Research themes

We integrate systems biology, multi-omics and artificial intelligence to characterize cancer biology and translate molecular information into clinically relevant knowledge. Our research addresses cancer molecular subtyping, tumor heterogeneity, progression, cellular plasticity and treatment resistance through the analysis of complex omics and clinical data. DISCO has a particular expertise in urological cancers, while collaborations within the CRCLille teams extend these approaches to breast, pancreatic, lung and brain cancers. We also investigate molecular links between cancer and autism and develop approaches towards precision and individualized medicine.

key publications:

• Moreno-Vega, A.*, Zambrano, M.*, Estrada-Virrueta, L.*, Meng, X.*, Puig, J.*, Neyret-Kahn, H., Shi, M., Dufour,F., Gilbert, G.,  Li, K.,  Groeneveld, C., Fontugne, J., Pérez-Escavy, M., Dhifli, W., Hua, C., Cabel, L., Krucker, C., Tanguy, L., Lindskrog, S.,  Beraud, C., Yanina V. Langle, Ye, T., Tahi, F., Davidson, I., Paramio, J.,  Dyrskjot, L., Allory, Y., LLUEL, Ph., Eiján, A., Lodillinsky, K.#, Elati, M.#, Radvanyi, F.#, Bernard-Pierrot, I.#. FGFR3-driven gene regulatory network analysis reveals a pro-tumoral role for p63 in luminal bladder tumors, The Journal of Clinical Investigation (JCI), 136(15), 2026. IF: 14,3.
• G. Marcq, K. Geles, W. Dhifli, P. Eriksson, C. Bernardo, C. Guenes, I. Bernard-Pierrot, G. Sjödahl, Y. Allory, F. Radvanyi, M. Elati, A universal molecular map of bladder cancer: from cell lines in vitro to tumors and back using co-regulatory networks, European Urology, Volume 89, Supplement 1, 2026. IF: 29.
• Bernhard, C., Geles, K., Pawlak, G., Dhifli, W., Dispot, A., Dusol, J., Kondratova, M., Martin, S., Messé, M., Reita, D., Tulasne, D.,  Van Seuningen, I., Entz-Werle, N., Anna Ciafrè, S., Dontenwill, M. & Elati, M. A coregulatory influence map of glioblastoma heterogeneity and plasticity. npj Precision Oncology, 9(1), 110, 2025. IF: 9,9.
• Truong, M.J., Pawlak, G., Meneboo, J.P., Sebda, S., Fernandes, M., Figeac, M., Elati, M. and Tulasne, D., Comprehensive map of the regulatory network triggered by MET exon 14 skipping reveals important involvement of the RAS-ERK signaling pathway. Cell Death & Disease, 16(1), p.783. 2025. IF: 12,2.
• Yin, L., Traversa, P., Elati, M., Moreno, Y., Marek-Trzonkowska, N., & Battail, C. Sample-specific network analysis identifies gene co-expression patterns of immunotherapy response in clear cell renal cell carcinoma. Iscience, 28(8). 2025. IF: 4,5.
• Halstuch D, Kool R, Marcq G, Breau RH, Black PC, Shayegan B, Kim M, Busca I, Abdi H, Dawidek MT, Uy M, Fervaha G, Cury FL, Alimohamed NS, Jeldres C, Rendon R, Brimo F, Siemens DR, Kulkarni GS, Kassouf W, Izawa JI. The Impact of Histologic Subtypes on Clinical Outcomes After Radiation-Based Therapy for Muscle-Invasive Bladder Cancer. Journal of Urology. 212(5):710-719, 2024. IF: 7,5.

We develop theoretical and computational approaches for learning from complex, heterogeneous and high-dimensional data. Our research combines machine learning, graph learning, representation and feature learning, ensemble methods, knowledge representation and causal inference to model biological systems and reconstruct molecular and regulatory networks. We develop algorithms and software for classification, prediction, network inference, data integration and network-driven hypothesis generation, with applications in cancer biology, biomedical data analysis, medical imaging and health data.

