Molecular dynamics and machine learning unlock possibilities in beauty design—A perspective
Computational molecular design—the endeavor to design molecules, with various missions, aided by machine learning and molecular dynamics approaches—has been widely applied to create valuable new molecular entities, from small molecule therapeutics to protein biologics. In the small data regime, phys...
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIP Publishing LLC
2025-01-01
|
| Series: | AIP Advances |
| Online Access: | http://dx.doi.org/10.1063/5.0245365 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832542797177028608 |
|---|---|
| author | Yuzhi Xu Haowei Ni Fanyu Zhao Qinhui Gao Ziqing Zhao Chia-Hua Chang Yanran Huo Shiyu Hu Yike Zhang Radu Grovu Hermione He John Z. H. Zhang Yuanqing Wang |
| author_facet | Yuzhi Xu Haowei Ni Fanyu Zhao Qinhui Gao Ziqing Zhao Chia-Hua Chang Yanran Huo Shiyu Hu Yike Zhang Radu Grovu Hermione He John Z. H. Zhang Yuanqing Wang |
| author_sort | Yuzhi Xu |
| collection | DOAJ |
| description | Computational molecular design—the endeavor to design molecules, with various missions, aided by machine learning and molecular dynamics approaches—has been widely applied to create valuable new molecular entities, from small molecule therapeutics to protein biologics. In the small data regime, physics-based approaches model the interaction between the molecule being designed and proteins of key physiological functions, providing structural insights into the mechanism. When abundant data have been collected, a quantitative structure–activity relationship can be more directly constructed from experimental data, from which machine learning can distill key insights to guide the design of the next round of experiment design. Machine learning methodologies can also facilitate physical modeling, from improving the accuracy of force fields and extending them to unseen chemical spaces to more directly enhancing the sampling on the conformational spaces. We argue that these techniques are mature enough to be applied to not just extend the longevity of life but the beauty it manifests. In this Perspective, we review the current frontiers in the research and development of skincare products, as well as the statistical and physical toolbox applicable to addressing the challenges in this industry. Feasible interdisciplinary research projects are proposed to harness the power of machine learning tools to design innovative, effective, and inexpensive skincare products. |
| format | Article |
| id | doaj-art-d2565e0f1f2842999ae5f09925f47039 |
| institution | Kabale University |
| issn | 2158-3226 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | AIP Publishing LLC |
| record_format | Article |
| series | AIP Advances |
| spelling | doaj-art-d2565e0f1f2842999ae5f09925f470392025-02-03T16:40:41ZengAIP Publishing LLCAIP Advances2158-32262025-01-01151010601010601-1210.1063/5.0245365Molecular dynamics and machine learning unlock possibilities in beauty design—A perspectiveYuzhi Xu0Haowei Ni1Fanyu Zhao2Qinhui Gao3Ziqing Zhao4Chia-Hua Chang5Yanran Huo6Shiyu Hu7Yike Zhang8Radu Grovu9Hermione He10John Z. H. Zhang11Yuanqing Wang12Simons Center for Computational Physical Chemistry, New York, New York 10003, USASimons Center for Computational Physical Chemistry, New York, New York 10003, USAShanghai Frontiers Science Center of Artificial Intelligence and Deep Learning and NYU-ECNU Center for Computational Chemistry, NYU Shanghai, Shanghai 200062, People’s Republic of ChinaDepartment of Digital Humanities, King’s College London, Strand, London WC2R 2LS, United KingdomDepartment of Chemistry, New York University, New York, New York 10003, USADepartment of Chemistry, New York University, New York, New York 10003, USADepartment of Chemistry, New York University, New York, New York 10003, USAShanghai Frontiers Science Center of Artificial Intelligence and Deep Learning and NYU-ECNU Center for Computational Chemistry, NYU Shanghai, Shanghai 200062, People’s Republic of ChinaDivision of Cardiology, The First Affiliated Hospital of Nanjing Medical