Mots-Clés

bioinformatics chemoinformatics machine learning

Description

Working environment

The Cancer Research Center of Marseille (CRCM) is the basic science and translational research unit of the private cancer hospital Institut Paoli Calmettes (IPC). The CRCM is also affiliated to INSERM, CNRS and Aix-Marseille University. The 400+ researchers working at the CRCM form a strongly multi-disciplinary research environment (https://www.crcm-marseille.fr/).

Project

The application of Machine Learning (ML) to large-scale virtual screening of small molecules against cancer cell lines exploiting pharmaco-omic datasets. The resulting models should be able to predict the potency and/or synergy of molecules, especially on those cell lines for which little screening data is available, to be used in innovative applications. The project is led by Dr Ballester at the CRCM, with collaborators in Montpellier (France). These are some relevant papers from this consortium:

• https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0061318
• https://www.oncotarget.com/article/20923/text/
• https://www.frontiersin.org/articles/10.3389/fchem.2019.00509/full
• https://www.jci.org/articles/view/131517
• https://www.embopress.org/doi/full/10.15252/embr.201846589

Selection criteria -Essential

• A PhD awarded in an area directly relevant to the project.
• Expertise in the application of machine learning algorithms to scientific problems.
• An excellent first and/or master degree, including their research projects, with a major focus on computational analysis of experimental data.
• Skilled in the implementation of R or Python scripts for scientific data analysis.
• Ability to communicate effectively in English, both orally and in writing.
• First-author publications in international journals.

Selection criteria - Desirable

• A track record of publications relevant to this project will be a strong advantage.
• Research projects in the application of supervised learning to solve real-world problems in the context of biomedical research, especially virtual screening.
• Prior use of high-performance computing to train machine learning algorithms.
• Working knowledge of open-source chemical informatics toolkits (e.g. RDKit or OpenBabel) and medicinal chemistry databases (e.g. ChEMBL, PubChem and ZINC).
• Prior experience in applying machine learning algorithms to drug design, e.g. QSAR.
• Familiarity with cancer pharmacogenomics databases (e.g. GDSC, CCLE or CTRP).
• Hands-on experience in the design and implementation of relational databases as well as in web programming to implement selected models as webservers.

What we offer

The successful candidate will receive a gross monthly salary of €2,620 to €3,615 gross monthly (depending on experience) for 3 years. This is an exciting opportunity for a bright and motivating scientist to work on a timely and exciting data science problem of therapeutic importance. Selected predictions made by the developed methods will be evaluated in vitro by our collaborators, thus the postdoc will be part of the resulting patents. The postdoc will join the Ballester team at the CRCM, which provides an international and stimulating research environment. The team is currently composed by 3 postdocs and 5 PhD students, working on the application of ML to drug design and precision oncology problems. In terms of quality of life, the CRCM is located in Marseille, thus the student will enjoy living in an exciting multi-cultural city right by the French Mediterranean coast (https://www.marseille.fr/decouvrir-marseille/).

How to apply

Candidates must send an email with their CV, grades for each held university degree and a covering letter (maximum two pages) to pedro.ballester@inserm.fr with the subject line “Postdoc in ML for PDD”. This letter should explain how they meet the essential selection criteria, which desirable selection criteria are also met and how this position would fit in their future career plans. Please also state the names and emails of three scientists involved in assessing their academic performance, who are willing to provide a reference.