Biosoft Project

This web application creates ROC curves, calculates area under the curve (AUC) values and confidence intervals for the AUC values, and performs multiple comparisons for ROC curves in a user-friendly, up-to-date and comprehensive way.

This application performs multivariate normality tests and graphical approaches and implements multivariate outlier detection and univariate normality of marginal distributions through plots and tests. Click for R Package version.

geneSurv: Survival Analysis for Genomics (Under construction)

Survival analysis is often used in cancer studies. It has been shown that combination of clinical data with genomics increases predictive performance of survival analysis methods. This tool provides a wide range of survival analysis methods for genomic research, especially in cancer studies. The tool includes analysis methods including Kaplan-Meier, Cox regression, Penalized Cox regression and Random Survival Forests. It also offers methods for optimal cutoff point determination for continuous markers.

geneSurv is under construction to be compatible with R version 4.0 and higher. Click here to continue with older version.

voomCLUSTER is a web application developed for RNA-Sequencing datasets to cluster. This application creates fast and truth results using voom method in clustering methods. Also, it consists different methods for grouping RNA-Seq data such as Poisson, model-based and edgeR in addition to classical clustering algorithms (k-means, k-medoid or hierarchical clustering). voomCLUSTER is a comprehensive tool, included interactive headmap and MDS graphs.

This web-tool is a comprehensive calculator which returns hypothesis test results, associaton/risk measures, diagnostic measures, agreement measures, and similarity/dissimilarity measures for a 2-by-2 contingency table.

VoomDDA is a decision support tool developed for RNA-Sequencing datasets to assist researchers in their decisions for diagnostic biomarker discovery and classification problem. VoomDDA consists both sparse and non-sparse statistical learning classifiers adapted with voom method and provides fast, accurate and sparser classification results for RNA-Seq data.

DDNAA: Decision support system for differential diagnosis of nontraumatic acute abdomen (Under construction)

This decision support tool is developed to assist physicians in their decisions to differentially diagnose of patients with acute abdomen. DDNAA includes several diagnostic tests which combine leukocyte count and d-dimer level based on statistical learning approaches.

DDNAA is under construction to be compatible with R version 4.0 and higher. Click here to continue with older version.

MLViS: machine learning-based virtual screening tool (Under construction)

This web-tool classifies the compounds as drug-like and nondrug-like based on various trained statistical machine learning algorithms.

MLViS is under construction to be compatible with R version 4.0 and higher. Click here to continue with older version.

This web-tool combines two diagnositic test to achieve a combined test with higher diagnostic accuracy. It uses several methods to find combinations of diagnostic tests.

MLSeq package provides several algorithms including support vector machines (SVM), bagging support vector machines (bagSVM), random forest (RF) and classification and regression trees (CART) to classify sequencing data. Click here for published article.