Cancer subtype classification and modeling by pathway attention and propagation

Lee, Sangseon; Lim, Sangsoo; Lee, Taeheon; Sung, Inyoung; Kim, Sun

doi:10.1093/bioinformatics/btaa203

Cited by 37 publications

(23 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the future, we will also try other machine learning methods or deep learning methods (Kong and Yu, 2018;Ding et al, 2019a,b;Shen et al, 2019;Gao et al, 2020;Lee et al, 2020;Wang et al, 2020), to deal with the problem of small samples and large features of cancer data and predict cancer subtypes more accurately.…”

Section: Resultsmentioning

confidence: 99%

Multi-Omics Data Fusion via a Joint Kernel Learning Model for Cancer Subtype Discovery and Essential Gene Identification

Feng

Jiang

et al. 2021

Front. Genet.

View full text Add to dashboard Cite

The multiple sources of cancer determine its multiple causes, and the same cancer can be composed of many different subtypes. Identification of cancer subtypes is a key part of personalized cancer treatment and provides an important reference for clinical diagnosis and treatment. Some studies have shown that there are significant differences in the genetic and epigenetic profiles among different cancer subtypes during carcinogenesis and development. In this study, we first collect seven cancer datasets from the Broad Institute GDAC Firehose, including gene expression profile, isoform expression profile, DNA methylation expression data, and survival information correspondingly. Furthermore, we employ kernel principal component analysis (PCA) to extract features for each expression profile, convert them into three similarity kernel matrices by Gaussian kernel function, and then fuse these matrices as a global kernel matrix. Finally, we apply it to spectral clustering algorithm to get the clustering results of different cancer subtypes. In the experimental results, besides using the P-value from the Cox regression model and survival analysis as the primary evaluation measures, we also introduce statistical indicators such as Rand index (RI) and adjusted RI (ARI) to verify the performance of clustering. Then combining with gene expression profile, we obtain the differential expression of genes among different subtypes by gene set enrichment analysis. For lung cancer, GMPS, EPHA10, C10orf54, and MAGEA6 are highly expressed in different subtypes; for liver cancer, CMYA5, DEPDC6, FAU, VPS24, RCBTB2, LOC100133469, and SLC35B4 are significantly expressed in different subtypes.

show abstract

Section: Resultsmentioning

confidence: 99%

Multi-Omics Data Fusion via a Joint Kernel Learning Model for Cancer Subtype Discovery and Essential Gene Identification

Feng

Jiang

et al. 2021

Front. Genet.

View full text Add to dashboard Cite

show abstract

“…Wright GW et al described an algorithm that determines the probability that a patient's lymphoma belongs to one of seven genetic subtypes based on its genetic features [21]. Lee S et al presented an explainable deep learning model with attention mechanism and network propagation for cancer subtype classi cation [22]. Most of these developed clari cation methods only focused on coding genes.…”

Section: Discussionmentioning

confidence: 99%

Inference of Molecular Subtypes of Uterine Corpus Endometrioid Carcinoma with Different Survival Based on Cancer Hallmarks-associated Long Non-Coding RNAs and Gene Modules

Zhao

et al. 2020

Preprint

View full text Add to dashboard Cite

Background: Uterine corpus endometrioid carcinoma (UCEC), a common gynecological malignancy with high incidence, affects the mental and physical health of women. It is increasingly evident that long non-coding RNAs (lncRNAs) have causative roles in cancers including UCEC. However, very little is known about the cancer hallmark-related risks for UCEC based on lncRNAs and genes. Methods: In this study, a computational integrated pipeline was development to evaluate cancer hallmark-related risk for each UCEC patient based on gene and lncRNA expression. Results: Some UCEC-specific cancer hallmark-related genes and lncRNAs were identified. Core modules were extracted from co-expressed UCEC-specific lncRNAs and genes networks for each cancer hallmark. Some core modules showed specific features and functions. Follow a multi-dimensional rank approach and core modules, each UCEC sample was given an integrated cancer hallmark-related risk score. We divided all the UCEC patients to diverse hallmark risk groups including multi-hallmark, media-hallmark and single-hallmark groups and they showed different prognosis. We also identified some key lncRNAs which participated in multiple kinds of cancer hallmarks. These key lncRNAs were associated with some essential pathways such as estrogen receptor signaling. Conclusions: In conclusion, the present study provide novel insights to the classification and treatment of UCEC.

show abstract

“…Lee et al implemented a GNN for cancer subtyping and tested five cancer types. Thus, the informative pathway was selected and used for subtype classification [147]. Furthermore, GNNs are also getting more attention in drug repositioning studies.…”

Section: Graph Neural Network Modelmentioning

confidence: 99%

Integrative Analysis of Next-Generation Sequencing for Next-Generation Cancer Research toward Artificial Intelligence

Park

Heider

Hauschild

2021

Cancers

View full text Add to dashboard Cite

The rapid improvement of next-generation sequencing (NGS) technologies and their application in large-scale cohorts in cancer research led to common challenges of big data. It opened a new research area incorporating systems biology and machine learning. As large-scale NGS data accumulated, sophisticated data analysis methods became indispensable. In addition, NGS data have been integrated with systems biology to build better predictive models to determine the characteristics of tumors and tumor subtypes. Therefore, various machine learning algorithms were introduced to identify underlying biological mechanisms. In this work, we review novel technologies developed for NGS data analysis, and we describe how these computational methodologies integrate systems biology and omics data. Subsequently, we discuss how deep neural networks outperform other approaches, the potential of graph neural networks (GNN) in systems biology, and the limitations in NGS biomedical research. To reflect on the various challenges and corresponding computational solutions, we will discuss the following three topics: (i) molecular characteristics, (ii) tumor heterogeneity, and (iii) drug discovery. We conclude that machine learning and network-based approaches can add valuable insights and build highly accurate models. However, a well-informed choice of learning algorithm and biological network information is crucial for the success of each specific research question.

show abstract

Cancer subtype classification and modeling by pathway attention and propagation

Cited by 37 publications

References 51 publications

Multi-Omics Data Fusion via a Joint Kernel Learning Model for Cancer Subtype Discovery and Essential Gene Identification

Multi-Omics Data Fusion via a Joint Kernel Learning Model for Cancer Subtype Discovery and Essential Gene Identification

Inference of Molecular Subtypes of Uterine Corpus Endometrioid Carcinoma with Different Survival Based on Cancer Hallmarks-associated Long Non-Coding RNAs and Gene Modules

Integrative Analysis of Next-Generation Sequencing for Next-Generation Cancer Research toward Artificial Intelligence

Contact Info

Product

Resources

About