Learning important features from multi-view data to predict drug side effects
Abstract The problem of drug side effects is one of the most crucial issues in pharmacological development. As there are many limitations in current experimental and clinical methods for detecting side effects, a lot of computational algorithms have been developed to predict side effects with differ...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2019-12-01
|
| Series: | Journal of Cheminformatics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13321-019-0402-3 |
| _version_ | 1818663960752160768 |
|---|---|
| author | Xujun Liang Pengfei Zhang Jun Li Ying Fu Lingzhi Qu Yongheng Chen Zhuchu Chen |
| author_facet | Xujun Liang Pengfei Zhang Jun Li Ying Fu Lingzhi Qu Yongheng Chen Zhuchu Chen |
| author_sort | Xujun Liang |
| collection | DOAJ |
| description | Abstract The problem of drug side effects is one of the most crucial issues in pharmacological development. As there are many limitations in current experimental and clinical methods for detecting side effects, a lot of computational algorithms have been developed to predict side effects with different types of drug information. However, there is still a lack of methods which could integrate heterogeneous data to predict side effects and select important features at the same time. Here, we propose a novel computational framework based on multi-view and multi-label learning for side effect prediction. Four different types of drug features are collected and graph model is constructed from each feature profile. After that, all the single view graphs are combined to regularize the linear regression functions which describe the relationships between drug features and side effect labels. L1 penalties are imposed on the regression coefficient matrices in order to select features relevant to side effects. Additionally, the correlations between side effect labels are also incorporated into the model by graph Laplacian regularization. The experimental results show that the proposed method could not only provide more accurate prediction for side effects but also select drug features related to side effects from heterogeneous data. Some case studies are also supplied to illustrate the utility of our method for prediction of drug side effects. |
| first_indexed | 2024-12-17T05:25:09Z |
| format | Article |
| id | doaj.art-2b27b071ee4547b695bbc3b5d6f5187d |
| institution | Directory Open Access Journal |
| issn | 1758-2946 |
| language | English |
| last_indexed | 2024-12-17T05:25:09Z |
| publishDate | 2019-12-01 |
| publisher | BMC |
| record_format | Article |
| series | Journal of Cheminformatics |
| spelling | doaj.art-2b27b071ee4547b695bbc3b5d6f5187d2022-12-21T22:01:53ZengBMCJournal of Cheminformatics1758-29462019-12-0111111710.1186/s13321-019-0402-3Learning important features from multi-view data to predict drug side effectsXujun Liang0Pengfei Zhang1Jun Li2Ying Fu3Lingzhi Qu4Yongheng Chen5Zhuchu Chen6NHC Key Laboratory of Cancer Proteomics, Xiangya Hospital, Central South UniversityNHC Key Laboratory of Cancer Proteomics, Xiangya Hospital, Central South UniversityNHC Key Laboratory of Cancer Proteomics, Xiangya Hospital, Central South UniversityNHC Key Laboratory of Cancer Proteomics, Xiangya Hospital, Central South UniversityNHC Key Laboratory of Cancer Proteomics, Xiangya Hospital, Central South UniversityNHC Key Laboratory of Cancer Proteomics, Xiangya Hospital, Central South UniversityNHC Key Laboratory of Cancer Proteomics, Xiangya Hospital, Central South UniversityAbstract The problem of drug side effects is one of the most crucial issues in pharmacological development. As there are many limitations in current experimental and clinical methods for detecting side effects, a lot of computational algorithms have been developed to predict side effects with different types of drug information. However, there is still a lack of methods which could integrate heterogeneous data to predict side effects and select important features at the same time. Here, we propose a novel computational framework based on multi-view and multi-label learning for side effect prediction. Four different types of drug features are collected and graph model is constructed from each feature profile. After that, all the single view graphs are combined to regularize the linear regression functions which describe the relationships between drug features and side effect labels. L1 penalties are imposed on the regression coefficient matrices in order to select features relevant to side effects. Additionally, the correlations between side effect labels are also incorporated into the model by graph Laplacian regularization. The experimental results show that the proposed method could not only provide more accurate prediction for side effects but also select drug features related to side effects from heterogeneous data. Some case studies are also supplied to illustrate the utility of our method for prediction of drug side effects.https://doi.org/10.1186/s13321-019-0402-3Side effect predictionHeterogeneous data integrationFeature selection |
| spellingShingle | Xujun Liang Pengfei Zhang Jun Li Ying Fu Lingzhi Qu Yongheng Chen Zhuchu Chen Learning important features from multi-view data to predict drug side effects Journal of Cheminformatics Side effect prediction Heterogeneous data integration Feature selection |
| title | Learning important features from multi-view data to predict drug side effects |
| title_full | Learning important features from multi-view data to predict drug side effects |
| title_fullStr | Learning important features from multi-view data to predict drug side effects |
| title_full_unstemmed | Learning important features from multi-view data to predict drug side effects |
| title_short | Learning important features from multi-view data to predict drug side effects |
| title_sort | learning important features from multi view data to predict drug side effects |
| topic | Side effect prediction Heterogeneous data integration Feature selection |
| url | https://doi.org/10.1186/s13321-019-0402-3 |
| work_keys_str_mv | AT xujunliang learningimportantfeaturesfrommultiviewdatatopredictdrugsideeffects AT pengfeizhang learningimportantfeaturesfrommultiviewdatatopredictdrugsideeffects AT junli learningimportantfeaturesfrommultiviewdatatopredictdrugsideeffects AT yingfu learningimportantfeaturesfrommultiviewdatatopredictdrugsideeffects AT lingzhiqu learningimportantfeaturesfrommultiviewdatatopredictdrugsideeffects AT yonghengchen learningimportantfeaturesfrommultiviewdatatopredictdrugsideeffects AT zhuchuchen learningimportantfeaturesfrommultiviewdatatopredictdrugsideeffects |