Prediction of traditional Chinese medicine for diabetes based on the multi-source ensemble method
IntroductionTraditional Chinese medicine (TCM) prescriptions are generally formulated by experienced TCM researchers based on their expertise and data statistical methods.MethodsIn order to predict TCM formulas for diabetes more accurately, this paper proposes a novel multi-source ensemble predictio...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Pharmacology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fphar.2025.1454029/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832579301360271360 |
|---|---|
| author | Bin Yang Qingyun Chi Xiang Li Jinglong Wang |
| author_facet | Bin Yang Qingyun Chi Xiang Li Jinglong Wang |
| author_sort | Bin Yang |
| collection | DOAJ |
| description | IntroductionTraditional Chinese medicine (TCM) prescriptions are generally formulated by experienced TCM researchers based on their expertise and data statistical methods.MethodsIn order to predict TCM formulas for diabetes more accurately, this paper proposes a novel multi-source ensemble prediction method that combines machine learning ensemble techniques and multi-source data. In this method, the multi-source data contain datasets based on the components and targets (DPP-4 and GLP-1). Gradient boosting decision tree (GBDT), flexible neural tree (FNT), and Light Gradient Boosting Machine (LightGBM) algorithms are trained using these two types of datasets, respectively. The compound dataset from the TCMSP database is then used as testing data to predict and screen the active ingredients. The frequencies of occurrences of medicinal herbs corresponding to these three algorithms are obtained, each containing an active ingredient list. Finally, the frequencies of occurrences of the medicinal herbs obtained from the three algorithms using the component and target datasets are integrated to select duplicate drugs as the candidate drugs for diabetes treatment.ResultsThe identification results reveal that theproposed ensemble method has higher accuracy than GBDT, FNT, and LightGBM. The medicinal herbs predicted include Lycii fructus, Amygdalus communis vas, Chrysanthemi flos, Hippophae fructus, Mori folium, Croci stigma, Maydis stigma, Ephedrae herba, Cimicifugae rhizoma, licorice, and Epimedii herba, all of which have been proven effective in the treatment of diabetes.DiscussionsThe results of network pharmacology show that myrrha can play a role in treating diabetes through multiple targets and pathways. |
| format | Article |
| id | doaj-art-a1952d046b19474083a465555f8f4c14 |
| institution | Kabale University |
| issn | 1663-9812 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Pharmacology |
| spelling | doaj-art-a1952d046b19474083a465555f8f4c142025-01-30T12:28:59ZengFrontiers Media S.A.Frontiers in Pharmacology1663-98122025-01-011610.3389/fphar.2025.14540291454029Prediction of traditional Chinese medicine for diabetes based on the multi-source ensemble methodBin Yang0Qingyun Chi1Xiang Li2Jinglong Wang3School of Information Science and Engineering, Zaozhuang University, Zaozhuang, ChinaSchool of Information Science and Engineering, Zaozhuang University, Zaozhuang, ChinaInformation Department, Qingdao Eighth People’s Hospital, Qingdao, ChinaCollege of Food Science and Pharmaceutical Engineering, Zaozhuang University, Zaozhuang, ChinaIntroductionTraditional Chinese medicine (TCM) prescriptions are generally formulated by experienced TCM researchers based on their expertise and data statistical methods.MethodsIn order to predict TCM formulas for diabetes more accurately, this paper proposes a novel multi-source ensemble prediction method that combines machine learning ensemble techniques and multi-source data. In this method, the multi-source data contain datasets based on the components and targets (DPP-4 and GLP-1). Gradient boosting decision tree (GBDT), flexible neural tree (FNT), and Light Gradient Boosting Machine (LightGBM) algorithms are trained using these two types of datasets, respectively. The compound dataset from the TCMSP database is then used as testing data to predict and screen the active ingredients. The frequencies of occurrences of medicinal herbs corresponding to these three algorithms are obtained, each containing an active ingredient list. Finally, the frequencies of occurrences of the medicinal herbs obtained from the three algorithms using the component and target datasets are integrated to select duplicate drugs as the candidate drugs for diabetes treatment.ResultsThe identification results reveal that theproposed ensemble method has higher accuracy than GBDT, FNT, and LightGBM. The medicinal herbs predicted include Lycii fructus, Amygdalus communis vas, Chrysanthemi flos, Hippophae fructus, Mori folium, Croci stigma, Maydis stigma, Ephedrae herba, Cimicifugae rhizoma, licorice, and Epimedii herba, all of which have been proven effective in the treatment of diabetes.DiscussionsThe results of network pharmacology show that myrrha can play a role in treating diabetes through multiple targets and pathways.https://www.frontiersin.org/articles/10.3389/fphar.2025.1454029/fulldiabetesmulti-sourcetraditional Chinese medicine formulasensemblemedicinal herbs |
| spellingShingle | Bin Yang Qingyun Chi Xiang Li Jinglong Wang Prediction of traditional Chinese medicine for diabetes based on the multi-source ensemble method Frontiers in Pharmacology diabetes multi-source traditional Chinese medicine formulas ensemble medicinal herbs |
| title | Prediction of traditional Chinese medicine for diabetes based on the multi-source ensemble method |
| title_full | Prediction of traditional Chinese medicine for diabetes based on the multi-source ensemble method |
| title_fullStr | Prediction of traditional Chinese medicine for diabetes based on the multi-source ensemble method |
| title_full_unstemmed | Prediction of traditional Chinese medicine for diabetes based on the multi-source ensemble method |
| title_short | Prediction of traditional Chinese medicine for diabetes based on the multi-source ensemble method |
| title_sort | prediction of traditional chinese medicine for diabetes based on the multi source ensemble method |
| topic | diabetes multi-source traditional Chinese medicine formulas ensemble medicinal herbs |
| url | https://www.frontiersin.org/articles/10.3389/fphar.2025.1454029/full |
| work_keys_str_mv | AT binyang predictionoftraditionalchinesemedicinefordiabetesbasedonthemultisourceensemblemethod AT qingyunchi predictionoftraditionalchinesemedicinefordiabetesbasedonthemultisourceensemblemethod AT xiangli predictionoftraditionalchinesemedicinefordiabetesbasedonthemultisourceensemblemethod AT jinglongwang predictionoftraditionalchinesemedicinefordiabetesbasedonthemultisourceensemblemethod |