Module: microarray data (GEO GSE94533) |
This suplementary software allows you to use our neural network to predict diagnosis of invasive epithelial ovarian cancer (vs. controls or borderline) depending on the levels of miRNAs.
In order to use this software please set up the values in the panel on your left hand side. The calculations will be performed automatically as the values change.
Module description:
After demonstating that the selected set of 14 microRNAs is sufficient to produce effective classifiers we tested both the dataset and the neural network framework on an independent dataset GSE31568 (Keller A et al.). The best neural network in terms of highest performance and lowest complexity had 4 neurons in the hidden layer. This neural network perfectly classified patients in the training set (AUC 1.00, 95%CI 1.00-1.00) and provided very good discriminatory power on the testing set (AUC 0.93, 95%CI 0.81-1.00). The neural network incorrectly classified one cancer sample as a control in the testing set which resulted in a sensitivity of 75% and specificity of 100%. This step assured us that the selected 14 miRNAs do in fact contain all the information needed for efficient diagnosis of ovarian cancer cases and that a properly trained neural network may use this information for near-perfect performance regardless of input data range or expression quantification algorithms.
The probability of cancer was estimated as:
Advanced details and features:
This tab allows you to evaluate several instances at once. Please upload CSV file and await the table with results. More details about CSV file format can be found in the other tab.
Comma-separated values (CSV) file stores tabular data (numbers and text) in plain text. Each line of the file is a data record. Each record consists of one or more fields, separated by commas. The use of the comma as a field separator is the source of the name for this file format. The first row should contain column "Id" and the miRNA names complient with the names on your left hand side. Column "Id" is important and should contain identifiers of patients, so you can recoginze and assing results to them. Please remember that this format may be dependent on regional settings. You can use Microsft Excel, but we strongly encourage you to check in notepad whether comma is used as column delimiter and not as the decimal mark. Please see the example below...
Example: Download examplary CSV
This software is a part of paper entitled 'Diagnostic potential for a serum miRNA neural network for detection of ovarian cancer' and authored by Kevin M. Elias, Wojciech Fendler, Konrad Stawiski, Stephen J. Fiascone, Allison F. Vitonis, Ross S. Berkowitz, Gyorgy Frendl, Panagiotis A. Konstantinopoulos, Christopher P. Crum, Magdalena Kedzierska, Daniel W. Cramer, and Dipanjan Chowdhury.
Corresponding author: Dipanjan Chowdhury, PhD, Department of Radiation Oncology, Dana-Farber Cancer Institute, dipanjan_chowdhury@dfci.harvard.edu.
Software author, technical issues: Konrad Stawiski, MD (contact: konrad.stawiski@umed.lodz.pl; Department of Biostatistics and Translational Medicine, Medical University of Lodz, Poland).