Print Email Facebook Twitter Finding Biomarkers for Schizophrenia Title Finding Biomarkers for Schizophrenia: Can Machine Learning algorithms identify schizophrenia-related biomarkers within metagenomic data derived from the human gut microbiome? Author Bastow, Timothy (TU Delft Electrical Engineering, Mathematics and Computer Science; TU Delft Pattern Recognition and Bioinformatics) Contributor van der Toorn, E.A. (mentor) Calderon Franco, D. (mentor) Abeel, T.E.P.M.F. (mentor) Höllt, T. (graduation committee) Degree granting institution Delft University of Technology Programme Computer Science and Engineering Project CSE3000 Research Project Date 2023-06-27 Abstract There is mounting evidence indicating a relation- ship between the gut microbiome composition and the development of mental diseases but the mech- anisms remain unclear. Shotgun sequenced data from 90 schizophrenic patients and 81 sex, age, weight, and location matched controls was used for three machine learning models: Logistic Re- gression, Random Forests, and XGBoost. The 20 most relevant species in the decision mak- ing of each classifier was retained and the over- lap between models recorded. There is a total 19 overlapping species between the models’ top 20 most relevant species, with 10 species over- lapping on all three models. Bifidobacterium bi- fidum, Akkermansia muciniphila, Eubacterium sir- aeum, Alistipes finegoldii, Intestinibacter bartlet- tii, Bifidobacterium pseudocatenulatum, and Strep- tococcus thermophilus are of particular interest as they are reported as enriched in schizophrenia sam- ples in existing literatures. Phoceicola vulgatus has been found to play a significant role in the classi- fiers decisions and is enriched in healthy samples in the literature. One species, Ruthenibacterium lactatiformans, and one co-abundant gene group, Eubacterium sp. CAG:180, consistently ranked as the most important features across all three classi- fiers, despite the absence of reporting in existing literature. This study could be expanded by using genus-level data. Further research should be done to validate the species mentioned above as potential biomarkers for schizophrenia. Subject Machine LearningschizophreniaGut microbiome To reference this document use: http://resolver.tudelft.nl/uuid:918b3af1-7cfc-4a68-8b5a-fe929228e6f7 Part of collection Student theses Document type bachelor thesis Rights © 2023 Timothy Bastow Files PDF RP_Paper.pdf 1.4 MB Close viewer /islandora/object/uuid:918b3af1-7cfc-4a68-8b5a-fe929228e6f7/datastream/OBJ/view