1
|
Zhang VY, O'Connor SL, Welsh WJ, James MH. Machine learning models to predict ligand binding affinity for the orexin 1 receptor. ARTIFICIAL INTELLIGENCE CHEMISTRY 2024; 2:100040. [PMID: 38476266 PMCID: PMC10927255 DOI: 10.1016/j.aichem.2023.100040] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 03/14/2024]
Abstract
The orexin 1 receptor (OX1R) is a G-protein coupled receptor that regulates a variety of physiological processes through interactions with the neuropeptides orexin A and B. Selective OX1R antagonists exhibit therapeutic effects in preclinical models of several behavioral disorders, including drug seeking and overeating. However, currently there are no selective OX1R antagonists approved for clinical use, fueling demand for novel compounds that act at this target. In this study, we meticulously curated a dataset comprising over 1300 OX1R ligands using a stringent filter and criteria cascade. Subsequently, we developed highly predictive quantitative structure-activity relationship (QSAR) models employing the optimized hyper-parameters for the random forest machine learning algorithm and twelve 2D molecular descriptors selected by recursive feature elimination with a 5-fold cross-validation process. The predictive capacity of the QSAR model was further assessed using an external test set and enrichment study, confirming its high predictivity. The practical applicability of our final QSAR model was demonstrated through virtual screening of the DrugBank database. This revealed two FDA-approved drugs (isavuconazole and cabozantinib) as potential OX1R ligands, confirmed by radiolabeled OX1R binding assays. To our best knowledge, this study represents the first report of highly predictive QSAR models on a large comprehensive dataset of diverse OX1R ligands, which should prove useful for the discovery and design of new compounds targeting this receptor.
Collapse
Affiliation(s)
- Vanessa Y Zhang
- Department of Psychiatry, Robert Wood Johnson Medical School, Rutgers University and Rutgers Biomedical Health Sciences, Piscataway, NJ, USA
- Brain Health Institute, Rutgers University and Rutgers Biomedical and Health Sciences, Piscataway, NJ, USA
- West Windsor-Plainsboro High School South, West Windsor, NJ, USA
| | - Shayna L O'Connor
- Department of Psychiatry, Robert Wood Johnson Medical School, Rutgers University and Rutgers Biomedical Health Sciences, Piscataway, NJ, USA
- Brain Health Institute, Rutgers University and Rutgers Biomedical and Health Sciences, Piscataway, NJ, USA
| | - William J Welsh
- Department of Pharmacology, Robert Wood Johnson Medical School, Rutgers University and Rutgers Biomedical Health Sciences, Piscataway, NJ, USA
| | - Morgan H James
- Department of Psychiatry, Robert Wood Johnson Medical School, Rutgers University and Rutgers Biomedical Health Sciences, Piscataway, NJ, USA
- Brain Health Institute, Rutgers University and Rutgers Biomedical and Health Sciences, Piscataway, NJ, USA
| |
Collapse
|
2
|
Cao C, Wang H, Yang JR, Chen Q, Guo YM, Chen JZ. MCPNET: Development of an interpretable deep learning model based on multiple conformations of the compound for predicting developmental toxicity. Comput Biol Med 2024; 171:108037. [PMID: 38377716 DOI: 10.1016/j.compbiomed.2024.108037] [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: 09/09/2023] [Revised: 12/21/2023] [Accepted: 01/26/2024] [Indexed: 02/22/2024]
Abstract
The development of deep learning models for predicting toxicological endpoints has shown great promise, but one of the challenges in the field is the accuracy and interpretability of these models. The bioactive conformation of a compound plays a critical role for it to bind in the target. It is a big issue to figure out the bioactive conformation in deep learning without the co-crystal structure or highly precise molecular simulations. In this study, we developed a deep learning framework of Multi-Conformation Point Network (MCPNET) to construct classification and regression models, respectively, based on electrostatic potential distributions on vdW surfaces around multiple conformations of the compound using a dataset of compounds with developmental toxicity in zebrafish embryo. MCPNET applied 3D multi-conformational surface point cloud to extract the molecular features for model training, which may be critical for capturing the structural diversity of compounds. The models achieved an accuracy of 85 % on the classification task and R2 of 0.66 on the regression task, outperforming traditional machine learning models and other deep learning models. The key feature of our model is its interpretability with the component visualization to identify the factors contributing to the prediction and to understand the compound action mechanism. MCPNET may predict the conformation quietly close to the bioactive conformation of a compound by attention-based multi-conformation pooling mechanism. Our results demonstrated the potential of deep learning based on 3D molecular representations in accurately predicting developmental toxicity. The source code is publicly available at https://github.com/Superlit-CC/MCPNET.
