English
Network-guided feature selection in high-dimensional genomic data
Post-edited
Auteurs : Azencott, Chloé (Auteur de la conférence)
CIRM (Editeur )
62P10 - Applications of statistics to biology and medical sciences
92-08 - Computational methods
92B15 - General biostatistics, See also {62P10}
92C42 - Systems biology, networks
Ressources complémentaires :
https://github.com/chagaz
https://github.com/mahito-sugiyama/Multi-SConES
CIRM (Editeur )
Loading the player...
|
| GWAS statistical test selection stability network-guided GWAS regularization network regularization multitask |
Résumé :
Differences in disease predisposition or response to treatment can be explained in great part by genomic differences between individuals. This has given birth to precision medicine, where treatment is tailored to the genome of patients. This field depends on collecting considerable amounts of molecular data for large numbers of individuals, which is being enabled by thriving developments in genome sequencing and other high-throughput experimental technologies.
Unfortunately, we still lack effective methods to reliably detect, from this data, which of the genomic features determine a phenotype such as disease predisposition or response to treatment. One of the major issues is that the number of features that can be measured is large (easily reaching tens of millions) with respect to the number of samples for which they can be collected (more usually of the order of hundreds or thousands), posing both computational and statistical difficulties.
In my talk I will discuss how to use biological networks, which allow us to understand mutations in their genomic context, to address these issues. All the methods I will present share the common hypotheses that genomic regions that are involved in a given phenotype are more likely to be connected on a given biological network than not.
Mots-Clés : bioinformatique; data integration
Codes MSC : Unfortunately, we still lack effective methods to reliably detect, from this data, which of the genomic features determine a phenotype such as disease predisposition or response to treatment. One of the major issues is that the number of features that can be measured is large (easily reaching tens of millions) with respect to the number of samples for which they can be collected (more usually of the order of hundreds or thousands), posing both computational and statistical difficulties.
In my talk I will discuss how to use biological networks, which allow us to understand mutations in their genomic context, to address these issues. All the methods I will present share the common hypotheses that genomic regions that are involved in a given phenotype are more likely to be connected on a given biological network than not.
Mots-Clés : bioinformatique; data integration
62P10 - Applications of statistics to biology and medical sciences
92-08 - Computational methods
92B15 - General biostatistics, See also {62P10}
92C42 - Systems biology, networks
Ressources complémentaires :
https://github.com/chagaz
https://github.com/mahito-sugiyama/Multi-SConES
|
Informations sur la Vidéo
Réalisateur : Hennenfent, GuillaumeLangue : Anglais Date de Publication : 23/03/2020 Date de Captation : 05/03/2020 Sous Collection : Research talks Catégorie arXiv : Machine Learning ; Quantitative Biology Domaine(s) : Probabilités & Statistiques Format : MP4 (.mp4) - HD Durée : 01:27:51 Audience : Chercheurs Download : https://videos.cirm-math.fr/2020-03-05_Azencott.mp4 
|
Informations sur la Rencontre
Nom de la Rencontre : Thematic Month Week 5: Networks and Molecular Biology / Mois thématique Semaine 5 : Réseaux et biologie moléculaireOrganisateurs de la Rencontre : Baudot, Anais ; Hubert, Florence ; Mossé, Brigitte ; Rémy, Elisabeth ; Tichit, Laurent ; Vignes, Matthieu Dates : 02/03/2020 - 06/03/2020 Année de la rencontre : 2020 URL de la Rencontre : https://conferences.cirm-math.fr/2305.html
Données de citation
DOI : 10.24350/CIRM.V.19620603Citer cette vidéo: Azencott, Chloé (2020). Network-guided feature selection in high-dimensional genomic data. CIRM. Audiovisual resource. doi:10.24350/CIRM.V.19620603 URI : http://dx.doi.org/10.24350/CIRM.V.19620603 |
Voir Aussi
- [Multi angle] Part 2 - Dynamic logic models complement machine learning for personalized medicine / Auteur de la conférence Saez-Rodriguez, Julio.
- [Multi angle] Matrix factorisation techniques for data integration / Auteur de la conférence Lê Cao, Kim-Anh.
- [Multi angle] Cell processes in space and time - exemplified with yeast mating / Auteur de la conférence Klipp, Edda.
- [Multi angle] Network approaches for personalized medicine / Auteur de la conférence Martinez-Rodriguez, Maria.
- [Multi angle] Learning interpretable networks from multivariate information in biological and clinical data / Auteur de la conférence Isambert, Hervé.
- [Multi angle] From data to biological processes: interactions, networks and analyses, to understand cellular functions / Auteur de la conférence Brun, Christine.
- [Multi angle] Part 1 - Networks of prior knowledge as frames to understand complex biological data / Auteur de la conférence Saez-Rodriguez, Julio.
Bibliographie
- AZENCOTT, Chloé-Agathe, GRIMM, Dominik, SUGIYAMA, Mahito, et al. Efficient network-guided multi-locus association mapping with graph cuts. Bioinformatics, 2013, vol. 29, no 13, p. i171-i179. - https://doi.org/10.1093/bioinformatics/btt238
- SUGIYAMA, Mahito, AZENCOTT, Chloé-Agathe, GRIMM, Dominik, et al. Multi-task feature selection on multiple networks via maximum flows. In : Proceedings of the 2014 SIAM International Conference on Data Mining. Society for Industrial and Applied Mathematics, 2014. p. 199-207. - https://doi.org/10.1137/1.9781611973440.23
Imagette Video
