1
|
de Azevedo WF, Quiroga R, Villarreal MA, da Silveira NJF, Bitencourt-Ferreira G, da Silva AD, Veit-Acosta M, Oliveira PR, Tutone M, Biziukova N, Poroikov V, Tarasova O, Baud S. SAnDReS 2.0: Development of machine-learning models to explore the scoring function space. J Comput Chem 2024; 45:2333-2346. [PMID: 38900052 DOI: 10.1002/jcc.27449] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/14/2024] [Revised: 05/04/2024] [Accepted: 06/02/2024] [Indexed: 06/21/2024]
Abstract
Classical scoring functions may exhibit low accuracy in determining ligand binding affinity for proteins. The availability of both protein-ligand structures and affinity data make it possible to develop machine-learning models focused on specific protein systems with superior predictive performance. Here, we report a new methodology named SAnDReS that combines AutoDock Vina 1.2 with 54 regression methods available in Scikit-Learn to calculate binding affinity based on protein-ligand structures. This approach allows exploration of the scoring function space. SAnDReS generates machine-learning models based on crystal, docked, and AlphaFold-generated structures. As a proof of concept, we examine the performance of SAnDReS-generated models in three case studies. For all three cases, our models outperformed classical scoring functions. Also, SAnDReS-generated models showed predictive performance close to or better than other machine-learning models such as KDEEP, CSM-lig, and ΔVinaRF20. SAnDReS 2.0 is available to download at https://github.com/azevedolab/sandres.
Collapse
Affiliation(s)
| | - Rodrigo Quiroga
- Instituto de Investigaciones en Fisicoquímica de Córdoba (INFIQC), CONICET-Departamento de Química Teórica y Computacional, Facultad de Ciencias Químicas, Universidad Nacional de Córdoba, Ciudad Universitaria, Córdoba, Argentina
| | - Marcos Ariel Villarreal
- Instituto de Investigaciones en Fisicoquímica de Córdoba (INFIQC), CONICET-Departamento de Química Teórica y Computacional, Facultad de Ciencias Químicas, Universidad Nacional de Córdoba, Ciudad Universitaria, Córdoba, Argentina
| | | | | | - Amauri Duarte da Silva
- Programa de Pós-Graduação em Tecnologias da Informação e Gestão em Saúde, Universidade Federal de Ciências da Saúde de Porto Alegre, Porto Alegre, Brazil
| | | | | | - Marco Tutone
- Dipartimento di Scienze e Tecnologie Biologiche Chimiche e Farmaceutiche (STEBICEF), Università di Palermo, Palermo, Italy
| | | | | | | | - Stéphaine Baud
- Laboratoire SiRMa, UMR CNRS/URCA 7369, UFR Sciences Exactes et Naturelles, Université de Reims Champagne-Ardenne, CNRS, MEDYC, Reims, France
| |
Collapse
|
2
|
Huang ETC, Yang JS, Liao KYK, Tseng WCW, Lee CK, Gill M, Compas C, See S, Tsai FJ. Predicting blood-brain barrier permeability of molecules with a large language model and machine learning. Sci Rep 2024; 14:15844. [PMID: 38982309 PMCID: PMC11233737 DOI: 10.1038/s41598-024-66897-y] [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: 03/06/2024] [Accepted: 07/05/2024] [Indexed: 07/11/2024] Open
Abstract
Predicting the blood-brain barrier (BBB) permeability of small-molecule compounds using a novel artificial intelligence platform is necessary for drug discovery. Machine learning and a large language model on artificial intelligence (AI) tools improve the accuracy and shorten the time for new drug development. The primary goal of this research is to develop artificial intelligence (AI) computing models and novel deep learning architectures capable of predicting whether molecules can permeate the human blood-brain barrier (BBB). The in silico (computational) and in vitro (experimental) results were validated by the Natural Products Research Laboratories (NPRL) at China Medical University Hospital (CMUH). The transformer-based MegaMolBART was used as the simplified molecular input line entry system (SMILES) encoder with an XGBoost classifier as an in silico method to check if a molecule could cross through the BBB. We used Morgan or Circular fingerprints to apply the Morgan