Machine Learning-Based Virtual Screening for the Identification of Cdk5 Inhibitors
Cyclin-dependent kinase 5 (Cdk5) is an atypical proline-directed serine/threonine protein kinase well-characterized for its role in the central nervous system rather than in the cell cycle. Indeed, its dysregulation has been strongly implicated in the progression of synaptic dysfunction and neurodeg...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | International Journal of Molecular Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1422-0067/23/18/10653 |
| _version_ | 1797487223838343168 |
|---|---|
| author | Miriana Di Stefano Salvatore Galati Gabriella Ortore Isabella Caligiuri Flavio Rizzolio Costanza Ceni Simone Bertini Giulia Bononi Carlotta Granchi Marco Macchia Giulio Poli Tiziano Tuccinardi |
| author_facet | Miriana Di Stefano Salvatore Galati Gabriella Ortore Isabella Caligiuri Flavio Rizzolio Costanza Ceni Simone Bertini Giulia Bononi Carlotta Granchi Marco Macchia Giulio Poli Tiziano Tuccinardi |
| author_sort | Miriana Di Stefano |
| collection | DOAJ |
| description | Cyclin-dependent kinase 5 (Cdk5) is an atypical proline-directed serine/threonine protein kinase well-characterized for its role in the central nervous system rather than in the cell cycle. Indeed, its dysregulation has been strongly implicated in the progression of synaptic dysfunction and neurodegenerative diseases, such as Alzheimer’s disease (AD) and Parkinson’s disease (PD), and also in the development and progression of a variety of cancers. For this reason, Cdk5 is considered as a promising target for drug design, and the discovery of novel small-molecule Cdk5 inhibitors is of great interest in the medicinal chemistry field. In this context, we employed a machine learning-based virtual screening protocol with subsequent molecular docking, molecular dynamics simulations and binding free energy evaluations. Our virtual screening studies resulted in the identification of two novel Cdk5 inhibitors, highlighting an experimental hit rate of 50% and thus validating the reliability of the in silico workflow. Both identified ligands, compounds <b>CPD1</b> and <b>CPD4</b>, showed a promising enzyme inhibitory activity and <b>CPD1</b> also demonstrated a remarkable antiproliferative activity in ovarian and colon cancer cells. These ligands represent a valuable starting point for structure-based hit-optimization studies aimed at identifying new potent Cdk5 inhibitors. |
| first_indexed | 2024-03-09T23:44:35Z |
| format | Article |
| id | doaj.art-2fa74ee0903b4348902072073cd542a8 |
| institution | Directory Open Access Journal |
| issn | 1661-6596 1422-0067 |
| language | English |
| last_indexed | 2024-03-09T23:44:35Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | International Journal of Molecular Sciences |
| spelling | doaj.art-2fa74ee0903b4348902072073cd542a82023-11-23T16:45:47ZengMDPI AGInternational Journal of Molecular Sciences1661-65961422-00672022-09-0123181065310.3390/ijms231810653Machine Learning-Based Virtual Screening for the Identification of Cdk5 InhibitorsMiriana Di Stefano0Salvatore Galati1Gabriella Ortore2Isabella Caligiuri3Flavio Rizzolio4Costanza Ceni5Simone Bertini6Giulia Bononi7Carlotta Granchi8Marco Macchia9Giulio Poli10Tiziano Tuccinardi11Department of Pharmacy, University of Pisa, Via Bonanno 6, 56126 Pisa, ItalyDepartment of Pharmacy, University of Pisa, Via Bonanno 6, 56126 Pisa, ItalyDepartment of Pharmacy, University of Pisa, Via Bonanno 6, 56126 Pisa, ItalyPathology Unit, Centro di Riferimento Oncologico di Aviano (CRO) IRCCS, 33081 Aviano, ItalyPathology Unit, Centro di Riferimento Oncologico di Aviano (CRO) IRCCS, 33081 Aviano, ItalyDepartment of Pharmacy, University of Pisa, Via Bonanno 6, 56126 Pisa, ItalyDepartment of Pharmacy, University of Pisa, Via Bonanno 6, 56126 Pisa, ItalyDepartment of Pharmacy, University of Pisa, Via Bonanno 6, 56126 Pisa, ItalyDepartment of Pharmacy, University