1
|
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
|
2
|
Hamadouche S, Merouani H, May AA, Ouddai N, Alam M, Micoli L, Erto A, Benguerba Y. Theoretical Exploration of Enhanced Antioxidant Activity in Copper Complexes of Tetrahydroxystilbenes: Insights into Mechanisms and Molecular Interactions. ACS OMEGA 2024; 9:9076-9089. [PMID: 38434904 PMCID: PMC10906065 DOI: 10.1021/acsomega.3c07885] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 10/09/2023] [Revised: 01/25/2024] [Accepted: 01/29/2024] [Indexed: 03/05/2024]
Abstract
A theoretical investigation was conducted using DFT/PW91/TZP/DMSO calculations on a complete set of exhaustive lists of 18 compounds resulting from the complexation of trans-2,4,3',5'-tetrahydroxystilbene (T-OXY) and cis-2,4,1',3'-tetrahydroxystilbene (C-OXY) with copper metal cations (Cu+ and Cu2+). The ligand-binding sites are the critical points of Quantum Theory of Atoms in Molecules (QTAIM) analysis on neutral and deprotonated ligands. Various mechanisms, including hydrogen atom transfer (HAT), sequential proton loss electron transfer (SPLET), single electron transfer followed by proton transfer (SET-PT), and bond dissociation energy (BDE(E0)) calculations, were employed to quantify the antioxidant activity. The BDE(E0) mechanism emerged as the most suitable approach for such analyses to evaluate the departure of hydrogen atoms since the results show the HAT mechanism is the most likely occurring. Particularly intriguing were the anionic Cu+ complexes with ligands adopting trans configurations and deprotonated conformations, displaying superior antioxidant activity compared to their counterparts. Remarkably, a single ligand within the Cu+ complex exhibited exceptional antioxidant prowess, yielding a BDE(E0) value of 91.47 kcal/mol. Furthermore, a complex involving two deprotonated ligands demonstrated antioxidant activity of 31.12 kcal/mol, signifying its potential as a potent antiradical agent, surpassing T-OXY by a factor of 3.91 and even surpassing the antioxidant efficiency of Vitamin C.
Collapse
Affiliation(s)
- Salima Hamadouche
- Laboratoire
de Chimie des Matériaux et des Vivants: Activité &
Réactivité (LCMVAR), Université
Batna 1, 5000 Batna, Algeria
| | - Hafida Merouani
- Laboratoire
de Chimie des Matériaux et des Vivants: Activité &
Réactivité (LCMVAR), Université
Batna 1, 5000 Batna, Algeria
- Département
de Socle Commun, Faculté de Technologie, Université Ben Boulaid Batna 2, 05078 Batna, Algeria
| | - Abd Alghani May
- Département
de Chimie, Faculté des Sciences Exacte, Université Frères Mentouri 1, 25017 Constantine, Algeria
| | - Nadia Ouddai
- Laboratoire
de Chimie des Matériaux et des Vivants: Activité &
Réactivité (LCMVAR), Université
Batna 1, 5000 Batna, Algeria
| | - Manawwer Alam
- Department
of Chemistry, College of Science, King Saud
University, P.O. Box 2455, Riyadh 11451, Saudi Arabia
| | - Luca Micoli
- Dipartimento
di Ingegneria Chimica, dei Materiali e della Produzione Industriale, Università di Napoli Federico II, P.le Tecchio, 80, 80125 Napoli, Italy
| | - Alessandro Erto
- Dipartimento
di Ingegneria Industriale, Università
di Napoli Federico II, P.le Tecchio, 80, 80125 Napoli, Italy
| | - Yacine Benguerba
- Laboratoire
de Biopharmacie and Pharmacotechnie (LBPt), Department of Process
Engineering, Faculty of Technology, Ferhat
Abbas Setif 1 University, 19000 Setif, Algeria
| |
Collapse
|
3
|
Li W, Yang Y, Xi X, Feng J. Hydrophilic Modification of Polylactic Acid Fiber and the Usage of Natural Dye for Multi-Levered Improvement of the Fabric Staining Depth and the Stability Effect. LANGMUIR : THE ACS JOURNAL OF SURFACES AND COLLOIDS 2024. [PMID: 38315682 DOI: 10.1021/acs.langmuir.3c03721] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/07/2024]
Abstract