algorithm to a set of atomic invariants as a baseline encoder also with an XGBoost classifier to compare the results. BBB permeability was assessed in vitro using three-dimensional (3D) human BBB spheroids (human brain microvascular endothelial cells, brain vascular pericytes, and astrocytes). Using multiple BBB databases, the results of the final in silico transformer and XGBoost model achieved an area under the receiver operating characteristic curve of 0.88 on the held-out test dataset. Temozolomide (TMZ) and 21 randomly selected BBB permeable compounds (Pred scores = 1, indicating BBB-permeable) from the NPRL penetrated human BBB spheroid cells. No evidence suggests that ferulic acid or five BBB-impermeable compounds (Pred scores < 1.29423E-05, which designate compounds that pass through the human BBB) can pass through the spheroid cells of the BBB. Our validation of in vitro experiments indicated that the in silico prediction of small-molecule permeation in the BBB model is accurate. Transformer-based models like MegaMolBART, leveraging the SMILES representations of molecules, show great promise for applications in new drug discovery. These models have the potential to accelerate the development of novel targeted treatments for disorders of the central nervous system.
Collapse
Affiliation(s)
- Eddie T C Huang
- NVIDIA AI Technology Center, NVIDIA Corporation, Santa Clara, USA
| | - Jai-Sing Yang
- Department of Medical Research, China Medical University Hospital, China Medical University, Taichung, Taiwan
| | - Ken Y K Liao
- NVIDIA AI Technology Center, NVIDIA Corporation, Santa Clara, USA
| | - Warren C W Tseng
- NVIDIA AI Technology Center, NVIDIA Corporation, Santa Clara, USA
| | - C K Lee
- NVIDIA AI Technology Center, NVIDIA Corporation, Santa Clara, USA
| | - Michelle Gill
- NVIDIA AI Technology Center, NVIDIA Corporation, Santa Clara, USA
| | - Colin Compas
- NVIDIA AI Technology Center, NVIDIA Corporation, Santa Clara, USA
| | - Simon See
- NVIDIA AI Technology Center, NVIDIA Corporation, Santa Clara, USA
| | - Fuu-Jen Tsai
- School of Chinese Medicine, College of Chinese Medicine, China Medical University, China Medical University Children's Hospital, No. 2, Yude Road, Taichung, 404332, Taiwan.
- China Medical University Children's Hospital, Taichung, Taiwan.
| |
Collapse
|
3
|
Liu H, Chen P, Hu B, Wang S, Wang H, Luan J, Wang J, Lin B, Cheng M. FaissMolLib: An efficient and easy deployable tool for ligand-based virtual screening. Comput Biol Chem 2024; 110:108057. [PMID: 38581840 DOI: 10.1016/j.compbiolchem.2024.108057] [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: 12/23/2023] [Revised: 03/06/2024] [Accepted: 03/20/2024] [Indexed: 04/08/2024]
Abstract
Virtual screening-based molecular similarity and fingerprint are crucial in drug design, target prediction, and ADMET prediction, aiding in identifying potential hits and optimizing lead compounds. However, challenges such as lack of comprehensive open-source molecular fingerprint databases and efficient search methods for virtual screening are prevalent. To address these issues, we introduce FaissMolLib, an open-source virtual screening tool that integrates 2.8 million compounds from ChEMBL and ZINC databases. Notably, FaissMolLib employs the highly efficient Faiss search algorithm, outperforming the Tanimoto algorithm in identifying similar molecules with its tighter clustering in scatter plots and lower mean, standard deviation, and variance in key molecular properties. This feature enables FaissMolLib to screen 2.8 million compounds in just 0.05 seconds, offering researchers an efficient, easily deployable solution for virtual screening on laptops and building unique compound databases. This significant advancement holds great potential for accelerating drug discovery efforts and enhancing chemical data analysis. FaissMolLib is freely available at http://liuhaihan.gnway.cc:80. The code and dataset of FaissMolLib are freely available at https://github.com/Superhaihan/FiassMolLib.
