I am seeking to apply my knowledge in computer science and statistics to understand real world data. I have interdisciplinary background spanning complex systems, Big Data, machine learning, biostatistics and genomics.
I have completed a PhD in which I applied clustering and PCA to epigenomics data and discovered new insights on the coupling between replication and epigenetics.
I worked at Dataiku, a dynamic start up in which I was actively engaged to help their clients to build their Big Data strategy and draw value from their data.
I studied the human microbiota during two years at MetaGenoPolis (MGP), an innovative research center. We aim at improving human health by developing strategies (eg. nutritional, therapeutical, preventive…) to restore dysbiosed microbiota with our industrial and academical partners.
I currently work in the statistical genetics group at the Pasteur Institut where I apply my software development and data science skills to quantify the impact of the human genome variation on diverse health parameters. More specifically, I am implicated in the JASS project (http://jass.pasteur.fr/index.html) that aim at analysing jointly numerous GWAS datasets. By doing so, we aim at increasing statistical power and to understand the molecular pathways underlying pleotropy.