index – Programme Numérique en Santé

BioFlow-Insight

PEPR SN,ShareFAIR

workflow

bioinformatics

reproducibility

From your workflow’s source code, BioFlow-Insight generates graph structures that represent the different steps of your workflow, easily and without any configuration or the need to execute it. BioFlow-Insight analyses the code of your Nextflow workflow and then automatically reconstructs its structure. It is even capable of detecting different types of errors in the code.

BioImageIT

Mainly biology and microscopie

BioImageIT is a workflow management system designed to drastically simplify the creation, execution, and duplication of data science experiments, with specialized features tailored for image analysis. The primary goal is to make bioimage analysis truly FAIR: Findable, Accessible, Interoperable, and Reproducible.

BrainVISA

Neuroimagerie

Plateforme logicielle pour le développement, la maintenance et la diffusion d’outils d’analyse d’image pour la recherche en Neuroimagerie

Cointepas Yann

C/C++,Python,DB (sql/no-sql)

Brian2

Neuromorphique

Logiciel de simulation de neurones biologiques

CARDAMOM

Bioinformatics

CARDAMOM (Cell type Analysis from scRna-seq Data achieved from a Mixture MOdel), is a new algorithm for inferring a GRN from timestamped scRNA-seq data, which crucially exploits the notions of metastability and transcriptional bursting.

CatiDB

Neuroimagerie

Infrastructure de stockage et portail web de l’UMR CATI pour centraliser le suivi du flux des données de neuroimagerie (acquisition, contrôle qualité, analyse, livraison).

Cointepas Yann

Python,JavaScript,DB (sql/no-sql)

PEPR SN,BHT,Institut de Neurosciences des Systèmes,Aix-Marseille University

ClinConNet-SSI-wallet

PEPR SN,HAL,TracIA

Computer Science, Informatique

SSI wallet browser extension for ClinConNet, based on VERAMO SDK

Montassar Naghmouchi

Cloud agent (SSI wallet) for clinConNet platform

PEPR SN,HAL,TracIA

Computer Science, Informatique

Cloud agent (SSI wallet) for clinConNet platform

Montassar Naghmouchi

Cytoscape

Visualisation

Réseaux géniques

Visualisation et exploration des réseaux biologiques.

DCM_PPLs

dynamic causal modeling

probabilistic programming languages

The aim is to provide inference services for Dynamical Causal Modeling of Event-Related Potentials (ERPs) measured with EEG/MEG, using SATO Probabilistic Programming Languages (PPLs): Numpyro Blackjax PyMC Stan

DecLearn

PEPR SN,HAL,SSF-ML-DH

Federated Learning

A modular and extensible framework for Federated Learning.

EDAMannot

PEPR SN,HAL,ShareFAIR

Bioinformatic softwares

Semantic annotation tool

Biotools

Edamontology

EDAMannot is a command-line toolbox leveraging the ShareFAIR-KG knowledge graph from the ShareFAIR Knowledge Base. It provides processing, metrics, and visualization features based on the EDAM ontology. The toolbox is particularly useful for EDAM annotations of tools registered in the bio.tools registry. This knowledge base and toolbox are supported by the ShareFAIR project WP2.

Ulysse Le Clanche

PYTHON 3,Jupyter Notebook,SPARQL

FED-BIOMED

PEPR SN,HAL,SSF-ML-DH

Federated learning

Healthcare

Fed-BioMed is an open-source research and development initiative for translating collaborative learning into real-world medical applications, including federated learning and federated analytics. The community of Fed-BioMed gathers experts in medical engineering, machine learning, communication, and security. We all contribute to provide an open, user-friendly, and trusted framework for deploying the state-of-the-art of collaborative learning in sensitive environments, such as in hospitals and health data lakes.

Frites

PEPR SN,HAL,BHT

neuroscience

statistics

functional-connectivity

electrophysiologicial-data

neurophysiological-data

information-theory

Frites is a Python toolbox designed for students and researchers for assessing information-based measures on human and animal neurophysiological data (M/EEG, Intracranial) for the discovery of cognitive brain networks.

