Development and validation of a NanoString BASE47 bladder cancer gene classifier
Ontology highlight
ABSTRACT:
ORGANISM(S): Homo sapiens
PROVIDER: GSE160693 | GEO | 2020/11/03
REPOSITORIES: GEO
Similar Datasets
Project description:The optimal treatment of patients with cancer depends on establishing accurate diagnoses by using a complex combination of clinical and histopathological data. In some instances, this task is difficult or impossible because of atypical clinical presentation or histopathology. To determine whether the diagnosis of multiple common adult malignancies could be achieved purely by molecular classification, we subjected 218 tumor samples, spanning 14 common tumor types, and 90 normal tissue samples to oligonucleotide microarray gene expression analysis. The expression levels of 16,063 genes and expressed sequence tags were used to evaluate the accuracy of a multiclass classifier based on a support vector machine algorithm. Overall classification accuracy was 78%, far exceeding the accuracy of random classification (9%). Poorly differentiated cancers resulted in low-confidence predictions and could not be accurately classified according to their tissue of origin, indicating that they are molecularly distinct entities with dramatically different gene expression patterns compared with their well differentiated counterparts. Taken together, these results demonstrate the feasibility of accurate, multiclass molecular cancer classification and suggest a strategy for future clinical implementation of molecular cancer diagnostics.
2015-05-16 | GSE68928 | GEO
Project description:Our aim to develop the 95GC (gene classifier) was to make an accurate diagnostic system using gene expression analysis by means of DNA microarray for prognosis of node-negative and estrogen receptor (ER)-positive breast cancer patients in order to identify a subset of patients who can be safely spared adjuvant chemotherapy. A diagnostic system comprising a 95-gene classifier was developed for predicting the prognosis of node-negative and ER-positive breast cancer patients by using DNA microarray (gene expression) data (n = 549) as the training set and the DNA microarray data (n = 105) as the validation set (= this data set). With the 95-gene classifier we could classify the 105 patients receiving only endocrine therapy without chemotherapy in the validation set into a high-risk (n = 44) and a low-risk (n = 61) group with 10-year recurrence-free survival rates of 93 and 53%, respectively (P = 8.6e-7). Multivariate analysis demonstrated that the 95-gene classifier was the most important and significant predictor of recurrence (P = 9.6e-4) independently of tumor size, histological grade, progesterone receptor, HER2, Ki67, or GGI. The 95-gene classifier developed by us can predict the prognosis of node-negative and ER-positive breast cancer patients with high accuracy. *Note: This old data has been updated multiple times by others. Then, there are some differences from the original 2011 paper and unclear points still remain. Therefore, do not use it for formal analysis aimed at public insurance coverage etc. This is for research purposes only. Please cite this paper when writing a new paper. DOI: 10.1007/s10549-010-1145-z
2023-05-28 | GSE233251 | GEO
Project description:The optimal treatment of patients with cancer depends on establishing accurate diagnoses by using a complex combination of clinical and histopathological data. In some instances, this task is difficult or impossible because of atypical clinical presentation or histopathology. To determine whether the diagnosis of multiple common adult malignancies could be achieved purely by molecular classification, we subjected 218 tumor samples, spanning 14 common tumor types, and 90 normal tissue samples to oligonucleotide microarray gene expression analysis. The expression levels of 16,063 genes and expressed sequence tags were used to evaluate the accuracy of a multiclass classifier based on a support vector machine algorithm. Overall classification accuracy was 78%, far exceeding the accuracy of random classification (9%). Poorly differentiated cancers resulted in low-confidence predictions and could not be accurately classified according to their tissue of origin, indicating that they are molecularly distinct entities with dramatically different gene expression patterns compared with their well differentiated counterparts. Taken together, these results demonstrate the feasibility of accurate, multiclass molecular cancer classification and suggest a strategy for future clinical implementation of molecular cancer diagnostics. golub-00236 Assay Type: Gene Expression Provider: Affymetrix Array Designs: Hu35KsubA, Hu6800 Organism: Homo sapiens (ncbitax) Material Types: synthetic_RNA, organism_part, whole_organism, total_RNA Disease States: Colorectal Adenocarcinoma, Melanoma, Normal, pancreatic adenocarcinoma, Acute Myeloid Leukemia, Breast Adenocarcinoma, T-cell ALL, Lung Adenocarcinoma, bladder transitional cell carcinoma, Ovarian Adenocarcinoma, Mesothelioma, B-cell ALL, prostate adenocarcinoma, Medulloblastoma, Follicular Lymphoma, renal cell carcinoma, uterine adenocarcinoma, large B-cell lymphoma, Glioblastoma, bladder transitonal cell carcinoma
2015-05-16 | E-GEOD-68928 | biostudies-arrayexpress
