Detection of Age-Related Changes in Networks of B Cells by Multivariate Time-Series Analysis
Immunosenescence concerns the gradual deterioration of the immune system due to aging. Recent advances in cellular phenotyping have enabled key improvements in this context during the last decades. In this work we present a novel extensions and integration of data-driven models for describing age-related changes in the network of relationships among cell quantities of eight peripheral B lymphocyte subpopulations. Our dataset contains about six thousands samples of patients having an age between one day and ninety-six years, where for each patient, cell quantities of eight peripheral B lymphocyte subpopulations were measured. By correlation-based multiple time series segmentation we generate four sets of age-related networks depending on the number of age segments. We first analyze a partition in 30 very short segments, then segmentations in 5, 3 and 2 segments. Moving from a fine to a large grain segmentation, different aspects of the dataset are highlighted and analyzed.
Authors would like to thank Antonio Vella (department of pathology and diagnostics, University Hospital of Verona) for providing the dataset used in this work and for interesting discussions on the role of B cells in the immune system.
- 1.Barnett, I., Onnela, J.-P.: Change point detection in correlation networks. Sci. Rep. 6(18893), 1–11 (2016)Google Scholar
- 4.Castellini, A., Franco, G., Vella, A.: Age-related relationships among peripheral B lymphocyte subpopulations. In: 2017 IEEE Congress of Evolutionary Computation - CEC, pp. 1864–1871 (2017). Springer, Berlin, GermanyGoogle Scholar
- 6.Chiu, B., Keogh, E., Lonardi, S.: Probabilistic discovery of time series motifs. In: Proceedings of the 9th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2003, pp. 493–498. ACM (2003)Google Scholar
- 12.Hallac, D., Vare, S., Boyd, S., Leskovec, J.: Toeplitz inverse covariance-based clustering of multivariate time series data. In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2017, pp. 215–223. ACM, New York (2017)Google Scholar
- 13.Hicks, M.J., Jones, J.F., Minnich, L.L., Wigle, K.A., Thies, A.C., Layton, J.M.: Age-related changes in T- and B-lymphocyte subpopulations in the peripheral blood. Arch. Pathol. Lab. Med. 107(10), 518–523 (1983)Google Scholar
- 14.Hyndman, R.J., Athanasopoulos, G.: Forecasting: Principles and Practice, 2nd edn., O Texts (2014)Google Scholar
- 15.Jerne, N.K.: Towards a network theory of the immune system. Annales d’immunologie 125C(1–2), 373–389 (1974)Google Scholar
- 16.Keogh, E., Chu, S., Hart, D., Pazzani, M.: Segmenting time series: a survey and novel approach. In: Data mining in Time Series Databases, pp. 1–22. World Scientific, Singapore (1993)Google Scholar
- 19.Lin, J., Keogh, E., Lonardi, S., Patel, P.: Finding Motifs in time series. In: Proceedings of the Second Workshop on Temporal Data Mining, pp. 52–68. ACM (2002)Google Scholar
- 20.Manca, V., Castellini, A., Franco, G., Marchetti, L., Pagliarini, R.: Metabolic P systems: a discrete model for biological dynamics. Chin. J. Electron. 22(4), 717–723 (2013)Google Scholar
- 24.Terzi, E., Tsaparas, P.: Efficient algorithms for sequence segmentation. In: Proceedings of the 2006 SIAM International Conference on Data Mining, pp. 316–327. SIAM (2006)Google Scholar
- 25.Vahdatpour, A., Amini, N., Sarrafzadeh, M.: Toward unsupervised activity discovery using multi-dimensional motif detection in time series. In: Proceedings of the 21st International Joint Conference on Artifical Intelligence, IJCAI 2009, pp. 1261–1266 (2009)Google Scholar
- 26.Veneri, D., Ortolani, R., Franchini, M., Tridente, G., Pizzolo, G., Vella, A.: Expression of CD27 and CD23 on peripheral blood B lymphocytes in humans of different ages. Blood Transfus. 7, 29–34 (2009)Google Scholar