GSAE: an autoencoder with embedded gene-set nodes for genomics functional characterization

Chen, Hung I Harry; Chiu, Yi-Chang; Zhang, Tinghe; Zhang, Songyao; Huang, Yufei; Chen, Yidong

doi:10.1186/s12918-018-0642-2

Cited by 41 publications

(34 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We will continue our work to investigate this issue by introducing yet another rich source of transcriptomic data from GTEx collection [33]. Furthermore, as suggested by previous studies [13,15,[34][35][36][37], we may incorporate additional genome-wide profiling information, such as DNA mutation, copy number variation, and DNA methylation as additional input matrices to enrich the complexity for model training, and thus to improve the classification accuracy.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Convolutional neural network models for cancer type prediction based on gene expression

Chiu²,

et al. 2020

Self Cite

View full text Add to dashboard Cite

BackgroundPrecise prediction of cancer types is vital for cancer diagnosis and therapy. Important cancer marker genes can be inferred through predictive model. Several studies have attempted to build machine learning models for this task however none has taken into consideration the effects of tissue of origin that can potentially bias the identification of cancer markers. ResultsIn this paper, we introduced several Convolutional Neural Network (CNN) models that take unstructured gene expression inputs to classify tumor and non-tumor samples into their designated cancer types or as normal. Based on different designs of gene embeddings and convolution schemes, we implemented three CNN models: 1D-CNN, 2D-Vanilla-CNN, and 2D-Hybrid-CNN. The models were trained and tested on combined 10,340 samples of 33 cancer types and 731 matched normal tissues of The Cancer Genome Atlas (TCGA). Our models achieved excellent prediction accuracies (93.9-95.0%) among 34 classes (33 cancers and normal). Furthermore, we interpreted one of the models, known as 1D-CNN model, with a guided saliency technique and identified a total of 2,090 cancer markers (108 per class). The concordance of differential expression of these markers between the cancer type they represent and others is confirmed. In breast cancer, for instance, our model identified well-known markers, such as GATA3 and ESR1. Finally, we extended the 1D-CNN model for prediction of breast cancer subtypes and achieved an average accuracy of 88.42% among 5 subtypes. The codes can be found at -3 -https://github.com/chenlabgccri/CancerTypePrediction. ConclusionsHere we present novel CNN designs for accurate and simultaneous cancer/normal and cancer types prediction based on gene expression profiles, and unique model interpretation scheme to elucidate biologically relevance of cancer marker genes after eliminating the effects of tissue-of-origin. The proposed model had light hyperparameters to be trained and thus can be easily adapt to facilitate cancer diagnosis in the future. BackgroundCancer is the second leading cause of death worldwide, an average of one in six deaths is due to cancer [1]. Considerable research efforts have been devoted to cancer diagnosis and treatment techniques to lessen its impact on human health. Cancer prediction's major focus is on cancer susceptibility, recurrence, and prognosis, while the aim of cancer detection is the classification of tumor types and identification of markers for each cancer such that we can build a learning machine to identify specific metastatic tumor type or detect cancer at their earlier stage. With the increased awareness of precision medicine and early detection techniques matured over years of technology development [2][3][4], including particularly many detection screens achieving a sensitivity around 70-80% [5], the demand for applying novel machine learning methods to discover new biomarkers has become one of the key driving factors in many clinical and translational applications.Deep learning (DL), a branch of Artificial ...

show abstract

Section: Discussionmentioning

confidence: 99%

“…In one of our earlier attempts [15], Chen, et al, constructed an autoencoder system (GSAE) with embedded pathways and functional gene-sets at each input node to reduce -6 -the number of weights to be estimated. They applied the GSAE to classify breast cancer subtypes.…”

mentioning

confidence: 99%

Convolutional neural network models for cancer type prediction based on gene expression

Chiu²,

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…For that purpose, Tan et al used denoising AEs derived from the transcriptomics of Pseudomonas aeruginosa and found a representation where each node coincided with known biological pathways (Tan et al 2016). Chen et al used cancer data and showed that starting from pathways represented as a priori defined hidden nodes, allowed the investigators to explain 88% of variance, which in turn produced an interpretable representation (Chen, et al, 2018). These results demonstrate that AEs can use pre-defined functional representations, and can learn such representations from input data, although systematic evaluation of how to balance between pre-defined features versus purely data-driven learning remains to be determined.…”

Section: Dnn Architectures Are Hierarchically Organized Layers Of Nonmentioning

confidence: 99%

Deriving Disease Modules from the Compressed Transcriptional Space Embedded in a Deep Auto-encoder

Dwivedi

Tjärnberg

Tegnér

et al. 2019

Preprint

View full text Add to dashboard Cite

Disease modules in molecular interaction maps have been useful for characterizing diseases.Yet biological networks, commonly used to define such modules are incomplete and biased toward some well-studied disease genes. Here we ask whether disease-relevant modules of genes can be discovered without assuming the prior knowledge of a biological network. To this end we train a deep auto-encoder on a large transcriptional data-set. Our hypothesis is that such modules could be discovered in the deep representations within the auto-encoder when trained to capture the variance in the input-output map of the transcriptional profiles. Using a three-layer deep auto-encoder we find a statistically significant enrichment of GWAS relevant genes in the third layer, and to a successively lesser degree in the second and first layers respectively. In contrast, we found an opposite gradient where a modular protein-protein interaction signal was strongest in the first layer but then vanishing smoothly deeper in the network. We conclude that a data-driven discovery approach, without assuming a particular biological network, is sufficient to discover groups of disease-related genes.

show abstract

“…Gene superset, which is an unbiased combination of gene sets, is the topic of the next paper. In the next study by Chen et al [4], the authors proposed a gene superset autoencoder (GSAE), a multi-layer autoencoder model with the incorporation of a priori defined gene sets that retain the crucial biological features in the latent layer. They introduced the concept of the gene superset, an unbiased combination of gene sets with weights trained by the autoencoder, where each node in the latent layer is a superset.…”

Section: The Science Program For the Icibm 2018 Systems Biology Trackmentioning

confidence: 99%

The International Conference on Intelligent Biology and Medicine (ICIBM) 2018: systems biology on diverse data types

et al. 2018

View full text Add to dashboard Cite

Between June 10–12, 2018, the International Conference on Intelligent Biology and Medicine (ICIBM 2018) was held in Los Angeles, California, USA. The conference included 11 scientific sessions, four tutorials, one poster session, four keynote talks and four eminent scholar talks that covered a wide range of topics in 3D genome structure analysis and visualization, next generation sequencing analysis, computational drug discovery, medical informatics, cancer genomics and systems biology. Systems biology has been a main theme in ICIBM 2018, with exciting advances presented in many areas of systems biology, covering various different data types such as gene regulation, circular RNAs expression, single-cell RNA-Seq, inter-chromosomal interactions, metabolomics, proteomics and phosphoproteomics. Here, we describe ten high quality papers to be published in BMC Systems Biology.

show abstract

GSAE: an autoencoder with embedded gene-set nodes for genomics functional characterization

Cited by 41 publications

References 51 publications

Convolutional neural network models for cancer type prediction based on gene expression

Convolutional neural network models for cancer type prediction based on gene expression

Deriving Disease Modules from the Compressed Transcriptional Space Embedded in a Deep Auto-encoder

The International Conference on Intelligent Biology and Medicine (ICIBM) 2018: systems biology on diverse data types

Contact Info

Product

Resources

About