Lucas Etourneau

Lucas Etourneau
Université Grenoble Alpes · Department of Applied Mathematics

Master of Engineering
I'm looking for collaborators on my PhD project. I work on multi-omic imputation of missing values in proteomics.

About

1
Publication
31
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
0
Citations
Introduction
I'm trying to develop missig value imputation algorithms on Mass-Spectrum proteomics. The aim is to leverages the available information at RNA level, to refine our imputation method at peptide level. We would like to develop an algorithm robust to MAR and MNAR case, as many missing values are due to low abundace peptides.
Skills and Expertise
Machine Learning
Image Processing
Classification
Neural Networks and Artificial Intelligence
Computer Vision
Supervised Learning
Feature Extraction
Advanced Machine Learning
Unsupervised Learning
Signal, Image and Video Processing

Publications

Publication (1)
Figure 3: Histogram of scores 's obtained with log diff of p-values...
Figure 5: FDP and power vs. target FDR for knockoff procedure with...
Unveiling the links between peptide identification and differential analysis FDR controls by means of a practical introduction to knockoff filters
Preprint
Full-text available
  • Aug 2021
In proteomic differential analysis, FDR control is often performed through a multiple test correction (i.e., the adjustment of the original p-values). In this protocol, we apply a recent and alternative method, based on so-called knockoff filters. It shares interesting conceptual similarities with the target-decoy competition procedure, classically...

Network