Chapter 9: Data analysis in metabolomics: from information to knowledge
by Jacopo Troisi, Giovanni Troisi, Giovanni Scala, Sean M. Richards
Abstract
Data analysis is a pivotal step in the metabolomics investigation pipeline as it allows to extract knowledge from datasets and get new insights and new perspectives as well as generate new hypotheses about biological complex processes. Data analysis uses various strategies including exploratory analysis which tends to evaluate metabolites individually and machine learning algorithms which in turn can be unsupervised (data driven) or supervised (task driven) allowing the study of the interplay of the several investigated metabolites. Among the first, particularly important in metabolomics are the clustering algorithms and the principal components analysis. Among the latter, a prominent role is played by partial least square discriminant analysis, artificial neural networks, supported vectors machines. These algorithms as well as solo, can be combined in ensemble models. Particular emphasis is placed in this chapter on strategies for evaluating the effectiveness of machine learning algorithms trainings, including validation strategies, features selection mechanisms and hyperparameter optimization.
Jacopo Troisi
Department of Medicine, Surgery and Dentistry “Scuola Medica Salernitana” University; Theoreo srl – spin off company of the University of Salerno, Italy; Department of Chemistry and Biology “A. Zambelli”, University of Salerno, Italy
Jacopo Troisi is visiting professor of Metabolomics in both Salerno University and University of Sannio in Italy. He is a Research Scientist and COO at the European Biomedical Research Institute of Salerno (EBRIS), co-founded by the Harvard University and the Salerno Medical School. He is also co-founder and CEO at Theoreo srl, a spin-off company of the University of Salerno. Prof. Troisi research is related to metabolomics. In particular, he studies the metabolomic fingerprint of several human diseases to develop diagnostic tools. He has received several international patents for diagnostic tests based on metabolomic profiling. Dr. Troisi has published widely in such peer reviewed journals as Science, Nature Microbiology, Nature Communications, Frontiers in Immunology, Nutrients, BMC Microbiology, Metabolomics, and Scientific Reports.
Giovanni Troisi
Giovanni Troisi is an informatic engineer, technical manager of research and development sector for impedentiometry applied to the human body in a big USA company. He supports one of the major Italian government bodies in the Salerno area for the processing of personal, financial and health data of citizens. Finally, he is fully involved in the field of artificial intelligence for the early recognition of new diseases.
Combining his studies in computer engineering with a passion for metabolomics and cellular nutrition, he has developed the technology that has collected and analyzed a huge amount of data coming from University, Hospital and Specialistic diagnostic center tests.
When he isn’t glued to a computer screen, he loves to play sports, enjoy long nature walks with his baby in pouch and trying very hard not to be the worst Russian language pupil in his living area.
He is currently committed to making wellness and health technology personal and within everyone's reach.
Giovanni Scala
Chemist, CTO and cofounder of Theoreo. He deals with the commercial and marketing area. His experience is in the field of advanced analytical technologies, in particular mass spectrometry and chromatographic separation. He coordinates several R&D projects granted by the European Union and managed by Campania Region. These projects deal with mass spectrometry and chromatography applied to various fields: metabolomics, diagnostics, food farming, pollution. From 2006 to 2010 he collaborated with the GCSAR (General Commission for Scientific Agriculture Research, Ministy of Agriculture) in Damasco, in a project dealing with oil and olive production. His current research is related to metabolomics. In particular, he studies the metabolomic fingerprint of several human diseases to develop diagnostic tools. He has received several international patents for diagnostic tests based on metabolomic profiling.
Sean M. Richards
Department of Biological and Environmental Sciences, University of Tennessee-Chattanooga, Chattanooga, TN 37403 - Department of Biological and Environmental Sciences, University of Tennessee-Chattanooga, Chattanooga, TN 37403, USA; Department of Obstetrics and Gynecology University of Tennessee Health Science Center College of Medicine Chattanooga, TN 37403
Over the last 25 years Dr. Richards has conducted research on the exposure and effects of multiple toxicants on organisms ranging from bacteria to humans. These toxicants include herbicides, insecticides, pharmaceuticals, Bisphenol A, Poly Aromatic Hydrocarbons, Per- and Polyfluoroalkyl Substances, metals, and Poly Chlorinated Biphenyls. Dr. Richards also has experience with the laws and regulations which govern exposure to toxicants through air, soil, and water.
Most recently, Dr. Richards has focused on metabolomics. Specifically, the alterations of metabolomes in response to toxicants or in populations of humans affected by endometrial cancer, congenital malformations, endometriosis, polycystic ovarian syndrome, and fetal central nervous system anomalies. The goal of this research is to determine specific biochemical pathways associated with the affected populations. Ultimately, understanding the changes in the metabolome as a result of disease or intoxication can lead to early detection and personalized treatments.
Contact