Collapse
Affiliation(s)
- Cheng Cao
- College of Pharmaceutical Sciences, Zhejiang University, 866 Yuhangtang Rd., Hangzhou, Zhejiang, 310058, China; Polytechnic Institute, Zhejiang University, 269 Shixiang Rd, Hangzhou, Zhejiang, 310015, China
| | - Hao Wang
- College of Pharmaceutical Sciences, Zhejiang University, 866 Yuhangtang Rd., Hangzhou, Zhejiang, 310058, China
| | - Jin-Rong Yang
- College of Pharmaceutical Sciences, Zhejiang University, 866 Yuhangtang Rd., Hangzhou, Zhejiang, 310058, China; Polytechnic Institute, Zhejiang University, 269 Shixiang Rd, Hangzhou, Zhejiang, 310015, China
| | - Qiang Chen
- College of Pharmaceutical Sciences, Zhejiang University, 866 Yuhangtang Rd., Hangzhou, Zhejiang, 310058, China
| | - Ya-Min Guo
- College of Pharmaceutical Sciences, Zhejiang University, 866 Yuhangtang Rd., Hangzhou, Zhejiang, 310058, China
| | - Jian-Zhong Chen
- College of Pharmaceutical Sciences, Zhejiang University, 866 Yuhangtang Rd., Hangzhou, Zhejiang, 310058, China.
| |
Collapse
|
3
|
Dorahy G, Chen JZ, Balle T. Computer-Aided Drug Design towards New Psychotropic and Neurological Drugs. Molecules 2023; 28:molecules28031324. [PMID: 36770990 PMCID: PMC9921936 DOI: 10.3390/molecules28031324] [Citation(s) in RCA: 8] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/15/2022] [Revised: 01/23/2023] [Accepted: 01/26/2023] [Indexed: 01/31/2023] Open
Abstract
Central nervous system (CNS) disorders are a therapeutic area in drug discovery where demand for new treatments greatly exceeds approved treatment options. This is complicated by the high failure rate in late-stage clinical trials, resulting in exorbitant costs associated with bringing new CNS drugs to market. Computer-aided drug design (CADD) techniques minimise the time and cost burdens associated with drug research and development by ensuring an advantageous starting point for pre-clinical and clinical assessments. The key elements of CADD are divided into ligand-based and structure-based methods. Ligand-based methods encompass techniques including pharmacophore modelling and quantitative structure activity relationships (QSARs), which use the relationship between biological activity and chemical structure to ascertain suitable lead molecules. In contrast, structure-based methods use information about the binding site architecture from an established protein structure to select suitable molecules for further investigation. In recent years, deep learning techniques have been applied in drug design and present an exciting addition to CADD workflows. Despite the difficulties associated with CNS drug discovery, advances towards new pharmaceutical treatments continue to be made, and CADD has supported these findings. This review explores various CADD techniques and discusses applications in CNS drug discovery from 2018 to November 2022.
Collapse
Affiliation(s)
- Georgia Dorahy
- Sydney Pharmacy School, Faculty of Medicine and Health, The University of Sydney, Sydney, NSW 2006, Australia
- Brain and Mind Centre, The University of Sydney, Camperdown, NSW 2050, Australia
| | - Jake Zheng Chen
- Sydney Pharmacy School, Faculty of Medicine and Health, The University of Sydney, Sydney, NSW 2006, Australia
- Brain and Mind Centre, The University of Sydney, Camperdown, NSW 2050, Australia
| | - Thomas Balle
- Sydney Pharmacy School, Faculty of Medicine and Health, The University of Sydney, Sydney, NSW 2006, Australia
- Brain and Mind Centre, The University of Sydney, Camperdown, NSW 2050, Australia
- Correspondence:
| |
Collapse
|
4
|
Das BK, Chakraborty D. Deciphering the competitive inhibition of dihydropteroate synthase by 8 marcaptoguanine analogs: enhanced potency in phenylsulfonyl fragments. J Biomol Struct Dyn 2022; 40:13083-13102. [PMID: 34581241 DOI: 10.1080/07391102.2021.1981452] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/27/2022]
Abstract
