Ghislain Durif -

Contact HAL orcid DBLP IdRef arXiv

Research engineer at CNRS, working at the Laboratory of Biology and Modeling of the Cell (LBMC), ENS Lyon, France, since 2022, member of the BioComputing Hub at LBMC.

Member of the technical support team at Computo, a statistics and machine learning oriented open peer-reviewed journal (ISSN 2824-7795) of the French Statistical Society (SFdS) with a focus on open and reproducible science.

Interests

Applied Mathematics
Statistics, Machine Learning, Artificial Intelligence
Applications to Biology
Software Development, Programming and Computing
Reproducible Research and Open Science

Organizations: CNRS | LBMC | BioComp Hub | ENS Lyon | Computo

Former positions

Research engineer at CNRS, working at IMAG (mathematics lab), University of Montpellier | Montpellier, France | 2019-2022
Research engineer at Inria, THOTH team, supervised by Julien Mairal | Grenoble, France | 2017-2019
Phd student at LBBE (biology lab), Lyon 1 University, supervised by Franck Picard and Sophie Lambert-Lacroix | Lyon, France | 2013-2017

Education

PhD in Statistics | Claude Bernard Lyon 1 University | Lyon, France | 2016
Master degree in Applied Mathematics | Claude Bernard Lyon 1 University | Lyon, France | 2013

News

Poster presentation of NuCount

The NuCount project will be presented as a poster at

Open science award for research free/open-source software to KeOps library

The KeOps library got a 2023 open science award for research free/open-source software, “espoir” in the category “documentation”, by the french Ministry of Higher Education…

Latest publications

See all publications

Latest presentations

See all presentations

Bayesian inference of parental allele inheritance in fetus for noninvasive prenatal diagnosis (poster)

StatLearn 2023, Montpellier France

R helper packages to develop R packages

BioComputing hub meeting, LBMC, ENS Lyon, France

Bayesian inference of parental allele inheritance in fetus for noninvasive prenatal diagnosis (poster)

Statistical Methods for Post-Genomic Data (SMPGD) 2023, Ghent, Belgium

Quarto: markdown-based document creation/edition, Static website generator and more

BioComputing hub meeting, LBMC, ENS Lyon, France

Introducing software licenses, focus on free and open source softwares

BioInfo club, LBMC, ENS Lyon, France

Developing an R package

Multiple sessions

Les licences logicielles, focus sur le logiciel libre

2ème rencontre ISDM-NUMEV “Logiciel libre : opportunités et valorisation ?”, Campus St Priest, Montpellier University, France

Statistics and machine learning for applications in biology

Lab seminar, LBMC, ENS Lyon, France

Reproducible research, Good practices and useful information

mtp-rr2021: Workshop on Reproducible Research, online (organiszed by Montpellier University, France)

Introduction to R shiny

Multiple sessions

R shiny: building interactive graphical applications seamlessly

ML-MTP online meeting, IMAG, Montpellier (France)

A non exhaustive tour of optimization-related tools for machine learning and statistics in R

“State of the R” online session, AgroParisTech, Paris (France)

KeOps: seamless Kernel Operations on GPU without memory overflows

useR 2020, online (originally Saint-Louis, Missouri, USA, cancelled due to Covid-19 crisis)

Introduction to Machine Learning

Transverse Thematic Meeting on Machine Learning-Deep Learning, Centre de Biochimie Structurale (CBS), Montpellier (France)

Loter2: Genome-wide local ancestry inference in admixed individuals with scalable penalized nearest neighbor algorithm

GenomeHarvest project seminar, CIRAD, Montpellier (France)

Genome-wide local ancestry inference in admixed individuals with scalable penalized nearest neighbor algorithm

Statistical Methods for Post Genomic Data (SMPGD) 2020, Pasteur Institute, Paris, France

Seamless Kernel Operations on GPU, with auto-differentiation and without memory overflows

SciDoLySE Meeting, Lyon University, Villeurbanne (France)

Dimension reduction for Single Cell Expression Data Analysis

Seminar of the Chromatin and cell biology team, Institute of Human Genetics (IGH), Montpellier (France)

KeOps: seamless Kernel Operations on GPU, with auto-differentiation and without memory overflows

Journées Calcul et Données (JCAD) 2019, Toulouse Federal University, Toulouse (France)

Probabilistic Count Matrix Factorization for Single Cell Expression Data Analysis

