Identification of Latent Oncogenes with a Network Embedding Method and Random Forest

Zhao, Ran; Hu, Bin; Lei, Chen; Zhou, Bo

doi:10.1155/2020/5160396

Cited by 4 publications

(5 citation statements)

References 71 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Guan et al (2018) [ 34 ] provide a general framework for incorporating prior knowledge into RF construction for biomarker discovery where network information may be considered. Zhao et al (2020) [ 35 ] use network information in the feature engineering step and construct standard RF with these created features. Similarly, Adnan et al (2019) [ 36 ] propose to use network edges as features in RF construction to obtain a better predictive model.…”

Section: Discussionmentioning

confidence: 99%

Evaluation of network-guided random forest for disease gene discovery

Hu,

Szymczak

2024

BioData Mining

View full text Add to dashboard Cite

Background Gene network information is believed to be beneficial for disease module and pathway identification, but has not been explicitly utilized in the standard random forest (RF) algorithm for gene expression data analysis. We investigate the performance of a network-guided RF where the network information is summarized into a sampling probability of predictor variables which is further used in the construction of the RF. Results Our simulation results suggest that network-guided RF does not provide better disease prediction than the standard RF. In terms of disease gene discovery, if disease genes form module(s), network-guided RF identifies them more accurately. In addition, when disease status is independent from genes in the given network, spurious gene selection results can occur when using network information, especially on hub genes. Our empirical analysis on two balanced microarray and RNA-Seq breast cancer datasets from The Cancer Genome Atlas (TCGA) for classification of progesterone receptor (PR) status also demonstrates that network-guided RF can identify genes from PGR-related pathways, which leads to a better connected module of identified genes. Conclusions Gene networks can provide additional information to aid the gene expression analysis for disease module and pathway identification. But they need to be used with caution and validation on the results need to be carried out to guard against spurious gene selection. More robust approaches to incorporate such information into RF construction also warrant further study.

show abstract

Section: Discussionmentioning

confidence: 99%

Evaluation of network-guided random forest for disease gene discovery

Hu,

Szymczak

2024

BioData Mining

View full text Add to dashboard Cite

show abstract

“…The PPI network is denoted as G . Such PPI network has been widely used in many researches [ 29 – 37 ].…”

Section: Methodsmentioning

confidence: 99%

“…Using the abovementioned data, we can construct a PPI network consisting of 19,247 nodes and 4,274,001 edges, which connects two nodes with interaction score as the weight if and only if two proteins interact. The PPI network is denoted as G. Such PPI network has been widely used in many researches [29][30][31][32][33][34][35][36][37].…”

Section: Ppismentioning

confidence: 99%

Identification of Novel Choroidal Neovascularization-Related Genes Using Laplacian Heat Diffusion Algorithm

Sheng

Cai

Cheng

et al. 2021

BioMed Research International

View full text Add to dashboard Cite

Choroidal neovascularization (CNV) is a type of eye disease that can cause vision loss. In recent years, many studies have attempted to investigate the major pathological processes and molecular pathogenic mechanisms of CNV. Because many diseases are related to genes, the genes associated with CNV need to be identified. In this study, we proposed a network-based approach for identifying novel CNV-associated genes. To execute such method, we first employed a protein-protein interaction network reported in STRING. Then, we applied a network diffusion algorithm, Laplacian heat diffusion, on this network by selecting validated CNV-related genes as the seed nodes. As a result, some novel genes that had unknown but strong relationships with validated genes were identified. Furthermore, we used a screening procedure to extract the most essential genes. Eleven latent CNV-related genes were finally obtained. Extensive analyses were performed to confirm that these genes are novel CNV-related genes.

show abstract

“…A network should be employed to execute the random walk algorithm. In recent years, the PPI network is widely used to study various problems related to proteins or genes ( Ng et al, 2010 ; Hu et al, 2011a ; Hu et al, 2011b ; Zhang et al, 2016 ; Cai et al, 2017 ; Zhang et al, 2019 ; Zhang and Chen, 2020 ; Zhao et al, 2020 ; Gao et al, 2021 ). Thus, we used the structure of one PPI network and mined new candidate genes related to lymphoma based on the validated ones.…”

Section: Methodsmentioning

confidence: 99%

A Random Walk-Based Method to Identify Candidate Genes Associated With Lymphoma

et al. 2021

View full text Add to dashboard Cite

Lymphoma is a serious type of cancer, especially for adolescents and elder adults, although this malignancy is quite rare compared with other types of cancer. The cause of this malignancy remains ambiguous. Genetic factor is deemed to be highly associated with the initiation and progression of lymphoma, and several genes have been related to this disease. Determining the pathogeny of lymphoma by identifying the related genes is important. In this study, we presented a random walk-based method to infer the novel lymphoma-associated genes. From the reported 1,458 lymphoma-associated genes and protein–protein interaction network, raw candidate genes were mined by using the random walk with restart algorithm. The determined raw genes were further filtered by using three screening tests (i.e., permutation, linkage, and enrichment tests). These tests could control false-positive genes and screen out essential candidate genes with strong linkages to validate the lymphoma-associated genes. A total of 108 inferred genes were obtained. Analytical results indicated that some inferred genes, such as RAC3, TEC, IRAK2/3/4, PRKCE, SMAD3, BLK, TXK, PRKCQ, were associated with the initiation and progression of lymphoma.

show abstract

Identification of Latent Oncogenes with a Network Embedding Method and Random Forest

Cited by 4 publications

References 71 publications

Evaluation of network-guided random forest for disease gene discovery

Evaluation of network-guided random forest for disease gene discovery

Identification of Novel Choroidal Neovascularization-Related Genes Using Laplacian Heat Diffusion Algorithm

A Random Walk-Based Method to Identify Candidate Genes Associated With Lymphoma

Contact Info

Product

Resources

About