Gudhi

Computational topology

Machine Learning

General library for topological data analysis

Carrière Mathieu

Soft-contributor,Devel

C/C++,Python

Génération SNIIRAM

PEPR SN,HAL,SafePaw

Machine Learning

Jumeau numérique

Outil de génération d’une base de données synthétique et partageable (sans soucis de contrainte de vie privée)

Guyet Thomas

Leader,Instigator,Devel

Aucun

Partenaires

HOI

PEPR SN,HAL,BHT

high-order interactions

statistics

information-theory

HOI (Higher Order Interactions) is a Python package to go beyond pairwise interactions by quantifying the statistical dependencies between 2 or more units using information-theoretical metrics.

Harissa: tools for mechanistic gene network inference from single-cell data

Stochastic gene expression

Transcriptional bursting

Gene regulatory networks

Harissa (HARtree approximation for Inference along with a Stochastic Simulation Algorithm) is a Python package for both inference and simulation of gene regulatory networks, based on stochastic gene expression with transcriptional bursting. It is implemented in the context of a mechanistic approach to gene regulatory network inference from single-cell data.

Ulysse Herbach

PEPR SN,HAL,Autonom-Health

HiDem

PEPR SN,Rewind

illness death model

longitudinal data

The goal of HIDeM is to perform variable selection in an illness-death model with interval-censored time to illness.

HiGHS

Recherche opérationelle

Logiciel open-source pour la résolution de modèle d’optimisation linéaire

IGoR

Bioinformatics

Immune repertoire sequence analysis

Airr data

IGoR is a C++ software designed to infer V(D)J recombination related processes from sequencing data such as:

Recombination model probability distribution

Hypermutation model

Best candidates recombination scenarios

Generation probabilities of sequences (even hypermutated)

The following paper describes the methodology, performance tests and some new biological results obtained with IGoR:

High-throughput immune repertoire analysis with IGoR, Nature Communications, (2018) Quentin Marcou, Thierry Mora, Aleksandra M. Walczak

Its heavily object oriented and modular style was designed to ensure long term support and evolvability for new tasks in assessing TCR and BCR receptors features using modern parallel architectures.

IGoR is a free (as in freedom) software released under the GNU-GPLv3 license.

Kaldi

speech recognition

Kaldi is a toolkit for speech recognition written in C++ and licensed under the Apache License v2.0. Kaldi is intended for use by speech recognition researchers.

LeasPy

PEPR SN,HAL,Rewind

Médecine de précision

données longitudinales

modèles statistiques

apprentissage automatique

apprentissage profond

statistiques bayésiennes

Leaspy is a software package for the statistical analysis of longitudinal data, particularly medical data that comes in a form of repeated observations of patients at different time-points.

MAPIE

P16

Quantification d'incertitude

Bibliothèque python pour la quantification d’incertitude des modèles de machine learning (à travers la prédiction conforme)

METAMATS

Cancérologie

Mathematical Modeling of Metastatic Cancer Progression

An R package for building and fitting mathematical models of metastatic disease. It uses size-structured partial differential equations (PDEs) to describe how tumors grow and disseminate metastases over time.

Benzekry Sébastien

Leader,Instigator,Devel

R,Python,Jupyter Notebook

MOTL

PEPR SN,HAL,M4DI

Multi‑omics

Bioinformatics

MOTL infers latent factor values for a multi-omics target dataset, consisting of a small number of samples, by incorporating latent factor values already inferred with a MOFA factorization of a large, heterogeneous, learning dataset.

David Hirst

Devel

PEPR SN,BHT,Institut de Neurosciences des Systèmes,Aix-Marseille University

Mixt-NNBR

Applied statistics for oncology

A new deconvolution algorithm based on a mixture of non-negative Beta regression

Monolix

Données longitudinales

Pharmacologie

Modélisation non-linéaire à effets mixtes

Napari

Imagerie

Bioinformatics

Généraliste

napari: a fast, interactive viewer for multi-dimensional images in Python

Neuro-forge

Neuroimagerie

Outils pour la création, la maintenance et le déploiement de packages Conda pour des logiciels de recherche en Neuroimagerie.

