Cd25ec3b-24e4-4260-afb6-7e65f4fadb73 - samples
Ontology highlight
ABSTRACT:
PROVIDER: EGAD00001009790 | EGA |
REPOSITORIES: EGA
Similar Datasets
Project description:Background There is a lack of tools for identifying the site of origin in mucinous cancer. This study aimed to evaluate the performance of a transcriptome-based classifier for identifying the site of origin in mucinous cancer. Methods Transcriptomic data of 1,878 non-mucinous and 82 mucinous cancer specimens, with 7 sites of origin, namely, the uterine cervix (CESC), colon (COAD), pancreas (PAAD), stomach (STAD), uterine endometrium (UCEC), uterine carcinosarcoma (UCS), and ovary (OV), obtained from The Cancer Genome Atlas, were used as the training and validation sets, respectively. Transcriptomic data of 14 mucinous cancer specimens from a tissue archive were used as the test set. For identifying the site of origin, a set of 100 differentially expressed genes for each site of origin was selected. After removing multiple iterations of the same gene, 626 genes were chosen, and their RNA expression profiles, at each site of origin, were used to train the deep neural network classifier. The performance of the classifier was estimated using the training, validation, and test sets. Results The accuracy of the model in the training set was 0.977, while that in the validation set was 0.939 (77/82). In the test set, the model showed an accuracy of 0.857 (12/14). t-SNE analysis revealed that samples in the test set were part of the clusters obtained for the training set. Conclusion Although limited by small sample size, we showed that a transcriptome-based classifier could correctly identify the site of origin of mucinous cancer.
2020-12-15 | GSE163126 | GEO
Project description:We aimed to investigate the diagnostic potential of tumor educated platelets in ESCC. In this study, seventy-one ESCC patients and eighty healthy individuals were enrolled and divided into training cohort (23 patients and 27 healthy individuals) and validation cohort (48 patients and 53 healthy individuals). Next-generation RNA sequencing was performed on platelets isolated from peripheral blood of all participants and a support vector machine/leave-one-out cross validation (SVM/LOOCV) approach was used for binary classification. A diagnostic signature composed of ARID1A, GTF2H2 and PRKRIR discriminated ESCC patients from healthy individuals with 91.3% sensitivity and 85.2% specificity in the training cohort and 87.5% sensitivity and 81.1% specificity in the validation cohort. The AUC was 0.924 (95% CI, 0.845–0.956) and 0.893 (95% CI, 0.821–0.966), respectively, in the training cohort and validation cohort. This 3-gene platelet RNA signature could effectively discriminate ESCC from healthy control. Our data highlighted the potential of tumor educated platelets for the noninvasive diagnosis of ESCC. Moreover, we found keratin and collagen protein families, and ECM-related pathways might be involved in tumor progression and metastasis of ESCC, which might provide insights to understand ESCC pathobiology and advance novel therapeutics.
2022-06-01 | GSE197514 | GEO
Project description:There are currently no screening methods for high grade ovarian cancer (HGOC) that guarantee effective early detection for high risk women such as germline BRCA mutation carriers. Therefore, the standard-of-care remains risk reducing salpingo-oophorectomy (RRSO) around age 40. Proximal liquid biopsy has been shown to be a promising source of biomarkers, but sensitivity has not yet qualified for clinical implementation. We report the discriminant performance of a novel proteomic classifier for detection of HGOC in high-risk population, and the safety and feasibility of simplified utero-tubal lavage (UtL) as a method for sampling proximal liquid biopsy.The training set included 93 women with high-risk for HGOC (BRCA1 and BRCA2 mutation carriers), including: 16 HGOC patients and 77 asymptomatic women, who donated UtL liquid biopsies, in 3 Israeli medical centers (Biomarkers for Early Detection of Ovarian Cancer Using Uterine Lavage (BEDOCA); ClinicalTrials.gov Identifier: NCT03150121). The proteome of the microvesicle fraction of the samples was profiled by mass spectrometry and a classifier was developed using logistic regression. An independent cohort of 104 BRCA mutation carriers was used as validation. Safety information was collected for all women who opted to UtL in a clinic setting.
