Literature DB >> 33437754

Classification of Cancer Types Using Graph Convolutional Neural Networks.

Ricardo Ramirez1, Yu-Chiao Chiu2, Allen Hererra1, Milad Mostavi1, Joshua Ramirez1, Yidong Chen2,3, Yufei Huang1,3, Yu-Fang Jin1.   

Abstract

BACKGROUND: Cancer has been a leading cause of death in the United States with significant health care costs. Accurate prediction of cancers at an early stage and understanding the genomic mechanisms that drive cancer development are vital to the improvement of treatment outcomes and survival rates, thus resulting in significant social and economic impacts. Attempts have been made to classify cancer types with machine learning techniques during the past two decades and deep learning approaches more recently.
RESULTS: In this paper, we established four models with graph convolutional neural network (GCNN) that use unstructured gene expressions as inputs to classify different tumor and non-tumor samples into their designated 33 cancer types or as normal. Four GCNN models based on a co-expression graph, co-expression+singleton graph, protein-protein interaction (PPI) graph, and PPI+singleton graph have been designed and implemented. They were trained and tested on combined 10,340 cancer samples and 731 normal tissue samples from The Cancer Genome Atlas (TCGA) dataset. The established GCNN models achieved excellent prediction accuracies (89.9-94.7%) among 34 classes (33 cancer types and a normal group). In silico gene-perturbation experiments were performed on four models based on co-expression graph, co-expression+singleton, PPI graph, and PPI+singleton graphs. The co-expression GCNN model was further interpreted to identify a total of 428 markers genes that drive the classification of 33 cancer types and normal. The concordance of differential expressions of these markers between the represented cancer type and others are confirmed. Successful classification of cancer types and a normal group regardless of normal tissues' origin suggested that the identified markers are cancer-specific rather than tissue-specific.
CONCLUSION: Novel GCNN models have been established to predict cancer types or normal tissue based on gene expression profiles. We demonstrated the results from the TCGA dataset that these models can produce accurate classification (above 94%), using cancer-specific markers genes. The models and the source codes are publicly available and can be readily adapted to the diagnosis of cancer and other diseases by the data-driven modeling research community.

Entities:  

Keywords:  Cancer classification2; Data-driven model4; Deep learning3; Graph convolutional neural network1; The Cancer Genome Atlas (TCGA)5

Year:  2020        PMID: 33437754      PMCID: PMC7799442          DOI: 10.3389/fphy.2020.00203

Source DB:  PubMed          Journal:  Front Phys        ISSN: 2296-424X


  28 in total

1.  Mortality and survival in breast and colorectal cancer.

Authors:  Peter Boyle; Jacques Ferlay
Journal:  Nat Clin Pract Oncol       Date:  2005-09

2.  Cancer statistics, 2019.

Authors:  Rebecca L Siegel; Kimberly D Miller; Ahmedin Jemal
Journal:  CA Cancer J Clin       Date:  2019-01-08       Impact factor: 508.702

3.  Utilizing Molecular Network Information via Graph Convolutional Neural Networks to Predict Metastatic Event in Breast Cancer.

Authors:  Hryhorii Chereda; Annalen Bleckmann; Frank Kramer; Andreas Leha; Tim Beissbarth
Journal:  Stud Health Technol Inform       Date:  2019-09-03

4.  Stage at diagnosis and early mortality from cancer in England.

Authors:  S McPhail; S Johnson; D Greenberg; M Peake; B Rous
Journal:  Br J Cancer       Date:  2015-03-31       Impact factor: 7.640

5.  Differential correlation for sequencing data.

Authors:  Charlotte Siska; Katerina Kechris
Journal:  BMC Res Notes       Date:  2017-01-19

6.  Differential correlation analysis of glioblastoma reveals immune ceRNA interactions predictive of patient survival.

Authors:  Yu-Chiao Chiu; Li-Ju Wang; Tzu-Pin Lu; Tzu-Hung Hsiao; Eric Y Chuang; Yidong Chen
Journal:  BMC Bioinformatics       Date:  2017-02-28       Impact factor: 3.169

7.  A comprehensive comparison of random forests and support vector machines for microarray-based cancer classification.

Authors:  Alexander Statnikov; Lily Wang; Constantin F Aliferis
Journal:  BMC Bioinformatics       Date:  2008-07-22       Impact factor: 3.169

8.  Integrative computational and experimental approaches to establish a post-myocardial infarction knowledge map.

Authors:  Nguyen T Nguyen; Xiaolin Zhang; Cathy Wu; Richard A Lange; Robert J Chilton; Merry L Lindsey; Yu-Fang Jin
Journal:  PLoS Comput Biol       Date:  2014-03-20       Impact factor: 4.475

Review 9.  Machine learning applications in cancer prognosis and prediction.