Montpellier Bio-Informatics (MBI) meeting, Genopolys, Montpellier (France)

Probabilistic Count Matrix Factorization for Single Cell Expression Data Analysis

Single-cell RNA-seq Day, INSA Toulouse, Toulouse (France)

Sparsity and dimension reduction

Bordeaux Data Science conference, Bordeaux (France)

Multivariate analysis of single cell genomic expression data

Paris Single Cell Day (PASIC) 2018, Muséum National d’Histoire Naturelle de Paris, Paris (France)

High Dimensional Classification with combined Adaptive Sparse PLS and Logistic Regression

Statistical modeling Seminar, IRMA, Strasbourg University, Strasbourg (France)

High Dimensional Classification with combined Adaptive Sparse PLS and Logistic Regression

Statistics seminar, Laboratoire Jean Kuntzmann (LJK), Grenoble Alpes University, Grenoble (France)

Probabilistic Count Matrix Factorization for Single Cell Expression Data Analysis

Research in Computational Molecular Biology, 22nd Annual International Conference RECOMB 2018, Pierre et Marie Curie Campus, Sorbonne University, Paris (France)

Count-based Probabilistic PCA for single-cell data analysis

ISCB NGS 2017 Structural Variation and Population Genomics, Barcelona Biomedical Research Park, Barcelona (Spain)

Multivariate statistics for single-data data analysis: zero-inflated count matrix factorization for data exploration and sparse PLS-based logistic regression for classification

StatOmique group meeting, AgroParisTech, Paris (France)

Count Matrix Factorization and Single Cell Data Analysis

Journées Ouvertes de Biologie Informatique et Mathématiques (JOBIM) 2016, ENS Lyon, Lyon (France)

Count Matrix Factorization and Single Cell Data Analysis

BCM seminar, TIMC-IMAG, Grenoble Alpes University, Grenoble (France)

Count Matrix Factorization for Dimension Reduction and Data Visualization

Statistical Methods for Post-Genomic Data (SMPGD) 2016, Lille University, Lille (France)

Adaptive Sparse PLS for Logistic Regression

Journées du GDR Stat et Santé, Paris Descartes University, Paris (France)

Adaptive Sparse PLS for Logistic Regression

Statistics seminar, IMAG/SupAgro, Montpellier (France)

Adaptive Sparse PLS for Logistic Regression

47èmes Journées de Statistique de la SFdS (JdS), Lille University, Lille (France)

Adaptive Sparse PLS for Logistic Regression

Statistical Methods for Post-Genomic Data (SMPGD) 2015, Ludwig-Maximilians-Universität, Munich (Germany)

Adaptive Spare PLS for Logistic Regression: Dimension reduction, variable selection and classification

Statistics seminar, Laboratoire MAP5, Paris-Descartes University, Paris (France)

Réduction de dimension, sélection de variables et classification supervisée: Sparse PLS et modèle linéaire généralisé (french)

Statistics seminar, Laboratoire J.-A. Dieudonné, Nice-Sophia-Antipolis University, Nice (France)

Multivariate analysis and dimension reduction: Sparse PLS, a comparative study

Statistics for System Biology seminar, INRA/AgroParisTech, Paris (France)

Latest software

See all software

NuCount

Aggregating nuclei segmentation methods to quantify cell counts in spatial transcriptomics data

funStatTest

Statistical Testing for Functional Data

dual.spls

Dual norm-based Sparse Partial Least Squares Regression

NIPD

Bayesian inference for non-invasive prenatal diagnostic of genetic diseases

YALES2BIO

Numerical solver for fluid mechanics

BenchOpt

Benchmark repository for optimization

DIYABC-RF GUI

Graphical User Interface for DYIABC-RF software

KeOps

Seamless Kernel Operations on GPU with auto-differentiation and without memory overflows

ckn-tf

Re-implementation of Convolutional Kernel Network (CKN) from Mairal (2016) in Python based on the TensorFlow framework

Loter

Python package for haplotype phasing and local ancestry inference (population genetics)

SPAMS

Optimization toolbox for sparse estimation, implementing algorithms that solve machine learning and signal processing problems involving sparse regularizations.

pCMF

Probabilistic count matrix factorization for single cell transcriptomic data analyses (dimension reduction, visualization).

plsgenomics

Supervised methods for dimension reduction in classification and regression framework (in particular PLS-based routines for genomic data analyses).