Comparer des méthodes

	Machine learning-assisted copy number variation analysis	Analyse des variations du nombre de copies
Domaine	Bio-informatique	Bio-informatique
Famille	Process / pipeline	Process / pipeline
Année d'origine	2010s–present	1998–2006
Auteur d'origine	Multiple groups; notable early ML-CNV tools include CNV-RF (Bellos et al., 2014) and CANOES (Backenroth et al., 2014)	Pinkel et al. (array CGH); Redon et al. (genome-wide CNV map)
Type	Supervised/unsupervised machine learning pipeline for genomic structural variant detection	Genomic structural variant detection pipeline
Source fondatrice	Aganezov, S., Goodwin, S., Sherman, R. M., Sedlazeck, F. J., Mehta, G., Rushbrook, S., ... & Schatz, M. C. (2020). Comprehensive analysis of structural variants in breast cancer genomes using single-molecule sequencing. Genome Research, 30(9), 1258-1273.	Redon, R., Ishikawa, S., Fitch, K. R., et al. (2006). Global variation in copy number in the human genome. Nature, 444(7118), 444–454.
Alias	ML-CNV analysis, ML-based CNV calling, machine learning CNV detection, deep learning CNV analysis	CNV analysis, copy number variant detection, CNV calling, somatic copy number alteration analysis
Apparentées	6	6
Résumé	Machine learning-assisted CNV analysis applies supervised, unsupervised, or deep learning algorithms to detect genomic regions that are duplicated or deleted relative to a reference genome. Rather than relying on fixed statistical thresholds, ML models learn discriminative patterns from read-depth signals, allele frequencies, and other features, substantially improving sensitivity and specificity over classical tools — especially in noisy or low-coverage sequencing data.	Copy number variation (CNV) analysis is a genomic pipeline for detecting regions where individuals carry fewer or more copies of a DNA segment than the reference genome. CNVs span kilobases to megabases and are a major class of structural variation implicated in cancer, neurodevelopmental disorders, and population diversity. The pipeline typically processes SNP array intensities or read-depth signals from whole-genome sequencing, applies segmentation algorithms, calls gain and loss events, and annotates them against gene and clinical databases.