A New Guidance for the Prediction of Hepatic Clearance in the Early Drug Discovery and Development from the in Vitro-to-in Vivo Extrapolation Method and an Approach for Exploring Whether an Albumin-Mediated Hepatic Uptake Phenomenon Could be Present Under in Vivo Conditions

Poulin, Patrick; Haddad, Sami

doi:10.1016/j.xphs.2021.04.002

Cited by 12 publications

(11 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, predictions of CLp from experimental data tend to suffer from either under-or overprediction bias, often emphasized by a human decision on if and how to account for the free drug hypothesis. 60 Compared to these published results, our ML models of CLp offer a comparable prediction performance (AAFEs of 2.05−2.66) and low bias (AFEs of 1.00−1.36), in the absence of any experimental input. Similarly, Vss can be predicted based on experimental fu,p, fu,tissue, logD, and pK a values, often leading to AAFE values of 1.5−3.0, depending on the ionization class.…”

Section: ■ Discussionmentioning

confidence: 51%

“…For ChemProp, test set performance metrics are represented by the green bars in Figure . We note production-ready performance for the mouse IV properties: With an AAFE < 3 and CCC > 0.5 for AUCiv, Vss, and CLp, our models match the level of performance typically achieved with conventional IVIVE approaches. ,− Properties associated with an oral administration remained more difficult to predict (AAFE > 3 for AUCpo and F). Predictions of rat PK properties performed significantly worse (AAFE > 4).…”

Section: Resultsmentioning

confidence: 61%

“…For example, metabolism-driven CLp is often predicted from in vitro hepatocyte CLint and plasma protein binding (fu,p), resulting in AAFE values of 2–3 [e.g., 2.05–2.53, 2.10–3.10, 2.0–3.0]. Additionally, predictions of CLp from experimental data tend to suffer from either under- or overprediction bias, often emphasized by a human decision on if and how to account for the free drug hypothesis . Compared to these published results, our ML models of CLp offer a comparable prediction performance (AAFEs of 2.05–2.66) and low bias (AFEs of 1.00–1.36), in the absence of any experimental input.…”

Section: Discussionmentioning

confidence: 98%

See 2 more Smart Citations

Computational Predictions of Nonclinical Pharmacokinetics at the Drug Design Stage

Stoyanova

Katzberger

Komissarov

et al. 2023

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Although computational predictions of pharmacokinetics (PK) are desirable at the drug design stage, existing approaches are often limited by prediction accuracy and human interpretability. Using a discovery data set of mouse and rat PK studies at Roche (9,685 unique compounds), we performed a proof-of-concept study to predict key PK properties from chemical structure alone, including plasma clearance (CLp), volume of distribution at steady-state (Vss), and oral bioavailability (F). Ten machine learning (ML) models were evaluated, including Single-Task, Multitask, and transfer learning approaches (i.e., pretraining with in vitro data). In addition to prediction accuracy, we emphasized human interpretability of outcomes, especially the quantification of uncertainty, applicability domains, and explanations of predictions in terms of molecular features. Results show that intravenous (IV) PK properties (CLp and Vss) can be predicted with good precision (average absolute fold error, AAFE of 1.96− 2.84 depending on data split) and low bias (average fold error, AFE of 0.98−1.36), with AutoGluon, Gaussian Process Regressor (GP), and ChemProp displaying the best performance. Driven by higher complexity of oral PK studies, predictions of F were more challenging, with the best AAFE values of 2.35−2.60 and higher overprediction bias (AFE of 1.45−1.62). Multi-Task approaches and pretraining of ChemProp neural networks with in vitro data showed similar precision to Single-Task models but helped reduce the bias and increase correlations between observations and predictions. A combination of GP-computed prediction variance, molecular clustering, and dimensionality-reduction provided valuable quantitative insights into prediction uncertainty and applicability domains. SHAPley Additive exPlanations (SHAPs) highlighted molecular features contributing to prediction outcomes of Vss, providing explanations that could aid drug design. Combined results show that computational predictions of PK are feasible at the drug design stage, with several ML technologies converging to successfully leverage historical PK data sets. Further studies are needed to unlock the full potential of this approach, especially with respect to data set sizes and quality, transfer learning between in vitro and in vivo data sets, model-independent quantification of uncertainty, and explainability of predictions.

