Dataset Information

Testing the gene expression classification of the EMT spectrum.

ABSTRACT: The epithelial-mesenchymal transition (EMT) plays a central role in cancer metastasis and drug resistance-two persistent clinical challenges. Epithelial cells can undergo a partial or full EMT, attaining either a hybrid epithelial/mesenchymal (E/M) or mesenchymal phenotype, respectively. Recent studies have emphasized that hybrid E/M cells may be more aggressive than their mesenchymal counterparts. However, mechanisms driving hybrid E/M phenotypes remain largely elusive. Here, to better characterize the hybrid E/M phenotype (s) and tumor aggressiveness, we integrate two computational methods-(a) RACIPE-to identify the robust gene expression patterns emerging from the dynamics of a given gene regulatory network, and (b) EMT scoring metric-to calculate the probability that a given gene expression profile displays a hybrid E/M phenotype. We apply the EMT scoring metric to RACIPE-generated gene expression data generated from a core EMT regulatory network and classify the gene expression profiles into relevant categories (epithelial, hybrid E/M, mesenchymal). This categorization is broadly consistent with hierarchical clustering readouts of RACIPE-generated gene expression data. We also show how the EMT scoring metric can be used to distinguish between samples composed of exclusively hybrid E/M cells and those containing mixtures of epithelial and mesenchymal subpopulations using the RACIPE-generated gene expression data.

SUBMITTER: Jia D

PROVIDER: S-EPMC7179477 | biostudies-literature | 2019 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Testing the gene expression classification of the EMT spectrum.

Jia Dongya D George Jason T JT Tripathi Satyendra C SC Kundnani Deepali L DL Lu Mingyang M Hanash Samir M SM Onuchic José N JN Jolly Mohit Kumar MK Levine Herbert H

Physical biology 20190118 2

The epithelial-mesenchymal transition (EMT) plays a central role in cancer metastasis and drug resistance-two persistent clinical challenges. Epithelial cells can undergo a partial or full EMT, attaining either a hybrid epithelial/mesenchymal (E/M) or mesenchymal phenotype, respectively. Recent studies have emphasized that hybrid E/M cells may be more aggressive than their mesenchymal counterparts. However, mechanisms driving hybrid E/M phenotypes remain largely elusive. Here, to better characte ...[more]

PMID: 30557866

Similar Datasets

Project description:Multiple molecular markers contribute to the pathogenesis of thyroid cancer and can provide valuable information to improve disease diagnosis and patient management. We performed a comprehensive evaluation of miRNA gene expression in diverse thyroid lesions (n = 534) and developed predictive models for the classification of thyroid nodules, alone or in combination with genotyping. Expression profiling by reverse transcription-quantitative polymerase chain reaction in surgical specimens (n = 257) identified specific miRNAs differentially expressed in 17 histopathological categories. Eight supervised machine learning algorithms were trained to discriminate benign from malignant lesions and evaluated for accuracy and robustness. The selected models showed invariant area under the receiver operating characteristic curve (AUC) in cross-validation (0.89), optimal AUC (0.94) in an independent set of preoperative thyroid nodule aspirates (n = 235), and classified 92% of benign lesions as low risk/negative and 92% of malignant lesions as high risk/positive. Surgical and preoperative specimens were further tested for the presence of 17 validated oncogenic gene alterations in the BRAF, RAS, RET or PAX8 genes. The miRNA-based classifiers complemented and significantly improved the diagnostic performance of the 17-mutation panel (p < 0.001 for McNemar's tests). In a subset of resected tissues (n = 54) and in an independent set of thyroid nodules with indeterminate cytology (n = 42), the optimized ThyraMIR Thyroid miRNA Classifier increased diagnostic sensitivity by 30-39% and correctly classified 100% of benign nodules negative by the 17-mutation panel. In contrast, testing with broad targeted next-generation sequencing panels decreased diagnostic specificity by detecting additional mutations of unknown clinical significance in 19-39% of benign lesions. Our results demonstrate that, independent of mutational status, miRNA expression profiles are strongly associated with altered molecular pathways underlying thyroid tumorigenesis. Combined testing for miRNA gene expression and well-established somatic gene alterations is a novel diagnostic strategy that can improve the preoperative diagnosis and surgical management of patients with indeterminate thyroid nodules.

