1 - 50 of 83 results


Provides a web resource for exploring, visualizing, and analyzing multidimensional cancer genomics data. cBioPortal reduces molecular profiling data from cancer tissues and cell lines into readily understandable genetic, epigenetic, gene expression, and proteomic events. The query interface combined with customized data storage enables researchers to interactively explore genetic alterations across samples, genes, and pathways and, when available in the underlying data, to link these to clinical outcomes.

TIMER / Tumor IMmune Estimation Resource

Allows explorations of the disease-specific clinical impact of different immune infiltrates in the tumor microenvironment. TIMER was developed to estimate the abundance of six tumor-infiltrating immune cell types (B cells, CD4 T cells, CD8 T cells, neutrophils, macrophages, and dendritic cells) to study 23 cancer types in The Cancer Genome Atlas (TCGA). This tool was validated thanks to Monte Carlo simulations, orthogonal estimates from DNA methylation-based inferences, as well as pathological assessment.


A multi-tiered compendium of bioinformatics algorithms and gene signatures for molecular subtyping and prognostication in breast cancer. Genefu provides bioinformatics implementations of classification algorithms to identify molecular subtypes, as well as prognostic predictors along with their published gene signatures. It also includes other functions to facilitate quick manipulation of gene expression datasets, including gene selection and probe-gene mapping across microarray platforms. The genefu package provides a unified framework for integration of molecular subtype and survival analysis of breast cancer. We have demonstrated how the package can be utilized to perform both meta-analyses across datasets and across algorithms, to facilitate integrated analysis of breast cancer gene expression profiles.


A web application that allows a user to download gene expression data sets directly from GEO in order to perform differential expression and survival analysis for a gene of interest. In addition, shinyGEO supports customized graphics, sample selection, data export, and R code generation so that all analyses are reproducible. The availability of shinyGEO makes GEO datasets more accessible to non-bioinformaticians, promising to lead to better understanding of biological processes and genetic diseases such as cancer.


A package that predicts true survival times for the individual patient based on microarray measurements. RCASPAR is based on a multivariate Cox regression model that is embedded in a Bayesian framework. A hierarchical prior distribution on the regression parameters is specifically designed to deal with high dimensionality (large number of genes) and low sample size settings, that are typical for microarray measurements. This enables RCASPAR to automatically select small, most informative subsets of genes for prediction.


An online tool for statistical validation of hypotheses regarding the effect of p53 mutational status on gene regulation in cancer. p53MutaGene is based on several large-scale clinical gene expression data sets and currently covers breast, colon and lung cancers. The tool detects differential co-expression patterns in expression data between p53 mutated versus p53 normal samples for the user-specified genes. Statistically significant differential co-expression for a gene pair is indicative that regulation of two genes is sensitive to the presence of p53 mutations. p53MutaGene can be used in 'single mode' where the user can test a specific pair of genes or in 'discovery mode' designed for analysis of several genes.


Builds a risk prediction signature for a specific stratum by down-weighting the observations from the other strata using a range of weights. CoxBoost actively controls the extent to which each stratum contributes to the variable selection and estimation of regression coefficients. It also focuses on building a risk prediction signature for a specific stratum by down-weighting the observations from the other strata using a range of weights. CoxBoost was designed to identify clusters of variables that either are important only in the stratum of interest or are also important to some extent in the other strata.


Allows users to develop, validate prediction model, estimate expected survival of patients and visualize them graphically. biospear is an R package that implements approaches to develop and evaluate a prediction model within a high-dimensional Cox regression setting, and to estimate expected survival at a given time point. The software consists of two core functions: BMsel, that identifies a prediction model, and expSurv, that estimates expected survival. biospear also provides a function for generating survival data.


Integrates nine machine learning (ML) algorithms to select the best performing classifier for a specific dataset and provides an interface for their exploration. blkbox is a software package, including a frontend, which provides the functionality to plot different metrics, allowing comparison of algorithm effectiveness for a given dataset. The intersection of selected features in each testing holdout can be visualized in a Venn diagram or heatmap to identify commonly used features and assess variance among holdouts.

miRNA Cancer Analyzer

Provides a machine-learning based system developed to help physicians to diagnose and recommend treatments for 21 different types of cancer. miRNA Cancer Analyzer, to analyze patient’s results, simply asks for data on 60 common miRNA molecules expression levels, as well as clinical data (age, gender, and ethnicity). It then spits out a diagnosis - whether the patient has cancer or not, what type of cancer they have, and with which probability. It also displays the three treatments that have the highest probability of forcing the cancer into remission, based on the patients personal genetic profile and clinical information.


