Abstract Large quantities of multi-omic data are increasingly becoming available. They provide complementary information about cells, tissues and diseases. We need to utilize them to better stratify patients into risk groups, discover new biomarkers and targets, re-purpose known and discover new drugs to personalize medical treatment. This is nontrivial, because of computational intractability of many underlying problems on large interconnected data (networks, or graphs), necessitating the development of new algorithms for finding approximate solutions (heuristics) [1]. We develop versatile data fusion artificial intelligence (AI) frameworks, that utilize the state-of-the-art network science methods, to address key challenges in precision medicine from time-series, multi-omics data: better stratification of patients, prediction of biomarkers and targets, and re-purposing of drugs, applied to different types of cancer [2,3], Covid-19 [4,5], Parkinson’s [6,7] and other diseases. Our new methods stem from graph-regularized non-negative matrix tri-factorization (NMTF), a machine learning (ML) technique for dimensionality reduction, inference, fusion and co-clustering of heterogeneous datasets, coupled with novel graphlet-based network science algorithms. We utilize our new frameworks to for improving the understanding the molecular organization and diseases from the omics data embedding spaces [8,9,10]. Also, we utilize local topology to correct for the topological information missed by random walks, which are used in many ML methods [11], and to enable embedding of networks into more linearly separable spaces, allowing for their better mining [12]. The aim is to develop an overreaching framework encompassing all multi-omics data that would simplify currently complex and energy inefficient AI methodologies for multi-omics data analyses [13].
References
[1] Nataša Pržulj, Noel Malod-Dognin: “Network analytics in the age of big data”, Science 353 (6295) 123-124, 2016
[2] Noël Malod-Dognin, Julia Petschnigg, Sam FL Windels, Janez Povh, Harry Hemingway, Robin Ketteler, Nataša Pržulj, “Towards a data-integrated cell,” Nature Communications, 10 (1) 805, 2019
[3] Vladimir Gligorijević, Noël Malod-Dognin, Nataša Pržulj, “Patient-specific data fusion for cancer stratification and personalised treatment,” Biocomputing 2016: Proceedings of the Pacific Symposium, 2016
[4] Alexandros Xenos, Noël Malod-Dognin, Carme Zambrana, Nataša Pržulj, “Integrated data analysis uncovers new COVID-19 related genes and potential drug re-purposing candidates,” International Journal of Molecular Sciences, 24 (2) 1431, 2023
[5] Carme Zambrana, Alexandros Xenos, René Böttcher, Noël Malod-Dognin, Nataša Pržulj, “Network neighbors of viral targets and differentially expressed genes in COVID-19 are drug target candidates,” Scientific Reports, 11 (1) 18985, 2021
[6] Katarina Mihajlović, Gaia Ceddia, Nöel Malod-Dognin, Gabriela Novak, Dimitrios Kyriakis, Alexander Skupin, Nataša Pržulj, “Multi-omics integration of scRNA-seq time series data predicts new intervention points for Parkinson's disease,” Scientific Reports 14 (10983), 2024
[7] Katarina Mihajlović, Noël Malod-Dognin, Corrado Ameli, Alexander Skupin, Nataša Pržulj, “MONFIT: Multi-omics factorization-based integration of time-series data sheds light on Parkinson’s disease,” NAR Molecular Medicine, 1 (4), 2024
[8] Alexandros Xenos, Noël Malod-Dognin, Stevan Milinković, Nataša Pržulj, “Linear functional organization of the omic embedding space,” Bioinformatics, 37 (21) 3839-3847, 2021
[9] Sergio Doria-Belenguer, Alexandros Xenos, Gaia Ceddia, Noël Malod-Dognin, Nataša Pržulj, “A functional analysis of omic network embedding spaces reveals key altered functions in cancer,” Bioinformatics, 39 (5) btad281, 2023
[10] Sergio Doria-Belenguer, Alexandros Xenos, Gaia Ceddia, Nöel Malod-Dognin, Nataša Pržulj, “The axes of biology: a novel axes-based network embedding paradigm to decipher the functional mechanisms of the cell,” Bioinformatics Advances 4(1), 2024
[11] Sam Windels, Noel Malod-Dognin, Nataša Pržulj, “Graphlets correct for the topological information missed by random walks,” arXiv:2405.14194, 2024
[12] Alexandros Xenos, Noel-Malod Dognin, Nataša Pržulj, “Simplifying complex machine learning by linearly separable network embedding spaces,” arXiv:2410.01865, 2024
[13] Nataša Pržulj, Noel Malod-Dognin, “Simplicity within biological complexity,” Bioinformatics Advances, 5(1), vbae164, 2025