Nilearn

Neuroimagerie

PEPR SN

BHT

Nilearn enables approachable and versatile analyses of brain volumes and surfaces. It provides statistical and machine-learning tools, with instructive documentation & open community.

It supports general linear model (GLM) based analysis and leverages the scikit-learn Python toolbox for multivariate statistics with applications such as predictive modeling, classification, decoding, or connectivity analysis.

OHIF

Imagerie

Visualisateur d’examens d’imagerie médicale au format dicom.

QualiCATI

Neuroimagerie

Logiciel pemettant de fair le contrôle qualité des images acquises pour la recherche en neuroimagerie (IRM et médecine nucléaire).

ROOFS: RObust biOmarker Feature Selection

Bioinformatics

Biomarkers

Computational biology

ROOFS is a Python package for benchmarking feature selection (FS) methods, designed to help researchers choose the most suitable FS method for their predictive task. ROOFS executes bootstrap-based machine learning pipelines that include the FS step and generates comprehensive reports summarizing key evaluation metrics: downstream predictive performance estimated with optimism correction, stability, reliability of individual features, and true positive and false positive rates assessed on semi-synthetic data with simulated outcomes. ROOFS includes 30+ FS methods from different algorithmic families.

SAFEPAW: Case-mix planning

PEPR SN,HAL,SafePaw

Santé

Outil d’optimisation stratégique qui relie le type de patients aux ressources nécessaires, pour analyser, comparer et planifier l’activité hospitalière sur un territoire.

SBI-VBMs

virtual brain models

simulation-based inference

Connectome-based models, also known as Virtual Brain Models (VBMs), have been well established in network neuroscience to investigate pathophysiological causes underlying a large range of brain diseases. The integration of an individual’s brain imaging data in VBMs has improved patient-specific predictivity, although Bayesian estimation of spatially distributed parameters remains challenging even with state- of-the-art Monte Carlo sampling. VBMs imply latent nonlinear state space models driven by noise and network input, necessitating advanced probabilistic machine learning techniques for widely applicable Bayesian estimation. Here we present Simulation-based Inference on Virtual Brain Models (SBI-VBMs), and demonstrate that training deep neural networks on both spatio-temporal and functional fea- tures allows for accurate estimation of generative parameters in brain disorders. The systematic use of brain stimulation provides an effective remedy for the non- identifiability issue in estimating the degradation limited to smaller subset of connections. By prioritizing model structure over data, we show that the hierarchical structure in SBI-VBMs renders the inference more effective, precise and biologically plausible. This approach could broadly advance precision medicine by enabling fast and reliable prediction of patient-specific brain disorders.

Meysam Hashemi

Jupyter Notebook,Python,C++

Leader,Soft-contributor,Devel

SCENIC (et bibliothèques associées)

Bioinformatics

Réseaux géniques

Outils pour inférer les réseaux de régulation génique à partir de données RNAseq.

Marku Malvina

Aucun

Personnel

SWoTTeD

Machine Learning

Analyse de trajectoires de soins

Identification de biomarqueurs

Données EHR

SWoTTeD est un modèle de machine learning pour l’analyse non-supervisée de trajectoire de soins. Il permet de découvrir des sous-séquences typiques à partir d’une collection de parcours décrits sous forme de tenseur (description d’une matrice d’évènements selon un axe de temps, ou chaque évènement est un vecteur).

