1
|
Bassani D, Parrott NJ, Manevski N, Zhang JD. Another string to your bow: machine learning prediction of the pharmacokinetic properties of small molecules. Expert Opin Drug Discov 2024; 19:683-698. [PMID: 38727016 DOI: 10.1080/17460441.2024.2348157] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/23/2023] [Accepted: 04/23/2024] [Indexed: 05/22/2024]
Abstract
INTRODUCTION Prediction of pharmacokinetic (PK) properties is crucial for drug discovery and development. Machine-learning (ML) models, which use statistical pattern recognition to learn correlations between input features (such as chemical structures) and target variables (such as PK parameters), are being increasingly used for this purpose. To embed ML models for PK prediction into workflows and to guide future development, a solid understanding of their applicability, advantages, limitations, and synergies with other approaches is necessary. AREAS COVERED This narrative review discusses the design and application of ML models to predict PK parameters of small molecules, especially in light of established approaches including in vitro-in vivo extrapolation (IVIVE) and physiologically based pharmacokinetic (PBPK) models. The authors illustrate scenarios in which the three approaches are used and emphasize how they enhance and complement each other. In particular, they highlight achievements, the state of the art and potentials of applying machine learning for PK prediction through a comphrehensive literature review. EXPERT OPINION ML models, when carefully crafted, regularly updated, and appropriately used, empower users to prioritize molecules with favorable PK properties. Informed practitioners can leverage these models to improve the efficiency of drug discovery and development process.
Collapse
Affiliation(s)
- Davide Bassani
- Pharmaceutical Research & Early Development, Roche Innovation Center Basel, F. Hoffmann-La Roche Ltd., Basel, Switzerland
| | - Neil John Parrott
- Pharmaceutical Research & Early Development, Roche Innovation Center Basel, F. Hoffmann-La Roche Ltd., Basel, Switzerland
| | - Nenad Manevski
- Pharmaceutical Research & Early Development, Roche Innovation Center Basel, F. Hoffmann-La Roche Ltd., Basel, Switzerland
| | - Jitao David Zhang
- Pharmaceutical Research & Early Development, Roche Innovation Center Basel, F. Hoffmann-La Roche Ltd., Basel, Switzerland
| |
Collapse
|
2
|
Manelfi C, Tazzari V, Lunghini F, Cerchia C, Fava A, Pedretti A, Stouten PFW, Vistoli G, Beccari AR. "DompeKeys": a set of novel substructure-based descriptors for efficient chemical space mapping, development and structural interpretation of machine learning models, and indexing of large databases. J Cheminform 2024; 16:21. [PMID: 38395961 PMCID: PMC10893756 DOI: 10.1186/s13321-024-00813-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/17/2023] [Accepted: 02/10/2024] [Indexed: 02/25/2024] Open
Abstract
The conversion of chemical structures into computer-readable descriptors, able to capture key structural aspects, is of pivotal importance in the field of cheminformatics and computer-aided drug design. Molecular fingerprints represent a widely employed class of descriptors; however, their generation process is time-consuming for large databases and is susceptible to bias. Therefore, descriptors able to accurately detect predefined structural fragments and devoid of lengthy generation procedures would be highly desirable. To meet additional needs, such descriptors should also be interpretable by medicinal chemists, and suitable for indexing databases with trillions of compounds. To this end, we developed-as integral part of EXSCALATE, Dompé's end-to-end drug discovery platform-the DompeKeys (DK), a new substructure-based descriptor set, which encodes the chemical features that characterize compounds of pharmaceutical interest. DK represent an exhaustive collection of curated SMARTS strings, defining chemical features at different levels of complexity, from specific functional groups and structural patterns to simpler pharmacophoric points, corresponding to a network of hierarchically interconnected substructures. Because of their extended and hierarchical structure, DK can be used, with good performance, in different kinds of applications. In particular, we demonstrate how they are very well suited for effective mapping of chemical space, as well as substructure search and virtual screening. Notably, the incorporation of DK yields highly performing machine learning models for the prediction of both compounds' activity and metabolic reaction occurrence. The protocol to generate the DK is freely available at https://dompekeys.exscalate.eu and is fully integrated with the Molecular Anatomy protocol for the generation and analysis of hierarchically interconnected molecular scaffolds and frameworks, thus providing a comprehensive and flexible tool for drug design applications.