Enables researchers to study the expression level of genes to compare primary tumor with normal tissue samples. UALCAN is an interactive web resource that provides critical information and graphic ability to make stage, grade, race and other sub status specific expression features from transcriptome sequencing data. This portal can aid in the identification of candidate biomarkers of specific cancer subclasses, with diagnostic, prognostic or therapeutic implications. It can also be used as a platform for in silico validation of target genes.


Detects network biomarkers using network-constrained support vector machines (NetSVM). CyNetSVM predicts clinical outcome of patients and identifies biologically meaningful networks. It includes a graphical user interface (GUI) and offers users to analyze largescale biomedical data efficiently. It generates a network view of the identified biomarkers in Cytoscape. This tool is useful to study breast cancer data for clinical outcome prediction and network biomarker identification.

QPATH / Quantitative methods for pathology

Predicts the molecular subtypes of colorectal cancer from the routine histology images. QPATH uses neural networks for extracting local descriptors which were then used for constructing a dictionary–based representation of each tumor sample. It is based on support vector machine (SVM) classifiers models, with radial basis functions kernels. The tool can identify with high confidence at least four of five subtypes, the most difficult to recognize is the subtype E.


Predictes the survival contribution of all annotated exons in the human genome. ExSurv uses RNA sequencing-based expression profiles for cancer samples from four cancer types available from The Cancer Genome Atlas. It also enables users to search for a gene of interest and shows survival probabilities for all the exons associated with a gene and found to be significant at the chosen threshold. ExSurv also includes raw expression values across the cancer cohort as well as the survival plots for prognostic exons.


Predicts prognostic outcome and identifies biomarkers for different human cancers. ENCAPP is an elastic-net-based approach that combines the reference human protein interactome network with gene expression data. The software identifies functional modules that are differentially expressed between patients with good and bad prognosis and uses these to fit a regression model that can be used to predict prognosis for breast, colon, rectal, and ovarian cancers. It can also accurately identify genes that can serve as prognostic biomarkers for different cancers.

sPAGM / subPathway Activity by integrating Gene and MiRNA

Deduces subpathway functional activity for single samples. sPAGM provides a method that determines subPathway Activity (sPA) scores from the expression levels of genes and miRNAs in corresponding subpathway graphs. It can be used for featuring biological mechanisms at the subpathway level and for detecting and characterizing functional signatures in the prognoses of cancer patient. Besides, the activity score generated by the method can also be applied to other researches, such as drug action mechanisms for various types of tumors.


Assists users in visualization of meaningful tiles to facilitate better clinical or biological understanding of tissue phenotypes. SarneckiEtAl2017 provides an image analysis workflow that can extract quantitative, texture information from whole-slide images through a tiling approach and recode this information through clustering analysis for spatial analysis. This method presents the opportunity to better separate patient subtypes and further analyse tissue phenotypes that are critical to patient stratification.


Calculates and visualizes survival statistics to assess the association between a continuous measure and outcome in a compositionally agnostic manner. survivALL is available as an R package and a web application. It allows greater resolution, transparency and flexibility and is applicable to any public or proprietary dataset. It also permits true biological effects and their relationship to outcome to be revealed, most notably in protecting against random compositional difference and falsenegatives in a meta-analysis.

M2EFM / Methylation-to-Expression Feature Model

Builds prognostic models. M2EFM is a data-integrated modeling approach that predicts risk based on data integrated from multiple sources, taking advantage of tried-and-true prognostic factors while incorporating data on relevant relationships between molecular data types at the individual level. This approach allows identification of biologically relevant pathways and possible therapeutic targets and genes involved in cancer progression. It was used to build models of overall survival (OS), distant recurrence-free survival (DRFS), and pathologic complete response (pCR) in breast cancer.

