Super.FELT: supervised feature extraction learning using triplet loss for drug response prediction with multi-omics data
Abstract Background Predicting the drug response of a patient is important for precision oncology. In recent studies, multi-omics data have been used to improve the prediction accuracy of drug response. Although multi-omics data are good resources for drug response prediction, the large dimension of...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2021-05-01
|
| Series: | BMC Bioinformatics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12859-021-04146-z |
| _version_ | 1819047331966746624 |
|---|---|
| author | Sejin Park Jihee Soh Hyunju Lee |
| author_facet | Sejin Park Jihee Soh Hyunju Lee |
| author_sort | Sejin Park |
| collection | DOAJ |
| description | Abstract Background Predicting the drug response of a patient is important for precision oncology. In recent studies, multi-omics data have been used to improve the prediction accuracy of drug response. Although multi-omics data are good resources for drug response prediction, the large dimension of data tends to hinder performance improvement. In this study, we aimed to develop a new method, which can effectively reduce the large dimension of data, based on the supervised deep learning model for predicting drug response. Results We proposed a novel method called Supervised Feature Extraction Learning using Triplet loss (Super.FELT) for drug response prediction. Super.FELT consists of three stages, namely, feature selection, feature encoding using a supervised method, and binary classification of drug response (sensitive or resistant). We used multi-omics data including mutation, copy number aberration, and gene expression, and these were obtained from cell lines [Genomics of Drug Sensitivity in Cancer (GDSC), Cancer Cell Line Encyclopedia (CCLE), and Cancer Therapeutics Response Portal (CTRP)], patient-derived tumor xenografts (PDX), and The Cancer Genome Atlas (TCGA). GDSC was used for training and cross-validation tests, and CCLE, CTRP, PDX, and TCGA were used for external validation. We performed ablation studies for the three stages and verified that the use of multi-omics data guarantees better performance of drug response prediction. Our results verified that Super.FELT outperformed the other methods at external validation on PDX and TCGA and was good at cross-validation on GDSC and external validation on CCLE and CTRP. In addition, through our experiments, we confirmed that using multi-omics data is useful for external non-cell line data. Conclusion By separating the three stages, Super.FELT achieved better performance than the other methods. Through our results, we found that it is important to train encoders and a classifier independently, especially for external test on PDX and TCGA. Moreover, although gene expression is the most powerful data on cell line data, multi-omics promises better performance for external validation on non-cell line data than gene expression data. Source codes of Super.FELT are available at https://github.com/DMCB-GIST/Super.FELT . |
| first_indexed | 2024-12-21T10:58:40Z |
| format | Article |
| id | doaj.art-deb7d559623d436d8dea879f775a090e |
| institution | Directory Open Access Journal |
| issn | 1471-2105 |
| language | English |
| last_indexed | 2024-12-21T10:58:40Z |
| publishDate | 2021-05-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Bioinformatics |
| spelling | doaj.art-deb7d559623d436d8dea879f775a090e2022-12-21T19:06:25ZengBMCBMC Bioinformatics1471-21052021-05-0122112310.1186/s12859-021-04146-zSuper.FELT: supervised feature extraction learning using triplet loss for drug response prediction with multi-omics dataSejin Park0Jihee Soh1Hyunju Lee2School of Electrical Engineering and Computer Science, Gwangju Institute of Science and TechnologySchool of Electrical Engineering and Computer Science, Gwangju Institute of Science and TechnologySchool of Electrical Engineering and Computer Science, Gwangju Institute of Science and TechnologyAbstract Background Predicting the drug response of a patient is important for precision oncology. In recent studies, multi-omics data have been used to improve the prediction accuracy of drug response. Although multi-omics data are good resources for drug response prediction, the large dimension of data tends to hinder performance improvement. In this study, we aimed to develop a new method, which can effectively reduce the large dimension of data, based on the supervised deep learning model for predicting drug response. Results We proposed a novel method called Supervised Feature Extraction Learning using Triplet loss (Super.FELT) for drug response prediction. Super.FELT consists of three stages, namely, feature selection, feature encoding using a supervised method, and binary classification of drug response (sensitive or resistant). We used multi-omics data including mutation, copy number aberration, and gene expression, and these were obtained from cell lines [Genomics of Drug Sensitivity in Cancer (GDSC), Cancer Cell Line Encyclopedia (CCLE), and Cancer Therapeutics Response Portal (CTRP)], patient-derived tumor xenografts (PDX), and The Cancer Genome Atlas (TCGA). GDSC was used for training and cross-validation tests, and CCLE, CTRP, PDX, and TCGA were used for external validation. We performed ablation studies for the three stages and verified that the use of multi-omics data guarantees better performance of drug response prediction. Our results verified that Super.FELT outperformed the other methods at external validation on PDX and TCGA and was good at cross-validation on GDSC and external validation on CCLE and CTRP. In addition, through our experiments, we confirmed that using multi-omics data is useful for external non-cell line data. Conclusion By separating the three stages, Super.FELT achieved better performance than the other methods. Through our results, we found that it is important to train encoders and a classifier independently, especially for external test on PDX and TCGA. Moreover, although gene expression is the most powerful data on cell line data, multi-omics promises better performance for external validation on non-cell line data than gene expression data. Source codes of Super.FELT are available at https://github.com/DMCB-GIST/Super.FELT .https://doi.org/10.1186/s12859-021-04146-zPrecision oncologyMulti-omics dataDrug response predictionencoder using supervised methodsTriplet lossPharmacogenomics |
| spellingShingle | Sejin Park Jihee Soh Hyunju Lee Super.FELT: supervised feature extraction learning using triplet loss for drug response prediction with multi-omics data BMC Bioinformatics Precision oncology Multi-omics data Drug response prediction encoder using supervised methods Triplet loss Pharmacogenomics |
| title | Super.FELT: supervised feature extraction learning using triplet loss for drug response prediction with multi-omics data |
| title_full | Super.FELT: supervised feature extraction learning using triplet loss for drug response prediction with multi-omics data |
| title_fullStr | Super.FELT: supervised feature extraction learning using triplet loss for drug response prediction with multi-omics data |
| title_full_unstemmed | Super.FELT: supervised feature extraction learning using triplet loss for drug response prediction with multi-omics data |
| title_short | Super.FELT: supervised feature extraction learning using triplet loss for drug response prediction with multi-omics data |
| title_sort | super felt supervised feature extraction learning using triplet loss for drug response prediction with multi omics data |
| topic | Precision oncology Multi-omics data Drug response prediction encoder using supervised methods Triplet loss Pharmacogenomics |
| url | https://doi.org/10.1186/s12859-021-04146-z |
| work_keys_str_mv | AT sejinpark superfeltsupervisedfeatureextractionlearningusingtripletlossfordrugresponsepredictionwithmultiomicsdata AT jiheesoh superfeltsupervisedfeatureextractionlearningusingtripletlossfordrugresponsepredictionwithmultiomicsdata AT hyunjulee superfeltsupervisedfeatureextractionlearningusingtripletlossfordrugresponsepredictionwithmultiomicsdata |