2022-04622 - PhD Position F/M Mechanistic modeling of circulating DNA combined to machine learning for prediction of response and survival following immunotherapy

Level of qualifications required : Graduate degree or equivalent

Fonction : PhD Position

About the research centre or Inria department

The Inria Université Côte d’Azur center counts 36 research teams as well as 7 support departments. The center's staff (about 500 people including 320 Inria employees) is made up of scientists of different nationalities (250 foreigners of 50 nationalities), engineers, technicians and administrative staff. 1/3 of the staff are civil servants, the others are contractual agents. The majority of the center’s research teams are located in Sophia Antipolis and Nice in the Alpes-Maritimes. Four teams are based in Montpellier and two teams are hosted in Bologna in Italy and Athens. The Center is a founding member of Université Côte d'Azur and partner of the I-site MUSE supported by the University of Montpellier.


The PhD position will take place within the framework of an interdisciplinary call between the immuno-oncology and Laënnec (artificial intelligernce for health) Marseille institutes. 

The position will be located in the Inria-Inserm team COMPO (COMputational Pharmacology in Oncology), located in the University Hospital of Marseille (AP-HM). The team is composed of mathematicians, pharmacists and clinicians and is a unique multidisciplinary environment focused on developing novel computational tools for decision- making in clinical oncology.

The project will consist in working within the SChISM (Size Cfdna Immunotherapies Signature Monitoring) clinical study, in collaboration with AP-HM and the id-Solution and ADELIS biotechs. The PhD student will be co-supervised by a mathematician (Dr S. Benzekry) and a clinical oncologist (Pr S. Salas).


Early prediction of resistance to immunotherapy is a major challenge in oncology. The ongoing SChISM clinical study proposes an innovative approach based on patented cfDNA (circulating free DNA) quantification methods. Leveraging the longitudinal and quantitative aspect of this data (260 patients in total), we propose to develop mechanistic models of cfDNA joint kinetics with other longitudinal markers and tumor size imaging. Such models embedded within a statistical mixed-effects framework will be calibrated to the population data and subsequently provide individual parameters using Bayesian estimation. Subsequently, we aim to develop integrative machine learning models able to predict outcome (response, PFS and OS) from the combination of these dynamic parameters and other variables available at baseline.

For a better knowledge of the proposed research subject :

[1] Claret, L. et al. A Model of Overall Survival Predicts Treatment Outcomes with Atezolizumab versus Chemotherapy in Non-Small Cell Lung Cancer Based on Early Tumor Kinetics. Clin Cancer Res, 24, 3292–3298 (2018).

[2] Khan, K. H. et al. Longitudinal Liquid Biopsy and Mathematical Modeling of Clonal Evolution Forecast Time to Treatment Failure in the PROSPECT-C Phase II Colorectal Cancer Clinical Trial. Cancer discovery (2018) doi:10.1158/2159-8290.cd-17-0891.

[3] Benzekry, S. Artificial intelligence and mechanistic modeling for clinical decision making in oncology. Clinical pharmacology and therapeutics (2020)

Main activities

The objectives are to:

1) Establish and validate a mechanistic model of the joint kinetics of cfDNA concentrations and other circulating markers

2) Establish and validate a mixed-effects statistical model for quantification of inter-individual variability

3) Integrate the kinetic parameters together with baseline variables into ML pipelines for early prediction of outcome (response, progression-free survival, 3-years survival, overall survival)

keywords: immunotherapy, cfDNA, mechanistic modeling, machine learning, mixed-effects modeling

Examples of activities:

  • Data exploration and visualization
  • Biostatistics (e.g. statistical tests, survival analysis)
  • Programming (R/python)
  • Mathematical modeling of the pharmaco-physio-pathology
  • Mixed-effects statistical modeling
  • Literature review
  • Analyze the requirements of the project partners
  • Write synthetic and meaningful reports and scientific publications


Technical skills and level required :

  • Excellent data science programming skills (python/R)
  • Familiarity with real-world data analysis
  • Ideally, experience in mixed-effects modeling

Relational skills :

  • Ability to work as a team

Benefits package

  • Subsidized meals
  • Partial reimbursement of public transport costs
  • Leave: 7 weeks of annual leave + 10 extra days off due to RTT (statutory reduction in working hours) + possibility of exceptional leave (sick children, moving home, etc.)
  • Possibility of teleworking (after 6 months of employment) and flexible organization of working hours
  • Professional equipment available (videoconferencing, loan of computer equipment, etc.)
  • Social, cultural and sports events and activities
  • Access to vocational training
  • Social security coverage


1982€brut per month (year 1 & 2) and 2085€ brut/month (year 3)