DeepCDR: a hybrid graph convolutional network for predicting cancer drug response

Li, Qiao; Hu, Zhiqiang; Jiang, Rui; Zhou, Mu

doi:10.1093/bioinformatics/btaa822

Cited by 119 publications

(103 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Overall, RS and deep learning have been the most widely MDL methods used for DRP. The results reported in the literature suggest the superiority of RSs [ 24 , 114 , 116 , 123 , 124 , 126 , 129 , 130 ] and deep learning methods [ 93 , 96 , 101 , 104 , 107 ] over more traditional approaches, such as linear regression, RF and SVM.…”

Section: Discussion and Outlookmentioning

confidence: 99%

“…GNNs can be used to encode drug features as points in a low-dimensional space, in which similar drugs are close to each other, by representing molecular structure of compounds as networks formed by sets of chemical bonds between atoms [ 105 , 106 ]. In DeepCDR [ 107 ] and GraphDRP [ 108 ], deep drug features learnt by GNNs are concatenated with deep multi-omics features, to be fed to feedforward ANNs for DRP. Manica et al.…”

Section: Drp Modelsmentioning

confidence: 99%

See 1 more Smart Citation

An overview of machine learning methods for monotherapy drug response prediction

Firoozbakht

Yousefi

Schwikowski

2021

Briefings in Bioinformatics

View full text Add to dashboard Cite

For an increasing number of preclinical samples, both detailed molecular profiles and their responses to various drugs are becoming available. Efforts to understand, and predict, drug responses in a data-driven manner have led to a proliferation of machine learning (ML) methods, with the longer term ambition of predicting clinical drug responses. Here, we provide a uniquely wide and deep systematic review of the rapidly evolving literature on monotherapy drug response prediction, with a systematic characterization and classification that comprises more than 70 ML methods in 13 subclasses, their input and output data types, modes of evaluation, and code and software availability. ML experts are provided with a fundamental understanding of the biological problem, and how ML methods are configured for it. Biologists and biomedical researchers are introduced to the basic principles of applicable ML methods, and their application to the problem of drug response prediction. We also provide systematic overviews of commonly used data sources used for training and evaluation methods.

show abstract

Section: Discussion and Outlookmentioning

confidence: 99%

Section: Drp Modelsmentioning

confidence: 99%

An overview of machine learning methods for monotherapy drug response prediction

Firoozbakht

Yousefi

Schwikowski

2021

Briefings in Bioinformatics

View full text Add to dashboard Cite

show abstract

“…Liu et al . [ 47 ] presented DeepCDR, a hybrid graph convolutional network (UGCN) for exploring intrinsic chemical structures of drugs for predicting cancer drug response (CDR), and the successful use of the synergy of multi-omics profiles significantly improves the performance of CDR prediction. Kumar et al .…”

Section: Discussionmentioning

confidence: 99%

BioNet: a large-scale and heterogeneous biological network model for interaction prediction with graph convolution

Yang

Wang

et al. 2021

Briefings in Bioinformatics

View full text Add to dashboard Cite

Motivation Understanding chemical–gene interactions (CGIs) is crucial for screening drugs. Wet experiments are usually costly and laborious, which limits relevant studies to a small scale. On the contrary, computational studies enable efficient in-silico exploration. For the CGI prediction problem, a common method is to perform systematic analyses on a heterogeneous network involving various biomedical entities. Recently, graph neural networks become popular in the field of relation prediction. However, the inherent heterogeneous complexity of biological interaction networks and the massive amount of data pose enormous challenges. This paper aims to develop a data-driven model that is capable of learning latent information from the interaction network and making correct predictions. Results We developed BioNet, a deep biological networkmodel with a graph encoder–decoder architecture. The graph encoder utilizes graph convolution to learn latent information embedded in complex interactions among chemicals, genes, diseases and biological pathways. The learning process is featured by two consecutive steps. Then, embedded information learnt by the encoder is then employed to make multi-type interaction predictions between chemicals and genes with a tensor decomposition decoder based on the RESCAL algorithm. BioNet includes 79 325 entities as nodes, and 34 005 501 relations as edges. To train such a massive deep graph model, BioNet introduces a parallel training algorithm utilizing multiple Graphics Processing Unit (GPUs). The evaluation experiments indicated that BioNet exhibits outstanding prediction performance with a best area under Receiver Operating Characteristic (ROC) curve of 0.952, which significantly surpasses state-of-theart methods. For further validation, top predicted CGIs of cancer and COVID-19 by BioNet were verified by external curated data and published literature.

show abstract

“…There are some other studies that focus on the effect of drug treatment on cell growth. Liu Q. et al (2020) predicted the therapeutic effect of drugs on cancer cells by constructing a cancer cell information sub-network and a drug structure sub-network. Considering the complexity of cancer factors, Singha et al (2020) integrated biological network, genomics, inhibitor analysis, and disease–gene association data into a large heterogeneous graph.…”

Section: Typical Application Of Gnns In Bioinformaticsmentioning

confidence: 99%

Graph Neural Networks and Their Current Applications in Bioinformatics

et al. 2021

View full text Add to dashboard Cite

Graph neural networks (GNNs), as a branch of deep learning in non-Euclidean space, perform particularly well in various tasks that process graph structure data. With the rapid accumulation of biological network data, GNNs have also become an important tool in bioinformatics. In this research, a systematic survey of GNNs and their advances in bioinformatics is presented from multiple perspectives. We first introduce some commonly used GNN models and their basic principles. Then, three representative tasks are proposed based on the three levels of structural information that can be learned by GNNs: node classification, link prediction, and graph generation. Meanwhile, according to the specific applications for various omics data, we categorize and discuss the related studies in three aspects: disease prediction, drug discovery, and biomedical imaging. Based on the analysis, we provide an outlook on the shortcomings of current studies and point out their developing prospect. Although GNNs have achieved excellent results in many biological tasks at present, they still face challenges in terms of low-quality data processing, methodology, and interpretability and have a long road ahead. We believe that GNNs are potentially an excellent method that solves various biological problems in bioinformatics research.

show abstract

DeepCDR: a hybrid graph convolutional network for predicting cancer drug response

Cited by 119 publications

References 32 publications

An overview of machine learning methods for monotherapy drug response prediction

An overview of machine learning methods for monotherapy drug response prediction

BioNet: a large-scale and heterogeneous biological network model for interaction prediction with graph convolution

Graph Neural Networks and Their Current Applications in Bioinformatics

Contact Info

Product

Resources

About