Internship mathematical modeling and machine learning for metabolic plasticity of melanoma
Stage · Stage M2 · 6 mois Bac+4 Laboratory of Pathogen Host Interactions · Montpellier (France) gratification
Date de prise de poste : 1 janvier 2023
network models, differential equations models, single cell data, machine learning, hierarchical modeling, oncology
Internship: Mechanistic models of plasticity in melanoma submitted to targeted treatment
Start and duration: January to March 2023 for at least 4 months.
Location: Computational Systems Biology team, LPHI, University of Montpellier, Montpellier.
Candidates: M1 or M2 students / and or engineering students with excellent background in computer science or mathematics and a taste for interdisciplinary research. The intern will receive a salary (gratification) at the standard rate used by French public research institutions.
Context: This internship is associated to two projects of our team: INSERM/ITMO cancer Malmo (collaboration with IRCM Montpellier and Brain Institute Paris, teams of Dr. Laurent Le Cam, and Prof. Daniel Racoceanu), CEFIPRA (collaboration with NCBS Bangalore, team of Prof. Upinder Bhalla). We are also looking for new phD students on this topics or related, so the internship could continue to the phD.
Summary: The most frequent mutations in melanoma affect the BRAF oncogene, a protein kinase of the MAPK signaling pathway. Therapies targeting both BRAF and MEK are effective for only 50% of patients and, almost systematically, generate drug resistance. Genetic and non-genetic mechanisms associated with the strong heterogeneity and plasticity of melanoma cells have been suggested to favor drug resistance but are still poorly understood. In this internship we will use changes of the transcriptional program of tumors (bulk and single cell RNA-seq data) submitted to treatment to build mechanistic models of tumor heterogeneity and plasticity.
Our goal is to characterize pathways that contribute to resistance to BRAF and MEK inhibitors of melanoma and build mechanistic models that are consistent with the available data. Current models are either phenomenological  or reductionist by considering either signaling, or metabolic pathways, without the interaction between these pathways. Our model will integrate the interaction between signaling and metabolism.
In order to deal with the heterogeneity of data we will use hierarchical learning strategies . Models of different types (from qualitative networks to quantitative differential equations models) will be placed in a hierarchy and connected one to another by mapping of components and parameters. The machine learning process will exploit the hierarchical relations between models, for instance simpler models parameters will constrain learning of more complex models.
The intern will extract the data from public databases, will analyse the changes of transcription programs induced by treatment using data dimensionality reduction methods, and will build and train with data the hierarchical models needed for the project.
Keywords: network models, differential equations models, single cell data, machine learning, hierarchical modeling, oncology
1. Hodgkinson, D Trucu, M Lacroix, L Le Cam, O Radulescu. Computational Model of Heterogeneity in Melanoma : Designing Therapies and Predicting Outcomes. Frontiers in Oncology, 12 (2022).
2. Anandalingam and T.L.Friesz. Hierarchical optimization: An introduction. Annals of Operations Research 34, 1-11 (1992).
Procédure : Send an email to ovidiu.radulescu@umontpellier including CV, motivation letter, last year(s) transcripts, name + emails of persons that could recommend you
Date limite : 17 décembre 2023
Offre publiée le 4 novembre 2022, affichage jusqu'au 17 décembre 2023