Team members

Scientific team

Yves Brun, Director

Professor, Université de Montréal, Microbiologie, infectiologie et immunologie
Canada 150 Research Chair in Bacterial Cell Biology
https://brunlab.com

Prof. Brun is known for developing transformative methods in bacterial cell biology. His pioneering research on bacterial growth, adhesion, and biofilm formation has been featured in high-impact scientific journals. He has managed many large research projects, infrastructure, and multidisciplinary collaborations and will oversee the management of this project with a focus on microbiology and microscopy. He will help develop and implement the screening platforms to identify targets and hits and determine the mechanism of action of identified hit compounds.

Jacques Corbeil, Co-Director

Professor, Université Laval, Molecular Medicine
Canada Research Chair Tier 1 in Medical Genomics
https://corbeillab.genome.ulaval.ca

Prof. Corbeil is a seasoned entrepreneur and professor, bridging ‘omics research, machine learning and translational medicine. His research tackles antimicrobial resistance and host-pathogen interactions, and he leads initiatives on COVID-19 and antimicrobial resistance nationally and globally. In this project, he will generate high-throughput metabolomics data and assess compound toxicity using organ-on-a-chip platforms. He will ensure tight integration between data science and wet lab teams and will oversee the industry partnerships.

Yoshua Bengio

Professor, Université de Montréal, Departement d’Informatique et Recherche Opérationnelle
Scientific director, Mila and IVADO
https://yoshuabengio.org

Prof. Bengio is recognized as a world expert in AI and deep learning. Concerned with the ethical and social impact of AI, he contributed to the Montreal Declaration for the Responsible Development of AI and with its involvement in promoting responsible regulation. His research encompasses the development of new concepts and methodology in machine learning (ML) and their applications to social good, foremost drug discovery. In this project, he will develop graph neural network and active learning models for antimicrobial prediction in silico, and for scaffold and building block selection for the DNA-encoded libraries.

Dominique Beaini

Research unit lead, Valence Labs, Deep learning research
Adjunct professor, Université de Montréal, Department of Informatics and Operational Research
https://mila.quebec/en/person/dominique-beaini/

Dr. Beaini leads research in machine learning applied to drug discovery. He is known for his contribution to geometric deep learning, especially in the case of graph neural networks expressivity and graph transformers. His goal is to push machine learning towards a better understanding of molecules and their interactions with human biology. At Valence labs, he is leading an effort to build ultra-large graph neural networks that are pre-trained on thousands of chemical and biological assays, which in this project will be adapted for antimicrobial prediction.

André Charette

Professor, Université de Montréal, Chemistry
https://charettelab.ca

Prof. Charette has extensive experience in developing synthetic methods under batch and continuous flow conditions to prepare small molecules. In this project, he will develop continuous flow synthesis routes for building blocks, important molecular scaffolds, and reagents identified by the team as important for antimicrobial drug discovery. Real-time monitoring and fine tuning of the flow chemistry system by AI-based analytics will improve the efficiency and cost-effectiveness of synthesis.

Audrey Durand

Associate professor, Université Laval, Informatique et génie logiciel; Génie électrique et génie informatique
Canada Institute for Advanced Research AI Chair
https://audur2.ift.ulaval.ca

Prof. Durand works in reinforcement learning and bandit algorithms, both theoretical and applied. She also uses machine learning approaches to study health-related data. Her work in machine learning has been published in prominent conferences and journals. She has been involved with Women in Machine Learning. In this project, she will contribute active learning strategies to guide building block selection for the DNA-encoded libraries.

Steven Laplante

Professor, INRS, Centre Armand Frappier Sante Biotechnologie
https://inrs.ca/en/research/professors/steven-laplante/

Prof. Laplante is an expert in biophysics-based drug discovery. In 2014, he founded the contract research company NMX, which discovers leads for many drug discovery programs for pharma, biotech, research institutes and academia. In his academic career, he has worked on discovering novel microbial agents against pathogens, and leads against targets in cancer, infectious diseases and neurobiology. His research focuses on designing biophysical strategies for discovering drug leads that target a variety of diseases. In this project, he will contribute to the optimization of validated hits using biophysical techniques.

Flavie Lavoie-Cardinal

Associate Professor, Université Laval, Psychiatry and Neuroscience
Canada Research Chair Tier 2 in Intelligent Nanoscopy of Cellular
https://www.flc-lab.com

Prof. Lavoie-Cardinal’s research focuses on the development of machine-learning-assisted super-resolution microscopy techniques applied to living cells. Pursuing quantitative optical microscopy using machine and deep learning, her approaches have pushed forward functional imaging of synaptic plasticity. In this project, she will help develop supervised and unsupervised quantitative microscopy image analysis approaches and AI-assisted microscopy acquisition methods.

