Julien Martinelli

Julien Martinelli

Postdoctoral researcher in Machine Learning

Inria - Statistics in System Biology and Translational Medicine

News

2 preprints currently under review!

Biography

I am a postdoctoral researcher at Inria Bordeaux, in the SISTM team. I work on the interplay between data-driven and mechanistic models, also known as Grey-box modeling, in a Bayesian framework, hopefully with concrete applications for clinical trial data analysis along the way. Before that, I was a postdoctoral researcher at Aalto University, in the Probabilistic Machine Learning group, working with Samuel Kaski, Vikas Garg and Markus Heinonen. There, I studied the integration of human feedback into machine learning algorithms, with an emphasis on de novo Drug Design applications.

And prior to that, I did my PhD jointly between Inria and Institut Curie, under the supervision of François Fages and Annabelle Ballesta. We developed methods at the boundary of Systems Biology and Machine Learning to infer mechanistic models from time series data. A major contribution of the manuscript was to apply such methods to investigate the impact of systemic regulators (e.g. temperature, nutrient exposure, hormones) on the cellular circadian clock, in an attempt to personalize Cancer Chronotherapies. The manuscript can be found here and the slides here.

Teaching

  • 2022-2023: Teaching Assistant • M. Sc. • Aalto University
  • 2019-2021: Teaching Assistant • 2nd year B. Sc. • Université de Paris
    • Real Analysis (42h)
    • Multivariate Functions (18h)
  • 2018-2019: Teaching Assistant • 1st year B. Sc. • Université de Paris
    • Mathematics and Calculus (60h)

Reviewing service

I have served as a reviewer for Machine Learning journals and conferences ( JMLR, PAMI, NeurIPS'23, ICML'23-24, ICLR'23-24) as well as for Computational Biology journals and conferences ( TCBB, CMSB'23, ECCB'20, CSBIO'19).

Miscellanous

For a few years now, I have been cultivating a passion for indoor bouldering, with a mild success thus far 🫠

Interests

  • Biological networks inference
  • Mechanistic Modeling
  • Bayesian Experimental Design
  • Human-In-The-Loop Machine Learning

Education

  • PhD in Computer Science, 2022

    Inria / Institut Curie / Ecole polytechnique

  • Master's Degree 2nd year - Random modelling, Finance and Data Science, 2018

    Université de Paris

  • Master's Degree 1st year - Applied Mathematics, 2017

    Université de Paris

Experience

 
 
 
 
 

Postdoctoral Researcher

Aalto University - Probabilistic Machine Learning Group

Feb 2022 – Present Espoo, Finland

Human-In-The-Loop Machine Learning - Application to de novo drug design

  • Bayesian Experimental Design
  • Bayesian Optimization, Gaussian Processes
  • Deep Generative Models
 
 
 
 
 

PhD Student

Inria EP Lifeware - Inserm U900 Syspharma - Ecole polytechnique

Oct 2018 – Feb 2022 Saclay / Saint-Cloud

On learning mechanistic models from time-series data with application to cancer chronotherapies

  • Learning ODE models of biological networks
  • Sparse regression
  • Mechanistic modeling of the circadian clock
  • PK-PD modeling
 
 
 
 
 

Intern

Inria EP Lifeware

Apr 2018 – Sep 2018 Saclay
Mechanistic model learning from time-series data
 
 
 
 
 

Intern

Université de Paris - Laboratoire MAP5

Jun 2017 – Aug 2017 Paris
Random matrix theory and applications to community detection in large graphs

Publications

Quickly discover relevant content by filtering publications.

Cost-aware learning of relevant contextual variables within Bayesian optimization

Multi-Fidelity Bayesian Optimization with Unreliable Information Sources

Reactmine, a search algorithm for inferring chemical reaction networks from time series data

Accelerating metabolic models evaluation with statistical metamodels - application to Salmonella infection models

A mathematical model of the circadian clock and drug pharmacology to optimize irinotecan administration timing in colorectal cancer

Contact