Software

Python package that facilitates leakage-reduced data splitting to enable realistic evaluation of ML models that are intended to be used in out-of-distribution scenarios.

Python tool to infer gene dysregulation events for individual samples in comparison to a control condition from gene expression data.

Python tool to quantify tissue heterogeneity based on spatial omics data.

Web tool for interactive exploration of putative epistatic interactions in eight complex diseases (late-onset Alzheimer's disease, bipolar disorder, coronary artery disease, hypertension, type-1 diabetes, type-2 diabetes, rheumatoid arthritis, inflammatory bowel disease).

Command line tool for network-based epistasis detection in complex diseases.

Plugin to turn your tool that outputs a list of genes or proteins into a feature rich, drug repurposing web tool with interactive network visualization.

BoostDiff is a Python tool to infer differential gene regulatory networks from gene expression data.

Our Python test suite confinspect allows to assess the effect of demographic confounders such as sex and age on methods for inferring gene regulatory and gene co-expression networks.

GraphSimViz is a web service for quantification of biases phenotype-based disease definitions introduce in disease association data.

CorrNet is a Python package for the analysis of historical correspondence networks.

TF-Prioritizer is an automated pipeline that prioritizes condition-specific transcription factors from multimodal data and generates an interactive web report.  It accepts ATAC, DNase, or ChIP sequencing and RNA sequencing data as input and identifies TFs with differential activity

DIGEST is a systems medicine tool for the in silico validation of gene and disease sets, clusterings, and subnetworks w.r.t. genetic and functional coherence. It is available as a web service, as a Python package, and via a REST API.

ROBUST is a Python tool which uses enumeration of diverse prize-collecting Steiner trees to compute disease modules that are robust to random bias.

Fever-PCA (federated principal component analysis for vertically partitioned data) is a federated, privacy-preserving tool for principal component analysis, including patient stratification and dimensionality reduction.

Flimma is a privacy-preserving hybrid federated tool for differential gene expression analysis. Flimma by design preserves the privacy of the local data, since the expression profiles never leave the local execution sites and shared meta-parameters are protected via secure multi-party computation.

NeDRex (network-based drug repurposing and exploration) is an interactive network medicine platform for disease module identification and drug repurposing.

The AIMe registry for artificial intelligence in biomedical research is a community-driven platform for reporting biomedical AI systems. It allows authors of new biomedical AIs to report their models in an explicit and transparent fashion and thereby fosters comparability and reproducibility.

A Python suite for testing the functional relevance of the results produced by active module identification methods, as well as their robustness to random pertubations of the employed protein-protein interaction networks.

BiCoN allows to stratify patients while elucidating disease mechanisms. BiCoN is a network-constrained biclustering approach, which restricts biclusters to functionally related genes connected in molecular networks and maximizes the expression difference between two groups of patients.

CoVex is a unique online network and systems medicine platform for data analysis that integrates virus-human interactions for SARS-CoV-2 and SARS-CoV-1. It implements different network-based approaches for the identification of new drug targets and new repurposable drugs.

EpiGEN is an easy-to-use epistasis simulation pipeline written in Python. It supports epistasis models of arbitrary size, the specification of the minor allele frequencies for both noise and disease SNPs, and  the simulation of observation bias.

GEDLIB is an easily extensible C++ library for (suboptimally) computing the graph edit distance (GED) between two labeled graphs. GEDLIB implements more than thirty state-of-the-art methods for computing GED and comes with predefined edit costs for some benchmark datasets.