Herb Target Prediction Based on Representation Learning of Symptom related Heterogeneous Network
Traditional Chinese Medicine (TCM) has received increasing attention as a complementary approach or alternative to modern medicine. However, experimental methods for identifying novel targets of TCM herbs heavily relied on the current available herb-compound-target relationships. In this work, we pr...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2019-01-01
|
| Series: | Computational and Structural Biotechnology Journal |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S200103701830151X |
| _version_ | 1818518027258298368 |
|---|---|
| author | Ning Wang Peng Li Xiaochen Hu Kuo Yang Yonghong Peng Qiang Zhu Runshun Zhang Zhuye Gao Hao Xu Baoyan Liu Jianxin Chen Xuezhong Zhou |
| author_facet | Ning Wang Peng Li Xiaochen Hu Kuo Yang Yonghong Peng Qiang Zhu Runshun Zhang Zhuye Gao Hao Xu Baoyan Liu Jianxin Chen Xuezhong Zhou |
| author_sort | Ning Wang |
| collection | DOAJ |
| description | Traditional Chinese Medicine (TCM) has received increasing attention as a complementary approach or alternative to modern medicine. However, experimental methods for identifying novel targets of TCM herbs heavily relied on the current available herb-compound-target relationships. In this work, we present an Herb-Target Interaction Network (HTINet) approach, a novel network integration pipeline for herb-target prediction mainly relying on the symptom related associations. HTINet focuses on capturing the low-dimensional feature vectors for both herbs and proteins by network embedding, which incorporate the topological properties of nodes across multi-layered heterogeneous network, and then performs supervised learning based on these low-dimensional feature representations. HTINet obtains performance improvement over a well-established random walk based herb-target prediction method. Furthermore, we have manually validated several predicted herb-target interactions from independent literatures. These results indicate that HTINet can be used to integrate heterogeneous information to predict novel herb-target interactions. Keywords: Network medicine, Herb target prediction, Symptoms, Network embedding |
| first_indexed | 2024-12-11T01:04:26Z |
| format | Article |
| id | doaj.art-1deae400af314afe95fe782e30bcbe51 |
| institution | Directory Open Access Journal |
| issn | 2001-0370 |
| language | English |
| last_indexed | 2024-12-11T01:04:26Z |
| publishDate | 2019-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Computational and Structural Biotechnology Journal |
| spelling | doaj.art-1deae400af314afe95fe782e30bcbe512022-12-22T01:26:13ZengElsevierComputational and Structural Biotechnology Journal2001-03702019-01-0117282290Herb Target Prediction Based on Representation Learning of Symptom related Heterogeneous NetworkNing Wang0Peng Li1Xiaochen Hu2Kuo Yang3Yonghong Peng4Qiang Zhu5Runshun Zhang6Zhuye Gao7Hao Xu8Baoyan Liu9Jianxin Chen10Xuezhong Zhou11School of Computer and Information Technology and Beijing Key Lab of Traffic Data Analysis and Mining, Beijing Jiaotong University, Beijing 100044, ChinaCollege of Arts and Sciences, Shanxi Agricultural University, Taigu 030801, ChinaSchool of Computer and Information Technology and Beijing Key Lab of Traffic Data Analysis and Mining, Beijing Jiaotong University, Beijing 100044, ChinaSchool of Computer and Information Technology and Beijing Key Lab of Traffic Data Analysis and Mining, Beijing Jiaotong University, Beijing 100044, ChinaFaculty of Computer Science, University of Sunderland, St Peters Campus, Sunderland SR6 0DD, UKMedical Intelligence Institute, School of Computer and Information Technology, Beijing Jiaotong University, Beijing 100044, ChinaGuanganmen Hospital, China Academy of Chinese Medical Sciences, Beijing 100053, ChinaDepartment of Cardiology, Xiyuan Hospital of China Academy of Chinese Medical Sciences, Beijing 100091, ChinaDepartment of Cardiology, Xiyuan Hospital of China Academy of Chinese Medical Sciences, Beijing 100091, ChinaData Center of Traditional Chinese Medicine, China Academy of Chinese