HPGCN: A graph convolutional network-based prediction model for herbal heat/cold properties
Herbal properties are part of the fundamental theories of traditional Chinese medicine (TCM), which has been of great significance for herbal formulas and disease treatment in clinics for thousands of years. However, determining herbal properties, such as heat/cold, still relies on ancient books and...
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-03-01
|
| Series: | Current Plant Biology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2214662825000167 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1825199417153552384 |
|---|---|
| author | Qikai Niu Jing’ai Wang Hongtao Li Lin Tong Haiyu Xu Weina Zhang Ziling Zeng Sihong Liu Wenjing Zong Siqi Zhang Siwei Tian Huamin Zhang Bing Li |
| author_facet | Qikai Niu Jing’ai Wang Hongtao Li Lin Tong Haiyu Xu Weina Zhang Ziling Zeng Sihong Liu Wenjing Zong Siqi Zhang Siwei Tian Huamin Zhang Bing Li |
| author_sort | Qikai Niu |
| collection | DOAJ |
| description | Herbal properties are part of the fundamental theories of traditional Chinese medicine (TCM), which has been of great significance for herbal formulas and disease treatment in clinics for thousands of years. However, determining herbal properties, such as heat/cold, still relies on ancient books and the doctor's experience, which can present significant limitations. In this study, we propose an herbal property graph convolutional network (HPGCN) model by combining TCM theory, modern pharmacological mechanisms, prior knowledge of herbal properties, and intelligent algorithms, which can effectively predict herbal heat/cold properties. Based on protein-protein interactions (PPI) and herb-herb networks, 30 target genes were selected as features for herbal heat/cold property prediction. Compared to previous machine learning algorithms, the HPGCN obtained optimal classification prediction results for ACC, Recall, Precision, F1, and AUC indicators by 5-fold cross-validation on the training and test sets. The function of herbs predicted by HPGCN improved by 3 % in hit@k compared to predictions that did not account for herbal properties. Herbs with disputed heat/cold properties in ancient books (such as Pulsatilliae Radix and Menthae Herba) were predicted using recommended property probabilities. The proposed HPGCN model may have profound practical value and significance for elucidating the scientific mechanisms of herbal property theory and in herbal medicine development. |
| format | Article |
| id | doaj-art-5de2a6b2e37840ac9a24507dbe53570c |
| institution | Kabale University |
| issn | 2214-6628 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Current Plant Biology |
| spelling | doaj-art-5de2a6b2e37840ac9a24507dbe53570c2025-02-08T05:00:30ZengElsevierCurrent Plant Biology2214-66282025-03-0141100448HPGCN: A graph convolutional network-based prediction model for herbal heat/cold propertiesQikai Niu0Jing’ai Wang1Hongtao Li2Lin Tong3Haiyu Xu4Weina Zhang5Ziling Zeng6Sihong Liu7Wenjing Zong8Siqi Zhang9Siwei Tian10Huamin Zhang11Bing Li12State Key Laboratory for Quality Ensurance and Sustainable Use of Dao-di Herbs, Institute of Chinese Materia Medica, China Academy of Chinese Medical Sciences, Beijing 100700, ChinaState Key Laboratory for Quality Ensurance and Sustainable Use of Dao-di Herbs, Institute of Chinese Materia Medica, China Academy of Chinese Medical Sciences, Beijing 100700, ChinaInstitute of Information on Traditional Chinese Medicine, China Academy of Chinese Medical Sciences, Beijing 100700, ChinaInstitute of Information on Traditional Chinese Medicine, China Academy of Chinese Medical Sciences, Beijing 100700, ChinaState Key Laboratory for Quality Ensurance and Sustainable Use of Dao-di Herbs, Institute of Chinese Materia Medica, China Academy of Chinese Medical Sciences, Beijing 100700, ChinaInstitute of Information on Traditional Chinese Medicine, China Academy of Chinese Medical Sciences, Beijing 100700, ChinaState Key Laboratory for Quality Ensurance and Sustainable Use of Dao-di Herbs, Institute of Chinese Materia Medica, China Academy of Chinese Medical Sciences, Beijing 100700, ChinaInstitute of Information on Traditional Chinese Medicine, China Academy of Chinese Medical Sciences, Beijing 100700, ChinaState Key Laboratory for Quality Ensurance and Sustainable Use of Dao-di Herbs, Institute of Chinese Materia Medica, China Academy of Chinese Medical Sciences, Beijing 100700, ChinaState Key Laboratory for Quality Ensurance and Sustainable Use of Dao-di Herbs, Institute of Chinese Materia Medica, China Academy of Chinese Medical Sciences, Beijing 100700, ChinaState Key Laboratory for Quality Ensurance and Sustainable Use of Dao-di Herbs, Institute of Chinese Materia Medica, China Academy of Chinese Medical Sciences, Beijing 100700, ChinaState Key Laboratory for Quality