A graph-embedded deep feedforward network for disease outcome classification and feature selection using gene expression data

Kong, Yunchuan; Yu, Tianwei

doi:10.1093/bioinformatics/bty429

Cited by 93 publications

(82 citation statements)

References 73 publications

(42 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Regarding the network architecture, models relying on four layer networks perform the best for both clinical outcomes (Table 3). This is in agreement with previous studies that have reported that such relatively small networks (i.e., with three or four layers) can efficiently predict clinical outcomes of kidney cancer patients [17] or can capture relevant features for survival analyses of a neuroblastoma cohort [12].…”

Section: Discussionsupporting

confidence: 92%

See 1 more Smart Citation

A deep neural network approach to predicting clinical outcomes of neuroblastoma patients

Tranchevent

Azuaje

Rajapakse

2019

Preprint

View full text Add to dashboard Cite

The availability of high-throughput omics datasets from large patient cohorts has allowed the development of methods that aim at predicting patient clinical outcomes, such as survival and disease recurrence. Such methods are also important to better understand the biological mechanisms underlying disease etiology and development, as well as treatment responses. Recently, different predictive models, relying on distinct algorithms (including Support Vector Machines and Random Forests) have been investigated. In this context, deep learning strategies are of special interest due to their demonstrated superior performance over a wide range of problems and datasets. One of the main challenges of such strategies is the "small n large p" problem. Indeed, omics datasets typically consist of small numbers of samples and large numbers of features relative to typical deep learning datasets. Neural networks usually tackle this problem through feature selection or by including additional constraints during the learning process.We propose to tackle this problem with a novel strategy that relies on a graph-based method for feature extraction, coupled with a deep neural network for clinical outcome prediction. The omics data are first represented as graphs whose nodes represent patients, and edges represent correlations between the patients' omics profiles. Topological features, such as centralities, are then extracted from these graphs for every node. Lastly, these features are used as input to train and test various classifiers.

show abstract

Section: Discussionsupporting

confidence: 92%

“…GEDFN accepts omics data as input together with a feature graph. Similarly to the original paper, we use the HINT database v4 [5] to retrieve the human protein-protein interaction network (PPIN) to be used as a feature graph [17]. The mapping between identifiers is performed through BioMart at EnsEMBL v92 [35].…”

Section: Other Modeling Approachesmentioning

confidence: 99%

A deep neural network approach to predicting clinical outcomes of neuroblastoma patients

Tranchevent

Azuaje

Rajapakse

2019

Preprint

View full text Add to dashboard Cite

show abstract

“…Also, a recent study [19] brings gene networks to deep learning, where applications on omics data were restricted primarily due to the n p issue [24]. In [19], a deep learning model Graph-Embedded Deep Feedforward Network (GEDFN) is proposed with the gene network embedded as a hidden layer in deep neural networks to achieve an informative sparse structure. In GEDFN, the graph-embedded layer helps achieve two effects.…”

Section: Introductionmentioning

confidence: 99%

forgeNet: a graph deep neural network model using tree-based ensemble classifiers for feature graph construction

Kong

2020

Bioinformatics

Self Cite

View full text Add to dashboard Cite

A unique challenge in predictive model building for omics data has been the small number of samples (n) versus the large amount of features (p). This "n p" property brings difficulties for disease outcome classification using deep learning techniques. Sparse learning by incorporating external gene network information such as the graph-embedded deep feedforward network (GEDFN) [19] model has been a solution to this issue. However, such methods require an existing feature graph, and potential mis-specification of the feature graph can be harmful on classification and feature selection. To address this limitation and develop a robust classification model without relying on external knowledge, we propose a forest graph-embedded deep feedforward network (forgeNet) model, to integrate the GEDFN architecture with a forest feature graph extractor, so that the feature graph can be learned in a supervised manner and specifically constructed for a given prediction task. To validate the method's capability, we experimented the forgeNet model with both synthetic and real datasets. The resulting high classification accuracy suggests that the method is a valuable addition to sparse deep learning models for omics data.

show abstract

“…Since we only use the correlation between omics for imputation, one possible direction is to leverage prior knowledge of gene-gene interaction network. The known relationships between variables/genes has demonstrated its ability to significantly reduce the model parameters by enforcing sparsity on the connections of neural network [19].…”

Section: Discussionmentioning

confidence: 99%

Imputing missing RNA-seq data from DNA methylation by using transfer learning based neural network

Zhou

Chai

Zhao

et al. 2019

Preprint

View full text Add to dashboard Cite

Multi-omics integrative analysis can capture the associations of different omics and thus provides a comprehensive view of the complex mechanisms in cancers. However, it is common that one portion of samples miss one type of omics data due to various limitations in experiments, which can be an obstacle for downstream analysis where complete dataset is needed. Current imputation methods mainly focus on single cancer dataset, which are limited by their ability to capture information from large pan-cancer dataset. We present a novel transfer learning-based deep neural network to impute missing gene expression data from DNA methylation data, namely TDimpute. The pan-cancer dataset was utilized to train a general model for all cancers, which was then fine-tuned on each cancer dataset for the specific cancer. We compared our method to other state-of-the-art methods on 16 cancer datasets, and found that our method consistently outperforms other methods in terms of imputation error, methylation-expression correlations recovery, and downstream analysis including the identification of DNA methylation-driving genes and prognosis-related genes, clustering analysis, and survival analysis. The improvements are especially pronounced at high missing rates. Author summaryAs an epigenetic modification, DNA methylation plays an important role in regulating gene expression. However, due to limitations of sample availability and cost, some samples aren't measured with gene expression, which results in a reduced sample size for integrative analysis of DNA methylation and gene expression. The accuracy of traditional imputation methods are limited since they cannot effectively utilize the information from DNA methylation data and other relevant datasets. With the power of modeling nonlinear relationship, we used deep neural network to impute missing gene expression data using the nonlinear transformation from DNA methylation data to gene expression data. We also employed transfer learning to alleviate the data insufficiency in training the deep leaning model. In 16 cancer datasets from The Cancer Genome Atlas (TCGA), our method yields higher accuracy compared to other methods. More importantly, better performance of the downstream analysis on imputed gene expression datasets are achieved, which indicates the missing data imputed by our method are more biologically meaningful.

show abstract

A graph-embedded deep feedforward network for disease outcome classification and feature selection using gene expression data

Abstract: Supplementary data are available at Bioinformatics online.

Cited by 93 publications

References 73 publications

A deep neural network approach to predicting clinical outcomes of neuroblastoma patients

A deep neural network approach to predicting clinical outcomes of neuroblastoma patients

forgeNet: a graph deep neural network model using tree-based ensemble classifiers for feature graph construction

Imputing missing RNA-seq data from DNA methylation by using transfer learning based neural network

Contact Info

Product

Resources

About