Guyet Thomas

Partenaires

Shanoir (SHAring iN vivO Imaging Resources)

Imagerie

Shanoir (SHAring iN vivO Imaging Resources) is a web platform (open-source) for clinical and preclinical research, designed to import, share, archive, search and visualize all kind of medical imaging data (MR, CT, PT, EEG, Bruker). Its origin goes back to neuroimaging, but its usage is now open for all kind of organs. It provides a user-friendly, secure web access and offers an intuitive workflow to facilitate the collecting and retrieving of imaging data from multiple sources and a wizzard to make the completion of metadata easy. Shanoir comes along with many features such as pseudonymization of data for all imports, automatic NIfTI conversion, support for multi-centres clinical studies and many more.

Kain Michael

Java,JavaScript,DB (sql/no-sql)

ShareFAIR-KG

PEPR SN,HAL,ShareFAIR

Knowledge graphs

Workflows

Ontology

SPARQL

This project aims at creating a knowledge base of workflow metadata and annotations. It deploys a SPARQL endpoints, fetches workflow metadata and ontologies, and upload them to the knowledge base.

Marie Schmit

Python,SPARQL

SimulAD

Imagerie

Bioinformatics

SimulAD is a disease progression model, allowing to learn dynamical relationships between pathological processes at stake during AD based on the analysis of multi-modal and longitudinal data.

The method was presented in the following paper in which its mathematical foundation is detailed as well as its application on a research cohort: Simulating the outcome of amyloid treatments in Alzheimer’s disease from imaging and clinical data by Clément Abi Nader, Nicholas Ayache, Giovanni B. Frisoni, Philippe Robert, Marco Lorenzi.

Spikeinterface

Imagerie

Logiciel d’analyse des signaux extracellulaires

TanaT - Temporal Analysis of Trajectories

PEPR SN,HAL,SafePaw

Clinical data analytics

Python library designed for advanced temporal sequence analysis, with specialized focus on patient care pathways and complex temporal data structures (trajectories).

Virtual Imaging Platform (VIP)

Imagerie médicale

VIP est un portail web qui permet l’accès à des applications scientifiques en tant que services.

Pop Sorina

Python,Java,JavaScript,Shell

Universelle

Web portal for ClinConNet platform

PEPR SN,HAL,TracIA

Computer Science, Informatique

Web portal for ClinConNet platform

Montassar Naghmouchi

chupverse

PEPR SN,SMATCH

CHU

Poitiers

Care

research

Innovation

The chupverse reposetory includes R packages for data analyses. We also share examples for estimations of sample size, presentations of speakers in the data science seminars, and LaTeX templates.

citcdf is a package to perform conditional independence testing using empirical conditional cumulative distribution function estimations. The main function of the package is cit(). It uses an asymptotic test (for large sample size , or a permutation test for small sample size with the argument method) to perform conditional independence testing. The approach implemented in this package is detailed in this article

citcdf

PEPR SN,SISTM,AI4scMED

single-cell

statistics

differential expression analysis

clinical-ssi-project

PEPR SN,TracIA

SSI

clinical data

security

ClinicalSync is an SSI solution for the clinical domain. It is envisioned as a daily application for patients and healthcare professionals. For that, this solution implements an agent-based model with edge and cloud agents. The edge agent contains the logic of a mobile application that allows the creation and management of DIDs and VCs, as well as connections between different edge agents. In contrast, the cloud agent implements the mediator functionality for the communication between the different agents and the connection with the Blockchain platform, acting as a Verifiable Data Registry (VDR).

compo.EDA: Data Analysis for Oncology

Biomarkers

Clinical studies

Statistiques

The package compoEDA aims to provide a comprehensive exploratory analysis of data from clinical studies in oncology. These studies commonly investigate biological markers able to reveal and distinguish different tumor profiles, in order to early adapt the therapeutic strategy for patients. The objective of this software is to provide a simplified tool for both computational scientists and clinical researchers to easily generate a graphical results and automatic reports containing the following analyses: - Overview and visualization of clinical data and biological markers - Univariate and multivariate classification analysis (logistic regression) - Univariate and multivariate survival analysis (Cox regression, Kaplan-Meier analysis) - Correlation analysis - Statistical tests - Visualizations of markers (boxplots, barplots, volcano plots, forest plots …).

