Driver gene mutations based clustering of tumors: methods and applications

Zhang, Wensheng; Flemington, Erik K.; Zhang, Kun

doi:10.1093/bioinformatics/bty232

Cited by 7 publications

(3 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, a biological information source (i.e., somatic TP53 mutation profile) critical to cancer progression was used to select a set of candidate signature genes. Naturally, this was a step of introducing external information (knowledge), which has been adopted in our and others’ published studies 59 , 60 . Second, the ranks of candidate genes regarding their differences in expression levels between BCR-positive and BCR-negative samples were not considered in any steps.…”

Section: Discussionmentioning

confidence: 99%

A transcriptomic signature for prostate cancer relapse prediction identified from the differentially expressed genes between TP53 mutant and wild-type tumors

Zhang

2022

Sci Rep

Self Cite

View full text Add to dashboard Cite

For prostate cancer (PCa) patients, biochemical recurrence (BCR) is the first sign of disease relapse and the subsequent metastasis. TP53 mutations are relatively prevalent in advanced PCa forms. We aimed to utilize this knowledge to identify robust transcriptomic signatures for BCR prediction in patients with Gleason score ≥ 7 cancers, which cause most PCa deaths. Using the TCGA-PRAD dataset and the novel data-driven stochastic approach proposed in this study, we identified a 25-gene signature from the genes whose expression in tumors was associated with TP53 mutation statuses. The predictive strength of the signature was assessed by AUC and Fisher’s exact test p-value according to the output of support vector machine-based cross validation. For the TCGA-PRAD dataset, the AUC and p-value were 0.837 and 5 × 10–13, respectively. For five external datasets, the AUCs and p-values ranged from 0.632 to 0.794 and 6 × 10–2 to 5 × 10–5, respectively. The signature also performed well in predicting relapse-free survival (RFS). The signature-based transcriptomic risk scores (TRS) explained 28.2% of variation in RFS on average. The combination of TRS and clinicopathologic prognostic factors explained 23–72% of variation in RFS, with a median of 54.5%. Our method and findings are useful for developing new prognostic tools in PCa and other cancers.

show abstract

Section: Discussionmentioning

confidence: 99%

A transcriptomic signature for prostate cancer relapse prediction identified from the differentially expressed genes between TP53 mutant and wild-type tumors

Zhang

2022

Sci Rep

Self Cite

View full text Add to dashboard Cite

show abstract

“…The somatic mutation profiles are sparse, that is, in each tumor, the number of mutated genes is relatively small compared to the total number of genes (Hofree et al, 2013;Zhang et al, 2018a). In most machine learning techniques, sparse data cannot train the model well (Zhang et al, 2018a), so data need to be smoothed. One of the most effective solutions for smoothing data is the network propagation (Hofree et al, 2013).…”

Section: Extracting and Smoothing Datamentioning

confidence: 99%

Classifying Breast Cancer Molecular Subtypes by Using Deep Clustering Approach

Rohani

Eslahchi

2020

Front. Genet.

View full text Add to dashboard Cite

Cancer is a complex disease with a high rate of mortality. The characteristics of tumor masses are very heterogeneous; thus, the appropriate classification of tumors is a critical point in the effective treatment. A high level of heterogeneity has also been observed in breast cancer. Therefore, detecting the molecular subtypes of this disease is an essential issue for medicine that could be facilitated using bioinformatics. This study aims to discover the molecular subtypes of breast cancer using somatic mutation profiles of tumors. Nonetheless, the somatic mutation profiles are very sparse. Therefore, a network propagation method is used in the gene interaction network to make the mutation profiles dense. Afterward, the deep embedded clustering (DEC) method is used to classify the breast tumors into four subtypes. In the next step, gene signature of each subtype is obtained using Fisher's exact test. Besides the enrichment of gene signatures in numerous biological databases, clinical and molecular analyses verify that the proposed method using mutation profiles can efficiently detect the molecular subtypes of breast cancer. Finally, a supervised classifier is trained based on the discovered subtypes to predict the molecular subtype of a new patient. The code and material of the method are available at: https://github.com/nrohani/MolecularSubtypes.

show abstract

“…Cancer progression is usually thought to result from the accumulation of driver genetic mutations which confer a selective growth advantage to the cell [ 2 ]. Many existing studies have been proposed to annotate cancer driver genes from genetic mutation data by counting mutation frequency, both alteration and conversion, and performing a series of statistical analyses, such as ccpwModel and xGeneModel [ 4 ]. In bladder cancer cells, the cancer driver genes reportedly tend to have a higher conversion frequency of C->G and C->T than other conversion patterns.…”

Section: Introductionmentioning

confidence: 99%

Identification of Cancer Driver Genes by Integrating Multiomics Data with Graph Neural Networks

Song

Yin

et al. 2023

Metabolites

View full text Add to dashboard Cite

Cancer is a heterogeneous disease that is driven by the accumulation of both genetic and nongenetic alterations, so integrating multiomics data and extracting effective information from them is expected to be an effective way to predict cancer driver genes. In this paper, we first generate comprehensive instructive features for each gene from genomic, epigenomic, transcriptomic levels together with protein–protein interaction (PPI)-networks-derived attributes and then propose a novel semisupervised deep graph learning framework GGraphSAGE to predict cancer driver genes according to the impact of the alterations on a biological system. When applied to eight tumor types, experimental results suggest that GGraphSAGE outperforms several state-of-the-art computational methods for driver genes identification. Moreover, it broadens our current understanding of cancer driver genes from multiomics level and identifies driver genes specific to the tumor type rather than pan-cancer. We expect GGraphSAGE to open new avenues in precision medicine and even further predict drivers for other complex diseases.

show abstract

Driver gene mutations based clustering of tumors: methods and applications

Cited by 7 publications

References 23 publications

A transcriptomic signature for prostate cancer relapse prediction identified from the differentially expressed genes between TP53 mutant and wild-type tumors

A transcriptomic signature for prostate cancer relapse prediction identified from the differentially expressed genes between TP53 mutant and wild-type tumors

Classifying Breast Cancer Molecular Subtypes by Using Deep Clustering Approach

Identification of Cancer Driver Genes by Integrating Multiomics Data with Graph Neural Networks

Contact Info

Product

Resources

About