Homepage of Céline Brouard
Permanent researcher (CRCN) in the MIAT (Applied Mathematics and Computer Science) unit, INRAE Toulouse
Research interests
Machine learning, Kernel methods, Optimization
Bioinformatics, Metabolite identification, Biological networks
Contact
Email: celine dot brouard at inrae dot fr
Address: MIAT, INRAE Toulouse, BP 52627, 31326 CASTANET cedex FRANCE
Publications
- L. Pomiès, C. Brouard, H. Duruflé, E. Maigné, C. Carré, L. Gody, F. Trösser, G. Katsirelos, B. Mangin, N. B. Langlade and S. de Givry: Gene regulatory network inference methodology for genomic and transcriptomic data acquired in genetically related heterozygote individuals. Bioinformatics, btac445, 2022. [Link to publisher | Code]
- L. Brogat-Motte, R. Flamary, C. Brouard, J. Rousu and F. d'Alché-Buc: Learning to predict graphs with fused Gromov-Wasserstein barycenters. In International Conference on Machine Learning (ICML) , p. 2321-2335, 2022. [PDF | Code]
- C. Brouard, J. Mariette, R. Flamary and N. Vialaneix: Feature selection for kernel methods in systems biology. NAR Genomics and Bioinformatics, 4(1), Iqac014, 2022. [ Link to publisher | Code]
- C. Brouard, S. de Givry and T. Schiex: Pushing data into CP models using Graphical Model Learning and Solving. In Proceedings of CP 2020, 2020. [ Link to publisher | PDF | Code | Video ]
- C. Penouilh-Suzette et al.: RNA expression dataset of 384 sunflower hybrids in field condition. OCL, 27(36), 2020. [ PDF | Data ]
- C. Brouard, A. Bassé, F. d'Alché-Buc and J. Rousu: Improved small molecule identification through learning combinations of kernel regression models. Metabolites, 9(8):160, 2019. [ Link to publisher | Code ]
- E. Bach, S. Szedmak, C. Brouard, S. Böcker and J. Rousu: Liquid-chromatography retention order prediction for metabolite identification. ECCB, Bioinformatics, 34(17):i875-i883, 2018. [ PDF | Code ]
- E. L. Schymanski, C. Ruttkies, M. Krauss, C. Brouard, T. Kind, K. Dührkop, F. Allen, A. Vaniya, D. Verdegem, S. Böcker, J. Rousu, H. Shen, H. Tsugawa, T. Sajed, O. Fiehn, B. Ghesquière and S. Neumann: Critical assessment of small molecule identification 2016: automated methods. Journal of Cheminformatics, 9:22, 2017. [ PDF | Supplements ]
- C. Brouard, E. Bach, S. Böcker and J. Rousu: Magnitude-preserving ranking for structured outputs. In Proceeding of the 9th Asian Conference on Machine learning (ACML), PMLR 77:407-422, 2017. [ PDF | Supplements ]
- C. Brouard, M. Szafranski and F. d'Alché-Buc: Input Output Kernel Regression: supervised and semi-supervised structured output prediction with operator-valued kernels. Journal of Machine Learning Research, 17(176):1-48, 2016. [ PDF ]
- C. Brouard, H. Shen, K. Dührkop, F. d'Alché-Buc, S. Böcker and J. Rousu: Fast metabolite identification with Input Output Kernel Regression. ISMB, Bioinformatics, 32(12):i28-i36, 2016. [ PDF | Code | Data ]
- J. Kludas, M. Arvas, S. Castillo, T. Pakula, M. Oja, C. Brouard, J. Jäntti, M. Penttilä and J. Rousu: Machine learning of protein interactions in fungal secretory pathways. PLoS ONE, 11(7):1-20, 2016. [ PDF ]
- H. Shen, S. Szedmak, C. Brouard and J. Rousu: Soft kernel target alignment for two-stage multiple kernel learning. In Proceedings of the 19th International Conference on Discovery Science (DS 2016), Springer International Publishing, p. 427-441, 2016.
- C. Brouard, C. Vrain, J. Dubois, D. Castel, M-A. Debily and F. d'Alché-Buc: Learning a Markov Logic Network for supervised gene regulatory network inference. BMC Bioinformatics, 14:273, 2013. [ PDF ]
- C. Brouard, F. d'Alché-Buc and M. Szafranski: Semi-supervised Penalized Output Kernel Regression for Link Prediction. In Proceedings of the 28th International Conference on Machine Learning (ICML), p. 593-600, 2011. [ PDF ]
Theses
- PhD thesis (in french): Inférence de réseaux d'interaction protéine-protéine par apprentissage statistique [ PDF ]
Students
PhD students
- Aurélie Mercardié (2022/...): Intégration de données omiques de la peau issues d'expériences multi-groupes. PhD co-supervised with Nathalie Vialaneix (MIAT, INRAE).
- Luc Brogat-Motte (2019/2022): Apprentissage de représentations de sortie et approches surrogées pour la prédiction d'objets structurés. PhD co-supervised with Florence d'Alché-Buc (Telecom Paris), Juho Rousu (Aalto university) and Alessandro Rudi (INRIA).
Interns
- Léa Grima (2022): Network inference on Bacillus subtilis expression data. Co-supervised with Nathalie Vialaneix, Anne Goelzer, Simon de Givry et Elise Maigné (MIAT, INRAE).
- Guilhem Huau (2021): Réseaux de neurones pour graphe pour la prédiction de phénotypes. Co-supervised with Nathalie Vialaneix (MIAT, INRAE).
- Tamim El Ahmad (2020): Learning deep hybrid kernel networks. Co-supervised with Florence d'Alché-Buc (Telecom Paris).
- Luc Brogat-Motte (2019): Learning output embedding in zero-shot learning and structured output prediction. Co-supervised with Florence d'Alché-Buc (Telecom Paris) and Juho Rousu (Aalto university).
- Antoine Bassé (2018): Learning output representation in the metabolite identification problem. Co-supervised with Florence d'Alché-Buc (Telecom Paris) and Juho Rousu (Aalto university).
- Fabio Colella (2018): Learning dependency structure between molecular properties. Co-supervised with Juho Rousu (Aalto university).
- Eric Bach (2015/2016): Metabolite identification using magnitude-preserving Input Output Kernel Regression. Co-supervised with Juho Rousu (Aalto university).
Resume
Past positions
2014–2018: Postdoc
Aalto University, Espoo (Finland)
KEPACO (Kernel Methods, Pattern Analysis and Computational Metabolomics) research group
Structured output prediction for metabolite identification from tandem mass spectra.
Education
2013: PhD
Université d'Evry (France)
Advisors: Florence d'Alché-Buc and Aleksander Edelman
Inference of protein-protein interaction networks using machine learning
2009: MSc in Mathematics and Computer Science for Integrative Biology
Université d'Evry (France)
2008: Master of Engineering
Télécom Bretagne (France)
Specialization: Computer Science and Biomedical