Collapse
Affiliation(s)
- Candida Manelfi
- EXSCALATE, Dompé Farmaceutici SpA, Via Tommaso de Amicis 95, 80123, Napoli, Italy
| | - Valerio Tazzari
- EXSCALATE, Dompé Farmaceutici SpA, Via Tommaso de Amicis 95, 80123, Napoli, Italy
| | - Filippo Lunghini
- EXSCALATE, Dompé Farmaceutici SpA, Via Tommaso de Amicis 95, 80123, Napoli, Italy
| | - Carmen Cerchia
- Department of Pharmacy, University of Naples "Federico II", Via D. Montesano 49, 80131, Napoli, Italy
| | - Anna Fava
- EXSCALATE, Dompé Farmaceutici SpA, Via Tommaso de Amicis 95, 80123, Napoli, Italy
| | - Alessandro Pedretti
- Dipartimento di Scienze Farmaceutiche, Università degli Studi di Milano, Via Mangiagalli, 25, 20133, Milano, Italy
| | - Pieter F W Stouten
- EXSCALATE, Dompé Farmaceutici SpA, Via Tommaso de Amicis 95, 80123, Napoli, Italy
- Stouten Pharma Consultancy BV, Kempenarestraat 47, 2860, Sint-Katelijne-Waver, Belgium
| | - Giulio Vistoli
- Dipartimento di Scienze Farmaceutiche, Università degli Studi di Milano, Via Mangiagalli, 25, 20133, Milano, Italy
| | | |
Collapse
|
3
|
Mazzolari A, Perazzoni P, Sabato E, Lunghini F, Beccari AR, Vistoli G, Pedretti A. MetaSpot: A General Approach for Recognizing the Reactive Atoms Undergoing Metabolic Reactions Based on the MetaQSAR Database. Int J Mol Sci 2023; 24:11064. [PMID: 37446241 DOI: 10.3390/ijms241311064] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/31/2023] [Revised: 06/27/2023] [Accepted: 06/28/2023] [Indexed: 07/15/2023] Open
Abstract
The prediction of drug metabolism is attracting great interest for the possibility of discarding molecules with unfavorable ADME/Tox profile at the early stage of the drug discovery process. In this context, artificial intelligence methods can generate highly performing predictive models if they are trained by accurate metabolic data. MetaQSAR-based datasets were collected to predict the sites of metabolism for most metabolic reactions. The models were based on a set of structural, physicochemical, and stereo-electronic descriptors and were generated by the random forest algorithm. For each considered biotransformation, two types of models were developed: the first type involved all non-reactive atoms and included atom types among the descriptors, while the second type involved only non-reactive centers having the same atom type(s) of the reactive atoms. All the models of the first type revealed very high performances; the models of the second type show on average worst performances while being almost always able to recognize the reactive centers; only conjugations with glucuronic acid are unsatisfactorily predicted by the models of the second type. Feature evaluation confirms the major role of lipophilicity, self-polarizability, and H-bonding for almost all considered reactions. The obtained results emphasize the possibility of recognizing the sites of metabolism by classification models trained on MetaQSAR database. The two types of models can be synergistically combined since the first models identify which atoms can undergo a given metabolic reactions, while the second models detect the truly reactive centers. The generated models are available as scripts for the VEGA program.
