A comparative study of supervised and unsupervised machine learning algorithms applied to human microbiome
V. 175 N. 3 (2024), Observational Study
V. 175 N. 3 (2024)

A comparative study of supervised and unsupervised machine learning algorithms applied to human microbiome: doi: 10.7417/CT.2024.5051

Observational Study
Pubblicato 2024-05-20
E. Kalluçi
Department of Applied Mathematics, Faculty of Natural Sciences, University of Tirana, Tirana, Albania
B. Preni
Department of Mathematics, Faculty of Engineering Mathematics and Engineering Physics, Polytechnic University of Tirana, Tirana, Albania
X. Dhamo
Department of Applied Mathematics, Faculty of Natural Sciences, University of Tirana, Tirana, Albania
E. Noka
Department of Applied Mathematics, Faculty of Natural Sciences, University of Tirana, Tirana, Albania
S. Bardhi
Department of Applied Statistics and Informatics, University of Tirana, Tirana, Albania
K. Bani
Department of Applied Mathematics, Faculty of Natural Sciences, University of Tirana, Tirana, Albania
A. Macchia
MAGI’S LAB, Rovereto (TN), Italy
G. Bonetti
MAGI’S LAB, Rovereto (TN), Italy - Department of Pharmaceutical Sciences, University of Perugia, Perugia, Italy
K. Dhuli
MAGI’S LAB, Rovereto (TN), Italy
K. Donato
MAGI EUREGIO, Bolzano, Italy - MAGISNAT, Atlanta Tech Park, Peachtree Corners, GA, USA
M. Bertelli
MAGI’S LAB, Rovereto (TN), Italy - MAGI EUREGIO, Bolzano, Italy - MAGISNAT, Atlanta Tech Park, Peachtree Corners, GA, USA
L.J.M. Zambrano
Computational Biology Group, Precision Nutrition and Cancer Research Program, IMDEA Food Institute, Madrid, Spain
S. Janaqi
EuroMov Digital Health in Motion, University of Montpellier IMT Mines Ales, France
PDF

Parole chiave

complex networks
modularity
non-negative matrix factorization
machine learning
complexity

Abstract

BACKGROUND: The human microbiome, consisting of diverse bacterial, fungal, protozoan and viral species, exerts a profound influence on various physiological processes and disease susceptibility. However, the complexity of microbiome data has presented significant challenges in the analysis and interpretation of these intricate datasets, leading to the development of specialized software that employs machine learning algorithms for this aims.

METHODS: In this paper, we analyze raw data taken from 16S rRNA gene sequencing from three studies, including stool samples from healthy control, patients with adenoma, and patients with colorectal cancer. Firstly, we use graph-based methods and projection methods to reduce dimensions of the dataset and consider only the most important features. In addition, we employ supervised machine learning algorithms to make prediction.

RESULTS: Results show that graph-based techniques reduces dimension from 255 up to 78 features with modularity score 0.73 based on different centrality measures. On the other hand, projection methods (non-negative matrix factorization and principal component analysis) reduce dimensions to 7 features. Furthermore, we apply supervised machine learning algorithms on the most important features obtained from centrality measures and on the ones obtained from projection methods, founding that the evaluation metrics have approximately the same scores when applying the algorithms on the entire dataset, on 78 feature and on 7 features.

CONCLUSIONS: This study demonstrates the efficacy of graph-based and projection methods in the interpretation for 16S rRNA gene sequencing data. Supervised machine learning on refined features from both approaches yields comparable predictive performance, emphasizing specific microbial features—bacteroides, prevotella, fusobacterium, lysinibacillus, blautia, sphingomonas, and faecalibacterium—as key in predicting patient conditions from raw data.

PDF