Training and evaluating a variational autoencoder for pan-cancer gene expression data

What you need to process the Quarterly DepMap-Omics releases from Terra

Identifying tumor cells at the single-cell level using machine learning

Backend Server for CIViC Project

Pan-cancer quantification of neoantigen-mediated immunoediting in cancer evolution

Analysis for "K27M in canonical and noncanonical H3 variants occurs in distinct oligodendroglial cell lineages in brain midline gliomas" (Jessa et al, Nature Genetics, 2022)

Deterministic evolution and stringent selection during pre-neoplasia

To use deep learning to identify patients whose tumor DNA mutations “look similar to” other tumors for which treatments are effective.

ImaGene: A multi-omic ML/AI software with guided operational reports and supporting files

Neoantigen Discovery pipeline

The evoverse is a package to implement cancer evolution analysis on multi-sample cancer sequecing data.

Applying Machine Learning Ras, NF1, and TP53 Classifiers to PDX model gene expression

Lab website.

A fully automated and reproducible Whole Genome Sequencing (WGS) pipeline built with Snakemake. Implements GATK Best Practices for alignment (BWA), variant calling, and functional annotation (SnpEff) on human (GRCh38) data.

Cell-of-origin analysis for "Histone H3.3G34-mutant interneuron progenitors co-opt PDGFRA for gliomagenesis" (Chen*, Deshmukh*, Jessa*, Hadjadj*, et al, Cell, 2020)

This R package repository performs optimal transport and kernel regression hypothesis testing. Functions to perform large scale simulations are also provided.

Formalin artefact filtering of tumour sample VCF files

Integrative multi-omics analysis of the ImmunoProfiler cancer cohort performed at the Léon Bérard Center (Lyon, France). This project explores genomic and immunologic data using MOFA to uncover latent molecular patterns and potential pan-cancer signatures.