Bioinformatician Position in the development of Machine Learning for AI-driven Anticancer Drug Discovery(M/F)

Job Description

Missions

We are looking for a motivated AI engineer / bioinformatician to join the AI for Genome Interpretation (AI4GI) group at the Institute of Molecular Genetics of Montpellier (IGMM, CNRS, Montpellier) for an initial 13 month engineer contract, with the possibility of renewal for 3 more years.
The project is a collaboration between the AI4GI group (Dr. Daniele Raimondi) and Dr. Michael Hahne group, at the interface of bioinformatics, machine learning, chemoinformatics, artificial intelligence and cancer biology.
This interdisciplinary project combines the expertise of the AI4GI laboratory in machine learning, bioinformatics and drug-response prediction with the expertise of the Hahne laboratory in experimental tumor biology and high-content phenotypic drug screening.
The overall goal is to develop a machine learning framework capable of predicting the response of treatment-resistant Consensus Molecular Subtype 4 (CMS4) colorectal cancers to small molecules and to use this model for large-scale virtual screening of the 78 billion compounds available in the Enamine REAL chemical library.
The project will integrate multiple sources of information, including:
● pharmacogenomic datasets (GDSC, DepMap, CCLE and related resources);
● molecular characterization of colorectal cancer cell lines;
● chemical representations of small molecules;
● experimental phenotypic measurements including cell proliferation, morphology, metabolic activity, cell cycle progression and cell death.
Using Active Learning, the computational model will continuously identify the most informative compounds to validate experimentally, allowing efficient exploration of an otherwise intractable chemical space. The long-term objective is to establish a general AI-assisted drug discovery framework that can later be extended to other difficult-to-treat cancer types.

Activity

The engineer will :
● Become familiar with the current literature on drug-response prediction, virtual screening, chemoinformatics and Active Learning.
● Explore and integrate large pharmacogenomic datasets (GDSC, CCLE, DepMap, CTRP and related resources).
● Develop machine learning and deep learning models for predicting drug response in colorectal cancer.
● Develop molecular representations for chemical compounds using modern chemoinformatics approaches (molecular fingerprints, graph neural networks, molecular embeddings, etc.).
● Implement Active Learning strategies to prioritize compounds for experimental validation.
● Perform virtual screening of ultra-large chemical libraries, including the Enamine REAL collection.
● Benchmark newly developed methods against state-of-the-art approaches.
● Collaborate closely with experimental biologists to integrate newly generated phenotypic data into the computational models.
● Contribute to scientific publications and open-source software developed within the project.

Your Profil

Skills

We are looking for a motivated and curious candidate with a background in bioinformatics, chemoinformatics and machine learning, ideally applied to drug discovery.
Drug-response prediction is a highly interdisciplinary and rapidly evolving field. The successful candidate is therefore expected to:
● enjoy learning new computational and biological concepts;
● be comfortable working at the interface between computer science and biology;
● enjoy solving challenging methodological problems;
● work both independently and collaboratively within an interdisciplinary team.
The ideal candidate has a background in Bioinformatics, Chemoinformatics, Computer Science, Machine Learning, Computational Biology, Data Science, Computational Chemistry, or a related discipline, together with:
● excellent Python programming skills;
● Chemoinformatics or bioinformatics background
● strong understanding of the mathematics behind machine learning and deep learning;
● good knowledge of linear algebra, optimization and statistical learning;
● familiarity with scientific computing (PyTorch, NumPy, scikit-learn, pandas);
● familiarity with GNU/Linux environments;
● strong problem-solving skills.
The project will primarily involve the development of novel machine learning methods using PyTorch.
At least B2 level English is required.
Skills required
We are looking for someone with:
● Strong background in machine learning, bioinformatics, chemoinformatics.
● Solid Python programming skills and experience with scientific computing libraries (PyTorch, NumPy, scikit-learn, pandas).
● Familiarity with GNU/Linux.
● Good software engineering and problem-solving skills.
● Good communication and teamwork skills.
The following are considered strong advantages:
● Experience in bioinformatics or computational biology.
● Experience with pharmacogenomic datasets.
● Experience in chemoinformatics (RDKit, molecular fingerprints, graph neural networks, molecular representations).
● Knowledge of drug-response prediction or virtual screening.
● Experience with Active Learning, uncertainty estimation or Bayesian optimization.
● Familiarity with high-performance computing or GPU programming.

Your Work Environment

The position is based at the Institute of Molecular Genetics of Montpellier (IGMM UMR5535, CNRS), in a highly international and interdisciplinary research environment. Montpellier is a dynamic Mediterranean city with an exceptional environment, culture, and quality of life. It is home to numerous high-quality research institutes and the University of Montpellier, with a vibrant population of 70,000 students and one of the world's oldest medical schools.
The Lab: The work will be carried out in the AI for Genome Interpretation (AI4GI) group, led by Dr. Daniele Raimondi. The group focuses on the development of advanced artificial intelligence and machine learning methods for genome interpretation, with a particular emphasis on modeling the relationship between genetic variation and phenotypic outcomes.

Colorectal cancer (CRC) is the second leading cause of cancer-related deaths in Europe, with treatment-resistant subtypes that still lack effective therapeutic options. Drug discovery remains slow and expensive, while the number of potentially drug-like molecules makes exhaustive experimental screening impossible.
Recent advances in machine learning and the availability of large pharmacogenomic datasets have made it possible to computationally predict drug responses and perform virtual screening before experimental validation. However, current approaches remain limited by incomplete biological readouts and by the difficulty of efficiently exploring enormous chemical spaces.
This project aims to develop a new generation of AI-driven drug discovery methods by combining machine learning, chemoinformatics and experimental cancer biology within an Active Learning framework. The computational model will iteratively guide biological experiments, while experimental results will continuously improve the model, creating an experiment-in-the-loop drug discovery pipeline.
If you are interested in developing novel AI methods for drug discovery, working at the intersection of machine learning, chemoinformatics and cancer biology, and contributing to the discovery of new therapies for difficult-to-treat colorectal cancers, we would be delighted to hear from you.

Compensation and benefits

Compensation

From 2521€ gross monthly salary, depending of experience

Annual leave and RTT

44 jours

Remote Working practice and compensation

Pratique et indemnisation du TT

Transport

Prise en charge à 75% du coût et forfait mobilité durable jusqu’à 300€

About the offer

About the CNRS

The CNRS is a major player in fundamental research on a global scale. The CNRS is the only French organization active in all scientific fields. Its unique position as a multi-specialist allows it to bring together different disciplines to address the most important challenges of the contemporary world, in connection with the actors of change.

CNRS

The research professions