Deep Learning Based Tumor Type Classification Using Gene Expression Data

Lyu, Boyu; Haque, Anamul

doi:10.1145/3233547.3233588

Cited by 102 publications

(70 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…OncoNetExplainer slightly outperforms the approach by Boyu et al [6] but 6.5% better than the approach by Yuanyuan et al [5]. Further, OncoNetExplainer can improve the false prediction rate for the READ, UCS, ESCA, and CHOL tumor samples.…”

Section: E Comparison With Related Workmentioning

confidence: 79%

“…Further, OncoNetExplainer can improve the false prediction rate for the READ, UCS, ESCA, and CHOL tumor samples. In particular, against 35%, 81%, 77%, and 56% of the correctly predicted cases by [6], our approach can predict 88.74%, 87.26%, 89.56%, and 84.55% (in cyan) of the same cases correctly. Although OncoNetExplainer performs slightly worse than [6] at classifying BRCA, THCA, and PRAD (in red), it is more consistent for the majority of cancer types and likely to perform more stably on new GE data.…”

Section: E Comparison With Related Workmentioning

confidence: 82%

“…Lyu et al [6] and Mostavi et al [17] embedded the RNA-Seq data from the PCA project into 2D images and trained a CNN to classify 33 tumor types, which outperforms the approach in [5]. Besides, they provide a functional analysis on the genes with high intensities in the HM based on GradCAM and validated that these top genes are related to tumor-specific pathways.…”

Section: Related Workmentioning

confidence: 99%

“…Besides, clinical outcomes, i.e., clinical and pathology information are provided. TCGA further analyzed over 11,000 cancer cases from 33 prevalent forms of cancer, which fostered the accomplishment of the Pan-Cancer Atlas (PCA), which results from the normalized GE data about 20K protein-coding genes [6].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

OncoNetExplainer: Explainable Predictions of Cancer Types Based on Gene Expression Data

Karim

Cochez

Beyan

et al. 2019

2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)

View full text Add to dashboard Cite

The discovery of important biomarkers is a significant step towards understanding the molecular mechanisms of carcinogenesis; enabling accurate diagnosis for, and prognosis of, a certain cancer type. Before recommending any diagnosis, genomics data such as gene expressions (GE) and clinical outcomes need to be analyzed. However, complex nature, high dimensionality, and heterogeneity in genomics data make the overall analysis challenging. Convolutional neural networks (CNN) have shown tremendous success in solving such problems. However, neural network models are perceived mostly as 'black box' methods because of their not well-understood internal functioning. However, interpretability is important to provide insights on why a given cancer case has a certain type. Besides, finding the most important biomarkers can help in recommending more accurate treatments and drug repositioning. Moreover, the 'right to explanation' of the EU GDPR gives patients the right to know why and how an algorithm made a diagnosis decision. Hence, in this paper, we propose a new approach called OncoNetExplainer to make explainable predictions of cancer types based on GE data. We used genomics data about 9,074 cancer patients covering 33 different cancer types from the Pan-Cancer Atlas on which we trained CNN and VGG16 networks using guided-gradient class activation maps++ (GradCAM++). Further, we generate class-specific heat maps to identify significant biomarkers and computed feature importance in terms of mean absolute impact to rank top genes across all the cancer types. Quantitative and qualitative analyses show that both models exhibit high confidence at predicting the cancer types correctly giving an average precision of 96.25%. To provide comparisons with the baselines, we identified top genes, and cancer-specific driver genes using gradient boosted trees and SHapley Additive ex-Planations (SHAP). Finally, our findings were validated with the annotations provided by the TumorPortal.

show abstract

Section: E Comparison With Related Workmentioning

confidence: 79%

Section: E Comparison With Related Workmentioning

confidence: 82%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

OncoNetExplainer: Explainable Predictions of Cancer Types Based on Gene Expression Data

Karim

Cochez

Beyan

et al. 2019

2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)

View full text Add to dashboard Cite

show abstract

“…Advances in profiling technologies are rapidly increasing the availability of expression datasets. This has enabled the application of the complex non-linear models, such as neural networks, to various biological problems in order to identify signals not detectable using simple linear models (Lyu and Haque, 2018;Preuer et al, 2018;Chaudhary et al, 2018).…”

Section: Introductionmentioning

confidence: 99%

Adversarial Deconfounding Autoencoder for Learning Robust Gene Expression Embeddings

Dincer

Janizek

Lee

2020

Preprint

View full text Add to dashboard Cite

Motivation: Increasing number of gene expression profiles has enabled the use of complex models, such as deep unsupervised neural networks, to extract a latent space from these profiles. However, expression profiles, especially when collected in large numbers, inherently contain variations introduced by technical artifacts (e.g., batch effects) and uninteresting biological variables (e.g., age) in addition to the true signals of interest. These sources of variations, called confounders, produce embeddings that fail to transfer to different domains, i.e., an embedding learned from one dataset with a specific confounder distribution does not generalize to different distributions. To remedy this problem, we attempt to disentangle confounders from true signals to generate biologically informative embeddings. Results: In this paper, we introduce the AD-AE (Adversarial Deconfounding AutoEncoder) approach to deconfounding gene expression latent spaces. The AD-AE model consists of two neural networks: (i) an autoencoder to generate an embedding that can reconstruct original measurements, and (ii) an adversary trained to predict the confounder from that embedding. We jointly train the networks to generate embeddings that can encode as much information as possible without encoding any confounding signal. By applying AD-AE to two distinct gene expression datasets, we show that our model can (1) generate embeddings that do not encode confounder information, (2) conserve the biological signals present in the original space, and (3) generalize successfully across different confounder domains. We demonstrate that AD-AE outperforms standard autoencoder and other deconfounding approaches.

show abstract

Lung cancer subtyping from gene expression data using general and enhanced Fuzzy min–max neural networks

Singh

Susan

2023

Engineering Reports

View full text Add to dashboard Cite

In this article, we address the problem of lung cancer diagnosis from gene expression data, which is now recognized as an effective means for early treatment and prevention of cancer. Specifically, we employ Fuzzy min–max (FMM) classifier for the task which is a well‐known neuro‐fuzzy neural network. The idea is to take advantage of the fuzzy class definitions whose boundaries are set using the min–max hyperbox constructed for each class. We implement two advanced FMM neural network architectures: general Fuzzy min–max (GFMM) and enhanced Fuzzy min–max (EFMM) for the classification of lung cancer subtypes from gene expression data. The advantage of GFMM is that it involves very simple operations for hyperbox manipulation, and can handle both labeled and unlabeled data. On the other hand, EFMM proposes three heuristic rules related to hyperbox expansion, contraction and the overlap test, which enhances the learning algorithm. We perform the classification of gene expression data using these two models, and then we analyze the performance by visualizing the hyperboxes obtained after training, and compare the accuracies of these classifiers with the state of the art. Least absolute shrinkage and selection operator (LASSO) is used for selecting the informative genes from the high‐dimensional gene expression data. From the empirical results, we observe that GFMM with LASSO gives the best performance of all, with validation accuracy of 98.04% and cross‐validation accuracy of 94.06%.

show abstract

Deep Learning Based Tumor Type Classification Using Gene Expression Data

Cited by 102 publications

References 16 publications

OncoNetExplainer: Explainable Predictions of Cancer Types Based on Gene Expression Data

OncoNetExplainer: Explainable Predictions of Cancer Types Based on Gene Expression Data

Adversarial Deconfounding Autoencoder for Learning Robust Gene Expression Embeddings

Lung cancer subtyping from gene expression data using general and enhanced Fuzzy min–max neural networks

Contact Info

Product

Resources

About