Portrait of Jacques Corbeil

Jacques Corbeil

Affiliate Member
Full Professor, Université Laval
General Partner et CSO, Linearis Venture and Labs
Research Topics
AI and Healthcare
Applied Machine Learning
Computational Biology
Website
Google Scholar
LinkedIn

Biography

Dr. Jacques Corbeil focuses on using the latest techniques in bioinformatics and machine learning to assist diagnostic, prognostic and response to treatment. Modern genomics and metabolomics techniques generate a deluge of data that needs to be interpreted using novel informatics approaches. Dr. Corbeil uses state-of-the-art instrumentation and methodologies to facilitate the interpretation of complex data, including high throughput mass spectrometry, in particular, metabolomics and next-gen sequencing.

Dr. Corbeil’s research includes investigating how infectious microorganisms interact with their host, the effects of antibiotics on our microbial flora and the environment, and exploring how to design small molecules and drugs to interfere with specific microbial functions and cancer progression. Operating at the interface of machine learning and omics sciences, he specializes in big data analytics applied to infectious diseases and cancer and he has expertise in the integration of omics data. Dr. Corbeil collaborates with many industries to ameliorate their process and implement artificial intelligence strategies. Since 2004, Dr. Corbeil holds the Canada Research Chair in Medical Genomics (Tier 1).

Publications

Sample Boosting Algorithm (SamBA) - An interpretable greedy ensemble classifier based on local expertise for fat data
Baptiste Bauvin
Cécile Capponi
Florence Clerc
Pascal Germain
Sokol Koço
Jacques Corbeil
2023-01-01
UAI (published)
proceedings.mlr.press
openreview.net
RandomSCM: interpretable ensembles of sparse classifiers tailored for omics data
Thibaud Godon
Pier-Luc Plante
Baptiste Bauvin
Élina Francovic-Fontaine
Alexandre Drouin
Jacques Corbeil
Background: Understanding the relationship between the Omics and the phenotype is a central problem in precision medicine. The high dimensio… (see more)nality of metabolomics data challenges learning algorithms in terms of scalability and generalization. Most learning algorithms do not produce interpretable models -- Method: We propose an ensemble learning algorithm based on conjunctions or disjunctions of decision rules. -- Results : Applications on metabolomics data shows that it produces models that achieves high predictive performances. The interpretability of the models makes them useful for biomarker discovery and patterns discovery in high dimensional data.
2022-08-11
ArXiv (preprint)
doi.org
arxiv.org