The emergence of sulfa-drug resistance and reduced efficacy of pterin-based analogs towards Dihydropteroate synthase (DHPS) inhibition dictate a pressing need of developing novel antimicrobial agents for immune-compromised patients. Recently, a series of 8-Marcaptoguanin (8-MG) derivatives synthesized for 6-Hydroxymethyl-7,8-dihydropterin pyrophosphokinase (experimental KD ∼ 100-.0.36) showed remarkable homology with the pteroic-acid and serve as a template for product antagonism in DHPS. The present work integrates ligand-based drug discovery techniques with structure-based docking, enhanced MD simulation, and MM/PBSA techniques to demonstrate the essential features of 8-MG analogs which make it a potent inhibitor for DHPS. The delicate balance in hydrophilic, hydrophobic substitutions on the 8-MG core is the crucial signature for DHPS inhibition. It is found that the dynamic interactions of active compounds are mainly dominated by consistent hydrogen bonding network with Asp 96, Asn 115, Asp 185, Ser 222, Arg 255 and π-π stacking, π-cation interactions with Phe 190, Lys 221. Further, two new 8-MG compounds containing N-phenylacetamide (compound S1, ΔGbind-eff = -62.03 kJ/mol) and phenylsulfonyl (compound S3, ΔGbind-eff = -71.29 kJ/mol) fragments were found to be the most potent inhibitor of DHPS, which stabilize the flexible pABA binding loop, thereby increasing their binding affinity. MM/PBSA calculation shows electrostatic energy contribution to be the principal component in stabilizing the inhibitors in the binding pocket. This fact is further confirmed by the higher energy barrier obtained in umbrella sampling for this class of inhibitors.
Collapse
Affiliation(s)
- Bratin Kumar Das
- Biophysical and Computational Chemistry Laboratory, Department of Chemistry, National Institute of Technology Karnataka, Mangalore, India
| | - Debashree Chakraborty
- Biophysical and Computational Chemistry Laboratory, Department of Chemistry, National Institute of Technology Karnataka, Mangalore, India
| |
Collapse
|
5
|
Fallica AN, Ciaffaglione V, Modica MN, Pittalà V, Salerno L, Amata E, Marrazzo A, Romeo G, Intagliata S. Structure-activity relationships of mixed σ1R/σ2R ligands with antiproliferative and anticancer effects. Bioorg Med Chem 2022; 73:117032. [DOI: 10.1016/j.bmc.2022.117032] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/28/2022] [Revised: 09/16/2022] [Accepted: 09/21/2022] [Indexed: 11/27/2022]
|
6
|
Xu L, Chen LY. Association of sigma-1 receptor with dopamine transporter attenuates the binding of methamphetamine via distinct helix-helix interactions. Chem Biol Drug Des 2021; 97:1194-1209. [PMID: 33754484 PMCID: PMC8113090 DOI: 10.1111/cbdd.13841] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/22/2021] [Revised: 02/23/2021] [Accepted: 03/07/2021] [Indexed: 02/06/2023]
Abstract
Dopamine transporter (DAT) and sigma-1 receptor (σ1R) are potential therapeutic targets to reduce the psychostimulant effects induced by methamphetamine (METH). Interaction of σ1R with DAT could modulate the binding of METH, but the molecular basis of the association of the two transmembrane proteins and how their interactions mediate the binding of METH to DAT or σ1R remain unclear. Here, we characterize the protein-ligand and protein-protein interactions at a molecular level by various theoretical approaches. The present results show that METH adopts a different binding pose in the binding pocket of σ1R and is more likely to act as an agonist. The relatively lower binding affinity of METH to σ1R supports the role of antagonists as inhibitors that protect against METH-induced effects. We demonstrate that σ1R could bind to Drosophila melanogaster DAT (dDAT) through interactions with either the transmembrane helix α12 or α5 of dDAT. Our results showed that the truncated σ1R displays stronger association with dDAT than the full-length σ1R. Although different helix-helix interactions between σ1R and dDAT lead to distinct effects on the dynamics of individual protein, both associations attenuate the binding affinity of METH to dDAT, particularly in the interactions with the helix α5 of dDAT. Together, the present study provides the first computational investigation on the molecular mechanism of coupling METH binding and the association of σ1R with dDAT.