Collapse
Affiliation(s)
- Haihan Liu
- Key Laboratory of Structure-Based Drug Design &Discovery of Ministry of Education, Shenyang Pharmaceutical University, Shenyang 110016, People's Republic of China; Key Laboratory of Intelligent Drug Design and New Drug Discovery of Liaoning Province, Shenyang Pharmaceutical University, Shenyang 110016, People's Republic of China; School of Pharmaceutical Engineering, Shenyang Pharmaceutical University, Shenyang 110016, People's Republic of China
| | - Peiying Chen
- Key Laboratory of Structure-Based Drug Design &Discovery of Ministry of Education, Shenyang Pharmaceutical University, Shenyang 110016, People's Republic of China; Key Laboratory of Intelligent Drug Design and New Drug Discovery of Liaoning Province, Shenyang Pharmaceutical University, Shenyang 110016, People's Republic of China; School of Pharmaceutical Engineering, Shenyang Pharmaceutical University, Shenyang 110016, People's Republic of China
| | - Baichun Hu
- Key Laboratory of Structure-Based Drug Design &Discovery of Ministry of Education, Shenyang Pharmaceutical University, Shenyang 110016, People's Republic of China; Key Laboratory of Intelligent Drug Design and New Drug Discovery of Liaoning Province, Shenyang Pharmaceutical University, Shenyang 110016, People's Republic of China; School of Pharmaceutical Engineering, Shenyang Pharmaceutical University, Shenyang 110016, People's Republic of China
| | - Shizun Wang
- Key Laboratory of Structure-Based Drug Design &Discovery of Ministry of Education, Shenyang Pharmaceutical University, Shenyang 110016, People's Republic of China; Key Laboratory of Intelligent Drug Design and New Drug Discovery of Liaoning Province, Shenyang Pharmaceutical University, Shenyang 110016, People's Republic of China; School of Pharmaceutical Engineering, Shenyang Pharmaceutical University, Shenyang 110016, People's Republic of China
| | - Hanxun Wang
- Key Laboratory of Structure-Based Drug Design &Discovery of Ministry of Education, Shenyang Pharmaceutical University, Shenyang 110016, People's Republic of China; Key Laboratory of Intelligent Drug Design and New Drug Discovery of Liaoning Province, Shenyang Pharmaceutical University, Shenyang 110016, People's Republic of China; School of Pharmaceutical Engineering, Shenyang Pharmaceutical University, Shenyang 110016, People's Republic of China
| | - Jiasi Luan
- Key Laboratory of Structure-Based Drug Design &Discovery of Ministry of Education, Shenyang Pharmaceutical University, Shenyang 110016, People's Republic of China; Key Laboratory of Intelligent Drug Design and New Drug Discovery of Liaoning Province, Shenyang Pharmaceutical University, Shenyang 110016, People's Republic of China; School of Medical Devices, Shenyang Pharmaceutical University, Shenyang 110016, People's Republic of China
| | - Jian Wang
- Key Laboratory of Structure-Based Drug Design &Discovery of Ministry of Education, Shenyang Pharmaceutical University, Shenyang 110016, People's Republic of China; Key Laboratory of Intelligent Drug Design and New Drug Discovery of Liaoning Province, Shenyang Pharmaceutical University, Shenyang 110016, People's Republic of China; School of Pharmaceutical Engineering, Shenyang Pharmaceutical University, Shenyang 110016, People's Republic of China.
| | - Bin Lin
- Key Laboratory of Structure-Based Drug Design &Discovery of Ministry of Education, Shenyang Pharmaceutical University, Shenyang 110016, People's Republic of China; Key Laboratory of Intelligent Drug Design and New Drug Discovery of Liaoning Province, Shenyang Pharmaceutical University, Shenyang 110016, People's Republic of China; School of Pharmaceutical Engineering, Shenyang Pharmaceutical University, Shenyang 110016, People's Republic of China.
