Persistent spectral-based machine learning (PerSpect ML) for protein-ligand binding affinity prediction

Persistent spectral-based machine learning (PerSpect ML) for protein-ligand binding affinity prediction

Molecular 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 fro...

Full description

Saved in:
Bibliographic Details
Main Authors: Meng, Zhenyu, Xia, Kelin
Other Authors: School of Physical and Mathematical Sciences
Format: Article
Language:English
Published: 2021
Subjects:
Science::Biological sciences
Binding Energy
Chemical Analysis
Online Access:https://hdl.handle.net/10356/151043
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-151043
record_format dspace
spelling sg-ntu-dr.10356-1510432023-02-28T19:27:09Z Persistent spectral-based machine learning (PerSpect ML) for protein-ligand binding affinity prediction Meng, Zhenyu Xia, Kelin School of Physical and Mathematical Sciences Science::Biological sciences Binding Energy Chemical Analysis Molecular 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. Ministry of Education (MOE) Nanyang Technological University Published version This 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. 2021-06-25T06:29:40Z 2021-06-25T06:29:40Z 2021 Journal Article Meng, 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.abc5329 2375-2548 https://hdl.handle.net/10356/151043 10.1126/sciadv.abc5329 33962954 2-s2.0-85105653469 19 7 eabc5329 en M4081842.110 RG109/19 MOE2018-T2-1-033 Science Advances © 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). application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Science::Biological sciences
Binding Energy
Chemical Analysis
spellingShingle Science::Biological sciences
Binding Energy
Chemical Analysis
Meng, Zhenyu
Xia, Kelin
Persistent spectral-based machine learning (PerSpect ML) for protein-ligand binding affinity prediction
description Molecular 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.
author2 School of Physical and Mathematical Sciences
author_facet School of Physical and Mathematical Sciences
Meng, Zhenyu
Xia, Kelin
format Article
author Meng, Zhenyu
Xia, Kelin
author_sort Meng, Zhenyu
title Persistent spectral-based machine learning (PerSpect ML) for protein-ligand binding affinity prediction
title_short Persistent spectral-based machine learning (PerSpect ML) for protein-ligand binding affinity prediction
title_full Persistent spectral-based machine learning (PerSpect ML) for protein-ligand binding affinity prediction
title_fullStr Persistent spectral-based machine learning (PerSpect ML) for protein-ligand binding affinity prediction
title_full_unstemmed Persistent spectral-based machine learning (PerSpect ML) for protein-ligand binding affinity prediction
title_sort persistent spectral-based machine learning (perspect ml) for protein-ligand binding affinity prediction
publishDate 2021
url https://hdl.handle.net/10356/151043
_version_ 1759855047694352384

Similar Items