University, Nanjing 210029, People’s Republic of ChinaInternal Medicine Department, Rhode Island Hospital, Brown University Health, Providence, Rhode Island 02903, USAXbiome, Inc., Cambridge, Massachusetts 01451, USADepartment of Chemistry, New York University, New York, New York 10003, USASimons Center for Computational Physical Chemistry, New York, New York 10003, USAComputational molecular design—the endeavor to design molecules, with various missions, aided by machine learning and molecular dynamics approaches—has been widely applied to create valuable new molecular entities, from small molecule therapeutics to protein biologics. In the small data regime, physics-based approaches model the interaction between the molecule being designed and proteins of key physiological functions, providing structural insights into the mechanism. When abundant data have been collected, a quantitative structure–activity relationship can be more directly constructed from experimental data, from which machine learning can distill key insights to guide the design of the next round of experiment design. Machine learning methodologies can also facilitate physical modeling, from improving the accuracy of force fields and extending them to unseen chemical spaces to more directly enhancing the sampling on the conformational spaces. We argue that these techniques are mature enough to be applied to not just extend the longevity of life but the beauty it manifests. In this Perspective, we review the current frontiers in the research and development of skincare products, as well as the statistical and physical toolbox applicable to addressing the challenges in this industry. Feasible interdisciplinary research projects are proposed to harness the power of machine learning tools to design innovative, effective, and inexpensive skincare products.http://dx.doi.org/10.1063/5.0245365 |
| spellingShingle | Yuzhi Xu Haowei Ni Fanyu Zhao Qinhui Gao Ziqing Zhao Chia-Hua Chang Yanran Huo Shiyu Hu Yike Zhang Radu Grovu Hermione He John Z. H. Zhang Yuanqing Wang Molecular dynamics and machine learning unlock possibilities in beauty design—A perspective AIP Advances |
| title | Molecular dynamics and machine learning unlock possibilities in beauty design—A perspective |
| title_full | Molecular dynamics and machine learning unlock possibilities in beauty design—A perspective |
| title_fullStr | Molecular dynamics and machine learning unlock possibilities in beauty design—A perspective |
| title_full_unstemmed | Molecular dynamics and machine learning unlock possibilities in beauty design—A perspective |
| title_short | Molecular dynamics and machine learning unlock possibilities in beauty design—A perspective |
| title_sort | molecular dynamics and machine learning unlock possibilities in beauty design a perspective |
| url | http://dx.doi.org/10.1063/5.0245365 |
| work_keys_str_mv | AT yuzhixu moleculardynamicsandmachinelearningunlockpossibilitiesinbeautydesignaperspective AT haoweini moleculardynamicsandmachinelearningunlockpossibilitiesinbeautydesignaperspective AT fanyuzhao moleculardynamicsandmachinelearningunlockpossibilitiesinbeautydesignaperspective AT qinhuigao moleculardynamicsandmachinelearningunlockpossibilitiesinbeautydesignaperspective AT ziqingzhao moleculardynamicsandmachinelearningunlockpossibilitiesinbeautydesignaperspective AT chiahuachang moleculardynamicsandmachinelearningunlockpossibilitiesinbeautydesignaperspective AT yanranhuo moleculardynamicsandmachinelearningunlockpossibilitiesinbeautydesignaperspective AT shiyuhu moleculardynamicsandmachinelearningunlockpossibilitiesinbeautydesignaperspective AT yikezhang moleculardynamicsandmachinelearningunlockpossibilitiesinbeautydesignaperspective AT radugrovu moleculardynamicsandmachinelearningunlockpossibilitiesinbeautydesignaperspective AT hermionehe moleculardynamicsandmachinelearningunlockpossibilitiesinbeautydesignaperspective AT johnzhzhang moleculardynamicsandmachinelearningunlockpossibilitiesinbeautydesignaperspective AT yuanqingwang moleculardynamicsandmachinelearningunlockpossibilitiesinbeautydesignaperspective |