Порівняння методів

	Машинне навчання для аналізу різноманіття мікробіому	Аналіз диференційної експресії генів методом RNA-seq
Галузь	Біоінформатика	Біоінформатика
Родина	Process / pipeline	Process / pipeline
Рік появи	2011–2016 (formalization of ML integration into microbiome pipelines)	2008–2010 (RNA-seq DE methodology established)
Автор методу	Pasolli, Segata and colleagues (meta-ML framework); broader field grew from Turnbaugh et al. human microbiome work	Multiple groups; foundational methods from Anders & Huber (DESeq, 2010), Robinson, McCarthy & Smyth (edgeR, 2010)
Тип	Computational pipeline (supervised/unsupervised ML + diversity metrics)	Quantitative genomics pipeline
Основоположне джерело	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.	Love, M. I., Huber, W., & Anders, S. (2014). Moderated estimation of fold change and dispersion for RNA-seq data with DESeq2. Genome Biology, 15(12), 550.
Інші назви	ML-based microbiome analysis, supervised microbiome diversity, microbiome ML classification, ML-driven alpha/beta diversity analysis	RNA-seq DE analysis, transcriptomic differential expression, bulk RNA-seq DE, DEA
Пов'язані	5	6
Підсумок	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.	RNA-seq differential expression (DE) analysis identifies genes whose transcript abundance differs significantly between two or more biological conditions — for example, treated versus control, or diseased versus healthy tissue. Starting from raw sequencing reads, the pipeline moves through alignment, count-based normalization, statistical modeling of count dispersion, hypothesis testing, and multiple-testing correction to produce a ranked list of differentially expressed genes accompanied by fold-change estimates and adjusted p-values.