Key publications:

• Karabadji, N. E., Lakhdari, A., Al Nuaim, A. A., Algefary, A., Yildirim, A., Assi, A., Elati, E. & Dhifli, W. Fractional class-specific weighted random forest optimization. Information Fusion, 104689. 2026. IF: 17,4.
• Manaa, N., Karabadji, N. E., Seridi, H., Mendjel, M. S. M., & Dhifli, W. Improved VAE-GAN via mixture of Gaussians applied to brain tumor MRI classification. Knowledge-Based Systems, 116198, 2026. IF: 8.
• Assi, A., Karabadji, N. E., Elati, M., & Dhifli, W. Learning Global-Local Multi-Scale Node Embeddings with Random Walks and Landmark-Guided Optimization. In Proceedings of the 34th ACM International Conference on Information and Knowledge Management (CIKM), pp. 77-86. 2025.
• Hadjadji, I., Karabadji, N. E., Seridi, H., Manaa, N., Elati, M., & Dhifli, W. Optimizing mlp network structure for classification problems using pso and dominating vertex set. In Proceedings of the International Conference on Data Mining (ICDMW) (pp. 529-534). IEEE. 2024.
• Dhifli, W., Karabadji, N. E. I., & Elati, M. Evolutionary mining of skyline clusters of attributed graph data. Information Sciences, 509, 501-514. 2020. IF: 6.
• Dhifli, W., Puig, J., Dispot, A., & Elati, M. Latent network-based representations for large-scale gene expression data analysis. BMC bioinformatics, 19(Suppl 13), 466, 2019. IF: 4,4.
• Lopez-Rincon, A., Tonda, A., Elati, M., Schwander, O., Piwowarski, B., & Gallinari, P. Evolutionary optimization of convolutional neural networks for cancer miRNA biomarkers classification. Applied Soft Computing, 65, 91-100. 2018. IF: 7,8.
• Bouyioukos, C., Bucchini, F., Elati, M., & Kepes, F. GREAT: a web portal for Genome Regulatory Architecture Tools. Nucleic acids research (NAR), 44(W1), W77-W82. 2016. IF: 15.
• Nicolle, R., Radvanyi, F., & Elati, M. CoRegNet: reconstruction and integrated analysis of co-regulatory networks. Bioinformatics, 31(18), 3066-3068. 2015. IF: 5,5.
• Winterhalter, C., Nicolle, R., Louis, A., To, C., Radvanyi, F., & Elati, M. PEPPER: cytoscape app for protein complex expansion using protein–protein interaction networks. Bioinformatics, 30(23), 3419-3420. 2014. IF: 5,5.
• Elati, M., Neuvial, P., Bolotin-Fukuhara, M., Barillot, E., Radvanyi, F., & Rouveirol, C. LICORN: learning cooperative regulation networks from gene expression data. Bioinformatics, 23(18), 2407-2414, 2007. IF: 5,5.

We develop intelligent digital systems that combine artificial intelligence, scientific knowledge and experimental or clinical workflows to address challenges in biomedical research and healthcare. Our research spans AI-driven precision oncology, laboratory automation and autonomous science, as well as digital health and clinical decision-support systems. We explore closed-loop workflows in which AI generates hypotheses, guides experimentation or supports clinical decisions, towards autonomous laboratories and AI-driven biomedical discovery. We also investigate the responsible deployment of AI in healthcare, with a focus on transparency, fairness, data governance and human oversight.

Key publications

• Guinhouya, B. C., Morgenroth, T., Boudis, F., Apété, G. K., Dossou, G. T., Gasso, G., & Zitouni, D. Impracticality of banning collection of data on race and ethnicity in artificial intelligence-enabled health care in France. The Lancet Digital Health. 2026. IF: 25,5.
• Tiwari, A., Mishra, S., & Kuo, T. R. Current AI technologies in cancer diagnostics and treatment. Molecular cancer, 24(1), 159., 2025. IF: 42,2.
• Coutant, A.*, Roper, K.*, Trejo-Banos*, D., Bouthinon, D., Carpenter, M., Grzebyta, J., Santini, G., Soldano, H., Elati#, M., Ramon, J.#, Rouveirol, C.#, Saldatova, L.#, & King, R. D.#. Closed-loop cycles of experiment design, execution, and learning accelerate systems biology model development in yeast. Proceedings of the National Academy of Sciences (PNAS), 116(36), 18142-18147, 2019. IF: 9,5.