| | - Maosheng Cheng
- Key Laboratory of Structure-Based Drug Design &Discovery of Ministry of Education, Shenyang Pharmaceutical University, Shenyang 110016, People's Republic of China; Key Laboratory of Intelligent Drug Design and New Drug Discovery of Liaoning Province, Shenyang Pharmaceutical University, Shenyang 110016, People's Republic of China; School of Pharmaceutical Engineering, Shenyang Pharmaceutical University, Shenyang 110016, People's Republic of China.
| |
Collapse
|
4
|
Meixner M, Zachmann M, Metzler S, Scheerer J, Zacharias M, Antes I. Dynamic Docking of Macrocycles in Bound and Unbound Protein Structures with DynaDock. J Chem Inf Model 2022; 62:3426-3441. [PMID: 35796228 DOI: 10.1021/acs.jcim.2c00436] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/30/2022]
Abstract
Macrocycles are interesting molecules with unique features due to their conformationally constrained yet flexible ring structure. This characteristic poses a difficult challenge for computational modeling studies since they rely on accurate structural descriptions. In particular, molecular docking calculations suffer from the lack of ring flexibility during pose generation, which is often compensated by using pregenerated ligand conformer ensembles. Moreover, receptor structures are mainly treated rigidly, which limits the use of many docking tools. In this study, we optimized our previous molecular dynamics-based sampling and docking pipeline specifically designed for the accurate prediction of macrocyclic compounds. We developed a dihedral classification procedure for in-depth conformational analysis of the macrocyclic rings and extracted structural ensembles that were subsequently docked in both bound and unbound protein structures employing a fully flexible approach. Our results suggest that including a ring conformer close to the bound state in the starting ensemble increases the chance of successful docking. The bioactive conformations of a diverse set of ligands could be predicted with high and decent accuracy in bound and unbound protein structures, respectively, due to the incorporation of full molecular flexibility in our approach. The remaining unsuccessful docking calculations were mainly caused by large flexible substituents that bind to surface-exposed binding sites, rather than the macrocyclic ring per se and could be further improved by explicit molecular dynamics simulations of the docked complex.
Collapse
Affiliation(s)
- Maximilian Meixner
- TUM School of Life Sciences, Technical University Munich, Am Staudengarten 2, Freising 85354, Germany
| | - Martin Zachmann
- TUM School of Life Sciences, Technical University Munich, Am Staudengarten 2, Freising 85354, Germany
| | - Sebastian Metzler
- TUM School of Life Sciences, Technical University Munich, Am Staudengarten 2, Freising 85354, Germany
| | - Jonathan Scheerer
- TUM School of Life Sciences, Technical University Munich, Am Staudengarten 2, Freising 85354, Germany
| | - Martin Zacharias
- Center of Functional Protein Assemblies, Technical University Munich, Ernst-Otto-Fischer-Straße 8, Garching bei München 85748, Germany
| | - Iris Antes
- TUM School of Life Sciences, Technical University Munich, Am Staudengarten 2, Freising 85354, Germany
| |
Collapse
|
5
|
Patel CN, Goswami D, Jaiswal DG, Jani SP, Parmar RM, Rawal RM, Pandya HA. Excavating phytochemicals from plants possessing antiviral activities for identifying SARS-CoV hemagglutinin-esterase inhibitors by diligent computational workflow. J Biomol Struct Dyn 2022; 41:2382-2397. [PMID: 35098887 DOI: 10.1080/07391102.2022.2033642] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/19/2022]
Abstract
