Campuses

As France's leading biocluster, Genopole is an incubator for cutting-edge projects in biotechnology. Located in the city of Évry, just south of Paris, Genopole provides a unique environment for scientists and entrepreneurs seeking to advance research and innovation.

Discover >

Advantages

Genopole accompanies researchers, postdocs and start-up entrepreneurs through all the phases of their projects to ensure the best possible conditions for business development.

Discover >

Genopole’s citizens

Every day, at Genopole, researchers, entrepreneurs and students cross paths, share ideas and unite forces in a veritable melting pot for innovation.

Discover >

Highlights

Giving wings to research and empowering employment in our community are cornerstones of Genopole's mission. Catch up on recent scientific advances, the accomplishments of our biotech actors and the events that enliven the biocluster.

Discover >

Innovate with us

Discover >
Highlights

An artificial intelligence to diagnose and explain


The IBISC laboratory has conceived an architecturally-innovative neural network able to provide not only a diagnostic prediction but also a biological explanation.
Publication parue de Bioinformatics 2022 >

Researchers from IBISC (Computer Science, Bio-informatics and Complex Systems, University of Évry-Paris Saclay) have developed GraphGONet, an artificial intelligence algorithm that furnishes a medical diagnosis accompanied by a biological explanation.

GraphGONet is a neural network, also called a deep learning model. Lying within the hidden layers of its virtual neurons is a collection of formalized, hierarchized and interlinked information derived from knowledge on genes and gene function. The architecture conceived by the team makes the model innovatively “self-explaining,” that is, it provides not only a diagnostic prediction but also an explanation of the involved biological concepts, making the tool directly employable by clinicians in the setting of personalized medicine.

While new thresholds are being crossed in the exploration of the human genome, the ever-growing knowledge on genes and their expression is laying paths to a new medicine able to address pathologies in a more exact fashion and establish early diagnoses, notably for cancers, cardiovascular diseases and metabolic disorders, among others. Artificial intelligence (AI) and deep learning methods in particular can contribute greatly to the emergence of this “precision medicine.”

Diagnosis by AI: explanations required!

In practice though, the use of AI in medicine has been limited because most AI algorithms are “black boxes” furnishing no explanations for their output. That aspect is problematic for researchers, clinicians and patients who need to be confident that AI predictions result from reliable medical characteristics and not artifacts.

For their system’s diagnostic predictions, the IBISC informaticians included the entry of data on patient genetic activity (i.e., gene expression and expression level / non-expression). For prediction interpretation, they integrated concepts from the Gene Ontology Bioinformatics Consortium’s knowledgebase into the deeper layers of GraphGONet. The Gene Ontology project standardizes knowledge on genes and their proteins, and links those data to associated functions, cellular components and biological mechanisms. Each aspect (function, mechanism, etc.), called a “GO term,” is coded and described via standardized vocabularies and rules.

GraphGONet: predictions and biological interpretations

Thus, GraphGONet furnishes its users with not only a diagnosis prediction but also a biological interpretation in the form of a collection of the GO terms most highly involved in the prediction and ranked by their contributions. The IBISC team’s work was published in Bioinformatics on 10 March 2022. Bioinformatics

Citation« We intend to include other ontologies, for example metabolic pathways, to enrich the biological explanations and address several uncertainties, » explains Blaise Hanczar, codirector of AI at the IBISC laboratory.

Beyond its clinical use, GraphGONet can also be employed as a research tool to discover novel biological mechanisms involved in disease.

The work of the IBISC lab contributes to the construction of a computational genomics sector at Genopole.

Reference

GraphGONet: a self-explaining neural network encapsulating the Gene Ontology graph for phenotype prediction on gene expression.

  • GraphGONet GraphGONet is freely available.

Watch a presentation by Blaise Hanczar recorded for the Hackathon D4GEN-Digital for Genomics 2022

(from the colloquium “Computational Genomics: Interpret and Act” – 21 November 2019)

Article posted on 5 April 2022

Share
Highlights

News


l’équipe « Dystrophies musculaires progressives » du laboratoire Généthon

Shining light on a key mechanism of Duchenne muscular dystrophy

A Genethon team has provided new insights on a complex genetic mechanism involved in mitochondrial dysfunction in Duchenne muscular dystrophy.

Discover
A trio of genome sites associated with arterial hypertension

A trio of genome sites associated with arterial hypertension

Researchers from the CNRGH and PARCC have identified three loci associated with an increased risk of developing primary hyperaldosteronism, a leading cause of arterial hypertension.

Discover
Genoscope - CNS - Genopole's laboratory

The story of the domestic donkey told by its genome

Genoscope participated in the sequencing of the DNA of 250 donkeys in a study revealing the domestication of this species highly contributive to human activities to this day.

