Nicolas Gambardella

Come work with us on #AI strategies for predicting the structure of small metabolites implicated in metabolic and #cardiovascular diseases from mass spectrometry.

Research engineer position supervised by Francesc Puig-Castellvi in the group of @MarcEDumas
and myself.
www.sfbi.fr/emplois/offr...

Happy birthday MWC This month marks the 60th anniversary of the Monod-Wyman-Changeux (MWC) model, which provides an explanation for one of the fundamental mechanism in molecular biology, cooperativity. All biomolecular ...

This month marks the 60th anniversary of the Monod-Wyman-Changeux (MWC) model, which provides an explanation for one of the fundamental mechanism in molecular biology, cooperativity.
www.linkedin.com/pulse/happy-...
#allostery

#Interdisciplinary PhD at Egid: develop #AI models to evaluate #cardiac (from ECG), #epigenetic (from DNAm), and #metabolomic (from UHPLC-HRMS) ages. Colab between Marc Dumas and @nicg69.bsky.social in Philippe Froguel’s research unit. Contact us for more info. tinyurl.com/AIECGmet

One of the most illustrating picture of #lockdown efficiency in limiting #covid impact on the healthcare system (in France). Now, try to imagine the first 3 curves with no lockdown by looking at the 4th.

Transformers without Normalization Normalization layers are ubiquitous in modern neural networks and have long been considered essential. This work demonstrates that Transformers without normalization can achieve the same or better per...

Interesting: one can train deep nets without #normalization layers by replacing them with a parameterized tanh()
arxiv.org/abs/2503.10622
tanh() are my favourite #activation function
#deeplearning #artificialintelligence

enhanced flux potential analysis (eFPA) predicts metabolic reaction fluxes from enzyme expression data ➡️ www.embopress.org/doi/full/10....

Ecole doctorale Biologie Santé Ecole doctorale

Reminder: PhD thesis, European genomics institute for diabetes: Graph Neural Networks linking #pathways and #ontologies, trained with #omics data, to understand and predict #cardiometabolic disorders. More tinyurl.com/GNNEgid #deeplearning #diabetes #obesity
Contact me for an initial application.

Ecole doctorale Biologie Santé Ecole doctorale

PhD from Sept 2025: Graph Neural Networks linking #pathways and #ontologies, trained using #genomic and functional genomic data to understand #cardiometabolic disorders . More at tinyurl.com/GNNEgid
#deeplearning #diabetes #obesity