2022-09-13 | PXD030390 | Pride
Project description:Purpose: Patients with locally advanced prostate cancer after radical prostatectomy are candidates for secondary therapy. However, this higher risk population is heterogeneous. Many cases do not metastasize even when conservatively managed. Given the limited specificity of pathological features to predict metastasis, newer risk prediction models are needed. We report a validation study of a genomic classifier that predicts metastasis after radical prostatectomy in a high risk population. Method:A case-cohort design was used to sample 1,010 patients after radical prostatectomy at high risk for recurrence who were treated from 2000 to 2006. Patients had preoperative prostate specific antigen greater than 20 ng/ml, Gleason 8 or greater, pT3b or a Mayo Clinic nomogram score of 10 or greater. Patients with metastasis at diagnosis or any prior treatment for prostate cancer were excluded from analysis. A 20% random sampling created a subcohort that included all patients with metastasis. We generated 22-marker genomic classifier scores for 235 patients with available genomic data. ROC and decision curves, competing risk and weighted regression models were used to assess genomic classifier performance.
2014-11-13 | GSE62116 | GEO
Project description:To identify and assess exosomal miRNA signatures with potential to predict individuals with persistent organ failure (POF) at early phase of acute pancreatitis. We analyzed serum collected from 790 AP patients. In discovery cohort, we profiled exosomal miRNAs in sera sampled from AP patients with or without POF (5 vs. 5) using microarrays and identified a list of miRNAs with increased expression pattern. Of notes, 10 AP samples with/without POF are collected within 24 hours after AP onset and later did/didn’t develop POF. We further constructed a miRNA classifier (Cmi) through logistic regression and identified certain individual miRNAs (OR>2) as candidate predictive markers in the training cohort of 227 AP samples. Predictive performance of these markers were validated in three independent cohorts (255, 226 and 78 AP samples respectively).
2024-08-01 | GSE136030 | GEO
Project description:The 2021 WHO Classification of Tumors of the Central Nervous System includes several tumor types and subtypes for which the diagnosis is at least partially reliant on utilization of whole genome methylation profiling. The current approach to array DNA methylation profiling utilizes a reference library of tumor DNA methylation data, and a machine learning-based tumor classifier. This approach was pioneered and popularized by the German Cancer Research Network (DKFZ) and University Hospital Heidelberg. This research group has kindly made their classifier for central nervous system tumors freely available as a research tool via a web-based portal. However, this classifier is not maintained in a clinical testing environment. Therefore, we validated our own DNA methylation-based classifier of central nervous system tumors. We validated our classifier using the same training and validation datasets as the DKFZ group. In addition, we performed a validation of samples tested in our own laboratory and compared the performance of both classifiers. Using the validation data set, our classifier’s performance showed high concordance (92%) and comparable accuracy (specificity 94.0% v. 84.9% for DKFZ, sensitivity 88.6% v. 94.7% for DKFZ). Receiver operator curve showed areas under the curve of 0.964 v. 0.966 for NM and DKFZ classifiers, respectively. Our classifier performed comparably well with samples tested in our own laboratory and is currently offered for clinical testing.
2022-03-19 | GSE198855 | GEO
Project description:Immunotherapy has improved the prognosis of patients with advanced non-small cell lung
cancer (NSCLC), but only a small subset of patients achieved clinical benefit. The purpose of our study was to integrate multidimensional data using a machine learning method to predict the therapeutic efficacy of immune checkpoint inhibitors (ICIs) monotherapy in patients with advanced NSCLC.The authors retrospectively enrolled 112 patients with stage IIIB-IV NSCLC receiving ICIs monotherapy. The random forest (RF) algorithm was used to establish efficacy prediction models based on five different input datasets, including precontrast computed tomography (CT) radiomic data, postcontrast CT radiomic data, combination of the two CT radiomic data, clinical data, and a combination of radiomic and clinical data. The 5-fold cross-validation was used to train and test the random forest classifier. The performance of the models was assessed according to the area under the curve (AUC) in the receiver operating characteristic (ROC) curve. Among these models(RF MLP LR XGBoost), our reproduced onnx models have better performance, especially for random forest. The response variable with a value (1/0) indicates the (efficacy/inefficacy) of PD-1/PD-L1 monotherapy in patients with advanced NSCLC
2023-07-11 | BIOMD0000001074 | BioModels
Project description:How to design experiments that accelerate knowledge discovery on complex biological landscapes remains a tantalizing question. Here, we present OPEX, an optimal experimental design method to identify informative omics experiments for both experimental space exploration and model training. OPEX-guided exploration of Escherichia coli's cross-behavior potential, when exposed to novel biocide and antibiotic combinations, led to accelerated knowledge discovery with predictive models that are more accurate while needing 44% fewer data to train. Selecting experiments favoring broader exploration followed by fine-tuning emerged as the optimal strategy. This led to the discovery of 29 cross-protection and 4 cross-vulnerability conditions, with further validation revealing the central role of chaperones, stress response proteins and transport pumps in cross-stress exposure. This work demonstrates how active learning can be used to automate omics data collection for training accurate predictive models, evidence-driven decision making and accelerated knowledge discovery in life sciences.
