SOFTWARE

SCEVAN is our tool to detect the clonal copy number substructure of tumors from single-cell data. It also can automatically classify tumor cells from non tumor cells. Check it out here. Read the paper here.

MOViDA is an interpretable deep learning model for drug sensitivity prediction, exploiting the Gene Ontology hierarchy. Check it out here. Read the paper here.

scTHI is an R/Bioconductor package to identify active pairs of ligand-receptors from single cells in order to study,among others, tumor-host interactions. scTHI contains a set of signatures to classify cells from the tumor microenvironment.

Our software tool for Adaptive One-Class Gaussian Processes (OCGP) for oncology drug targets prioritization. See our paper for details.

CPTACBiolinks is our tools to download and analyze CPTAC data.

RGBM: Regularized LS-TreeBoost & LAD-TreeBoost algorithm for Regulatory Network inference from any type of expression data (Microarray/RNA-seq etc). See our Mall et al. NAR paper.

ncrna-deep is a deep learning method to predict the function on short non coding RNA. The method is detailed in the paper “Deep learning predicts non-coding RNA functions from only raw sequence data

TCGABiolinks is a pupular R/Bioconductor package for the integrative analysis of TCGA data developed with Antonio Colaprico, Thiago Silva and Houtan Noushmehr.

VEGA is a n R/Bioconductor package for Copy Number detection. It’s a segmentation algorithm based on the Mumford&Shah variational model.

ExomePipeline is our python notebook for running tumor-normal somatic variation calling for multiple samples.

TimeDelay-ARACNE is an R/Bioconductor package for gene regulatory network inference from time-course data based on Mutual Information.

GAIA is an R/Bioconductor package for the identification of recurrent Copy Number alteration from multiple tumors based on an homogeneous peel-off algorithm.

VEGAWES is the extension of VEGA segmentation algorithm for NGS data. See the our paper for details.

VegaMC is an R/Bioconductor package which extend the VEGA algorithm to multiple samples. Details are available in the Bioinformatics paper.