Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/151043
Full metadata record
DC FieldValueLanguage
dc.contributor.authorMeng, Zhenyuen_US
dc.contributor.authorXia, Kelinen_US
dc.date.accessioned2021-06-25T06:29:40Z-
dc.date.available2021-06-25T06:29:40Z-
dc.date.issued2021-
dc.identifier.citationMeng, Z. & Xia, K. (2021). Persistent spectral-based machine learning (PerSpect ML) for protein-ligand binding affinity prediction. Science Advances, 7(19), eabc5329-. https://dx.doi.org/10.1126/sciadv.abc5329en_US
dc.identifier.issn2375-2548en_US
dc.identifier.urihttps://hdl.handle.net/10356/151043-
dc.description.abstractMolecular descriptors are essential to not only quantitative structure-activity relationship (QSAR) models but also machine learning–based material, chemical, and biological data analysis. Here, we propose persistent spectral–based machine learning (PerSpect ML) models for drug design. Different from all previous spectral models, a filtration process is introduced to generate a sequence of spectral models at various different scales. PerSpect attributes are defined as the function of spectral variables over the filtration value. Molecular descriptors obtained from PerSpect attributes are combined with machine learning models for protein-ligand binding affinity prediction. Our results, for the three most commonly used databases including PDBbind-2007, PDBbind-2013, and PDBbind-2016, are better than all existing models, as far as we know. The proposed PerSpect theory provides a powerful feature engineering framework. PerSpect ML models demonstrate great potential to significantly improve the performance of learning models in molecular data analysis.en_US
dc.description.sponsorshipMinistry of Education (MOE)en_US
dc.description.sponsorshipNanyang Technological Universityen_US
dc.language.isoenen_US
dc.relationM4081842.110en_US
dc.relationRG109/19en_US
dc.relationMOE2018-T2-1-033en_US
dc.relation.ispartofScience Advancesen_US
dc.rights© 2021 The Authors, some rights reserved; exclusive licensee American Association for the Advancement of Science. No claim to original U.S. Government Works. Distributed under a Creative Commons Attribution NonCommercial License 4.0 (CC BY-NC).en_US
dc.subjectScience::Biological sciencesen_US
dc.titlePersistent spectral-based machine learning (PerSpect ML) for protein-ligand binding affinity predictionen_US
dc.typeJournal Articleen
dc.contributor.schoolSchool of Physical and Mathematical Sciencesen_US
dc.identifier.doi10.1126/sciadv.abc5329-
dc.description.versionPublished versionen_US
dc.identifier.pmid33962954-
dc.identifier.scopus2-s2.0-85105653469-
dc.identifier.issue19en_US
dc.identifier.volume7en_US
dc.identifier.spageeabc5329en_US
dc.subject.keywordsBinding Energyen_US
dc.subject.keywordsChemical Analysisen_US
dc.description.acknowledgementThis work was supported, in part, by Nanyang Technological University Startup Grant M4081842.110 and Singapore Ministry of Education Academic Research Fund Tier 1 RG109/19 and Tier 2 MOE2018-T2-1-033.en_US
item.fulltextWith Fulltext-
item.grantfulltextopen-
Appears in Collections:SPMS Journal Articles
Files in This Item:
File Description SizeFormat 
11.pdf4.2 MBAdobe PDFThumbnail
View/Open

SCOPUSTM   
Citations 5

82
Updated on Mar 24, 2024

Web of ScienceTM
Citations 5

58
Updated on Oct 25, 2023

Page view(s)

185
Updated on Mar 28, 2024

Download(s) 20

223
Updated on Mar 28, 2024

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.