Polylactic acid (PLA) fiber is a degradable material with good environmental friendliness for textile applications. However, the main problems of difficult dyeing of PLA fibers were: high crystallinity to the adsorption of dyes, more ester and methyl groups producing non-hydrophilic problems, long chains making dyes difficult to penetrate, and producing a low dyeing rate. Here, we attempted to change the crystallinity of the PLA fiber to a lower degree from hydrophobic to hydrophilicity property variation, destroy the long chain structure to grant more staining sites, and improve the PLA fiber staining depth and the resilience dyeing effect with deep eutectic solvent (DES) treatment and natural dyes. We discovered that a controlled DES treatment process could make PLA fibers less crystallized, help amorphous areas form, and break up long chains, which lead to more dye sites. After DES treatment, the crystallinity decreased from 56.12 to 29.86%, and the instantaneous water contact angle decreased from 108.79 to 64.39°. The DES-treated PLA fabric exhibited a higher K/S value of 15.14 for natural dyes under specific conditions. The fabric, which had remarkable fastness characteristics and wash resistance, could endure frequent laundering and fulfill the demands of everyday use. Moreover, the fabric had good antimicrobial activity against Escherichia coli, Staphylococcus aureus, and Candida albicans and possessed a certain level of biocompatibility with fibroblasts. This DES treatment and natural dye combination method offered a new strategy for improving PLA fabric staining depth and color fastness, making it a promising option for low-carbon environmental protection in the textile industry.
Collapse
Affiliation(s)
- Wei Li
- College of Textile Science and Engineering (International Institute of Silk), Zhejiang Sci-Tech University, No. 928, Second Street, Xiasha Higher Education Zone, Hangzhou 310018, China
| | - Ying Yang
- State Key Laboratory for Diagnosis and Treatment of Infectious Diseases, the First Affiliated Hospital, Zhejiang University School of Medicine, No. 79, Qingchun Road, Shangcheng District, Hangzhou 310000, China
| | - Xiaoqing Xi
- Key Laboratory of Safety Evaluation of Medical Devices of Zhejiang Province, No. 379, 25th Avenue, Qiantang District, Hangzhou 310018, China
| | - Jianyong Feng
- College of Textile Science and Engineering (International Institute of Silk), Zhejiang Sci-Tech University, No. 928, Second Street, Xiasha Higher Education Zone, Hangzhou 310018, China
- Cavendish Laboratory, University of Cambridge, J. J. Thomson Avenue, Cambridge CB3 0HE, U.K
- Key Laboratory of Intelligent Textile and Flexible Interconnection of Zhejiang Province, Hangzhou 310018, China
| |
Collapse
|
4
|
Mittal A, Nagpal M, Vashistha VK, Arora R, Issar U. Recent advances in the antioxidant activity of metal-curcumin complexes: a combined computational and experimental review. Free Radic Res 2024; 58:11-26. [PMID: 38145454 DOI: 10.1080/10715762.2023.2298857] [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: 08/21/2023] [Accepted: 12/01/2023] [Indexed: 12/26/2023]
Abstract
Curcumin, an extensively studied phytochemical compound, has gained attention for its potential therapeutic applications across a spectrum of diseases. Its notable attributes include its relatively high tolerability within the human body and its perceived absence of adverse side effects. This review article presents a comprehensive overview of the antioxidant effects exhibited by complexes formed by curcumin and curcumin derived ligands with metals like Mn, Cu, Fe, Zn, Ga and In, which leads to toxic effects beyond a certain limit, based on both experimental and theoretical findings. Additionally, the discussion delves into metal-curcumin complexes characterized by stoichiometries of 1:1 and 1:2, exploring their geometric arrangements and corresponding antioxidant activity, as highlighted in recent studies. These complexes hold the promise of improving curcumin's solubility, stability, and bioavailability, potentially augmenting its overall therapeutic potential and expanding its scope for medical applications.
Collapse
Affiliation(s)
- Ankit Mittal
- Department of Chemistry, Shyam Lal College, University of Delhi, Delhi, India
| | - Mudita Nagpal
- School of Engineering and Technology, Vivekananda Institute of Professional Studies - Technical Campus, Delhi, India
| | - Vinod Kumar Vashistha
- Department of Chemistry, Institute of Applied Sciences and Humanities, GLA University, Mathura, India
| | - Richa Arora
- Department of Chemistry, Shivaji College, University of Delhi, Delhi, India
| | - Upasana Issar
- Department of Chemistry, Kalindi College, University of Delhi, Delhi, India
| |
Collapse
|