Quadratic descriptors and reduction methods in a two-layered model for compound inference
Compound inference models are crucial for discovering novel drugs in bioinformatics and chemo-informatics. These models rely heavily on useful descriptors of chemical compounds that effectively capture important information about the underlying compounds for constructing accurate prediction function...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Genetics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fgene.2024.1483490/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832582885684543488 |
|---|---|
| author | Jianshen Zhu Naveed Ahmed Azam Shengjuan Cao Ryota Ido Kazuya Haraguchi Liang Zhao Hiroshi Nagamochi Tatsuya Akutsu |
| author_facet | Jianshen Zhu Naveed Ahmed Azam Shengjuan Cao Ryota Ido Kazuya Haraguchi Liang Zhao Hiroshi Nagamochi Tatsuya Akutsu |
| author_sort | Jianshen Zhu |
| collection | DOAJ |
| description | Compound inference models are crucial for discovering novel drugs in bioinformatics and chemo-informatics. These models rely heavily on useful descriptors of chemical compounds that effectively capture important information about the underlying compounds for constructing accurate prediction functions. In this article, we introduce quadratic descriptors, the products of two graph-theoretic descriptors, to enhance the learning performance of a novel two-layered compound inference model. A mixed-integer linear programming formulation is designed to approximate these quadratic descriptors for inferring desired compounds with the two-layered model. Furthermore, we introduce different methods to reduce descriptors, aiming to avoid computational complexity and overfitting issues during the learning process caused by the large number of quadratic descriptors. Experimental results show that for 32 chemical properties of monomers and 10 chemical properties of polymers, the prediction functions constructed by the proposed method achieved high test coefficients of determination. Furthermore, our method inferred chemical compounds in a time ranging from a few seconds to approximately 60 s. These results indicate a strong correlation between the properties of chemical graphs and their quadratic graph-theoretic descriptors. |
| format | Article |
| id | doaj-art-d781f3f754334c82b2f06a9ae75f069d |
| institution | Kabale University |
| issn | 1664-8021 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Genetics |
| spelling | doaj-art-d781f3f754334c82b2f06a9ae75f069d2025-01-29T06:46:20ZengFrontiers Media S.A.Frontiers in Genetics1664-80212025-01-011510.3389/fgene.2024.14834901483490Quadratic descriptors and reduction methods in a two-layered model for compound inferenceJianshen Zhu0Naveed Ahmed Azam1Shengjuan Cao2Ryota Ido3Kazuya Haraguchi4Liang Zhao5Hiroshi Nagamochi6Tatsuya Akutsu7Department of Applied Mathematics and Physics, Graduate School of Informatics, Kyoto University, Kyoto, JapanDepartment of Mathematics, Quaid-i-Azam University, Islamabad, PakistanDepartment of Applied Mathematics and Physics, Graduate School of Informatics, Kyoto University, Kyoto, JapanDepartment of Applied Mathematics and Physics, Graduate School of Informatics, Kyoto University, Kyoto, JapanDepartment of Applied Mathematics and Physics, Graduate School of Informatics, Kyoto University, Kyoto, JapanGraduate School of Advanced Integrated Studies in Human Survivability (Shishu-Kan), Kyoto University, Kyoto, JapanDepartment of Applied Mathematics and Physics, Graduate School of Informatics, Kyoto University, Kyoto, JapanBioinformatics Center, Institute for Chemical Research, Kyoto University, Uji, JapanCompound inference models are crucial for discovering novel drugs in bioinformatics and chemo-informatics. These models rely heavily on useful descriptors of chemical compounds that effectively capture important information about the underlying compounds for constructing accurate prediction functions. In this article, we introduce quadratic descriptors, the products of two graph-theoretic descriptors, to enhance the learning performance of a novel two-layered compound inference model. A mixed-integer linear programming formulation is designed to approximate these quadratic descriptors for inferring desired compounds with the two-layered model. Furthermore, we introduce different methods to reduce descriptors, aiming to avoid computational complexity and overfitting issues during the learning process caused by the large number of quadratic descriptors. Experimental results show that for 32 chemical properties of monomers and 10 chemical properties of polymers, the prediction functions constructed by the proposed method achieved high test coefficients of determination. Furthermore, our method inferred chemical compounds in a time ranging from a few seconds to approximately 60 s. These results indicate a strong correlation between the properties of chemical graphs and their quadratic graph-theoretic descriptors.https://www.frontiersin.org/articles/10.3389/fgene.2024.1483490/fullmachine learninginteger programmingchemo-informaticsmaterials informaticsQSAR/QSPRmolecular design |
| spellingShingle | Jianshen Zhu Naveed Ahmed Azam Shengjuan Cao Ryota Ido Kazuya Haraguchi Liang Zhao Hiroshi Nagamochi Tatsuya Akutsu Quadratic descriptors and reduction methods in a two-layered model for compound inference Frontiers in Genetics machine learning integer programming chemo-informatics materials informatics QSAR/QSPR molecular design |
| title | Quadratic descriptors and reduction methods in a two-layered model for compound inference |
| title_full | Quadratic descriptors and reduction methods in a two-layered model for compound inference |
| title_fullStr | Quadratic descriptors and reduction methods in a two-layered model for compound inference |
| title_full_unstemmed | Quadratic descriptors and reduction methods in a two-layered model for compound inference |
| title_short | Quadratic descriptors and reduction methods in a two-layered model for compound inference |
| title_sort | quadratic descriptors and reduction methods in a two layered model for compound inference |
| topic | machine learning integer programming chemo-informatics materials informatics QSAR/QSPR molecular design |
| url | https://www.frontiersin.org/articles/10.3389/fgene.2024.1483490/full |
| work_keys_str_mv | AT jianshenzhu quadraticdescriptorsandreductionmethodsinatwolayeredmodelforcompoundinference AT naveedahmedazam quadraticdescriptorsandreductionmethodsinatwolayeredmodelforcompoundinference AT shengjuancao quadraticdescriptorsandreductionmethodsinatwolayeredmodelforcompoundinference AT ryotaido quadraticdescriptorsandreductionmethodsinatwolayeredmodelforcompoundinference AT kazuyaharaguchi quadraticdescriptorsandreductionmethodsinatwolayeredmodelforcompoundinference AT liangzhao quadraticdescriptorsandreductionmethodsinatwolayeredmodelforcompoundinference AT hiroshinagamochi quadraticdescriptorsandreductionmethodsinatwolayeredmodelforcompoundinference AT tatsuyaakutsu quadraticdescriptorsandreductionmethodsinatwolayeredmodelforcompoundinference |