Mots-Clés

machine learning ADN circulant biomarqueurs cancer

Description

Funded PhD thesis in machine learning applied to circulating DNA and cancer diagnosis

The analysis of circulating, cell-free DNA (cfDNA) in the blood is revolutionizing the non-invasive diagnosis of various diseases and conditions, from fetus pre-natal tests to cancer early detection [1,2]. The application of next generation sequencing to cfDNA delivers enormous amounts of information that can be exploited successfully with machine learning and data science techniques [3,4]. Beyond the clinical perspective of medical tests, the analysis of cfDNA also provide information related to the genome organization and nucleosome structures.

In this PhD thesis, the successful candidate will develop a variety of machine learning and bioinformatics approaches to establish new non-invasive detection procedure of colorectal and breast cancers. Among the techniques envisioned, we will consider combining the information provided by cfDNA fragment sizes, but also their methylation status. The thesis will be under the supervision of Prof. Jacques Colinge in collaboration with cfDNA expert Dr. Alain Thierry, both PIs at IRCM in Montpellier. A significant part of the research will take place within the frame of various French national and European collaborative projects involving the analysis of cfDNA.

We are looking for a highly motivated student with background in bioinformatics or math/cs/physics/biochemistry with some basic knowledge of molecular biology and solid computer programing skills in at least one of R, Python, or C/C++. Basic training in machine learning is necessary. Most of the analyses will be implemented in R. The Colinge Cancer Bioinformatics and Systems Biology Lab is a multidisciplinary team including mathematicians, biologists, and a biophysicist. We work in close collaboration with wet lab biologists and clinicians. Proper support will be provided to the PhD student to complement potentially weaker skills and help her to start her project efficiently.

Expected start before October 1, 2023, the earlier the better.

Colinge publications: https://scholar.google.com/citations?hl=fr&user=duClhDAAAAAJ

Thierry publications: https://scholar.google.com/citations?hl=fr&user=dprGAvIAAAAJ

References

1.            Thierry AR. Circulating DNA fragmentomics and cancer screening. Cell Genom. 2023;3: 100242. doi:10.1016/j.xgen.2022.100242

2.            Sun K, Jiang P, Cheng SH, Cheng THT, Wong J, Wong VWS, et al. Orientation-aware plasma cell-free DNA fragmentation analysis in open chromatin regions informs tissue of origin. Genome Res. 2019;29: 418–427. doi:10.1101/gr.242719.118

3.            Tanos R, Tosato G, Otandault A, Al Amir Dache Z, Pique Lasorsa L, Tousch G, et al. Machine Learning-Assisted Evaluation of Circulating DNA Quantitative Analysis for Cancer Screening. Adv Sci (Weinh). 2020;7: 2000486. doi:10.1002/advs.202000486

4.            Cristiano S, Leal A, Phallen J, Fiksel J, Adleff V, Bruhm DC, et al. Genome-wide cell-free DNA fragmentation in patients with cancer. Nature. 2019;570: 385–389. doi:10.1038/s41586-019-1272-6