Discover
Galaxy-SynBioCAD: accelerating the arrival of green chemistry

Galaxy-SynBioCAD: accelerating the arrival of green chemistry

Conceived by the Genomics Metabolics Unit, Galaxy-SynBioCAD accelerates biological design and engineering for the production of next generation chemical compounds.

Discover
Equipe Sysfate de l'UMR 8030 - projet T-Fitness

T-FITNESS: Toward empowering CAR-T therapies for solid tumors

The Genopole team SysFate is participating in the international project T-FITNESS. The project, selected by the European Innovation Council, aims to resolve the difficulty of T-cell exhaustion in CAR-T therapies for solid tumors.

Discover
Ynsect & Genoscope : Vers la sélection génomique des insectes d’élevage

Toward the genomic selection of farmed insects

France is historically a land of livestock farming. Cows for meat or milk, sheep, pigs, fowl of all sorts; France rears them all. And insects! With its genomic selection project for Tenebrio molitor beetles, the Genopole company Ÿnsect and its biocluster partner, the sequencing center Genoscope, are making France a pioneer in insect farming.

Discover
Couverture de la revue Cell Genomics - Le plancton

A feat in the study of planktonic life

A Genoscope research team was part of a pioneering study in environmental genomics. The researchers were able to at least partially reconstitute the genomes of close to 700 eukaryote species.

Discover
Logos Istem & Généthon

A two-drug combination to treat limb-girdle muscular dystrophies and cystic fibrosis

The I-Stem and Genethon laboratories have identified a promising drug combination in the setting of three genetic diseases sharing similar molecular mechanisms.

Discover
Christophe Lanneau - Research & Platforms Department Director

News from the human genome

The 1 April edition of Science announced the publication of the human genome with the previously-missing 8% now added to it. Comments from the Genopole Director of Research.

Discover
CNRGH - Consequences of phthalate exposure during pregnancy

Consequences of phthalate exposure during pregnancy

Jörg Tost and his team of the National Center of Human Genomics Research (CNRGH; CEA) were part of a large collaborative study aimed at determining the genome-wide correlation between phthalate exposure during pregnancy and methylation of placental DNA.

Discover
INtegrare / Généthon - Efficacité à long terme de la thérapie génique d’un déficit immunitaire

Long-term efficacy for an immunodeficiency gene therapy

A gene therapy conceived by Genethon has been shown to confer long-term efficacy against Wiskott-Aldrich syndrome, an immune deficiency disorder.

Discover
I-Stem, IPSEN & LMN recreate the human muscle-nerve system

A cellular model to recreate the human muscle-nerve system

Researchers from I-Stem, IPSEN and LMN have conceived a cellular muscle-nerve model to test the therapeutic potential of botulinum toxins in vitro.

Discover
Genoscope - CNS - Genopole's laboratory

Filling the gaps in the banana’s genome

Des chercheurs de Genoscope en collaboration avec une équipe du Cirad sont parvenus à reconstituer la séquence intégrale de chromosomes de bananier.

Discover
traitement des plaies diabétiques issu de peau et d’écailles de poissons

CERITD: Treating deep wounds with fish skin

CERITD and the South Île-de-France Medical Center are testing an innovative, natural fish-skin-based treatment for diabetic foot ulcers.

Discover
SYSFATE

Sysfate Team: A tool to digitize organs

Sysfate at Genoscope has combined image analysis and genomics to create MULTILAYER, a tool to digitize biological tissues and organs.

Discover
muscle fiber

Signs of myopathy detected before muscle formation

An I-Stem team has revealed very early embryonic molecular signs of Duchenne muscular dystrophy occurring upstream of muscle development itself

Discover
Neurons representation - Cells affected by CMT

Gene therapy for Charcot-Marie-Tooth disease makes headway

A gene therapy for Charcot-Marie-Tooth disease has been shown to be efficacious in an animal-model study cosigned by a research team created through Genopole support.

Discover
LAST - Makeup by Global Bioenergies

Global Bioenergies launches its makeup brand

Interview with Marc Delcourt, founder and CEO of Global Bioenergies, launches its makeup brand : LAST

Discover
NEB France celebrate 10 years @ Genopole

New England Biolabs France Celebrates 10 Years!

Its French affiliate arrived at Genopole in 2011 and to mark its 10th anniversary in France, the company invites you to participate in monthly activities to be held throughout 2021.

Discover
Visualization and quantification by MTBench technology of protein-protein interactions observed at Opera Phenix + in a cell line.

Seeing in high resolution at the Structural Biology Platform

With the support of Genopole & the University of Évry and to enrich its technological offer, the Structural Biology Platform has acquired the Opera Phenix Plus high content screening (HCS) system.

Discover
View all >
With the support from