Ollivier persistent Ricci curvature-based machine learning for the protein-ligand binding affinity prediction
Efficient molecular featurization is one of the major issues for machine learning models in drug design. Here, we propose a persistent Ricci curvature (PRC), in particular, Ollivier PRC (OPRC), for the molecular featurization and feature engineering, for the first time. The filtration process propos...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/160294 |
| _version_ | 1811688690459607040 |
|---|---|
| author | Wee, Junjie Xia, Kelin |
| author2 | School of Physical and Mathematical Sciences |
| author_facet | School of Physical and Mathematical Sciences Wee, Junjie Xia, Kelin |
| author_sort | Wee, Junjie |
| collection | NTU |
| description | Efficient molecular featurization is one of the major issues for machine learning models in drug design. Here, we propose a persistent Ricci curvature (PRC), in particular, Ollivier PRC (OPRC), for the molecular featurization and feature engineering, for the first time. The filtration process proposed in the persistent homology is employed to generate a series of nested molecular graphs. Persistence and variation of Ollivier Ricci curvatures on these nested graphs are defined as OPRC. Moreover, persistent attributes, which are statistical and combinatorial properties of OPRCs during the filtration process, are used as molecular descriptors and further combined with machine learning models, in particular, gradient boosting tree (GBT). Our OPRC-GBT model is used in the prediction of the protein-ligand binding affinity, which is one of the key steps in drug design. Based on three of the most commonly used data sets from the well-established protein-ligand binding databank, that is, PDBbind, we intensively test our model and compare with existing models. It has been found that our model can achieve the state-of-the-art results and has advantages over traditional molecular descriptors. |
| first_indexed | 2024-10-01T05:36:13Z |
| format | Journal Article |
| id | ntu-10356/160294 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T05:36:13Z |
| publishDate | 2022 |
| record_format | dspace |
| spelling | ntu-10356/1602942022-07-19T01:51:49Z Ollivier persistent Ricci curvature-based machine learning for the protein-ligand binding affinity prediction Wee, Junjie Xia, Kelin School of Physical and Mathematical Sciences Science::Mathematics Metric-Measure-Spaces Aided Drug Design Efficient molecular featurization is one of the major issues for machine learning models in drug design. Here, we propose a persistent Ricci curvature (PRC), in particular, Ollivier PRC (OPRC), for the molecular featurization and feature engineering, for the first time. The filtration process proposed in the persistent homology is employed to generate a series of nested molecular graphs. Persistence and variation of Ollivier Ricci curvatures on these nested graphs are defined as OPRC. Moreover, persistent attributes, which are statistical and combinatorial properties of OPRCs during the filtration process, are used as molecular descriptors and further combined with machine learning models, in particular, gradient boosting tree (GBT). Our OPRC-GBT model is used in the prediction of the protein-ligand binding affinity, which is one of the key steps in drug design. Based on three of the most commonly used data sets from the well-established protein-ligand binding databank, that is, PDBbind, we intensively test our model and compare with existing models. It has been found that our model can achieve the state-of-the-art results and has advantages over traditional molecular descriptors. Ministry of Education (MOE) Nanyang Technological University This work was supported in part by Nanyang Technological University Startup Grant M4081842.110, Singapore Ministry of Education Academic Research fund Tier 1 RG109/19 and Tier 2 MOE2018-T2-1-033. 2022-07-19T01:51:49Z 2022-07-19T01:51:49Z 2021 Journal Article Wee, J. & Xia, K. (2021). Ollivier persistent Ricci curvature-based machine learning for the protein-ligand binding affinity prediction. Journal of Chemical Information and Modeling, 61(4), 1617-1626. https://dx.doi.org/10.1021/acs.jcim.0c01415 1549-9596 https://hdl.handle.net/10356/160294 10.1021/acs.jcim.0c01415 33724038 2-s2.0-85103780511 4 61 1617 1626 en M4081842.110 RG109/19 MOE2018-T2-1-033 Journal of Chemical Information and Modeling © 2021 American Chemical Society. All rights reserved. |
| spellingShingle | Science::Mathematics Metric-Measure-Spaces Aided Drug Design Wee, Junjie Xia, Kelin Ollivier persistent Ricci curvature-based machine learning for the protein-ligand binding affinity prediction |
| title | Ollivier persistent Ricci curvature-based machine learning for the protein-ligand binding affinity prediction |
| title_full | Ollivier persistent Ricci curvature-based machine learning for the protein-ligand binding affinity prediction |
| title_fullStr | Ollivier persistent Ricci curvature-based machine learning for the protein-ligand binding affinity prediction |
| title_full_unstemmed | Ollivier persistent Ricci curvature-based machine learning for the protein-ligand binding affinity prediction |
| title_short | Ollivier persistent Ricci curvature-based machine learning for the protein-ligand binding affinity prediction |
| title_sort | ollivier persistent ricci curvature based machine learning for the protein ligand binding affinity prediction |
| topic | Science::Mathematics Metric-Measure-Spaces Aided Drug Design |
| url | https://hdl.handle.net/10356/160294 |
| work_keys_str_mv | AT weejunjie ollivierpersistentriccicurvaturebasedmachinelearningfortheproteinligandbindingaffinityprediction AT xiakelin ollivierpersistentriccicurvaturebasedmachinelearningfortheproteinligandbindingaffinityprediction |