show abstract

Section: ■ Discussionmentioning

confidence: 51%

Section: Resultsmentioning

confidence: 61%

Section: Discussionmentioning

confidence: 98%

See 1 more Smart Citation

Computational Predictions of Nonclinical Pharmacokinetics at the Drug Design Stage

Stoyanova

Katzberger

Komissarov

et al. 2023

J. Chem. Inf. Model.

View full text Add to dashboard Cite

show abstract

“…Attempts to use these data to improve in vitro-in vivo extrapolation (IVIVE) through different scaling approaches have yielded varying degrees of success (Grime and Riley, 2006;Berezhkovskiy, 2011;Ring et al, 2011;Hallifax and Houston, 2012). Recently, researchers have expanded on these approaches to assess prediction accuracy, and evaluated the advantages and disadvantages amongst the various methods (Lombardo et al, 2014(Lombardo et al, , 2018Benet and Sodhi, 2020;Umehara et al, 2020;Poulin and Haddad, 2021).…”

Section: Introductionmentioning

confidence: 99%

Application of Empirical Scalars To Enable Early Prediction of Human Hepatic Clearance Using In Vitro-In Vivo Extrapolation in Drug Discovery: An Evaluation of 173 Drugs

et al. 2022

View full text Add to dashboard Cite

“…For IBU, the influence of a lower protein binding in plasma/medium on the partition coefficient was demonstrated with the theoretical calculations using the Schmitt algorithm, resulting in an increasing tissue/cellular concentration with decreasing protein binding. Recently, the influence of plasma protein binding was addressed not with respect to implications for the partitioning into the tissue (as we did) but with respect to influencing the QIVIVE of hepatic clearance, in particular, considering plasma protein-mediated uptake ( Bteich et al, 2019 ; Francis et al, 2021 ; Poulin and Haddad, 2021 ). In the example with IBU, although being a highly protein-bound drug, the partitioning into the tissue is strongly affected, we observed only a 14% lower predicted in vitro clearance than in vivo , which is within the normal variability.…”

Section: Discussionmentioning

confidence: 99%

In Vitro–In Vivo Extrapolation by Physiologically Based Kinetic Modeling: Experience With Three Case Studies and Lessons Learned

et al. 2022

View full text Add to dashboard Cite

Physiologically based kinetic (PBK) modeling has been increasingly used since the beginning of the 21st century to support dose selection to be used in preclinical and clinical safety studies in the pharmaceutical sector. For chemical safety assessment, the use of PBK has also found interest, however, to a smaller extent, although an internationally agreed document was published already in 2010 (IPCS/WHO), but at that time, PBK modeling was based mostly on in vivo data as the example in the IPCS/WHO document indicates. Recently, the OECD has published a guidance document which set standards on how to characterize, validate, and report PBK models for regulatory purposes. In the past few years, we gained experience on using in vitro data for performing quantitative in vitro–in vivo extrapolation (QIVIVE), in which biokinetic data play a crucial role to obtain a realistic estimation of human exposure. In addition, pharmaco-/toxicodynamic aspects have been introduced into the approach. Here, three examples with different drugs/chemicals are described, in which different approaches have been applied. The lessons we learned from the exercise are as follows: 1) in vitro conditions should be considered and compared to the in vivo situation, particularly for protein binding; 2) in vitro inhibition of metabolizing enzymes by the formed metabolites should be taken into consideration; and 3) it is important to extrapolate from the in vitro measured intracellular concentration and not from the nominal concentration to the tissue/organ concentration to come up with an appropriate QIVIVE for the relevant adverse effects.

show abstract

A New Guidance for the Prediction of Hepatic Clearance in the Early Drug Discovery and Development from the in Vitro-to-in Vivo Extrapolation Method and an Approach for Exploring Whether an Albumin-Mediated Hepatic Uptake Phenomenon Could be Present Under in Vivo Conditions

Cited by 12 publications

References 27 publications

Computational Predictions of Nonclinical Pharmacokinetics at the Drug Design Stage

Computational Predictions of Nonclinical Pharmacokinetics at the Drug Design Stage

Application of Empirical Scalars To Enable Early Prediction of Human Hepatic Clearance Using In Vitro-In Vivo Extrapolation in Drug Discovery: An Evaluation of 173 Drugs

In Vitro–In Vivo Extrapolation by Physiologically Based Kinetic Modeling: Experience With Three Case Studies and Lessons Learned

Contact Info

Product

Resources

About