Collapse
Affiliation(s)
- Liang Xu
- Department of Physics and Astronomy, University of Texas at San Antonio, San Antonio, TX, USA
| | - Liao Y Chen
- Department of Physics and Astronomy, University of Texas at San Antonio, San Antonio, TX, USA
| |
Collapse
|
7
|
Peng Y, Zhang Q, Welsh WJ. Novel Sigma 1 Receptor Antagonists as Potential Therapeutics for Pain Management. J Med Chem 2021; 64:890-904. [PMID: 33372782 DOI: 10.1021/acs.jmedchem.0c01964] [Citation(s) in RCA: 7] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
Abstract
The sigma 1 receptor (S1R) is a molecular chaperone protein located in the endoplasmic reticulum and plasma membranes and has been shown to play important roles in various pathological disorders including pain and, as recently discovered, COVID-19. Employing structure- and QSAR-based drug design strategies, we rationally designed, synthesized, and biologically evaluated a series of novel triazole-based S1R antagonists. Compound 10 exhibited potent binding affinity for S1R, high selectivity over S2R and 87 other human targets, acceptable in vitro metabolic stability, slow clearance in liver microsomes, and excellent blood-brain barrier permeability in rats. Further in vivo studies in rats showed that 10 exhibited negligible acute toxicity in the rotarod test and statistically significant analgesic effects in the formalin test for acute inflammatory pain and paclitaxel-induced neuropathic pain models during cancer chemotherapy. These encouraging results promote further development of our triazole-based S1R antagonists as novel treatments for pain of different etiologies.
Collapse
Affiliation(s)
- Youyi Peng
- Biomedical Informatics Shared Resource, Cancer Institute of New Jersey, Rutgers, The State University of New Jersey, 195 Little Albany Street, New Brunswick, New Jersey 08903, United States
| | - Qiang Zhang
- Department of Pharmacology, Robert Wood Johnson Medical School, Rutgers, The State University of New Jersey, 661 Hoes Lane West, Piscataway, New Jersey 08854, United States
| | - William J Welsh
- Biomedical Informatics Shared Resource, Cancer Institute of New Jersey, Rutgers, The State University of New Jersey, 195 Little Albany Street, New Brunswick, New Jersey 08903, United States
- Department of Pharmacology, Robert Wood Johnson Medical School, Rutgers, The State University of New Jersey, 661 Hoes Lane West, Piscataway, New Jersey 08854, United States
| |
Collapse
|
8
|
Perić V, Golubović M, Lazarević M, Marjanović V, Kostić T, Đorđević M, Milić D, Veselinović AM. Development of potential therapeutics for pain treatment by inducing Sigma 1 receptor antagonism – in silico approach. NEW J CHEM 2021. [DOI: 10.1039/d1nj00883h] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/21/2022]
Abstract
QSAR modeling with computer-aided drug design were used for the in silico development of novel therapeutics for pain treatment.
Collapse
Affiliation(s)
- Velimir Perić
- Department for Cardiac Surgery
- Clinic for Anaesthesiology and Intensive Therapy
- Clinical Center Niš
- Niš
- Serbia
| | - Mladjan Golubović
- Department for Cardiac Surgery
- Clinic for Anaesthesiology and Intensive Therapy
- Clinical Center Niš
- Niš
- Serbia
| | - Milan Lazarević
- Faculty of Medicine
- Department of Chemistry
- Medical School of Niš
- University of Niš
- 18000 Niš
| | - Vesna Marjanović
- Faculty of Medicine
- Department of Chemistry
- Medical School of Niš
- University of Niš
- 18000 Niš
| | - Tomislav Kostić
- Faculty of Medicine
- Department of Chemistry
- Medical School of Niš
- University of Niš
- 18000 Niš
| | - Miodrag Đorđević
- Faculty of Medicine
- Department of Chemistry
- Medical School of Niš
- University of Niš
- 18000 Niš
| | - Dragan Milić
- Faculty of Medicine
- Department of Chemistry
- Medical School of Niš
- University of Niš
- 18000 Niš
| | | |
Collapse
|
9
|
Greenfield DA, Schmidt HR, Skiba MA, Mandler MD, Anderson JR, Sliz P, Kruse AC. Virtual Screening for Ligand Discovery at the σ 1 Receptor. ACS Med Chem Lett 2020; 11:1555-1561. [PMID: 32832023 DOI: 10.1021/acsmedchemlett.9b00314] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/20/2020] [Accepted: 07/27/2020] [Indexed: 01/04/2023] Open
Abstract
The σ1 receptor is a transmembrane protein implicated in several pathophysiological conditions, including neurodegenerative disease (J. Pharmacol. Sci.2015127 (1), 1729), drug addiction (Behav. Pharmacol.201627 (2-3 Spec Issue), 10015), cancer (Handb. Exp. Pharmacol.2017244237308), and pain (Neural Regener. Res.201813 (5), 775778). However, there are no high-throughput functional assays for σ1 receptor drug discovery. Here, we assessed high-throughput structure-based computational docking for discovery of novel ligands of the σ1 receptor. We screened a library of over 6 million compounds using the Schrödinger Glide package, followed by experimental characterization of top-scoring candidates. 77% of tested candidates bound σ1 with high affinity (KD < 1 μM). These include compounds with high selectivity for the σ1 receptor compared to the genetically unrelated but pharmacologically similar σ2 receptor, as well as compounds with substantial crossreactivity between the two receptors. These results establish structure-based virtual screening as a highly effective platform for σ1 receptor ligand discovery and provide compounds to prioritize in studies of σ1 biology.