Medical Sciences, Beijing 100700, ChinaBeijing University of Chinese Medicine, Beijing 100029, China; Corresponding author.School of Computer and Information Technology and Beijing Key Lab of Traffic Data Analysis and Mining, Beijing Jiaotong University, Beijing 100044, China; Data Center of Traditional Chinese Medicine, China Academy of Chinese Medical Sciences, Beijing 100700, China; Corresponding author at: School of Computer and Information Technology and Beijing Key Lab of Traffic Data Analysis and Mining, Beijing Jiaotong University, Beijing 100044, China.Traditional Chinese Medicine (TCM) has received increasing attention as a complementary approach or alternative to modern medicine. However, experimental methods for identifying novel targets of TCM herbs heavily relied on the current available herb-compound-target relationships. In this work, we present an Herb-Target Interaction Network (HTINet) approach, a novel network integration pipeline for herb-target prediction mainly relying on the symptom related associations. HTINet focuses on capturing the low-dimensional feature vectors for both herbs and proteins by network embedding, which incorporate the topological properties of nodes across multi-layered heterogeneous network, and then performs supervised learning based on these low-dimensional feature representations. HTINet obtains performance improvement over a well-established random walk based herb-target prediction method. Furthermore, we have manually validated several predicted herb-target interactions from independent literatures. These results indicate that HTINet can be used to integrate heterogeneous information to predict novel herb-target interactions. Keywords: Network medicine, Herb target prediction, Symptoms, Network embeddinghttp://www.sciencedirect.com/science/article/pii/S200103701830151X |
| spellingShingle | Ning Wang Peng Li Xiaochen Hu Kuo Yang Yonghong Peng Qiang Zhu Runshun Zhang Zhuye Gao Hao Xu Baoyan Liu Jianxin Chen Xuezhong Zhou Herb Target Prediction Based on Representation Learning of Symptom related Heterogeneous Network Computational and Structural Biotechnology Journal |
| title | Herb Target Prediction Based on Representation Learning of Symptom related Heterogeneous Network |
| title_full | Herb Target Prediction Based on Representation Learning of Symptom related Heterogeneous Network |
| title_fullStr | Herb Target Prediction Based on Representation Learning of Symptom related Heterogeneous Network |
| title_full_unstemmed | Herb Target Prediction Based on Representation Learning of Symptom related Heterogeneous Network |
| title_short | Herb Target Prediction Based on Representation Learning of Symptom related Heterogeneous Network |
| title_sort | herb target prediction based on representation learning of symptom related heterogeneous network |
| url | http://www.sciencedirect.com/science/article/pii/S200103701830151X |
| work_keys_str_mv | AT ningwang herbtargetpredictionbasedonrepresentationlearningofsymptomrelatedheterogeneousnetwork AT pengli herbtargetpredictionbasedonrepresentationlearningofsymptomrelatedheterogeneousnetwork AT xiaochenhu herbtargetpredictionbasedonrepresentationlearningofsymptomrelatedheterogeneousnetwork AT kuoyang herbtargetpredictionbasedonrepresentationlearningofsymptomrelatedheterogeneousnetwork AT yonghongpeng herbtargetpredictionbasedonrepresentationlearningofsymptomrelatedheterogeneousnetwork AT qiangzhu herbtargetpredictionbasedonrepresentationlearningofsymptomrelatedheterogeneousnetwork AT runshunzhang herbtargetpredictionbasedonrepresentationlearningofsymptomrelatedheterogeneousnetwork AT zhuyegao herbtargetpredictionbasedonrepresentationlearningofsymptomrelatedheterogeneousnetwork AT haoxu herbtargetpredictionbasedonrepresentationlearningofsymptomrelatedheterogeneousnetwork AT baoyanliu herbtargetpredictionbasedonrepresentationlearningofsymptomrelatedheterogeneousnetwork AT jianxinchen herbtargetpredictionbasedonrepresentationlearningofsymptomrelatedheterogeneousnetwork AT xuezhongzhou herbtargetpredictionbasedonrepresentationlearningofsymptomrelatedheterogeneousnetwork |