Project description:Alzheimer's disease (AD) is a progressive disease leading to cognitive decline, and to prevent it, researchers seek to diagnose mild cognitive impairment (MCI) early. Particularly, non-amnestic MCI (naMCI) is often mistaken for normal aging as the representative symptom of AD, memory decline, is absent. Subjective cognitive decline (SCD), an intermediate step between normal aging and MCI, is crucial for prediction or early detection of MCI, which determines the presence of AD spectrum pathology. We developed a computer-based cognitive task to classify the presence or absence of AD pathology and stage within the AD spectrum, and attempted to perform multi-stage classification through electroencephalography (EEG) during resting and memory encoding state. The resting and memory-encoding states of 58 patients (20 with SCD, 10 with naMCI, 18 with aMCI, and 10 with AD) were measured and classified into four groups. We extracted features that could reflect the phase, spectral, and temporal characteristics of the resting and memory-encoding states. For the classification, we compared nine machine learning models and three deep learning models using Leave-one-subject-out strategy. Significant correlations were found between the existing neurophysiological test scores and performance of our computer-based cognitive task for all cognitive domains. In all models used, the memory-encoding states realized a higher classification performance than resting states. The best model for the 4-class classification was cKNN. The highest accuracy using resting state data was 67.24%, while it was 93.10% using memory encoding state data. This study involving participants with SCD, naMCI, aMCI, and AD focused on early Alzheimer's diagnosis. The research used EEG data during resting and memory encoding states to classify these groups, demonstrating the significance of cognitive process-related brain waves for diagnosis. The computer-based cognitive task introduced in the study offers a time-efficient alternative to traditional neuropsychological tests, showing a strong correlation with their results and serving as a valuable tool to assess cognitive impairment with reduced bias.

Project description:BackgroundThe increasing number of gene expression microarray studies represents an important resource in biomedical research. As a result, gene expression based diagnosis has entered clinical practice for patient stratification in breast cancer. However, the integration and combined analysis of microarray studies remains still a challenge. We assessed the potential benefit of data integration on the classification accuracy and systematically evaluated the generalization performance of selected methods on four breast cancer studies comprising almost 1000 independent samples. To this end, we introduced an evaluation framework which aims to establish good statistical practice and a graphical way to monitor differences. The classification goal was to correctly predict estrogen receptor status (negative/positive) and histological grade (low/high) of each tumor sample in an independent study which was not used for the training. For the classification we chose support vector machines (SVM), predictive analysis of microarrays (PAM), random forest (RF) and k-top scoring pairs (kTSP). Guided by considerations relevant for classification across studies we developed a generalization of kTSP which we evaluated in addition. Our derived version (DV) aims to improve the robustness of the intrinsic invariance of kTSP with respect to technologies and preprocessing.ResultsFor each individual study the generalization error was benchmarked via complete cross-validation and was found to be similar for all classification methods. The misclassification rates were substantially higher in classification across studies, when each single study was used as an independent test set while all remaining studies were combined for the training of the classifier. However, with increasing number of independent microarray studies used in the training, the overall classification performance improved. DV performed better than the average and showed slightly less variance. In particular, the better predictive results of DV in across platform classification indicate higher robustness of the classifier when trained on single channel data and applied to gene expression ratios.ConclusionsWe present a systematic evaluation of strategies for the integration of independent microarray studies in a classification task. Our findings in across studies classification may guide further research aiming on the construction of more robust and reliable methods for stratification and diagnosis in clinical practice.

Dataset Information

Testing the gene expression classification of the EMT spectrum.

Publications

Testing the gene expression classification of the EMT spectrum.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets