scholarly journals A hierarchical integration deep flexible neural forest framework for cancer subtype classification by integrating multi-omics data

2019 ◽  
Vol 20 (1) ◽  
Author(s):  
Jing Xu ◽  
Peng Wu ◽  
Yuehui Chen ◽  
Qingfang Meng ◽  
Hussain Dawood ◽  
...  
Keyword(s):  
Gene Expression ◽  
Gene Expression Data ◽  
High Throughput Sequencing ◽  
Omics Data ◽  
Expression Data ◽  
Cancer Subtypes ◽  
Stacked Autoencoder ◽  
Subtype Classification ◽  
Sequencing Technologies ◽  
Cancer Subtype

Abstract Background Cancer subtype classification attains the great importance for accurate diagnosis and personalized treatment of cancer. Latest developments in high-throughput sequencing technologies have rapidly produced multi-omics data of the same cancer sample. Many computational methods have been proposed to classify cancer subtypes, however most of them generate the model by only employing gene expression data. It has been shown that integration of multi-omics data contributes to cancer subtype classification. Results A new hierarchical integration deep flexible neural forest framework is proposed to integrate multi-omics data for cancer subtype classification named as HI-DFNForest. Stacked autoencoder (SAE) is used to learn high-level representations in each omics data, then the complex representations are learned by integrating all learned representations into a layer of autoencoder. Final learned data representations (from the stacked autoencoder) are used to classify patients into different cancer subtypes using deep flexible neural forest (DFNForest) model.Cancer subtype classification is verified on BRCA, GBM and OV data sets from TCGA by integrating gene expression, miRNA expression and DNA methylation data. These results demonstrated that integrating multiple omics data improves the accuracy of cancer subtype classification than only using gene expression data and the proposed framework has achieved better performance compared with other conventional methods. Conclusion The new hierarchical integration deep flexible neural forest framework(HI-DFNForest) is an effective method to integrate multi-omics data to classify cancer subtypes.

scholarly journals A Cascade Flexible Neural Forest Model for Cancer Subtypes Classification on Gene Expression Data

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Lianxin Zhong ◽  
Qingfang Meng ◽  
Yuehui Chen
Keyword(s):  
Gene Expression ◽  
Sample Size ◽  
Gene Expression Data ◽  
Small Sample Size ◽  
Small Sample ◽  
Expression Data ◽  
Cancer Subtypes ◽  
Subtype Classification ◽  
Cancer Subtype

The correct classification of cancer subtypes is of great significance for the in-depth study of cancer pathogenesis and the realization of accurate treatment for cancer patients. In recent years, the classification of cancer subtypes using deep neural networks and gene expression data has become a hot topic. However, most classifiers may face the challenges of overfitting and low classification accuracy when dealing with small sample size and high-dimensional biological data. In this paper, the Cascade Flexible Neural Forest (CFNForest) Model was proposed to accomplish cancer subtype classification. CFNForest extended the traditional flexible neural tree structure to FNT Group Forest exploiting a bagging ensemble strategy and could automatically generate the model’s structure and parameters. In order to deepen the FNT Group Forest without introducing new hyperparameters, the multilayer cascade framework was exploited to design the FNT Group Forest model, which transformed features between levels and improved the performance of the model. The proposed CFNForest model also improved the operational efficiency and the robustness of the model by sample selection mechanism between layers and setting different weights for the output of each layer. To accomplish cancer subtype classification, FNT Group Forest with different feature sets was used to enrich the structural diversity of the model, which make it more suitable for processing small sample size datasets. The experiments on RNA-seq gene expression data showed that CFNForest effectively improves the accuracy of cancer subtype classification. The classification results have good robustness.

scholarly journals A Graph Feature Auto-Encoder for the prediction of unobserved node features on biological networks

2021 ◽  
Vol 22 (1) ◽  
Author(s):  
Ramin Hasibi ◽  
Tom Michoel
Keyword(s):  
Gene Expression ◽  
Neural Networks ◽  
Gene Expression Data ◽  
Biological Networks ◽  
Molecular Interaction ◽  
Interaction Networks ◽  
Omics Data ◽  
Expression Data ◽  
Molecular Interaction Networks ◽  
Graph Neural Networks

Abstract Background Molecular interaction networks summarize complex biological processes as graphs, whose structure is informative of biological function at multiple scales. Simultaneously, omics technologies measure the variation or activity of genes, proteins, or metabolites across individuals or experimental conditions. Integrating the complementary viewpoints of biological networks and omics data is an important task in bioinformatics, but existing methods treat networks as discrete structures, which are intrinsically difficult to integrate with continuous node features or activity measures. Graph neural networks map graph nodes into a low-dimensional vector space representation, and can be trained to preserve both the local graph structure and the similarity between node features. Results We studied the representation of transcriptional, protein–protein and genetic interaction networks in E. coli and mouse using graph neural networks. We found that such representations explain a large proportion of variation in gene expression data, and that using gene expression data as node features improves the reconstruction of the graph from the embedding. We further proposed a new end-to-end Graph Feature Auto-Encoder framework for the prediction of node features utilizing the structure of the gene networks, which is trained on the feature prediction task, and showed that it performs better at predicting unobserved node features than regular MultiLayer Perceptrons. When applied to the problem of imputing missing data in single-cell RNAseq data, the Graph Feature Auto-Encoder utilizing our new graph convolution layer called FeatGraphConv outperformed a state-of-the-art imputation method that does not use protein interaction information, showing the benefit of integrating biological networks and omics data with our proposed approach. Conclusion Our proposed Graph Feature Auto-Encoder framework is a powerful approach for integrating and exploiting the close relation between molecular interaction networks and functional genomics data.

CrossICC: iterative consensus clustering of cross-platform gene expression data without adjusting batch effect

2019 ◽  
Vol 21 (5) ◽  
pp. 1818-1824 ◽  
Author(s):  
Qi Zhao ◽  
Yu Sun ◽  
Zekun Liu ◽  
Hongwan Zhang ◽  
Xingyang Li ◽  
...  
Keyword(s):  
Gene Expression ◽  
Gene Expression Data ◽  
Gene Signature ◽  
Unsupervised Clustering ◽  
Batch Effect ◽  
Consensus Clustering ◽  
Expression Data ◽  
Personalized Care ◽  
Cancer Subtypes ◽  
Multiple Datasets

Abstract   Unsupervised clustering of high-throughput gene expression data is widely adopted for cancer subtyping. However, cancer subtypes derived from a single dataset are usually not applicable across multiple datasets from different platforms. Merging different datasets is necessary to determine accurate and applicable cancer subtypes but is still embarrassing due to the batch effect. CrossICC is an R package designed for the unsupervised clustering of gene expression data from multiple datasets/platforms without the requirement of batch effect adjustment. CrossICC utilizes an iterative strategy to derive the optimal gene signature and cluster numbers from a consensus similarity matrix generated by consensus clustering. This package also provides abundant functions to visualize the identified subtypes and evaluate subtyping performance. We expected that CrossICC could be used to discover the robust cancer subtypes with significant translational implications in personalized care for cancer patients. Availability and Implementation The package is implemented in R and available at GitHub (https://github.com/bioinformatist/CrossICC) and Bioconductor (http://bioconductor.org/packages/release/bioc/html/CrossICC.html) under the GPL v3 License.

scholarly journals A Novel Deep Flexible Neural Forest Model for Classification of Cancer Subtypes Based on Gene Expression Data

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 22086-22095 ◽  
Author(s):  
Jing Xu ◽  
Peng Wu ◽  
Yuehui Chen ◽  
Qingfang Meng ◽  
Hussain Dawood ◽  
...  
Keyword(s):  
Gene Expression ◽  
Gene Expression Data ◽  
Expression Data ◽  
Cancer Subtypes ◽  
Forest Model

scholarly journals A laminar augmented cascading flexible neural forest model for classification of cancer subtypes based on gene expression data

