MOLI: multi-omics late integration with deep neural networks for drug response prediction - PubMed (original) (raw)
MOLI: multi-omics late integration with deep neural networks for drug response prediction
Hossein Sharifi-Noghabi et al. Bioinformatics. 2019.
Abstract
Motivation: Historically, gene expression has been shown to be the most informative data for drug response prediction. Recent evidence suggests that integrating additional omics can improve the prediction accuracy which raises the question of how to integrate the additional omics. Regardless of the integration strategy, clinical utility and translatability are crucial. Thus, we reasoned a multi-omics approach combined with clinical datasets would improve drug response prediction and clinical relevance.
Results: We propose MOLI, a multi-omics late integration method based on deep neural networks. MOLI takes somatic mutation, copy number aberration and gene expression data as input, and integrates them for drug response prediction. MOLI uses type-specific encoding sub-networks to learn features for each omics type, concatenates them into one representation and optimizes this representation via a combined cost function consisting of a triplet loss and a binary cross-entropy loss. The former makes the representations of responder samples more similar to each other and different from the non-responders, and the latter makes this representation predictive of the response values. We validate MOLI on in vitro and in vivo datasets for five chemotherapy agents and two targeted therapeutics. Compared to state-of-the-art single-omics and early integration multi-omics methods, MOLI achieves higher prediction accuracy in external validations. Moreover, a significant improvement in MOLI's performance is observed for targeted drugs when training on a pan-drug input, i.e. using all the drugs with the same target compared to training only on drug-specific inputs. MOLI's high predictive power suggests it may have utility in precision oncology.
Availability and implementation: https://github.com/hosseinshn/MOLI.
Supplementary information: Supplementary data are available at Bioinformatics online.
© The Author(s) 2019. Published by Oxford University Press.
Figures
Fig. 1.
Schematic overview of MOLI (A) pre-processing mutation, CNA and gene expression data. (B) Each encoding sub-network learns features for its omics data type and the learned features are concatenated into one representation. (C) MOLI cost function consists of a triplet loss and a classification loss, obtained from the classifier sub-network that uses the multi-omics representation to predict drug response
Fig. 2.
(A) Using MOLI to make predictions for PDX/patient inputs during external validation. (B) Combining targeted drugs that target the same pathway or molecule to make a pan-drug training dataset for MOLI
Similar articles
- A fair experimental comparison of neural network architectures for latent representations of multi-omics for drug response prediction.
Hauptmann T, Kramer S. Hauptmann T, et al. BMC Bioinformatics. 2023 Feb 14;24(1):45. doi: 10.1186/s12859-023-05166-7. BMC Bioinformatics. 2023. PMID: 36788531 Free PMC article. - Super.FELT: supervised feature extraction learning using triplet loss for drug response prediction with multi-omics data.
Park S, Soh J, Lee H. Park S, et al. BMC Bioinformatics. 2021 May 25;22(1):269. doi: 10.1186/s12859-021-04146-z. BMC Bioinformatics. 2021. PMID: 34034645 Free PMC article. - Deep learning assisted multi-omics integration for survival and drug-response prediction in breast cancer.
Malik V, Kalakoti Y, Sundar D. Malik V, et al. BMC Genomics. 2021 Mar 24;22(1):214. doi: 10.1186/s12864-021-07524-2. BMC Genomics. 2021. PMID: 33761889 Free PMC article. - Deep structure integrative representation of multi-omics data for cancer subtyping.
Yang B, Yang Y, Su X. Yang B, et al. Bioinformatics. 2022 Jun 27;38(13):3337-3342. doi: 10.1093/bioinformatics/btac345. Bioinformatics. 2022. PMID: 35639657 - A roadmap for multi-omics data integration using deep learning.
Kang M, Ko E, Mersha TB. Kang M, et al. Brief Bioinform. 2022 Jan 17;23(1):bbab454. doi: 10.1093/bib/bbab454. Brief Bioinform. 2022. PMID: 34791014 Free PMC article. Review.
Cited by
- Deep learning methods for drug response prediction in cancer: Predominant and emerging trends.
Partin A, Brettin TS, Zhu Y, Narykov O, Clyde A, Overbeek J, Stevens RL. Partin A, et al. Front Med (Lausanne). 2023 Feb 15;10:1086097. doi: 10.3389/fmed.2023.1086097. eCollection 2023. Front Med (Lausanne). 2023. PMID: 36873878 Free PMC article. Review. - Machine learning: its challenges and opportunities in plant system biology.
Hesami M, Alizadeh M, Jones AMP, Torkamaneh D. Hesami M, et al. Appl Microbiol Biotechnol. 2022 May;106(9-10):3507-3530. doi: 10.1007/s00253-022-11963-6. Epub 2022 May 16. Appl Microbiol Biotechnol. 2022. PMID: 35575915 Review. - HYGIEIA: HYpothesizing the Genesis of Infectious Diseases and Epidemics through an Integrated Systems Biology Approach.
Ward B, Yombi JC, Balligand JL, Cani PD, Collet JF, de Greef J, Dewulf JP, Gatto L, Haufroid V, Jodogne S, Kabamba B, Pyr Dit Ruys S, Vertommen D, Elens L, Belkhir L. Ward B, et al. Viruses. 2022 Jun 23;14(7):1373. doi: 10.3390/v14071373. Viruses. 2022. PMID: 35891354 Free PMC article. - moBRCA-net: a breast cancer subtype classification framework based on multi-omics attention neural networks.
Choi JM, Chae H. Choi JM, et al. BMC Bioinformatics. 2023 Apr 26;24(1):169. doi: 10.1186/s12859-023-05273-5. BMC Bioinformatics. 2023. PMID: 37101124 Free PMC article. - Performance Comparisons of AlexNet and GoogLeNet in Cell Growth Inhibition IC50 Prediction.
Lee Y, Nam S. Lee Y, et al. Int J Mol Sci. 2021 Jul 19;22(14):7721. doi: 10.3390/ijms22147721. Int J Mol Sci. 2021. PMID: 34299341 Free PMC article.
References
- Almendro V. et al. (2013) Cellular heterogeneity and molecular evolution in cancer. Ann. Rev. Pathol., 8, 277–302. - PubMed
Publication types
MeSH terms
Substances
LinkOut - more resources
Full Text Sources
Other Literature Sources