Application of machine learning in combination with mechanistic modeling to predict plasma exposure of small molecules
Prediction of a new molecule’s exposure in plasma is a critical first step toward understanding its efficacy/toxicity profile and concluding whether it is a possible first-in-class, best-in-class candidate. For this prediction, traditional pharmacometrics use a variety of scaling methods that are he...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-06-01
|
| Series: | Frontiers in Systems Biology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fsysb.2023.1180948/full |
| _version_ | 1797791520508608512 |
|---|---|
| author | Panteleimon D. Mavroudis Donato Teutonico Alexandra Abos Nikhil Pillai |
| author_facet | Panteleimon D. Mavroudis Donato Teutonico Alexandra Abos Nikhil Pillai |
| author_sort | Panteleimon D. Mavroudis |
| collection | DOAJ |
| description | Prediction of a new molecule’s exposure in plasma is a critical first step toward understanding its efficacy/toxicity profile and concluding whether it is a possible first-in-class, best-in-class candidate. For this prediction, traditional pharmacometrics use a variety of scaling methods that are heavily based on pre-clinical pharmacokinetic (PK) data. We here propose a novel framework based on which preclinical exposure prediction is performed by applying machine learning (ML) in tandem with mechanism-based modeling. In our proposed method, a relationship is initially established between molecular structure and physicochemical (PC)/PK properties using ML, and then the ML-driven PC/PK parameters are used as input to mechanistic models that ultimately predict the plasma exposure of new candidates. To understand the feasibility of our proposed framework, we evaluated a number of mechanistic models (1-compartment, physiologically based pharmacokinetic (PBPK)), PBPK distribution models (Berezhkovskiy, PK-Sim standard, Poulin and Theil, Rodgers and Rowland, and Schmidt), and PBPK parameterizations (using in vivo, or in vitro clearance). For most of the scenarios tested, our results demonstrate that PK profiles can be adequately predicted based on the proposed framework. Our analysis further indicates some limitations when liver microsomal intrinsic clearance (CLint) is used as the only clearance pathway and underscores the necessity of investigating the variability emanating from the different distribution models when providing PK predictions. The suggested approach aims at earlier exposure prediction in the drug development process so that critical decisions on molecule screening, chemistry design, or dose selection can be made as early as possible. |
| first_indexed | 2024-03-13T02:20:01Z |
| format | Article |
| id | doaj.art-6a15d59481f444f890704204a16bd684 |
| institution | Directory Open Access Journal |
| issn | 2674-0702 |
| language | English |
| last_indexed | 2024-03-13T02:20:01Z |
| publishDate | 2023-06-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Systems Biology |
| spelling | doaj.art-6a15d59481f444f890704204a16bd6842023-06-30T10:05:26ZengFrontiers Media S.A.Frontiers in Systems Biology2674-07022023-06-01310.3389/fsysb.2023.11809481180948Application of machine learning in combination with mechanistic modeling to predict plasma exposure of small moleculesPanteleimon D. Mavroudis0Donato Teutonico1Alexandra Abos2Nikhil Pillai3Quantitative Pharmacology Research, DMPK, Sanofi, Cambridge, MA, United StatesTranslational Medicine and Early Development, Sanofi, Chilly-Mazarin, FranceCommercial Data Science, Sanofi, Barcelona, SpainQuantitative Pharmacology Research, DMPK, Sanofi, Cambridge, MA, United StatesPrediction of a new molecule’s exposure in plasma is a critical first step toward understanding its efficacy/toxicity profile and concluding whether it is a possible first-in-class, best-in-class candidate. For this prediction, traditional pharmacometrics use a variety of scaling methods that are heavily based on pre-clinical pharmacokinetic (PK) data. We here propose a novel framework based on which preclinical exposure prediction is performed by applying machine learning (ML) in tandem with mechanism-based modeling. In our proposed method, a relationship is initially established between molecular structure and physicochemical (PC)/PK properties using ML, and then the ML-driven PC/PK parameters are used as input to mechanistic models that ultimately predict the plasma exposure of new candidates. To understand the feasibility of our proposed framework, we evaluated a number of mechanistic models (1-compartment, physiologically based pharmacokinetic (PBPK)), PBPK distribution models (Berezhkovskiy, PK-Sim standard, Poulin and Theil, Rodgers and Rowland, and Schmidt), and PBPK parameterizations (using in vivo, or in vitro clearance). For most of the scenarios tested, our results demonstrate that PK profiles can be adequately predicted based on the proposed framework. Our analysis further indicates some limitations when liver microsomal intrinsic clearance (CLint) is used as the only clearance pathway and underscores the necessity of investigating the variability emanating from the different distribution models when providing PK predictions. The suggested approach aims at earlier exposure prediction in the drug development process so that critical decisions on molecule screening, chemistry design, or dose selection can be made as early as possible.https://www.frontiersin.org/articles/10.3389/fsysb.2023.1180948/fullmachine learningdrug discoverypharmacokineticsPBPKmodel-based drug developmentartificial intelligence |
| spellingShingle | Panteleimon D. Mavroudis Donato Teutonico Alexandra Abos Nikhil Pillai Application of machine learning in combination with mechanistic modeling to predict plasma exposure of small molecules Frontiers in Systems Biology machine learning drug discovery pharmacokinetics PBPK model-based drug development artificial intelligence |
| title | Application of machine learning in combination with mechanistic modeling to predict plasma exposure of small molecules |
| title_full | Application of machine learning in combination with mechanistic modeling to predict plasma exposure of small molecules |
| title_fullStr | Application of machine learning in combination with mechanistic modeling to predict plasma exposure of small molecules |
| title_full_unstemmed | Application of machine learning in combination with mechanistic modeling to predict plasma exposure of small molecules |
| title_short | Application of machine learning in combination with mechanistic modeling to predict plasma exposure of small molecules |
| title_sort | application of machine learning in combination with mechanistic modeling to predict plasma exposure of small molecules |
| topic | machine learning drug discovery pharmacokinetics PBPK model-based drug development artificial intelligence |
| url | https://www.frontiersin.org/articles/10.3389/fsysb.2023.1180948/full |
| work_keys_str_mv | AT panteleimondmavroudis applicationofmachinelearningincombinationwithmechanisticmodelingtopredictplasmaexposureofsmallmolecules AT donatoteutonico applicationofmachinelearningincombinationwithmechanisticmodelingtopredictplasmaexposureofsmallmolecules AT alexandraabos applicationofmachinelearningincombinationwithmechanisticmodelingtopredictplasmaexposureofsmallmolecules AT nikhilpillai applicationofmachinelearningincombinationwithmechanisticmodelingtopredictplasmaexposureofsmallmolecules |