2021 ◽  
Vol 22 (1) ◽  
Author(s):  
Lianxin Zhong ◽  
Qingfang Meng ◽  
Yuehui Chen ◽  
Lei Du ◽  
Peng Wu
Keyword(s):  
Gene Expression ◽  
Gene Expression Data ◽  
Small Sample Size ◽  
Small Sample ◽  
Expression Data ◽  
Cancer Subtypes ◽  
Cancer Pathogenesis ◽  
Depth Study ◽  
And Function

Abstract Background Correctly classifying the subtypes of cancer is of great significance for the in-depth study of cancer pathogenesis and the realization of personalized treatment for cancer patients. In recent years, classification of cancer subtypes using deep neural networks and gene expression data has gradually become a research hotspot. However, most classifiers may face overfitting and low classification accuracy when dealing with small sample size and high-dimensional biology data. Results In this paper, a laminar augmented cascading flexible neural forest (LACFNForest) model was proposed to complete the classification of cancer subtypes. This model is a cascading flexible neural forest using deep flexible neural forest (DFNForest) as the base classifier. A hierarchical broadening ensemble method was proposed, which ensures the robustness of classification results and avoids the waste of model structure and function as much as possible. We also introduced an output judgment mechanism to each layer of the forest to reduce the computational complexity of the model. The deep neural forest was extended to the densely connected deep neural forest to improve the prediction results. The experiments on RNA-seq gene expression data showed that LACFNForest has better performance in the classification of cancer subtypes compared to the conventional methods. Conclusion The LACFNForest model effectively improves the accuracy of cancer subtype classification with good robustness. It provides a new approach for the ensemble learning of classifiers in terms of structural design.

scholarly journals Differential proportionality - a normalization-free approach to differential gene expression

2017 ◽  
Author(s):  
Ionas Erb ◽  
Thomas Quinn ◽  
David Lovell ◽  
Cedric Notredame
Keyword(s):  
Gene Expression ◽  
Differential Expression ◽  
Gene Expression Data ◽  
Expression Data ◽  
Computationally Efficient ◽  
Data Set ◽  
Sequencing Technologies ◽  
Expression Of Genes ◽  
The One ◽  
Log Ratio

AbstractGene expression data, such as those generated by next generation sequencing technologies (RNA-seq), are of an inherently relative nature: the total number of sequenced reads has no biological meaning. This issue is most often addressed with various normalization techniques which all face the same problem: once information about the total mRNA content of the origin cells is lost, it cannot be recovered by mere technical means. Additional knowledge, in the form of an unchanged reference, is necessary; however, this reference can usually only be estimated. Here we propose a novel method where sample normalization is unnecessary, but important insights can be obtained nevertheless. Instead of trying to recover absolute abundances, our method is entirely based on ratios, so normalization factors cancel by default. Although the differential expression of individual genes cannot be recovered this way, the ratios themselves can be differentially expressed (even when their constituents are not). Yet, most current analyses are blind to these cases, while our approach reveals them directly. Specifically, we show how the differential expression of gene ratios can be formalized by decomposing log-ratio variance (LRV) and deriving intuitive statistics from it. Although small LRVs have been used to detect proportional genes in gene expression data before, we focus here on the change in proportionality factors between groups of samples (e.g. tissue-specific proportionality). For this, we propose a statistic that is equivalent to the squared t-statistic of one-way ANOVA, but for gene ratios. In doing so, we show how precision weights can be incorporated to account for the peculiarities of count data, and, moreover, how a moderated statistic can be derived in the same way as the one following from a hierarchical model for individual genes. We also discuss approaches to deal with zero counts, deriving an expression of our statistic that is able to incorporate them. In providing a detailed analysis of the connections between the differential expression of genes and the differential proportionality of pairs, we facilitate a clear interpretation of new concepts. The proposed framework is applied to a data set from GTEx consisting of 98 samples from the cerebellum and cortex, with selected examples shown. A computationally efficient implementation of the approach in R has been released as an addendum to the propr package.1

Correlation of intratumor gene expression heterogeneity with chemotherapy sensitivity in breast cancer.