APPEX / Analysis Platform for identification of Prognostic gene EXpression signature in cancer

A web-based software platform to help researchers in the efforts to identify prognostic signatures from genomics data. APPEX is designed to be easy to use and flexible, and it is freely available for advanced statistical survival analyses. A user-friendly graphical interface similar to a desktop application is provided so that users can easily handle their own data on APPEX even if they are not familiar with statistical analysis packages. In addition, APPEX contains >200 publicly available datasets directly applicable on the system so that users can easily validate newly identified signatures in independent patient cohorts.


Performs survival analyses and draws Kaplan–Meier (KM) plots for submitted ‘microRNA' across several available data sets, which cover more than 800 patients. A robust statistical procedure is implemented to account for multiple testing. MIRUMIR is incorporated into BioProfiling.de, analytical portal for high-throughput cell biology. MIRUMIR supports the need of biomedical researchers to estimate the power of miR to serve as potential biomarker to predict survival of cancer patients. MIRUMIR provides such analyses based on several publicly available clinical miR data sets annotated with patient survival information.

RSF / Random Survival Forests

A unified treatment of Breiman's random forests for survival, regression and classification problems. RSF provides a unified treatment of Breiman’s random forests for a variety of data settings. Regression and classification forests are grown when the response is numeric or categorical. Multivariate regression and classification responses as well as mixed outcomes are also handled as are unsupervised forests. Different splitting rules invoked under deterministic or random splitting are available for all families. Variable predictiveness can be assessed using variable importance measures for single, as well as grouped variables. Missing data can be imputed on both training and test data.

InSilico DB

A collaborative platform that allows users to share genomic datasets. Dataset administrators can add/remove collaborators or groups of collaborators through a dedicated sharing interface. It is possible, as discussed in the 'Grouping and sub-grouping' section to create a new dataset by grouping samples from independent datasets. These newly generated datasets are private by default - that is, only the owner has access to them. Sharing preferences and the public status of the dataset can be changed by the owner. An owner of a dataset can make it public to the InSilico DB community or keep it private. A private dataset can be shared with collaborators who can be given read-only or read-and-write permissions. A user who has read-and-write permissions on a dataset can edit its sharing preferences.


Automatically derives the currently known interactome for a gene of interest and correlates expression levels of its interactome, with survival outcome in multiple publicly available clinical expression data sets. PPISURV automatically correlates expression of an input gene interactome with survival rates on >40 publicly available clinical expression data sets covering various tumours involving about 8000 patients in total. To derive the query gene interactome, PPISURV employs several public databases including protein-protein interactions, regulatory and signalling pathways and protein post-translational modifications.


A web application that can be used for studying prognostic implications of mRNA biomarkers in a variety of cancers. We have compiled data from public repositories such as GEO, EBI Array Express and The Cancer Genome Atlas for creating PROGgene. Survival analysis can be performed on a) single genes b) multiple genes as a signature, c) ratio of expression of two genes, and d) curated/published gene signatures. Users can also adjust the survival analysis models for available covariates. Users can study prognostic implications of entire gene signatures in different cancer types, which are searchable by keywords. PROGgene is useful in accelerating biomarker discovery in cancer and quickly providing results that may indicate disease-specific prognostic value of specific biomarkers.


Provides experimentalists a comprehensive toolkit for gene/protein list interpretation. In one submission, the gene list is profiled with respect to the most information available regarding gene function (GO), pathway relations (KEGG database, Reactome knowledgebase), protein interactions (IntAct), in silico predicted gene to MiRNA associations (GeneSet2MiRNA), information collected by text mining (PLIPS and CCancer) and protein ‘amino acid triplets’ composition. BioProfiling.de provides a user-friendly dialog-driven web interface and supports most available gene/protein identifiers. BioProfiling.de provides analyses for the six organisms: Homo sapiens, Mus musculus, Rattus norvegicus, Caenorhabditis elegans, Drosophila melanogaster, Arabidopsis thaliana.


An artificial neural networks (ANN) framework to predict patient prognosis from high throughput transcriptomics data. Cox-nnet utilizes feature importance scores based on the partial derivatives of gene features selected by the model, so that the relative importance of the genes to prognosis outcome can be directly assessed. The hidden layer node structure in ANN can be harnessed to reveal much richer information of featuring genes and biological pathways, compared to other methods. Cox-nnet is a desirable survival analysis method with both excellent predictive power and usage to gain biological functions related to prognosis.