Dataset Information

Oncocytoma-Related Gene Signature to Differentiate Chromophobe Renal Cancer and Oncocytoma Using Machine Learning.

ABSTRACT: Publicly available gene expression datasets were analyzed to develop a chromophobe and oncocytoma related gene signature (COGS) to distinguish chRCC from RO. The datasets GSE11151, GSE19982, GSE2109, GSE8271 and GSE11024 were combined into a discovery dataset. The transcriptomic differences were identified with unsupervised learning in the discovery dataset (97.8% accuracy) with density based UMAP (DBU). The top 30 genes were identified by univariate gene expression analysis and ROC analysis, to create a gene signature called COGS. COGS, combined with DBU, was able to differentiate chRCC from RO in the discovery dataset with an accuracy of 97.8%. The classification accuracy of COGS was validated in an independent meta-dataset consisting of TCGA-KICH and GSE12090, where COGS could differentiate chRCC from RO with 100% accuracy. The differentially expressed genes were involved in carbohydrate metabolism, transcriptomic regulation by TP53, beta-catenin-dependent Wnt signaling, and cytokine (IL-4 and IL-13) signaling highly active in cancer cells. Using multiple datasets and machine learning, we constructed and validated COGS as a tool that can differentiate chRCC from RO and complement histology in routine clinical practice to distinguish these two tumors.

SUBMITTER: Satter KB

PROVIDER: S-EPMC8774230 | biostudies-literature | 2022 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Oncocytoma-Related Gene Signature to Differentiate Chromophobe Renal Cancer and Oncocytoma Using Machine Learning.

Satter Khaled Bin KB Tran Paul Minh Huy PMH Tran Lynn Kim Hoang LKH Ramsey Zach Z Pinkerton Katheine K Bai Shan S Savage Natasha M NM Kavuri Sravan S Terris Martha K MK She Jin-Xiong JX Purohit Sharad S

Cells 20220115 2

Publicly available gene expression datasets were analyzed to develop a chromophobe and oncocytoma related gene signature (COGS) to distinguish chRCC from RO. The datasets GSE11151, GSE19982, GSE2109, GSE8271 and GSE11024 were combined into a discovery dataset. The transcriptomic differences were identified with unsupervised learning in the discovery dataset (97.8% accuracy) with density based UMAP (DBU). The top 30 genes were identified by univariate gene expression analysis and ROC analysis, to ...[more]

PMID: 35053403

Similar Datasets

Project description:Background: While subtyping of the majority of malignant chromophobe renal cell carcinoma (cRCC) and benign renal oncocytoma (rO) is possible on morphology alone, additional histochemical, immunohistochemical or molecular investigations are required in a subset of cases. As currently used histochemical and immunohistological stains as well as genetic aberrations show considerable overlap in both tumors, additional techniques are required for differential diagnostics. Mass spectrometry imaging (MSI) combining the detection of multiple peptides with information about their localization in tissue may be a suitable technology to overcome this diagnostic challenge. Patients and Methods: Formalin-fixed paraffin embedded (FFPE) tissue specimens from cRCC (n=71) and rO (n=64) were analyzed by MSI. Data were classified by linear discriminant analysis (LDA), classification and regression trees (CART), k-nearest neighbors (KNN), support vector machine (SVM), and random forest (RF) algorithm with internal cross validation and visualized by t-distributed stochastic neighbor embedding (t-SNE). Most important variables for classification were identified and the classification algorithm was optimized. Results: Applying different machine learning algorithms on all m/z peaks, classification accuracy between cRCC and rO was 85%, 82%, 84%, 77% and 64% for RF, SVM, KNN, CART and LDA. Under the assumption that a reduction of m/z peaks would lead to improved classification accuracy, m/z peaks were ranked based on their variable importance. Reduction to six most important m/z peaks resulted in improved accuracy of 89%, 85%, 85% and 85% for RF, SVM, KNN, and LDA and remained at the level of 77% for CART. t-SNE showed clear separation of cRCC and rO after algorithm improvement. Conclusion: In summary, we acquired MSI data on FFPE tissue specimens of cRCC and rO, performed classification and detected most relevant biomarkers for the differential diagnosis of both diseases. MSI data might be a useful adjunct method in the differential diagnosis of cRCC and rO.

Project description:BACKGROUND: Chromophobe renal cell carcinoma (chRCC) and renal oncocytoma are two distinct but closely related entities with strong morphologic and genetic similarities. While chRCC is a malignant tumor, oncocytoma is usually regarded as a benign entity. The overlapping characteristics are best explained by a common cellular origin, and the biologic differences between chRCC and oncocytoma are therefore of considerable interest in terms of carcinogenesis, diagnosis and clinical management. Previous studies have been relatively limited in terms of examining the differences between oncocytoma and chromophobe RCC. METHODS: Gene expression profiling using the Affymetrix HGU133Plus2 platform was applied on chRCC (n = 15) and oncocytoma specimens (n = 15). Supervised analysis was applied to identify a discriminatory gene signature, as well as differentially expressed genes. High throughput single-nucleotide polymorphism (SNP) genotyping was performed on independent samples (n = 14) using Affymetrix GeneChip Mapping 100 K arrays to assess correlation between expression and gene copy number. Immunohistochemical validation was performed in an independent set of tumors. RESULTS: A novel 14 probe-set signature was developed to classify the tumors internally with 93% accuracy, and this was successfully validated on an external data-set with 94% accuracy. Pathway analysis highlighted clinically relevant dysregulated pathways of c-erbB2 and mammalian target of rapamycin (mTOR) signaling in chRCC, but no significant differences in p-AKT or extracellular HER2 expression was identified on immunohistochemistry. Loss of chromosome 1p, reflected in both cytogenetic and expression analysis, is common to both entities, implying this may be an early event in histogenesis. Multiple regional areas of cytogenetic alterations and corresponding expression biases differentiating the two entities were identified. Parafibromin, aquaporin 6, and synaptogyrin 3 were novel immunohistochemical markers effectively discriminating the two pathologic entities. CONCLUSIONS: Gene expression profiles, high-throughput SNP genotyping, and pathway analysis effectively distinguish chRCC from oncocytoma. We have generated a novel transcript predictor that is able to discriminate between the two entities accurately, and which has been validated both in an internal and an independent data-set, implying generalizability. A cytogenetic alteration, loss of chromosome 1p, common to renal oncocytoma and chRCC has been identified, providing the opportunities for identifying novel tumor suppressor genes and we have identified a series of immunohistochemical markers that are clinically useful in discriminating chRCC and oncocytoma.

Dataset Information

Oncocytoma-Related Gene Signature to Differentiate Chromophobe Renal Cancer and Oncocytoma Using Machine Learning.

Publications

Oncocytoma-Related Gene Signature to Differentiate Chromophobe Renal Cancer and Oncocytoma Using Machine Learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets