Uporedite metode

	Analiza diverziteta mikrobioma uz pomoć mašinskog učenja	Analiza raznolikosti mikrobioma korišćenjem više omika
Oblast	Bioinformatika	Bioinformatika
Porodica	Process / pipeline	Process / pipeline
Godina nastanka	2011–2016 (formalization of ML integration into microbiome pipelines)	2010s–present
Tvorac	Pasolli, Segata and colleagues (meta-ML framework); broader field grew from Turnbaugh et al. human microbiome work	Developed collectively; key frameworks by Le Cao et al. (mixOmics, 2017) and Argelaguet et al. (MOFA, 2018)
Tip	Computational pipeline (supervised/unsupervised ML + diversity metrics)	Integrative computational pipeline
Temeljni izvor	Pasolli, E., Truong, D. T., Malik, F., Waldron, L., & Segata, N. (2016). Machine Learning Meta-analysis of Large Metagenomic Datasets: Tools and Biological Insights. PLOS Computational Biology, 12(7), e1004977.	Rohart, F., Gautier, B., Singh, A., & Le Cao, K.-A. (2017). mixOmics: An R package for 'omics feature selection and multiple data integration. PLOS Computational Biology, 13(11), e1005752.
Drugi nazivi	ML-based microbiome analysis, supervised microbiome diversity, microbiome ML classification, ML-driven alpha/beta diversity analysis	multi-omics microbiome profiling, integrated microbiome omics, multi-modal microbiome analysis, microbiome multi-omics integration
Srodne	5	5
Sažetak	Machine learning-assisted microbiome diversity analysis integrates classical alpha and beta diversity metrics with supervised or unsupervised ML models to classify host phenotypes, identify discriminant taxa, and uncover community-level signatures from 16S rRNA or shotgun metagenomic data. It extends traditional diversity analysis beyond descriptive statistics toward predictive and explanatory modelling across health, ecology, and environmental science.	Multi-omics microbiome diversity analysis integrates two or more omic data layers — such as metagenomics, metatranscriptomics, metabolomics, and metaproteomics — to characterise both the composition and functional activity of microbial communities. By linking taxonomic diversity metrics with molecular phenotype data, the approach uncovers how community structure translates into ecological and host-relevant functions that no single omic layer can reveal alone.