of Pisa, Via Bonanno 6, 56126 Pisa, ItalyDepartment of Pharmacy, University of Pisa, Via Bonanno 6, 56126 Pisa, ItalyDepartment of Pharmacy, University of Pisa, Via Bonanno 6, 56126 Pisa, ItalyDepartment of Pharmacy, University of Pisa, Via Bonanno 6, 56126 Pisa, ItalyCyclin-dependent kinase 5 (Cdk5) is an atypical proline-directed serine/threonine protein kinase well-characterized for its role in the central nervous system rather than in the cell cycle. Indeed, its dysregulation has been strongly implicated in the progression of synaptic dysfunction and neurodegenerative diseases, such as Alzheimer’s disease (AD) and Parkinson’s disease (PD), and also in the development and progression of a variety of cancers. For this reason, Cdk5 is considered as a promising target for drug design, and the discovery of novel small-molecule Cdk5 inhibitors is of great interest in the medicinal chemistry field. In this context, we employed a machine learning-based virtual screening protocol with subsequent molecular docking, molecular dynamics simulations and binding free energy evaluations. Our virtual screening studies resulted in the identification of two novel Cdk5 inhibitors, highlighting an experimental hit rate of 50% and thus validating the reliability of the in silico workflow. Both identified ligands, compounds <b>CPD1</b> and <b>CPD4</b>, showed a promising enzyme inhibitory activity and <b>CPD1</b> also demonstrated a remarkable antiproliferative activity in ovarian and colon cancer cells. These ligands represent a valuable starting point for structure-based hit-optimization studies aimed at identifying new potent Cdk5 inhibitors.https://www.mdpi.com/1422-0067/23/18/10653virtual screeningmachine learningkinaseCDK5 |
| spellingShingle | Miriana Di Stefano Salvatore Galati Gabriella Ortore Isabella Caligiuri Flavio Rizzolio Costanza Ceni Simone Bertini Giulia Bononi Carlotta Granchi Marco Macchia Giulio Poli Tiziano Tuccinardi Machine Learning-Based Virtual Screening for the Identification of Cdk5 Inhibitors International Journal of Molecular Sciences virtual screening machine learning kinase CDK5 |
| title | Machine Learning-Based Virtual Screening for the Identification of Cdk5 Inhibitors |
| title_full | Machine Learning-Based Virtual Screening for the Identification of Cdk5 Inhibitors |
| title_fullStr | Machine Learning-Based Virtual Screening for the Identification of Cdk5 Inhibitors |
| title_full_unstemmed | Machine Learning-Based Virtual Screening for the Identification of Cdk5 Inhibitors |
| title_short | Machine Learning-Based Virtual Screening for the Identification of Cdk5 Inhibitors |
| title_sort | machine learning based virtual screening for the identification of cdk5 inhibitors |
| topic | virtual screening machine learning kinase CDK5 |
| url | https://www.mdpi.com/1422-0067/23/18/10653 |
| work_keys_str_mv | AT mirianadistefano machinelearningbasedvirtualscreeningfortheidentificationofcdk5inhibitors AT salvatoregalati machinelearningbasedvirtualscreeningfortheidentificationofcdk5inhibitors AT gabriellaortore machinelearningbasedvirtualscreeningfortheidentificationofcdk5inhibitors AT isabellacaligiuri machinelearningbasedvirtualscreeningfortheidentificationofcdk5inhibitors AT flaviorizzolio machinelearningbasedvirtualscreeningfortheidentificationofcdk5inhibitors AT costanzaceni machinelearningbasedvirtualscreeningfortheidentificationofcdk5inhibitors AT simonebertini machinelearningbasedvirtualscreeningfortheidentificationofcdk5inhibitors AT giuliabononi machinelearningbasedvirtualscreeningfortheidentificationofcdk5inhibitors AT carlottagranchi machinelearningbasedvirtualscreeningfortheidentificationofcdk5inhibitors AT marcomacchia machinelearningbasedvirtualscreeningfortheidentificationofcdk5inhibitors AT giuliopoli machinelearningbasedvirtualscreeningfortheidentificationofcdk5inhibitors AT tizianotuccinardi machinelearningbasedvirtualscreeningfortheidentificationofcdk5inhibitors |