Société Française de Bioinformatique

Mots-Clés

Troubles bipolaires IRM Machine Learning Statistique Neuroimagerie Neurodéveloppement

Description

Bipolar disorder is a psychiatric disorder affecting more than 2% of the population. It is a very heterogeneous pathology where patients with similar symptoms exhibit very distinct evolutions. A recent hypothesis postulates that a subgroup of patients with particularly severe bipolar disorder can be characterized by altered neurodevelopment. A set of clinical criteria was selected by Dr. Lefrère and his team to develop a score quantifying these neurodevelopmental alterations: the NDP score. It has been shown on a cohort of 120 patients that the patient subgroup with high NDP is characterized by a poorer prognosis and increased resistance to lithium, the most common treatment for bipolar disorder whose efficacy is quantified by the ALDA scale [1].
One of the challenges is to further characterize the high NDP subgroup by identifying physiopathological biomarkers that can explain the poor response to treatment. This project follows the recent literature that established that bipolar disorder and poor treatment response are associated with morphometric abnormalities and structural connectivity abnormalities [2-5]. In addition, abnormalities in these same modalities have also been reported in certain neurodevelopmental disorders, such as attention-deficit/hyperactivity disorder (ADHD) and autism spectrum disorder (ASD) [6,7]. The aim of this internship is therefore to investigate the specific structural neuroimaging signatures of the neurodevelopmental subgroup and consider their statistical relationship with the ALDA score. The data are already available, so the project will start with a literature review to identify regions of interest related to the different clinical factors. Then, the student will compare several statistical analyses ranging from descriptive to predictive statistics to characterize the targeted patient subgroup.

1. Lefrere, A., Godin, O., Jamain, S., Dansou, Y., Samalin, L., Alda, M., … & Belzeaux, R. (2025). Refining criteria for a neurodevelopmental subphenotype of bipolar disorders: A FondaMental Advanced Centers of Expertise for Bipolar Disorders study. BiologicalPsychiatry, 97(8), 806-815.

2. Ching, C. R., Hibar, D. P., Gurholt, T. P., Nunes, A., Thomopoulos, S. I., Abé, C., … & ENIGMA Bipolar Disorder Working Group. (2022). What we learn about bipolar disorder from large‐scale neuroimaging: Findings and future directions from the ENIGMA Bipolar Disorder Working Group. Human brain mapping, 43(1), 56-82.

3. Nabulsi L, McPhilemy G, O’Donoghue S, Cannon DM, Kilmartin L, O’Hora D, Sarrazin S, Poupon C, D’Albis MA, Versace A, Delavest M, Linke J, Wessa M, Phillips ML, Houenou J, McDonald C. Aberrant Subnetwork and Hub Dysconnectivity in Adult Bipolar Disorder: A Multicenter Graph Theory Analysis. Cereb Cortex. 2022 May 14;32(10):2254-2264. doi: 10.1093/cercor/bhab356. PMID: 34607352; PMCID: PMC9113298.

4. Athey TL, Ceritoglu C, Tward DJ, Kutten KS, DePaulo JR, Glazer K, Goes FS, Kelsoe JR, Mondimore F, Nievergelt CM, Rootes-Murdy K, Zandi PP, Ratnanather JT, Mahon PB. A 7 Tesla Amygdalar-Hippocampal Shape Analysis of Lithium Response in Bipolar Disorder. Front Psychiatry. 2021 Feb 16;12:614010. doi: 10.3389/fpsyt.2021.614010. PMID: 33664682; PMCID: PMC7920967.

5. Boere E, van der Wee NJA, de Leeuw M. Lithium effects in the frontolimbic circuitry: a systematic review of neuroimaging findings in bipolar disorder. Transl Psychiatry. 2026 Feb 12;16(1):73. doi: 10.1038/s41398-026-03868-z. PMID: 41672966; PMCID: PMC12916775.

6. Boedhoe, P. S., Van Rooij, D., Hoogman, M., Twisk, J. W., Schmaal, L., Abe, Y., … & Weiss, E. O. (2020). Subcortical brain volume, regional cortical thickness, and cortical surface area across disorders: findings from the ENIGMA ADHD, ASD, and OCD working groups. American Journal of Psychiatry, 177(9), 834-843.

7. Tolonen T, Roine T, Alho K, Leppämäki S, Tani P, Koski A, Laine M, Salmi J. Abnormal wiring of the structural connectome in adults with ADHD. Netw Neurosci. 2023 Dec 322;7(4):1302-1325. doi: 10.1162/netn_a_00326. PMID: 38144696; PMCID: PMC10631790

We are looking for a Master’s student (M2) or a final-year engineering student specializing in bioinformatics, with a background in machine learning and proficiency in Python, particularly libraries such as Pandas, Matplotlib and Scikit-learn. The candidate should have a good understanding of statistical methods and be familiar with R. Theoretical knowledge of molecular biology would be an asset.

The internship will take place within the BraiNets team at the INT, providing an optimal research environment thanks to the team’s strong expertise in the field. In practice, the intern will work under the cosupervision of Julie Feriau, a PhD student supervised by M Gilson and A Lefrère, which will strengthen the teamwork.