DualGCN: a dual graph convolutional network model to predict cancer drug response
Abstract Background Drug resistance is a critical obstacle in cancer therapy. Discovering cancer drug response is important to improve anti-cancer drug treatment and guide anti-cancer drug design. Abundant genomic and drug response resources of cancer cell lines provide unprecedented opportunities f...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2022-04-01
|
| Series: | BMC Bioinformatics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12859-022-04664-4 |
| _version_ | 1797743961257803776 |
|---|---|
| author | Tianxing Ma Qiao Liu Haochen Li Mu Zhou Rui Jiang Xuegong Zhang |
| author_facet | Tianxing Ma Qiao Liu Haochen Li Mu Zhou Rui Jiang Xuegong Zhang |
| author_sort | Tianxing Ma |
| collection | DOAJ |
| description | Abstract Background Drug resistance is a critical obstacle in cancer therapy. Discovering cancer drug response is important to improve anti-cancer drug treatment and guide anti-cancer drug design. Abundant genomic and drug response resources of cancer cell lines provide unprecedented opportunities for such study. However, cancer cell lines cannot fully reflect heterogeneous tumor microenvironments. Transferring knowledge studied from in vitro cell lines to single-cell and clinical data will be a promising direction to better understand drug resistance. Most current studies include single nucleotide variants (SNV) as features and focus on improving predictive ability of cancer drug response on cell lines. However, obtaining accurate SNVs from clinical tumor samples and single-cell data is not reliable. This makes it difficult to generalize such SNV-based models to clinical tumor data or single-cell level studies in the future. Results We present a new method, DualGCN, a unified Dual Graph Convolutional Network model to predict cancer drug response. DualGCN encodes both chemical structures of drugs and omics data of biological samples using graph convolutional networks. Then the two embeddings are fed into a multilayer perceptron to predict drug response. DualGCN incorporates prior knowledge on cancer-related genes and protein–protein interactions, and outperforms most state-of-the-art methods while avoiding using large-scale SNV data. Conclusions The proposed method outperforms most state-of-the-art methods in predicting cancer drug response without the use of large-scale SNV data. These favorable results indicate its potential to be extended to clinical and single-cell tumor samples and advancements in precision medicine. |
| first_indexed | 2024-03-12T15:03:01Z |
| format | Article |
| id | doaj.art-041c74d4b1a34ebca25e32eb9c9bdc56 |
| institution | Directory Open Access Journal |
| issn | 1471-2105 |
| language | English |
| last_indexed | 2024-03-12T15:03:01Z |
| publishDate | 2022-04-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Bioinformatics |
| spelling | doaj.art-041c74d4b1a34ebca25e32eb9c9bdc562023-08-13T11:24:55ZengBMCBMC Bioinformatics1471-21052022-04-0123S411310.1186/s12859-022-04664-4DualGCN: a dual graph convolutional network model to predict cancer drug responseTianxing Ma0Qiao Liu1Haochen Li2Mu Zhou3Rui Jiang4Xuegong Zhang5MOE Key Laboratory of Bioinformatics, Bioinformatics Division, BNRIST and Department of Automation, Tsinghua UniversityDepartment of Statistics, Stanford UniversitySchool of Medicine, Center for Synthetic and Systems Biology, Tsinghua UniversitySenseBrain ResearchMOE Key Laboratory of Bioinformatics, Bioinformatics Division, BNRIST and Department of Automation, Tsinghua UniversityMOE Key Laboratory of Bioinformatics, Bioinformatics Division, BNRIST and Department of Automation, Tsinghua UniversityAbstract Background Drug resistance is a critical obstacle in cancer therapy. Discovering cancer drug response is important to improve anti-cancer drug treatment and guide anti-cancer drug design. Abundant genomic and drug response resources of cancer cell lines provide unprecedented opportunities for such study. However, cancer cell lines cannot fully reflect heterogeneous tumor microenvironments. Transferring knowledge studied from in vitro cell lines to single-cell and clinical data will be a promising direction to better understand drug resistance. Most current studies include single nucleotide variants (SNV) as features and focus on improving predictive ability of cancer drug response on cell lines. However, obtaining accurate SNVs from clinical tumor samples and single-cell data is not reliable. This makes it difficult to generalize such SNV-based models to clinical tumor data or single-cell level studies in the future. Results We present a new method, DualGCN, a unified Dual Graph Convolutional Network model to predict cancer drug response. DualGCN encodes both chemical structures of drugs and omics data of biological samples using graph convolutional networks. Then the two embeddings are fed into a multilayer perceptron to predict drug response. DualGCN incorporates prior knowledge on cancer-related genes and protein–protein interactions, and outperforms most state-of-the-art methods while avoiding using large-scale SNV data. Conclusions The proposed method outperforms most state-of-the-art methods in predicting cancer drug response without the use of large-scale SNV data. These favorable results indicate its potential to be extended to clinical and single-cell tumor samples and advancements in precision medicine.https://doi.org/10.1186/s12859-022-04664-4Cancer drug responseGraph convolutional networksProtein–protein interactionsTumor heterogeneity |
| spellingShingle | Tianxing Ma Qiao Liu Haochen Li Mu Zhou Rui Jiang Xuegong Zhang DualGCN: a dual graph convolutional network model to predict cancer drug response BMC Bioinformatics Cancer drug response Graph convolutional networks Protein–protein interactions Tumor heterogeneity |
| title | DualGCN: a dual graph convolutional network model to predict cancer drug response |
| title_full | DualGCN: a dual graph convolutional network model to predict cancer drug response |
| title_fullStr | DualGCN: a dual graph convolutional network model to predict cancer drug response |
| title_full_unstemmed | DualGCN: a dual graph convolutional network model to predict cancer drug response |
| title_short | DualGCN: a dual graph convolutional network model to predict cancer drug response |
| title_sort | dualgcn a dual graph convolutional network model to predict cancer drug response |
| topic | Cancer drug response Graph convolutional networks Protein–protein interactions Tumor heterogeneity |
| url | https://doi.org/10.1186/s12859-022-04664-4 |
| work_keys_str_mv | AT tianxingma dualgcnadualgraphconvolutionalnetworkmodeltopredictcancerdrugresponse AT qiaoliu dualgcnadualgraphconvolutionalnetworkmodeltopredictcancerdrugresponse AT haochenli dualgcnadualgraphconvolutionalnetworkmodeltopredictcancerdrugresponse AT muzhou dualgcnadualgraphconvolutionalnetworkmodeltopredictcancerdrugresponse AT ruijiang dualgcnadualgraphconvolutionalnetworkmodeltopredictcancerdrugresponse AT xuegongzhang dualgcnadualgraphconvolutionalnetworkmodeltopredictcancerdrugresponse |