hidimstat

Health data diagnosis

The HiDimStat package provides statistical inference methods to solve the problem of support recovery in the context of high-dimensional and spatially structured data.

kAOV : kernel hypothesis testing on general designs

Kernel testing

Analysis of variance

A Python library for kernel hypothesis testing on general designs

Polina Arsenteva

Python 3

ktest : two-sample kernel testing

Instigator,Soft-contributor

Statistics, Statistiques

This package implements kernel tests such as kFDA and MMD. Contains source code for publication: Anthony Ozier-Lafontaine, Camille Fourneaux, Ghislain Durif, Polina Arsenteva, Céline Vallot, Olivier Gandrillon, Sandrine Gonin-Giraud, Bertrand Michel, Franck Picard. (2024). Kernel-Based Testing for Single-Cell Differential Analysis. Preprint, 10.48550/arXiv.2307.08509. The results presented in the paper are available at https://github.com/AnthoOzier/ktest_experiment_genome_biology_2024. The source code for experimental_data and squair scripts are based on the branch “publication_genome_biology” (https://github.com/LMJL-Alea/ktest/tree/publication_genome_biology). The reversion scripts are based on the branch “publication_genome_biology_reversion” (https://github.com/LMJL-Alea/ktest/tree/publication_genome_biology_reversion). See https://github.com/AnthoOzier/ktest_experiment_genome_biology_2024 for more details.

Anthony Ozier-Lafontaine

Python,R

mixOmics

Multi-omics

mixOmics is an R package for exploring and integrating omics data, including transcriptomics, proteomics, lipidomics, microbiome, metagenomics and beyond. The mixOmics package includes tools for data integration, biomarker discovery, and data visualisation, using advanced multivariate methods to reduce data dimensionality and uncover relationships within and across datasets.

https://mixomics.org

Dejean Sébastien

INSERM‑U1141 – Neurodiderot

multiomics_MDD

PEPR SN,HAL,M4DI

Multi‑omics

Bioinformatics

Study of multiomic peripheral blood biomarkers for Major Depressive Disorder (MDD) published in 2025 (https://doi.org/10.1016/j.ebiom.2025.105569). Integration of gene expression data with DNA methylation (DNAm) and microRNAs (miRNAs) derived from peripheral blood samples from a well-characterized cohort of individuals with MDD (n=80) and healthy controls (n=89). The raw and processed data are available on GEO with accession number GSE251786.

Devel

The goal is to create a library to quantify and mitigate data leaks from Large Language Models. This code has been used for the paper Towards the Anonymization of the Language Modeling.

nlp-attacks

PEPR SN,SSF-ML-DH

LLM

data leaks

security

pppca: Principal Component Analysis for replicated point process data.

Dimension reduction

Point process

Principal Component Analysis for replicated point process data.

Ghislain Durif

shapash

P16

Explicabilité

Bibliothèque python pour l’explicabilité des modèles de machine learning

skrub

P16

Science des données

Machine Learning

Bibliothèque Python pour la préparation des données

survgen-clinical-trials

PEPR SN,Rewind

survival data

clinical trials

Code accompanying the paper “Toward Valid Generative Clinical Trial Data with Survival Endpoints”. This repository provides tools to generate and analyze synthetic clinical trial data with survival endpoints using a generative modeling approach. It includes our extension of the Heterogeneous and Incomplete Variational Autoencoder (HI-VAE) supporting survival data, enabling the model to handle time-to-event analysis with incomplete and heterogeneous data types.

Agathe Guilloux

python,jupyter notebook

Aucun

survinsight

PEPR SN,Rewind,HeKa

ML-based

survival methods

survinsights is a Python framework for interpreting survival models, with support for static and longitudinal covariates, dynamic prediction settings, and Shapley-based explainability methods. This repository provides general-purpose tools for survival model interpretation and also contains experimental code accompanying specific research papers.

Van Tuan Nguyen

Jupyter Notebook,Python