Collapse
Affiliation(s)
- Angelica Mazzolari
- Dipartimento di Scienze Farmaceutiche, Università degli Studi di Milano, Via Luigi Mangiagalli, 25, I-20133 Milano, Italy
| | - Pietro Perazzoni
- Dipartimento di Scienze Farmaceutiche, Università degli Studi di Milano, Via Luigi Mangiagalli, 25, I-20133 Milano, Italy
| | - Emanuela Sabato
- Dipartimento di Scienze Farmaceutiche, Università degli Studi di Milano, Via Luigi Mangiagalli, 25, I-20133 Milano, Italy
| | - Filippo Lunghini
- EXSCALATE, Dompé Farmaceutici S.p.A., Via Tommaso De Amicis, 95, I-80131 Napoli, Italy
| | - Andrea R Beccari
- EXSCALATE, Dompé Farmaceutici S.p.A., Via Tommaso De Amicis, 95, I-80131 Napoli, Italy
| | - Giulio Vistoli
- Dipartimento di Scienze Farmaceutiche, Università degli Studi di Milano, Via Luigi Mangiagalli, 25, I-20133 Milano, Italy
| | - Alessandro Pedretti
- Dipartimento di Scienze Farmaceutiche, Università degli Studi di Milano, Via Luigi Mangiagalli, 25, I-20133 Milano, Italy
| |
Collapse
|
4
|
Artasensi A, Angeli A, Lammi C, Bollati C, Gervasoni S, Baron G, Matucci R, Supuran CT, Vistoli G, Fumagalli L. Discovery of a Potent and Highly Selective Dipeptidyl Peptidase IV and Carbonic Anhydrase Inhibitor as "Antidiabesity" Agents Based on Repurposing and Morphing of WB-4101. J Med Chem 2022; 65:13946-13966. [PMID: 36201615 PMCID: PMC9937538 DOI: 10.1021/acs.jmedchem.2c01192] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
Abstract
The management of patients with type 2 diabetes mellitus (T2DM) is shifting from cardio-centric to weight-centric or, even better, adipose-centric treatments. Considering the downsides of multidrug therapies and the relevance of dipeptidyl peptidase IV (DPP IV) and carbonic anhydrases (CAs II and V) in T2DM and in the weight loss, we report a new class of multitarget ligands targeting the mentioned enzymes. We started from the known α1-AR inhibitor WB-4101, which was progressively modified through a tailored morphing strategy to optimize the potency of DPP IV and CAs while losing the adrenergic activity. The obtained compound 12 shows a satisfactory DPP IV inhibition with a good selectivity CA profile (DPP IV IC50: 0.0490 μM; CA II Ki 0.2615 μM; CA VA Ki 0.0941 μM; CA VB Ki 0.0428 μM). Furthermore, its DPP IV inhibitory activity in Caco-2 and its acceptable pre-ADME/Tox profile indicate it as a lead compound in this novel class of multitarget ligands.
Collapse
Affiliation(s)
- Angelica Artasensi
- Department
of Pharmaceutical Sciences “DISFARM”, Università degli Studi di Milano, via Mangiagalli 25, I-20133 Milan, Italy
| | - Andrea Angeli
- Department
of Pharmaceutical Sciences “NEUROFARBA”, University of Florence, via Ugo Schiff 6, 50019 Sesto Fiorentino, Florence, Italy
| | - Carmen Lammi
- Department
of Pharmaceutical Sciences “DISFARM”, Università degli Studi di Milano, via Mangiagalli 25, I-20133 Milan, Italy
| | - Carlotta Bollati
- Department
of Pharmaceutical Sciences “DISFARM”, Università degli Studi di Milano, via Mangiagalli 25, I-20133 Milan, Italy
| | - Silvia Gervasoni
- Department
of Pharmaceutical Sciences “DISFARM”, Università degli Studi di Milano, via Mangiagalli 25, I-20133 Milan, Italy,Department
of Physics, Citt. Universitaria, University
of Cagliari, I-09042 Cagliari, Monserrato, Italy
| | - Giovanna Baron
- Department
of Pharmaceutical Sciences “DISFARM”, Università degli Studi di Milano, via Mangiagalli 25, I-20133 Milan, Italy
| | - Rosanna Matucci
- Department
of Pharmacology and Toxicology “NEUROFARBA”, University of Florence, Viale Pieraccini 6, 50134 Florence, Italy
| | - Claudiu T. Supuran
- Department
of Pharmaceutical Sciences “NEUROFARBA”, University of Florence, via Ugo Schiff 6, 50019 Sesto Fiorentino, Florence, Italy
| | - Giulio Vistoli
- Department
of Pharmaceutical Sciences “DISFARM”, Università degli Studi di Milano, via Mangiagalli 25, I-20133 Milan, Italy
| | - Laura Fumagalli
- Department
of Pharmaceutical Sciences “DISFARM”, Università degli Studi di Milano, via Mangiagalli 25, I-20133 Milan, Italy,. Phone: +39-02-50319303