2013 ◽  
Vol 31 (15_suppl) ◽  
pp. 1013-1013 ◽  
Author(s):  
Rene Natowicz ◽  
Tingting Jiang ◽  
Weiwei Shi ◽  
Yuan Qi ◽  
Yann Delpech ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Gene Expression ◽  
Neoadjuvant Chemotherapy ◽  
Gene Expression Data ◽  
Pathologic Complete Response ◽  
Intratumor Heterogeneity ◽  
Expression Data ◽  
Chemotherapy Sensitivity ◽  
Cancer Subtypes ◽  
Gene Expression Heterogeneity

1013 Background: The goal of this study was to develop a method to quantify intratumor heterogeneity of cancers using gene expression data. We compared gene expression heterogeneity between different molecular subtypes of breast cancer and between basal like cancers with or without pathologic complete response (pCR) to neoadjuvant chemotherapy. Methods: Affymetrix U133A gene expression data of 335 stage I-III breast cancers were analyzed. Molecular class was assigned using the PAM50 predictor. All patients received neoadjuvant chemotherapy. We measured tumor heterogeneity by the Gini index (GI) calculated individually for each case over the expression of all probe sets and random subsets. The GI was used as a metric of inequality of gene expression distributions between cases. The higher the GI, the greater the inequality of the expression distribution. Results: Basal like cancers (n=138) had greater heterogeneity than luminal cancers (n=197) (mean GI values 24.51 vs 23.05, p<0.001) and luminal B (n=71) cancers had greater heterogeneity compared to Luminal A (n=126) cancers (24.49 vs 22.25, p<0.001). Among the basal-like cancers, those with pCR (n=44) had significantly higher heterogeneity compared to cancers with residual disease (RD, n=94) (26.10 vs 23.77, p<0.001). Significant differences in GI between cancer subtypes remained for as low 2500 randomly selected probe sets. Conclusions: Breast cancer subtypes differ in intratumor gene expression heterogeneity. Greater degree of heterogeneity correlate with greater chemotherapy sensitivity. Importantly, among basal-like cancers only the heterogeneity metric differed significantly between cases with pCR or RD but not individual genes expression values or gene signatures.

scholarly journals Classification of Breast Cancer Subtypes by combining Gene Expression and DNA Methylation Data

2014 ◽  
Vol 11 (2) ◽  
pp. 1-14 ◽  
Author(s):  
Markus List ◽  
Anne-Christin Hauschild ◽  
Qihua Tan ◽  
Torben A. Kruse ◽  
Jan Baumbach ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Gene Expression ◽  
Gene Expression Data ◽  
Breast Cancer Subtype ◽  
Methylation Data ◽  
Expression Data ◽  
Model Based ◽  
Cancer Subtype ◽  
Expression Model ◽  
Gene Expression Model

Summary Selecting the most promising treatment strategy for breast cancer crucially depends on determining the correct subtype. In recent years, gene expression profiling has been investigated as an alternative to histochemical methods. Since databases like TCGA provide easy and unrestricted access to gene expression data for hundreds of patients, the challenge is to extract a minimal optimal set of genes with good prognostic properties from a large bulk of genes making a moderate contribution to classification. Several studies have successfully applied machine learning algorithms to solve this so-called gene selection problem. However, more diverse data from other OMICS technologies are available, including methylation. We hypothesize that combining methylation and gene expression data could already lead to a largely improved classification model, since the resulting model will reflect differences not only on the transcriptomic, but also on an epigenetic level. We compared so-called random forest derived classification models based on gene expression and methylation data alone, to a model based on the combined features and to a model based on the gold standard PAM50. We obtained bootstrap errors of 10-20% and classification error of 1-50%, depending on breast cancer subtype and model. The gene expression model was clearly superior to the methylation model, which was also reflected in the combined model, which mainly selected features from gene expression data. However, the methylation model was able to identify unique features not considered as relevant by the gene expression model, which might provide deeper insights into breast cancer subtype differentiation on an epigenetic level.

Sign in / Sign up

Export Citation Format

Share Document