2020-07-09 | GSE144604 | GEO
Project description:We have previously identified a prognostic 31-gene expression signature in locally advanced cervical cancer that is associated with tumor hypoxia and reflected by the dynamic contrast enhanced magnetic resonance (DCE-MR) image parameter ABrix. To bring the signature closer to clinical use, we here aimed to construct a classifier with key signature genes that retained an association to ABrix and separated the patients into groups with different hypoxia status and chemoradiotherapy outcome. A training cohort of 42 patients and two independent cohorts of 108 and 131 patients were included. Gene expression data were generated from tumor biopsies by two Illumina array generations (WG6, HT12), and for a subset of 74 patients, by the RT-qPCR platform. The amplitude ABrix in the Brix pharmacokinetic model was extracted from DCE-MR images of 64 patients and used as a measure of hypoxia. Different classifiers were constructed in the training cohort. By evaluating their ability to separate the patients correctly according to ABrix, a 6-gene classifier with strong correlation to ABrix was identified. In validation analyses, the classifier separated the patients into two groups with 5-years progression-free survival probabilities of 85% and 60%. Both the prognostic value and ABrix-association were confirmed in an independent cohort, and robustness across array generations and assay platforms was demonstrated. The prognostic value was independent of existing clinical markers. A robust, prognostic hypoxia classifier has been constructed, and might be used alone or combined with DCE-MR imaging to achieve an early indication of a patientâs risk of failure and allocate high risk patients to adjuvant hypoxia-targeted therapy. Total 150 patient and 2 cell line samples were analysed with Illumina WG-6, while 136 patient and 6 cell line samples were analyzied with Illumina HT-12.
2016-03-29 | E-GEOD-72723 | biostudies-arrayexpress
Project description:Purpose: Gastric cancer (GC) is one of the most common causes of cancer deaths worldwide; however, reliable and non-invasive screening methods for GC are not established. Therefore, we conducted this study to develop a biomarker for GC detection, consisting of urinary microRNAs (miRNAs). Experimental Design: We matched 306 participants by age and sex (153 pairs consisting of patients with GC and healthy controls [HCs]), then randomly divided them across three groups: (1) the discovery cohort (4 pairs); (2) the training cohort (95 pairs); (3) the validation cohort (54 pairs). Moreover, 64 participants (32 pairs) with serum samples were also enrolled in the serum cohort. Result: There were 22 urinary miRNAs with significantly aberrant expressions between the two groups in the discovery cohort. Upon multivariate analysis of the training cohort, urinary expression levels of miR-6807-5p and miR-6856-5p were significantly independent biomarkers for diagnosis of GC, in addition to Helicobacter pylori (H. pylori) status. A diagnostic panel that combined the aberrant miRNAs and H. pylori status distinguished between HC and GC samples with an area under the curve (AUC) = 0.736. In the validation cohort, urinary miR-6807-5p and miR-6856-5p showed significantly higher expression levels in the GC group, and the combination biomarker panel of miR-6807-5p, miR-6856-5p, and H. pylori status also showed excellent performance (AUC = 0.885). In addition, serum levels of miR-6807-5p and miR-6856-5p were significantly higher in the GC group. Conclusion: This novel biomarker panel enables early and non-invasive detection of GC.
2019-12-22 | GSE128720 | GEO