Usporedite metode

	Pozivanje vrhunaca pomoću potpomognutog strojnog učenja za ChIP-seq	RNA-seq diferencijalna ekspresija
Područje	Bioinformatika	Bioinformatika
Obitelj	Process / pipeline	Process / pipeline
Godina nastanka	2008 (classical); ML-assisted variants 2012–present	2008–2010 (RNA-seq DE methodology established)
Tvorac	Building on MACS (Zhang et al. 2008); ML extensions by Haiminen et al. and others (2010s–2020s)	Multiple groups; foundational methods from Anders & Huber (DESeq, 2010), Robinson, McCarthy & Smyth (edgeR, 2010)
Vrsta	Supervised/unsupervised ML-augmented peak detection pipeline	Quantitative genomics pipeline
Temeljni izvor	Kharchenko, P. V., Tolstorukov, M. Y., & Park, P. J. (2008). Design and analysis of ChIP-seq experiments for DNA-binding proteins. Nature Biotechnology, 26(12), 1351-1359.	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.
Drugi nazivi	ML-based ChIP-seq peak detection, deep learning ChIP-seq peak calling, ML-enhanced ChIP-seq analysis, AI-assisted ChIP-seq peak identification	RNA-seq DE analysis, transcriptomic differential expression, bulk RNA-seq DE, DEA
Srodne	6	6
Sažetak	Machine learning-assisted ChIP-seq peak calling extends classical statistical peak detection with supervised or unsupervised learning models that distinguish genuine protein-binding sites from background noise. By training on sequence composition, read coverage profiles, and epigenomic features, these methods improve sensitivity and specificity compared with threshold-based approaches, particularly in low-signal or heterogeneous chromatin contexts.	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.