Coronaviruses (CoVs) belong to a group of RNA viruses that cause diseases in vertebrates including. Newer and deadlier than SARS CoV-2 are sought to appear in future for which the scientific community must be prepared with the strategies for their control. Spike protein (S-protein) of all the CoVs require angiotensin-converting enzyme2 (ACE2), while CoVs also require hemagglutinin-acetylesterase (HE) glycoprotein receptor to simultaneously interact with O-acetylated sialic acids on host cells, both these interactions enable viral particle to enter host cell leading to its infection. Target inhibition of viral S-protein and HE glycoprotein receptor can lead to a development of therapy against the SARS CoV-2. The proposition is to recognize molecules from the bundle of phytochemicals of medicinal plants known to possess antiviral potentials as a lead that could interact and mask the active site of, HE glycoprotein which would ideally bind to O-acetylated sialic acids on human host cells. Such molecules can be addressed as 'HE glycoprotein blockers'. A library of 110 phytochemicals from Withania somnifera, Asparagus racemosus, Zinziber officinalis, Allium sativum, Curcuma longa and Adhatoda vasica was constructed and was used under present study. In silico analysis was employed with plant-derived phytochemicals. The molecular docking, molecular dynamics simulations over the scale of 1000 ns (1 μs) and ADMET prediction revealed that the Withania somnifera (ashwagandha) and Asparagus racemosus (shatavari) plants possessed various steroidal saponins and alkaloids which could potentially inhibit the COVID-19 virus and even other CoVs targeted HE glycoprotein receptor.
Collapse
Affiliation(s)
- Chirag N Patel
- Department of Botany, Bioinformatics, and Climate Change Impacts Management, School of Sciences, Gujarat University, Ahmedabad, Gujarat, India
| | - Dweipayan Goswami
- Department of Microbiology & Biotechnology, School of Sciences, Gujarat University, Ahmedabad, Gujarat, India
| | - Dharmesh G Jaiswal
- Department of Zoology, School of Sciences, Gujarat University, Ahmedabad, Gujarat, India
| | - Siddhi P Jani
- Department of Botany, Bioinformatics, and Climate Change Impacts Management, School of Sciences, Gujarat University, Ahmedabad, Gujarat, India
| | - Robin M Parmar
- Department of Zoology, School of Sciences, Gujarat University, Ahmedabad, Gujarat, India
| | - Rakesh M Rawal
- Department of Life Science, School of Sciences, Gujarat University, Ahmedabad, Gujarat, India
| | - Himanshu A Pandya
- Department of Botany, Bioinformatics, and Climate Change Impacts Management, School of Sciences, Gujarat University, Ahmedabad, Gujarat, India
| |
Collapse
|
6
|
Bukhdruker S, Varaksa T, Grabovec I, Marin E, Shabunya P, Kadukova M, Grudinin S, Kavaleuski A, Gusach A, Gilep A, Borshchevskiy V, Strushkevich N. Hydroxylation of Antitubercular Drug Candidate, SQ109, by Mycobacterial Cytochrome P450. Int J Mol Sci 2020; 21:E7683. [PMID: 33081390 PMCID: PMC7589583 DOI: 10.3390/ijms21207683] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/05/2020] [Revised: 10/12/2020] [Accepted: 10/14/2020] [Indexed: 01/04/2023] Open
Abstract
Spreading of the multidrug-resistant (MDR) strains of the one of the most harmful pathogen Mycobacterium tuberculosis (Mtb) generates the need for new effective drugs. SQ109 showed activity against resistant Mtb and already advanced to Phase II/III clinical trials. Fast SQ109 degradation is attributed to the human liver Cytochrome P450s (CYPs). However, no information is available about interactions of the drug with Mtb CYPs. Here, we show that Mtb CYP124, previously assigned as a methyl-branched lipid monooxygenase, binds and hydroxylates SQ109 in vitro. A 1.25 Å-resolution crystal structure of the CYP124-SQ109 complex unambiguously shows two conformations of the drug, both positioned for hydroxylation of the ω-methyl group in the trans position. The hydroxylated SQ109 presumably forms stabilizing H-bonds with its target, Mycobacterial membrane protein Large 3 (MmpL3). We anticipate that Mtb CYPs could function as analogs of drug-metabolizing human CYPs affecting pharmacokinetics and pharmacodynamics of antitubercular (anti-TB) drugs.
