En poursuivant votre navigation sur ce site, vous acceptez le dépôt de cookies dans votre navigateur. (En savoir plus)
Portail > Offres > Offre UMR5672-BENAUD-006 - Apprentissage automatique et optimisation pour déchiffrer la cinétique de réplication de l'ADN (H/F)

Machine learning and optimization to decipher DNA replication kinetics

This offer is available in the following languages:
Français - Anglais

Date Limite Candidature : vendredi 8 juillet 2022

Assurez-vous que votre profil candidat soit correctement renseigné avant de postuler. Les informations de votre profil complètent celles associées à chaque candidature. Afin d’augmenter votre visibilité sur notre Portail Emploi et ainsi permettre aux recruteurs de consulter votre profil candidat, vous avez la possibilité de déposer votre CV dans notre CVThèque en un clic !

General information

Reference : UMR5672-BENAUD-006
Workplace : LYON 07
Date of publication : Friday, June 17, 2022
Type of Contract : FTC Scientist
Contract Period : 12 months
Expected date of employment : 1 September 2022
Proportion of work : Full time
Remuneration : Monthly gross salary will range from 2690 et 4255 euros depending on experience.
Desired level of education : PhD
Experience required : 1 to 4 years

Missions

The project aims at reaching a rigorous, quantitative description of the DNA replication programme in yeast and human by exploiting novel high-throughput single-molecule data. Replication studies typically monitor the incorporation of non standard nucleotides. Here, the objectives are to follow this incorporation using nanopore sequencing to detect non-standard nucleotides and to extract from the incorporation profiles that reveal the bidirectional motion and collisions of the replication machineries, quantitative information about the DNA replication program (location, orientation and speed of DNA synthesis along chromosomes). This approach has the potential for high-throughput genomic profiling of DNA replication, allowing to precisely model this fundamental cellular process and to understand its links to chromosome organisation.

Activities

The successful researcher will join the Sisyph team at Laboratoire de Physique de l'ENS de Lyon (LPENSL, CNRS UMR5672, project supervisors: B. Audit, N. Pustelnik, P. Abry).

He/she will develop a research activity at the interface between information sciences and biology, investigating the usage of artificial intelligence for genomic data. He/she will pursue the following main objectives: (i) expanding our analysis pipelines based on machine learning technics (neural networks) for the emerging nanopore sequencing technology that extend the detection to non-standard nucleotides (DOI: 10.1186/s13059-020-02013-3), in particular exploring unsupervised learning approaches, (ii) develop signal processing tools (eg, using optimization strategies based on change-point detection, dictionary fitting or neural networks) to extract the underlying DNA replication patterns and (iii) integrate the new gathered information with other source of genomic information, focussing on explainable AI at this stage.

Skills

- The candidate should have have skills in some of the following areas: Signal and Image Processing, Data science, Optimization, Machine Learning
- Demonstrated interest for biology. Knowledge of DNA replication mechanisms will be appreciated.
- Willingness to work in an interdisciplinary context.

Work Context

The work of the selected researcher will integrate with the hosting team projects funded by Agence National de la Recherche (ANR NanoPoRep and hudror) aiming at a high-performance genomic profiling of DNA replication and .the reconciliation of disparate views on DNA replication origins (collaborative projects with the Eukaryotic Chromosome Replication team at Institut de Biologie de l'Ecole Normale Supérieure (IBENS, CNRS UMR8197, Inserm U1024, project supervisor and team leader: O. Hyrien)). It will also profit from the implication of the team in the CHIST-ERA project GraphNEx that aims at developing inherently explainable artificial inteligence.

The researcher will benefit from the rich and stimulating scientific environment of ENS de Lyon, including the access to the knowhow and computing resources of Pôle Scientifique de Modélisation Numérique de l'ENS de Lyon (PSMN).

Constraints and risks

The work will require 1-2 days working visits to IBENS in Paris.

Additional Information

Further inquiry should be send to Benjamin Audit (benjamin.audit@ens-lyon.fr).

We talk about it on Twitter!