Statistical and Machine Learning Techniques in Human Microbiome Studies: Contemporary Challenges and Solutions
Isabel Moreno‐Indias, Leo Lahti, Miroslava Nedyalkova, Ilze Elbere, Gennady V. Roshchupkin, Muhamed Adilović, Önder Aydemir, Burcu Bakır-Güngör, Enrique Carrillo de Santa Pau, Domenica D’Elia, Mahesh S. Desai, Laurent Falquet, Aycan Gündoğdu, Karel Hron, Thomas Klammsteiner, Marta B. Lopes, Laura Judith Marcos-Zambrano, Cláudia Marques, Mike J. Mason, Patrick May, Lejla Pašić, Gianvito Pio, Sándor Pongor, Vasilis J. Promponas, Piotr Przymus, Julio Sáez-Rodríguez, Alexia Sampri, Rajesh Shigdel, Blaž Stres, Ramona Suharoschi, Jaak Truu, Ciprian‐Octavian Truică, Baiba Vilne, Dimitriοs Vlachakis, Ercüment Yılmaz, Georg Zeller, Aldert Zomer, David Gómez-Cabrero, Marcus J. Claesson
Abstract
The human microbiome has emerged as a central research topic in human biology and biomedicine. Current microbiome studies generate high-throughput omics data across different body sites, populations, and life stages. Many of the challenges in microbiome research are similar to other high-throughput studies, the quantitative analyses need to address the heterogeneity of data, specific statistical properties, and the remarkable variation in microbiome composition across individuals and body sites. This has led to a broad spectrum of statistical and machine learning challenges that range from study design, data processing, and standardization to analysis, modeling, cross-study comparison, prediction, data science ecosystems, and reproducible reporting. Nevertheless, although many statistics and machine learning approaches and tools have been developed, new techniques are needed to deal with emerging applications and the vast heterogeneity of microbiome data. We review and discuss emerging applications of statistical and machine learning techniques in human microbiome studies and introduce the COST Action CA18131 "ML4Microbiome" that brings together microbiome researchers and machine learning experts to address current challenges such as standardization of analysis pipelines for reproducibility of data analysis results, benchmarking, improvement, or development of existing and new tools and ontologies.