Project description:Background We have recently constructed a DNA methylation classifier that can discriminate between pancreatic ductal adenocarcinoma (PAAD) liver metastasis and intrahepatic cholangiocarcinoma (iCCA) with high accuracy (PAAD-iCCA-Classifier). PAAD is one of the leading causes of cancer of unknown primary and diagnosis is based on exclusion of other malignancies. Therefore, our focus was to investigate whether the PAAD-iCCA-Classifier can be used to diagnose PAAD metastases from other sites. Methods For this scope, the anomaly detection filter of the initial classifier was expanded by 8 additional mimicker carcinomas, amounting to a total of 10 carcinomas in the negative class. We validated the updated version of the classifier on a validation set, which consisted of a biological cohort (n = 3579) and a technical one (n = 15). We then assessed the performance of the classifier on a test set, which included a positive control cohort of 16 PAAD metastases from various sites and a cohort of 124 negative control samples consisting of 96 breast cancer metastases from 18 anatomical sites and 28 carcinoma metastases to the brain. Results The updated PAAD-iCCA-Classifier achieved 98.21% accuracy on the biological validation samples, and on the technical validation ones it reached 100%. The classifier also correctly identified 15/16 (93.75%) metastases of the positive control as PAAD, and on the negative control, it correctly classified 122/124 samples (98.39%) for a 97.85% overall accuracy on the test set. We used this DNA methylation dataset to explore the organotropism of PAAD metastases and observed that PAAD liver metastases are distinct from PAAD peritoneal carcinomatosis and primary PAAD, and are characterized by specific copy number alterations and hypomethylation of enhancers involved in epithelial-mesenchymal-transition. Conclusions The updated PAAD-iCCA-Classifier (available at https://classifier.tgc-research.de/) can accurately classify PAAD samples from various metastatic sites and it can serve as a diagnostic aid.
2024-11-20 | GSE252130 | GEO
Project description:The analytes qualified as biomarkers are potent tools to diagnose various diseases, monitor therapy responses, and design therapeutic interventions. The early assessment of the diverseness of human disease is essential for the speedy and cost-efficient implementation of personalized medicine. We developed g3mclass, the Gaussian mixture modeling software for molecular assay data classification. This software automates the validated multiclass classifier applicable to single analyte tests and multiplexing assays. The g3mclass achieves automation using the original semi-constrained expectation-maximization (EM) algorithm that allows inference from the test, control, and query data that human experts cannot interpret. In this study, we used real-world clinical data and gene expression datasets (ERBB2, ESR1, PGR) to provide examples of how g3mclass may help overcome the problems of over-/underdiagnosis and equivocal results in diagnostic tests for breast cancer. We showed the g3mclass output’s accuracy, robustness, scalability, and interpretability. The user-friendly interface and free dissemination of this multi-platform software aim to ease its use by research laboratories, biomedical pharma, companion diagnostic developers, and healthcare regulators. Furthermore, the g3mclass automatic extracting information through probabilistic modeling is adaptable for blending with machine learning and artificial intelligence.
2022-11-09 | GSE214540 | GEO
Project description:Many innovative techniques and scientific improvements are available to tackle societal concerns, like public health safety and confining the risk of cancerous exposure to chemicals, but have not been thoroughly tested and implicated yet. We investigated if microRNA and mRNA transcription profiles can be implemented in a short-term carcinogen classifier assay. Our study is additionally focusing on the drawbacks of present-day carcinogen screening strategies and also aims to contribute to a more ethical approach towards animal use and welfare within risk assessment. Since current in vitro and in silico assays are still not able to mimic the in vivo situation accurately we set out to develop an alternative short-term in vivo assay. Five genotoxic, seven non-genotoxic and five non-carcinogen exposure studies were used to investigate if murine hepatic microRNA and mNA profiles after 7-day exposure are suitable tools to classify carcinogens. Classification analyses showed that a small transcript set, consisting of both microRNA and mRNA, is able to classify the genotoxic, non-genotoxic and non-carcinogens tested with 100% accuracy. The results indicate that microRNAs have the potential to be used as transcriptional classifiers and that a short-term transcriptional classifier assay in mice can be a powerful tool in carcinogenicity risk assessment. Since current in vitro and in silico assays are still not able to mimic the in vivo situation accurately we set out to develop an alternative short-term in vivo assay. Five genotoxic, seven non-genotoxic and five non-carcinogen exposure studies were used to investigate if murine hepatic microRNA and mNA profiles after 7-day exposure are suitable tools to classify carcinogens. Classification analyses showed that a small transcript set, consisting of both microRNA and mRNA, is able to classify the genotoxic, non-genotoxic and non-carcinogens tested with 100% accuracy. The results indicate that microRNAs have the potential to be used as transcriptional classifiers and that a short-term transcriptional classifier assay in mice can be a powerful tool in carcinogenicity risk assessment. [mRNA profling] 96 hepatic samples in total, 8 control untreated samples, replicates per treated group n=4-6
2014-04-01 | E-GEOD-43977 | biostudies-arrayexpress
Project description:Development of a non-invasive, whole blood microarray gene expression signature that accurately distinguishes malignant from benign lung nodules detected by LDCT and the successful transition of that signature to a custom NanoString panel with no loss of accuracy.
