MGAE-DC: Predicting the synergistic effects of drug combinations through multi-channel graph autoencoders

Peng Zhang and Shikui Tu

PLOS Computational Biology, 2023, vol. 19, issue 3, 1-19

Abstract: Accurate prediction of synergistic effects of drug combinations can reduce the experimental costs for drug development and facilitate the discovery of novel efficacious combination therapies for clinical studies. The drug combinations with high synergy scores are regarded as synergistic ones, while those with moderate or low synergy scores are additive or antagonistic ones. The existing methods usually exploit the synergy data from the aspect of synergistic drug combinations, paying little attention to the additive or antagonistic ones. Also, they usually do not leverage the common patterns of drug combinations across different cell lines. In this paper, we propose a multi-channel graph autoencoder (MGAE)-based method for predicting the synergistic effects of drug combinations (DC), and shortly denote it as MGAE-DC. A MGAE model is built to learn the drug embeddings by considering not only synergistic combinations but also additive and antagonistic ones as three input channels. The later two channels guide the model to explicitly characterize the features of non-synergistic combinations through an encoder-decoder learning process, and thus the drug embeddings become more discriminative between synergistic and non-synergistic combinations. In addition, an attention mechanism is incorporated to fuse each cell-line’s drug embeddings across various cell lines, and a common drug embedding is extracted to capture the invariant patterns by developing a set of cell-line shared decoders. The generalization performance of our model is further improved with the invariant patterns. With the cell-line specific and common drug embeddings, our method is extended to predict the synergy scores of drug combinations by a neural network module. Experiments on four benchmark datasets demonstrate that MGAE-DC consistently outperforms the state-of-the-art methods. In-depth literature survey is conducted to find that many drug combinations predicted by MGAE-DC are supported by previous experimental studies. The source code and data are available at https://github.com/yushenshashen/MGAE-DC.Author summary: Drug combination therapy is widely employed for various complex diseases because of its advantages of enhancing the efficiency, overcoming the drug resistance and reducing dose-dependent toxicity relative to monotherapy. To identify novel reliable and efficacious drug combinations for the patients, various methods have been proposed in the past decades. The trial-based methods are based on the clinical trials directly, but may cause patients to receive unnecessary or even harmful treatments. The experimental methods are labour and cost intensive, it is infeasible to test the complete drug combination space due to the combinatorial explosion. Computational methods provide attractive solutions to make the prediction based on the known data in silico, and thus narrow down the searching range of potential combinations. We have developed a novel deep learning method, named MGAE-DC, for predicting the synergistic effects of drug combinations. Our method explicitly characterizes not only synergistic combinations but also non-synergistic ones to obtain discriminative drug embeddings. Our method also learns common features of drug combinations across the cell lines for improved generalization performance. Computational experiments have verified the effectiveness of MGAE-DC.

Date: 2023
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1010951 (text/html)
https://journals.plos.org/ploscompbiol/article/fil ... 10951&type=printable (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:plo:pcbi00:1010951

DOI: 10.1371/journal.pcbi.1010951

Access Statistics for this article

More articles in PLOS Computational Biology from Public Library of Science
Bibliographic data for series maintained by ploscompbiol ().