| |
Collapse
|
5
|
Pavletić P, Semeano A, Yano H, Bonifazi A, Giorgioni G, Piergentili A, Quaglia W, Sabbieti MG, Agas D, Santoni G, Pallini R, Ricci-Vitiani L, Sabato E, Vistoli G, Del Bello F. Highly Potent and Selective Dopamine D 4 Receptor Antagonists Potentially Useful for the Treatment of Glioblastoma. J Med Chem 2022; 65:12124-12139. [PMID: 36098685 PMCID: PMC9511495 DOI: 10.1021/acs.jmedchem.2c00840] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/03/2022]
Abstract
![]()
To better understand
the role of dopamine D4 receptor
(D4R) in glioblastoma (GBM), in the present paper, new
ligands endowed with high affinity and selectivity for D4R were discovered starting from the brain penetrant and D4R selective lead compound 1-(3-(4-phenylpiperazin-1-yl)propyl)-3,4-dihydroquinolin-2(1H)-one (6). In particular, the D4R antagonist 24, showing the highest affinity and selectivity
over D2R and D3R within the series (D2/D4 = 8318, D3/D4 = 3715), and the
biased ligand 29, partially activating D4R
Gi-/Go-protein and blocking β-arrestin
recruitment, emerged as the most interesting compounds. These compounds,
evaluated for their GBM antitumor activity, induced a decreased viability
of GBM cell lines and primary GBM stem cells (GSC#83), with the maximal
efficacy being reached at a concentration of 10 μM. Interestingly,
the treatment with both compounds 24 and 29 induced an increased effect in reducing the cell viability with
respect to temozolomide, which is the first-choice chemotherapeutic
drug in GBM.
Collapse
Affiliation(s)
- Pegi Pavletić
- Scuola di Scienze del Farmaco e dei Prodotti della Salute, Università di Camerino,, Camerino 62032, Italy
| | - Ana Semeano
- Department of Pharmaceutical Sciences, School of Pharmacy and Pharmaceutical Sciences, Bouvé College of Health Sciences, Center for Drug Discovery, Northeastern University, Boston, Massachusetts 02115, United States
| | - Hideaki Yano
- Department of Pharmaceutical Sciences, School of Pharmacy and Pharmaceutical Sciences, Bouvé College of Health Sciences, Center for Drug Discovery, Northeastern University, Boston, Massachusetts 02115, United States
| | - Alessandro Bonifazi
- Medicinal Chemistry Section, Molecular Targets and Medications Discovery Branch, National Institute on Drug Abuse-Intramural Research Program, National Institutes of Health, 333 Cassell Drive, Baltimore, Maryland 21224, United States
| | - Gianfabio Giorgioni
- Scuola di Scienze del Farmaco e dei Prodotti della Salute, Università di Camerino,, Camerino 62032, Italy
| | - Alessandro Piergentili
- Scuola di Scienze del Farmaco e dei Prodotti della Salute, Università di Camerino,, Camerino 62032, Italy
| | - Wilma Quaglia
- Scuola di Scienze del Farmaco e dei Prodotti della Salute, Università di Camerino,, Camerino 62032, Italy
| | - Maria Giovanna Sabbieti
- Scuola di Bioscienze e Medicina Veterinaria, Università di Camerino, Via Gentile III da Varano, Camerino 62032, Italy
| | - Dimitrios Agas
- Scuola di Bioscienze e Medicina Veterinaria, Università di Camerino, Via Gentile III da Varano, Camerino 62032, Italy
| | - Giorgio Santoni
- Scuola di Scienze del Farmaco e dei Prodotti della Salute, Università di Camerino,, Camerino 62032, Italy
| | - Roberto Pallini
- Institute of Neurosurgery, Scientific Hospitalization and Care Institute (IRCCS), Gemelli University Polyclinic Foundation, Rome 00168, Italy.,Institute of Neurosurgery, School of Medicine, Catholic University, Rome 00168, Italy
| | - Lucia Ricci-Vitiani
- Department of Hematology, Oncology and Molecular Medicine, Istituto Superiore di Sanità, Rome 00161, Italy
| | - Emanuela Sabato
- Dipartimento di Scienze Farmaceutiche, Università degli Studi di Milano, Via Mangiagalli 25, Milano 20133, Italy
| | - Giulio Vistoli
- Dipartimento di Scienze Farmaceutiche, Università degli Studi di Milano, Via Mangiagalli 25, Milano 20133, Italy
| | - Fabio Del Bello
- Scuola di Scienze del Farmaco e dei Prodotti della Salute, Università di Camerino,, Camerino 62032, Italy
| |
Collapse
|