Collapse
Affiliation(s)
- Daniel A. Greenfield
- Harvard Medical School, Department of Biological Chemistry and Molecular Pharmacology, Boston, Massachusetts 02115, United States
| | - Hayden R. Schmidt
- Harvard Medical School, Department of Biological Chemistry and Molecular Pharmacology, Boston, Massachusetts 02115, United States
| | - Meredith A. Skiba
- Harvard Medical School, Department of Biological Chemistry and Molecular Pharmacology, Boston, Massachusetts 02115, United States
| | - Michael D. Mandler
- Harvard University, Department of Chemistry and Chemical Biology, Cambridge, Massachusetts 02138, United States
| | - Jacob R. Anderson
- Harvard Medical School, Department of Biological Chemistry and Molecular Pharmacology, Boston, Massachusetts 02115, United States
| | - Piotr Sliz
- Harvard Medical School, Department of Biological Chemistry and Molecular Pharmacology, Boston, Massachusetts 02115, United States
- Boston Children’s Hospital, Boston, Massachusetts 02115, United States
| | - Andrew C. Kruse
- Harvard Medical School, Department of Biological Chemistry and Molecular Pharmacology, Boston, Massachusetts 02115, United States
| |
Collapse
|
10
|
Pascual R, Almansa C, Plata-Salamán C, Vela JM. A New Pharmacophore Model for the Design of Sigma-1 Ligands Validated on a Large Experimental Dataset. Front Pharmacol 2019; 10:519. [PMID: 31214020 PMCID: PMC6555132 DOI: 10.3389/fphar.2019.00519] [Citation(s) in RCA: 19] [Impact Index Per Article: 3.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/04/2019] [Accepted: 04/24/2019] [Indexed: 11/13/2022] Open
Abstract
The recent publication of the σ1R crystal structure is an important cornerstone for the derivation of more accurate activity prediction models. We report here a comparative study involving a set of more than 25,000 structures from our internal database that had been screened for σ1R affinity. Using the recently published crystal structure, 5HK1, two new pharmacophore models were generated. The first one, 5HK1-Ph.A, was obtained by an algorithm that identifies the most important receptor-ligand interactions including volume restrictions enforced by the atomic structure of the recognition site. The second, 5HK1-Ph.B, resulted from a manual edition of the first one by the fusion of two hydrophobic (HYD) features. Finally, we also docked the database using a high throughput docking technique and scored the resulting poses with seven different scoring functions. Statistical performance measures were obtained for the two models, comparing them with previously published σ1R pharmacophores (Hit Rate, sensitivity, specificity, and Receiver Operator Characteristic) and 5HK1-Ph.B emerged as the best one in discriminating between active and inactive compounds, with a ROC-AUC value above 0.8 and enrichment values above 3 at different fractions of screened samples. 5HK1-Ph.B also showed better results than the direct docking, which may be due to the rigidity of the crystal structure in the docking process (i.e., feature tolerances in the pharmacophore model). Additionally, the impact of the HYD interactions and the penalty for desolvating ligands with polar atoms may be not adequately captured by scoring functions, whereas HYD groups filling up such regions of the binding site are entailed in the pharmacophore model. Altogether, using annotated data from a large and diverse compound collection together with crystal structure information provides a sound basis for the generation and validation of predictive models to design new molecules.
Collapse
Affiliation(s)
- Rosalia Pascual
- ESTEVE Pharmaceuticals S.A., Drug Discovery and Preclinical Development, Barcelona, Spain
| | - Carmen Almansa
- ESTEVE Pharmaceuticals S.A., Drug Discovery and Preclinical Development, Barcelona, Spain
| | - Carlos Plata-Salamán
- ESTEVE Pharmaceuticals S.A., Drug Discovery and Preclinical Development, Barcelona, Spain
| | - José Miguel Vela
- ESTEVE Pharmaceuticals S.A., Drug Discovery and Preclinical Development, Barcelona, Spain
| |
Collapse
|