-lives are shorter than 2 h. Through matched molecular pair analyses, we also show that the strategic introduction of halogens is likely to increase half-life and lower projected human dose even though increased lipophilicity does not guarantee extended half-life.

Oral drug suitability parameters

Assessing the oral drug suitability of compounds as early as possible within drug discovery is an important objective. This study describes a methodology that attempts to simplify the evaluation of compounds based on their in vivo quantity levels within a mammalian body, represented using a mathematical model that imposes a time limitation on oral absorption and assumes non-instantaneous drug distribution between plasma and tissue. This simplification results in two new oral drug suitability parameters that can quantitatively relate oral dose to in vivo exposure for compounds with vastly different tendencies in terms of absorption into, and elimination from, the body. Consequently, the complexities associated with evaluating a compound's oral drug suitability are simplified to an assessment of these two new parameters. Application of this methodology at the virtual design stage is discussed, along with functionality that accounts for uncertainty related to a compound's distribution kinetics and errors associated to in silico QSAR predictions for the required input data.

Designing safer oral drugs

Designing an oral drug such that its estimated dose to humans is both efficacious and safe is challenging. During the early design stage, where in vitro or preclinical species in vivo safety data are limited, heuristic-based criteria often related to physicochemical properties are used for guidance. The causal relationship between a compound's log P and its human in vivo toxicity is considered. With respect to designing efficacious oral drugs that potentially have reduced toxicity liabilities, an alternative heuristic-based criterion is proposed based on the amount of compound in the body at steady state. In humans, a threshold for the amount of compound in the body at steady state of 0.5 mg kg-1 is suggested. The criterion is based on the minimum toxic blood-plasma concentration that produces clinically relevant side effects or symptoms in humans for 242 oral drugs. It can be used to estimate a therapeutic window against which a compound's estimated in vivo plasma levels for a particular dose size and frequency can be assessed. The relationship between this criterion and acceptable oral dose sizes for different charge types with different in vivo plasma clearances is discussed.

Automatically updating predictive modeling workflows support decision-making in drug design

Using predictive models for early decision-making in drug discovery has become standard practice. We suggest that model building needs to be automated with minimum input and low technical maintenance requirements. Models perform best when tailored to answering specific compound optimization related questions. If qualitative answers are required, 2-bin classification models are preferred. Integrating predictive modeling results with structural information stimulates better decision making. For in silico models supporting rapid structure–activity relationship cycles the performance deteriorates within weeks. Frequent automated updates of predictive models ensure best predictions. Consensus between multiple modeling approaches increases the prediction confidence. Combining qualified and nonqualified data optimally uses all available information. Dose predictions provide a holistic alternative to multiple individual property predictions for reaching complex decisions.

Oral drug-likeness criteria in preclinical species

This study considers how the estimated in vivo free plasma concentrations for compounds tends to vary between human, dog and rat and proposes empirical-based criteria to aid drug design.