Anne Marinier

Director of Medicinal Chemistry & Drug Discovery Unit, Université de Montréal, Institute of Research in Immunology and Cancer
https://www.iric.ca/en/research/research-units/medicinal-chemistry

Prof. Marinier has expertise in medicinal chemistry and strong industry expertise in drug discovery, including with antimicrobials. She has a background in drug discovery in industry has co- founded 2 companies, ExCellThera and RejuvenRx (RRX), and is the CEO of RRX. In this project, she will contribute to the synthesis of DNA-encoded libraries, the selection of hits and the synthesis and optimization of lead compounds. She will also oversee EDI in the project, together with Prof. Nguyen (below).

Dao Nguyen

Associate professor, McGill University, Medicine
Director, McGill Antimicrobial Resistance Center
https://www.mcgill.ca/microimm/dao-nguyen

Prof. Nguyen’s research focuses on Pseudomonas biology, the pathogenesis of cystic fibrosis lung infections, the mechanisms of antibiotic tolerance, and host-pathogen interactions. In this project, she will coordinate the selection of bacterial strains for screening, together with her clinician colleagues, and transfer knowledge to the clinic. She will also help develop high-throughput assays and pre-clinical studies of lead compounds in cellular and animal models. She will also oversee EDI in the project alongside Prof. Marinier (above).

Jian Tang

Associate Professor, HEC Montréal, Department of Decision Science
Canada Institute for Advanced Research AI Chair
https://jian-tang.com

Prof. Tang has expertise in geometric deep learning, graph neural nets, knowledge graphs, generative models and their applications to molecular modeling. His pioneering work on graph representation learning is highly cited, with a tangible impact on drug discovery. In this project, he will develop new approaches for peptide design based on geometric deep learning and deep generative models, and contribute to methods for optimizing synthetic methodologies for continuous flow synthesis.

Pierre Thibault

Professor, Université de Montréal, Chemistry
Director, IRIC Proteomics facility
https://capa.iric.ca/?_LOCALE_=fr

Prof. Thibault is a renowned bioanalytical chemist specializing in mass spectrometry and proteomics who has served as a principal investigator in academic, government and industry laboratories. His research program in mass spectrometry-based proteomics provides a deeper understanding of molecular mechanisms and post-translational modifications, which regulate protein functions involved in e.g. immunity and cell signalling. Here, he will contribute infrastructure and expertise in proteomics and identify protein targets of lead compounds.

Michael Tyers

Professor, Department of Molecular Genetics, University of Toronto
Senior Scientist, The Hospital for Sick Children, Molecular Medicine Canada
https://www.sickkids.ca/en/staff/t/mike-tyers/

Prof. Tyers’ research efforts focus on generating novel antimicrobial agents against pathogens including M. tuberculosis, E. coli, S. aureus, P. falciparum, and SARS-CoV-2 using synthetic biology methods. He has developed CRISPR-based methods to uncover small molecule mechanism-of-action for hundreds of drugs and bioactive compounds in human cells. In this project, he will contribute infrastructure to generate, screen and analyze large peptide libraries designed by AI as well as cell- and target-based assays to validate antimicrobial hits.

Teodor Veres

Co-director, Centre for Research and Applications in Fluidic Technologies
Professor, University of Toronto, Mechanical Engineering
https://craftmicrofluidics.ca

Prof. Veres leads the development of bio-microsystems for integrated molecular analytics applied to medical, food, and environmental safety applications. Towards this, he is the co-founder and co-director of a collaborative centre for developing lab-on-chip systems for in vitro diagnostics, chip-based living systems, and precision medicine. In this project, he will design and fabricate new microfluidics devices for high-throughput screening using cell and organ-on-chip systems to test compound toxicity.

David Wishart

Professor, University of Alberta, Biological Sciences and Computing Sciences
https://www.wishartlab.com

Prof. Wishart has developed a number of widely-used techniques based on NMR spectroscopy, mass spectrometry, liquid chromatography and gas chromatography to characterize the structures of small and large molecules. He has also led the “Human Metabolome Project”, which catalogs all the known chemicals in human tissues and biofluids. His lab uses machine learning and artificial intelligence techniques to help create useful chemistry databases and software tools to help characterize and identify metabolites, drugs, pesticides and natural products. Here, he will contribute method development for the metabolomic toxicity profiling of compounds.