Ensurance and Sustainable Use of Dao-di Herbs, Institute of Chinese Materia Medica, China Academy of Chinese Medical Sciences, Beijing 100700, China; Institute of Basic Theory for Chinese Medicine, China Academy of Chinese Medicine Science, Beijing 100700, China; Corresponding author at: State Key Laboratory for Quality Ensurance and Sustainable Use of Dao-di Herbs, Institute of Chinese Materia Medica, China Academy of Chinese Medical Sciences, Beijing 100700, China.State Key Laboratory for Quality Ensurance and Sustainable Use of Dao-di Herbs, Institute of Chinese Materia Medica, China Academy of Chinese Medical Sciences, Beijing 100700, China; Corresponding author.Herbal properties are part of the fundamental theories of traditional Chinese medicine (TCM), which has been of great significance for herbal formulas and disease treatment in clinics for thousands of years. However, determining herbal properties, such as heat/cold, still relies on ancient books and the doctor's experience, which can present significant limitations. In this study, we propose an herbal property graph convolutional network (HPGCN) model by combining TCM theory, modern pharmacological mechanisms, prior knowledge of herbal properties, and intelligent algorithms, which can effectively predict herbal heat/cold properties. Based on protein-protein interactions (PPI) and herb-herb networks, 30 target genes were selected as features for herbal heat/cold property prediction. Compared to previous machine learning algorithms, the HPGCN obtained optimal classification prediction results for ACC, Recall, Precision, F1, and AUC indicators by 5-fold cross-validation on the training and test sets. The function of herbs predicted by HPGCN improved by 3 % in hit@k compared to predictions that did not account for herbal properties. Herbs with disputed heat/cold properties in ancient books (such as Pulsatilliae Radix and Menthae Herba) were predicted using recommended property probabilities. The proposed HPGCN model may have profound practical value and significance for elucidating the scientific mechanisms of herbal property theory and in herbal medicine development.http://www.sciencedirect.com/science/article/pii/S2214662825000167Herbal property predictionTraditional Chinese Medicine (TCM)Graph convolutional networkHerbal heat/cold propertiesHerbal function |
| spellingShingle | Qikai Niu Jing’ai Wang Hongtao Li Lin Tong Haiyu Xu Weina Zhang Ziling Zeng Sihong Liu Wenjing Zong Siqi Zhang Siwei Tian Huamin Zhang Bing Li HPGCN: A graph convolutional network-based prediction model for herbal heat/cold properties Current Plant Biology Herbal property prediction Traditional Chinese Medicine (TCM) Graph convolutional network Herbal heat/cold properties Herbal function |
| title | HPGCN: A graph convolutional network-based prediction model for herbal heat/cold properties |
| title_full | HPGCN: A graph convolutional network-based prediction model for herbal heat/cold properties |
| title_fullStr | HPGCN: A graph convolutional network-based prediction model for herbal heat/cold properties |
| title_full_unstemmed | HPGCN: A graph convolutional network-based prediction model for herbal heat/cold properties |
| title_short | HPGCN: A graph convolutional network-based prediction model for herbal heat/cold properties |
| title_sort | hpgcn a graph convolutional network based prediction model for herbal heat cold properties |
| topic | Herbal property prediction Traditional Chinese Medicine (TCM) Graph convolutional network Herbal heat/cold properties Herbal function |
| url | http://www.sciencedirect.com/science/article/pii/S2214662825000167 |
| work_keys_str_mv | AT qikainiu hpgcnagraphconvolutionalnetworkbasedpredictionmodelforherbalheatcoldproperties AT jingaiwang hpgcnagraphconvolutionalnetworkbasedpredictionmodelforherbalheatcoldproperties AT hongtaoli hpgcnagraphconvolutionalnetworkbasedpredictionmodelforherbalheatcoldproperties AT lintong hpgcnagraphconvolutionalnetworkbasedpredictionmodelforherbalheatcoldproperties AT haiyuxu hpgcnagraphconvolutionalnetworkbasedpredictionmodelforherbalheatcoldproperties AT weinazhang hpgcnagraphconvolutionalnetworkbasedpredictionmodelforherbalheatcoldproperties AT zilingzeng hpgcnagraphconvolutionalnetworkbasedpredictionmodelforherbalheatcoldproperties AT sihongliu hpgcnagraphconvolutionalnetworkbasedpredictionmodelforherbalheatcoldproperties AT wenjingzong hpgcnagraphconvolutionalnetworkbasedpredictionmodelforherbalheatcoldproperties AT siqizhang hpgcnagraphconvolutionalnetworkbasedpredictionmodelforherbalheatcoldproperties AT siweitian hpgcnagraphconvolutionalnetworkbasedpredictionmodelforherbalheatcoldproperties AT huaminzhang hpgcnagraphconvolutionalnetworkbasedpredictionmodelforherbalheatcoldproperties AT bingli hpgcnagraphconvolutionalnetworkbasedpredictionmodelforherbalheatcoldproperties |