DPDDI: a deep predictor for drug-drug interactions
Abstract Background The treatment of complex diseases by taking multiple drugs becomes increasingly popular. However, drug-drug interactions (DDIs) may give rise to the risk of unanticipated adverse effects and even unknown toxicity. DDI detection in the wet lab is expensive and time-consuming. Thus...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2020-09-01
|
| Series: | BMC Bioinformatics |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s12859-020-03724-x |
| _version_ | 1828837631727763456 |
|---|---|
| author | Yue-Hua Feng Shao-Wu Zhang Jian-Yu Shi |
| author_facet | Yue-Hua Feng Shao-Wu Zhang Jian-Yu Shi |
| author_sort | Yue-Hua Feng |
| collection | DOAJ |
| description | Abstract Background The treatment of complex diseases by taking multiple drugs becomes increasingly popular. However, drug-drug interactions (DDIs) may give rise to the risk of unanticipated adverse effects and even unknown toxicity. DDI detection in the wet lab is expensive and time-consuming. Thus, it is highly desired to develop the computational methods for predicting DDIs. Generally, most of the existing computational methods predict DDIs by extracting the chemical and biological features of drugs from diverse drug-related properties, however some drug properties are costly to obtain and not available in many cases. Results In this work, we presented a novel method (namely DPDDI) to predict DDIs by extracting the network structure features of drugs from DDI network with graph convolution network (GCN), and the deep neural network (DNN) model as a predictor. GCN learns the low-dimensional feature representations of drugs by capturing the topological relationship of drugs in DDI network. DNN predictor concatenates the latent feature vectors of any two drugs as the feature vector of the corresponding drug pairs to train a DNN for predicting the potential drug-drug interactions. Experiment results show that, the newly proposed DPDDI method outperforms four other state-of-the-art methods; the GCN-derived latent features include more DDI information than other features derived from chemical, biological or anatomical properties of drugs; and the concatenation feature aggregation operator is better than two other feature aggregation operators (i.e., inner product and summation). The results in case studies confirm that DPDDI achieves reasonable performance in predicting new DDIs. Conclusion We proposed an effective and robust method DPDDI to predict the potential DDIs by utilizing the DDI network information without considering the drug properties (i.e., drug chemical and biological properties). The method should also be useful in other DDI-related scenarios, such as the detection of unexpected side effects, and the guidance of drug combination. |
| first_indexed | 2024-12-12T18:46:04Z |
| format | Article |
| id | doaj.art-39c8572784ac4983ab9510e04db8640b |
| institution | Directory Open Access Journal |
| issn | 1471-2105 |
| language | English |
| last_indexed | 2024-12-12T18:46:04Z |
| publishDate | 2020-09-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Bioinformatics |
| spelling | doaj.art-39c8572784ac4983ab9510e04db8640b2022-12-22T00:15:31ZengBMCBMC Bioinformatics1471-21052020-09-0121111510.1186/s12859-020-03724-xDPDDI: a deep predictor for drug-drug interactionsYue-Hua Feng0Shao-Wu Zhang1Jian-Yu Shi2Key Laboratory of Information Fusion Technology of Ministry of Education, School of Automation, Northwestern Polytechnical UniversityKey Laboratory of Information Fusion Technology of Ministry of Education, School of Automation, Northwestern Polytechnical UniversitySchool of Life Sciences, Northwestern Polytechnical UniversityAbstract Background The treatment of complex diseases by taking multiple drugs becomes increasingly popular. However, drug-drug interactions (DDIs) may give rise to the risk of unanticipated adverse effects and even unknown toxicity. DDI detection in the wet lab is expensive and time-consuming. Thus, it is highly desired to develop the computational methods for predicting DDIs. Generally, most of the existing computational methods predict DDIs by extracting the chemical and biological features of drugs from diverse drug-related properties, however some drug properties are costly to obtain and not available in many cases. Results In this work, we presented a novel method (namely DPDDI) to predict DDIs by extracting the network structure features of drugs from DDI network with graph convolution network (GCN), and the deep neural network (DNN) model as a predictor. GCN learns the low-dimensional feature representations of drugs by capturing the topological relationship of drugs in DDI network. DNN predictor concatenates the latent feature vectors of any two drugs as the feature vector of the corresponding drug pairs to train a DNN for predicting the potential drug-drug interactions. Experiment results show that, the newly proposed DPDDI method outperforms four other state-of-the-art methods; the GCN-derived latent features include more DDI information than other features derived from chemical, biological or anatomical properties of drugs; and the concatenation feature aggregation operator is better than two other feature aggregation operators (i.e., inner product and summation). The results in case studies confirm that DPDDI achieves reasonable performance in predicting new DDIs. Conclusion We proposed an effective and robust method DPDDI to predict the potential DDIs by utilizing the DDI network information without considering the drug properties (i.e., drug chemical and biological properties). The method should also be useful in other DDI-related scenarios, such as the detection of unexpected side effects, and the guidance of drug combination.http://link.springer.com/article/10.1186/s12859-020-03724-xDrug-drug interactionDDI predictionGraph convolution network (GCN)Feature extractionDeep neural network |
| spellingShingle | Yue-Hua Feng Shao-Wu Zhang Jian-Yu Shi DPDDI: a deep predictor for drug-drug interactions BMC Bioinformatics Drug-drug interaction DDI prediction Graph convolution network (GCN) Feature extraction Deep neural network |
| title | DPDDI: a deep predictor for drug-drug interactions |
| title_full | DPDDI: a deep predictor for drug-drug interactions |
| title_fullStr | DPDDI: a deep predictor for drug-drug interactions |
| title_full_unstemmed | DPDDI: a deep predictor for drug-drug interactions |
| title_short | DPDDI: a deep predictor for drug-drug interactions |
| title_sort | dpddi a deep predictor for drug drug interactions |
| topic | Drug-drug interaction DDI prediction Graph convolution network (GCN) Feature extraction Deep neural network |
| url | http://link.springer.com/article/10.1186/s12859-020-03724-x |
| work_keys_str_mv | AT yuehuafeng dpddiadeeppredictorfordrugdruginteractions AT shaowuzhang dpddiadeeppredictorfordrugdruginteractions AT jianyushi dpddiadeeppredictorfordrugdruginteractions |