Interpretable Machine Learning of Two‐Photon Absorption
Abstract Molecules with strong two‐photon absorption (TPA) are important in many advanced applications such as upconverted laser and photodynamic therapy, but their design is hampered by the high cost of experimental screening and accurate quantum chemical (QC) calculations. Here a systematic study...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-03-01
|
| Series: | Advanced Science |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/advs.202204902 |
| _version_ | 1827989665312931840 |
|---|---|
| author | Yuming Su Yiheng Dai Yifan Zeng Caiyun Wei Yangtao Chen Fuchun Ge Peikun Zheng Da Zhou Pavlo O. Dral Cheng Wang |
| author_facet | Yuming Su Yiheng Dai Yifan Zeng Caiyun Wei Yangtao Chen Fuchun Ge Peikun Zheng Da Zhou Pavlo O. Dral Cheng Wang |
| author_sort | Yuming Su |
| collection | DOAJ |
| description | Abstract Molecules with strong two‐photon absorption (TPA) are important in many advanced applications such as upconverted laser and photodynamic therapy, but their design is hampered by the high cost of experimental screening and accurate quantum chemical (QC) calculations. Here a systematic study is performed by collecting an experimental TPA database with ≈900 molecules, analyzing with interpretable machine learning (ML) the key molecular features explaining TPA magnitudes, and building a fast ML model for predictions. The ML model has prediction errors of similar magnitude compared to experimental and affordable QC methods errors and has the potential for high‐throughput screening as additionally validated with the new experimental measurements. ML feature analysis is generally consistent with common beliefs which is quantified and rectified. The most important feature is conjugation length followed by features reflecting the effects of donor and acceptor substitution and coplanarity. |
| first_indexed | 2024-04-10T00:23:56Z |
| format | Article |
| id | doaj.art-1b7d4cb83504495ba9507aee341c0a6f |
| institution | Directory Open Access Journal |
| issn | 2198-3844 |
| language | English |
| last_indexed | 2024-04-10T00:23:56Z |
| publishDate | 2023-03-01 |
| publisher | Wiley |
| record_format | Article |
| series | Advanced Science |
| spelling | doaj.art-1b7d4cb83504495ba9507aee341c0a6f2023-03-15T13:19:15ZengWileyAdvanced Science2198-38442023-03-01108n/an/a10.1002/advs.202204902Interpretable Machine Learning of Two‐Photon AbsorptionYuming Su0Yiheng Dai1Yifan Zeng2Caiyun Wei3Yangtao Chen4Fuchun Ge5Peikun Zheng6Da Zhou7Pavlo O. Dral8Cheng Wang9State Key Laboratory of Physical Chemistry of Solid Surfaces Department of Chemistry College of Chemistry and Chemical Engineering, iChem Innovation Laboratory for Sciences and Technologies of Energy Materials of Fujian Province (IKKEM) Xiamen University 361005 Xiamen P. R. ChinaState Key Laboratory of Physical Chemistry of Solid Surfaces Department of Chemistry College of Chemistry and Chemical Engineering, iChem Innovation Laboratory for Sciences and Technologies of Energy Materials of Fujian Province (IKKEM) Xiamen University 361005 Xiamen P. R. ChinaState Key Laboratory of Physical Chemistry of Solid Surfaces Department of Chemistry College of Chemistry and Chemical Engineering, iChem Innovation Laboratory for Sciences and Technologies of Energy Materials of Fujian Province (IKKEM) Xiamen University 361005 Xiamen P. R. ChinaState Key Laboratory of Physical Chemistry of Solid Surfaces Department of Chemistry College of Chemistry and Chemical Engineering, iChem Innovation Laboratory for Sciences and Technologies of Energy Materials of Fujian Province (IKKEM) Xiamen University 361005 Xiamen P. R. ChinaState Key Laboratory of Physical Chemistry of Solid Surfaces Department of Chemistry College of Chemistry and Chemical Engineering, iChem Innovation Laboratory for Sciences and Technologies of Energy Materials of Fujian Province (IKKEM) Xiamen University 361005 Xiamen P. R. ChinaDepartment of Chemistry College of Chemistry and Chemical Engineering iChem Xiamen University Fujian Provincial Key Laboratory of Theoretical and Computational Chemistry Xiamen University 361005 Xiamen P. R. ChinaDepartment of Chemistry College of Chemistry and Chemical Engineering iChem Xiamen University Fujian Provincial Key Laboratory of Theoretical and Computational Chemistry Xiamen University 361005 Xiamen P. R. ChinaSchool of Mathematical Sciences and Fujian Provincial Key Laboratory of Mathematical Modeling and High‐Performance Scientific Computation Xiamen University Xiamen 361005 P. R. ChinaDepartment of Chemistry College of Chemistry and Chemical Engineering iChem Xiamen University Fujian Provincial Key Laboratory of Theoretical and Computational Chemistry Xiamen University 361005 Xiamen P. R. ChinaState Key Laboratory of Physical Chemistry of Solid Surfaces Department of Chemistry College of Chemistry and Chemical Engineering, iChem Innovation Laboratory for Sciences and Technologies of Energy Materials of Fujian Province (IKKEM) Xiamen University 361005 Xiamen P. R. ChinaAbstract Molecules with strong two‐photon absorption (TPA) are important in many advanced applications such as upconverted laser and photodynamic therapy, but their design is hampered by the high cost of experimental screening and accurate quantum chemical (QC) calculations. Here a systematic study is performed by collecting an experimental TPA database with ≈900 molecules, analyzing with interpretable machine learning (ML) the key molecular features explaining TPA magnitudes, and building a fast ML model for predictions. The ML model has prediction errors of similar magnitude compared to experimental and affordable QC methods errors and has the potential for high‐throughput screening as additionally validated with the new experimental measurements. ML feature analysis is generally consistent with common beliefs which is quantified and rectified. The most important feature is conjugation length followed by features reflecting the effects of donor and acceptor substitution and coplanarity.https://doi.org/10.1002/advs.202204902conjugation lengthmachine learningrational designtwo‐photon absorption |
| spellingShingle | Yuming Su Yiheng Dai Yifan Zeng Caiyun Wei Yangtao Chen Fuchun Ge Peikun Zheng Da Zhou Pavlo O. Dral Cheng Wang Interpretable Machine Learning of Two‐Photon Absorption Advanced Science conjugation length machine learning rational design two‐photon absorption |
| title | Interpretable Machine Learning of Two‐Photon Absorption |
| title_full | Interpretable Machine Learning of Two‐Photon Absorption |
| title_fullStr | Interpretable Machine Learning of Two‐Photon Absorption |
| title_full_unstemmed | Interpretable Machine Learning of Two‐Photon Absorption |
| title_short | Interpretable Machine Learning of Two‐Photon Absorption |
| title_sort | interpretable machine learning of two photon absorption |
| topic | conjugation length machine learning rational design two‐photon absorption |
| url | https://doi.org/10.1002/advs.202204902 |
| work_keys_str_mv | AT yumingsu interpretablemachinelearningoftwophotonabsorption AT yihengdai interpretablemachinelearningoftwophotonabsorption AT yifanzeng interpretablemachinelearningoftwophotonabsorption AT caiyunwei interpretablemachinelearningoftwophotonabsorption AT yangtaochen interpretablemachinelearningoftwophotonabsorption AT fuchunge interpretablemachinelearningoftwophotonabsorption AT peikunzheng interpretablemachinelearningoftwophotonabsorption AT dazhou interpretablemachinelearningoftwophotonabsorption AT pavloodral interpretablemachinelearningoftwophotonabsorption AT chengwang interpretablemachinelearningoftwophotonabsorption |