Collapse
Affiliation(s)
- Sergey Bukhdruker
- Research Center for Molecular Mechanisms of Aging and Age-Related Diseases, Moscow Institute of Physics and Technology, 141701 Dolgoprudny, Russia; (S.B.); (E.M.); (M.K.); (A.G.)
- Institute of Biological Information Processing (IBI-7: Structural Biochemistry), Research Center Jülich, 52428 Jülich, Germany
- JuStruct: Jülich Center for Structural Biology, Research Center Jülich, 52428 Jülich, Germany
| | - Tatsiana Varaksa
- Institute of Bioorganic Chemistry, National Academy of Sciences of Belarus, 220141 Minsk, Belarus; (T.V.); (I.G.); (P.S.); (A.K.); (A.G.)
| | - Irina Grabovec
- Institute of Bioorganic Chemistry, National Academy of Sciences of Belarus, 220141 Minsk, Belarus; (T.V.); (I.G.); (P.S.); (A.K.); (A.G.)
| | - Egor Marin
- Research Center for Molecular Mechanisms of Aging and Age-Related Diseases, Moscow Institute of Physics and Technology, 141701 Dolgoprudny, Russia; (S.B.); (E.M.); (M.K.); (A.G.)
| | - Polina Shabunya
- Institute of Bioorganic Chemistry, National Academy of Sciences of Belarus, 220141 Minsk, Belarus; (T.V.); (I.G.); (P.S.); (A.K.); (A.G.)
| | - Maria Kadukova
- Research Center for Molecular Mechanisms of Aging and Age-Related Diseases, Moscow Institute of Physics and Technology, 141701 Dolgoprudny, Russia; (S.B.); (E.M.); (M.K.); (A.G.)
- Grenoble Alpes University, CNRS, Inria, Grenoble INP, LJK, 38000 Grenoble, France;
| | - Sergei Grudinin
- Grenoble Alpes University, CNRS, Inria, Grenoble INP, LJK, 38000 Grenoble, France;
| | - Anton Kavaleuski
- Institute of Bioorganic Chemistry, National Academy of Sciences of Belarus, 220141 Minsk, Belarus; (T.V.); (I.G.); (P.S.); (A.K.); (A.G.)
| | - Anastasiia Gusach
- Research Center for Molecular Mechanisms of Aging and Age-Related Diseases, Moscow Institute of Physics and Technology, 141701 Dolgoprudny, Russia; (S.B.); (E.M.); (M.K.); (A.G.)
| | - Andrei Gilep
- Institute of Bioorganic Chemistry, National Academy of Sciences of Belarus, 220141 Minsk, Belarus; (T.V.); (I.G.); (P.S.); (A.K.); (A.G.)
- Department of Proteomic Research and Mass Spectrometry, Institute of Biomedical Chemistry, 119435 Moscow, Russia
- R&D Department, MT-Medicals LLC, 121205 Moscow, Russia
| | - Valentin Borshchevskiy
- Research Center for Molecular Mechanisms of Aging and Age-Related Diseases, Moscow Institute of Physics and Technology, 141701 Dolgoprudny, Russia; (S.B.); (E.M.); (M.K.); (A.G.)
- Institute of Biological Information Processing (IBI-7: Structural Biochemistry), Research Center Jülich, 52428 Jülich, Germany
- JuStruct: Jülich Center for Structural Biology, Research Center Jülich, 52428 Jülich, Germany
| | - Natallia Strushkevich
- Institute of Bioorganic Chemistry, National Academy of Sciences of Belarus, 220141 Minsk, Belarus; (T.V.); (I.G.); (P.S.); (A.K.); (A.G.)
- Center for Computational and Data-Intensive Science and Engineering (CDISE), Skolkovo Institute of Science and Technology, 121205 Moscow, Russia
| |
Collapse
|