2018-12-20 | GSE108375 | GEO
Project description:Contemporary treatment of pediatric acute myeloid leukemia (AML) requires the assignment of patients to specific risk groups. To explore whether expression profiling of leukemic blasts could accurately distinguish between the known risk groups of AML, we analyzed 130 pediatric and 20 adult AML diagnostic bone marrow or peripheral blood samples using the Affymetrix U133A microarray. Class discriminating genes were identified for each of the major prognostic subtypes of pediatric AML, including t(15;17)[PML-RARalpha], t(8;21)[AML1-ETO], inv(16) [CBFbeta-MYH11], MLL chimeric fusion genes, and cases classified as FAB-M7. When subsets of these genes were used in supervised learning algorithms, an overall classification accuracy of more than 93% was achieved. Moreover, we were able to use the expression signatures generated from the pediatric samples to accurately classify adult de novo AMLs with the same genetic lesions. The class discriminating genes also provided novel insights into the molecular pathobiology of these leukemias. Finally, using a combined pediatric data set of 130 AMLs and 137 acute lymphoblastic leukemias, we identified an expression signature for cases with MLL chimeric fusion genes irrespective of lineage. Surprisingly, AMLs containing partial tandem duplications of MLL failed to cluster with MLL chimeric fusion gene cases, suggesting a significant difference in their underlying mechanism of transformation. All the gene expression arrays are available through http://www.stjuderesearch.org/site/data/AML1/ in the original study (PMID:15226186). To study the RAS gene expression in the human AML patients, a total of 104 AML cases with known KRAS and NRAS status (including 72 gene expression arrays in the original study and 32 additional arrays acquired later on), as well as 4 CD34+ normal bone marrow cases deposited in GEO GSE33315, were including in this depository. Gene expression profiling was performed on 104 single diagnosis tumor samples and 4 CD34+ normal bone marrow samples
2013-07-02 | E-GEOD-43176 | biostudies-arrayexpress
Project description:Motivation: Monitoring, assessment and prediction of environmental risks that chemicals pose demand rapid and accurate diagnostic assays. A variety of toxicological effects have been associated with explosive compounds TNT and RDX. One important goal of microarray experiments is to discover novel biomarkers for toxicity evaluation. We have developed an earthworm microarray containing 15,208 unique oligo probes. Our objective was to identify biomarker genes that can separate earthworm samples into three groups: control, TNT-treated, and RDX-treated. Results: We developed a discriminant analysis and cluster (DAC) pipeline to analyze a 248-array dataset. First, a total of 869 significantly changed genes in response to TNT or RDX exposure were inferred by class comparison statistical algorithms. Then, nine decision tree-based algorithms were applied to generate classification rules and a set of 286 classifier genes. These classifier genes were ranked by their overall weight of significance, and were used to build support vector machines (SVMs). An SVM containing all 286 classifier genes had the highest classification accuracy (91.5%). An unsupervised clustering method was used to cluster the worm samples and results show that the use of the top 100 classifier genes can assign the largest number of worm samples into the three reference clusters obtained by using all the 14,188 filtered genes, suggesting that these top-ranked genes may be potential candidates for biomarkers. This study demonstrates that the DAC pipeline can be used to identify a small set of biomarker genes from high dimensional datasets and generate a reliable SVM classification model for multiple classes.
2010-10-08 | GSE18495 | GEO
Project description:Small B-cell lymphoid neoplasms (SBCLNs) are a heterogeneous group of diseases characterized by malignant clonal proliferation of mature B-cells. However, the classification of SBCLNs remains a challenge, especially in cases where histopathological analysis is unavailable or those with atypical laboratory findings or equivocal pathologic data. In this study, gene expression profiling of 1,039 samples from 27 GEO datasets was first investigated to select highly and differentially expressed genes among SBCLNs. Samples from 57 SBCLN cases and 102 nonmalignant control samples were used to train a classifier using the NanoString platform. The classifier was built by employing a cascade binary classification method based on the random forest algorithm with 35 refined gene signatures. Cases were successively classified as chronic lymphocytic leukemia/small lymphocytic lymphoma, conventional mantle cell lymphoma, follicular lymphoma, leukemic non-nodal mantle cell lymphoma, marginal zone lymphoma, lymphoplasmacytic lymphoma/Waldenström’s macroglobulinemia, and other undetermined. The classifier algorithm was then validated using an independent cohort of 197 patients with SBCLNs. Under the distribution of our validation cohort, the overall sensitivity and specificity of proposed algorithm model were >95% respectively for all the cases with tumor cell content greater than 0.72. Combined with additional genetic aberrations including IGH-BCL2 translocation, MYD88 L265P mutation, and BRAF V600E mutation, the optimal sensitivity and specificity were respectively found at 0.88 and 0.98. In conclusion, the established algorithm demonstrated to be an effective and valuable ancillary diagnostic approach for the sub-classification and pathologic investigation of SBCLN in daily practice.
2021-11-18 | GSE183030 | GEO