Authors:  Konstantina Kourou; Themis P Exarchos; Konstantinos P Exarchos; Michalis V Karamouzis; Dimitrios I Fotiadis
Journal:  Comput Struct Biotechnol J       Date:  2014-11-15       Impact factor: 7.271

10.  Predicting drug response of tumors from integrated genomic profiles by deep neural networks.

Authors:  Yu-Chiao Chiu; Hung-I Harry Chen; Tinghe Zhang; Songyao Zhang; Aparna Gorthi; Li-Ju Wang; Yufei Huang; Yidong Chen
Journal:  BMC Med Genomics       Date:  2019-01-31       Impact factor: 3.063

View more
  11 in total

1.  gene2gauss: A multi-view gaussian gene embedding learner for analyzing transcriptomic networks.

Authors:  Sudhir Ghandikota; Anil G Jegga
Journal:  AMIA Annu Symp Proc       Date:  2022-05-23

2.  Assessment of deep learning and transfer learning for cancer prediction based on gene expression data.

Authors:  Blaise Hanczar; Victoria Bourgeais; Farida Zehraoui
Journal:  BMC Bioinformatics       Date:  2022-07-03       Impact factor: 3.307

3.  Pathway importance by graph convolutional network and Shapley additive explanations in gene expression phenotype of diffuse large B-cell lymphoma.

Authors:  Jin Hayakawa; Tomohisa Seki; Yoshimasa Kawazoe; Kazuhiko Ohe
Journal:  PLoS One       Date:  2022-06-24       Impact factor: 3.752

4.  Deep learning tackles single-cell analysis-a survey of deep learning for scRNA-seq analysis.

Authors:  Mario Flores; Zhentao Liu; Tinghe Zhang; Md Musaddaqui Hasib; Yu-Chiao Chiu; Zhenqing Ye; Karla Paniagua; Sumin Jo; Jianqiu Zhang; Shou-Jiang Gao; Yu-Fang Jin; Yidong Chen; Yufei Huang
Journal:  Brief Bioinform       Date:  2022-01-17       Impact factor: 13.994

5.  Predicting and characterizing a cancer dependency map of tumors with deep learning.

Authors:  Yu-Chiao Chiu; Siyuan Zheng; Li-Ju Wang; Brian S Iskra; Manjeet K Rao; Peter J Houghton; Yufei Huang; Yidong Chen
Journal:  Sci Adv       Date:  2021-08-20       Impact factor: 14.136

6.  A Novel Attention-Mechanism Based Cox Survival Model by Exploiting Pan-Cancer Empirical Genomic Information.

Authors:  Xiangyu Meng; Xun Wang; Xudong Zhang; Chaogang Zhang; Zhiyuan Zhang; Kuijie Zhang; Shudong Wang
Journal:  Cells       Date:  2022-04-22       Impact factor: 7.666

7.  Prediction and interpretation of cancer survival using graph convolution neural networks.

Authors:  Ricardo Ramirez; Yu-Chiao Chiu; SongYao Zhang; Joshua Ramirez; Yidong Chen; Yufei Huang; Yu-Fang Jin
Journal:  Methods       Date:  2021-01-21       Impact factor: 4.647

8.  DEGnext: classification of differentially expressed genes from RNA-seq data using a convolutional neural network with transfer learning.

Authors:  Tulika Kakati; Dhruba K Bhattacharyya; Jugal K Kalita; Trina M Norden-Krichmar
Journal:  BMC Bioinformatics       Date:  2022-01-06       Impact factor: 3.169

9.  Gated Graph Attention Network for Cancer Prediction.

Authors:  Linling Qiu; Han Li; Meihong Wang; Xiaoli Wang
Journal:  Sensors (Basel)       Date:  2021-03-10       Impact factor: 3.576

Review 10.  Deep learning in cancer diagnosis, prognosis and treatment selection.

Authors:  Khoa A Tran; Olga Kondrashova; Andrew Bradley; Elizabeth D Williams; John V Pearson; Nicola Waddell
Journal:  Genome Med       Date:  2021-09-27       Impact factor: 11.117

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.