%0 Journal Article
%A Young, Cameron C
%A Eason, Katherine
%A Manzano Garcia, Raquel
%A Moulange, Richard
%A Mukherjee, Sach
%A Chin, Suet-Feung
%A Caldas, Carlos
%A Rueda, Oscar M
%T Development and validation of a reliable DNA copy-number-based machine learning algorithm (CopyClust) for breast cancer integrative cluster classification.
%J Scientific reports
%V 14
%N 1
%@ 2045-2322
%C [London]
%I Macmillan Publishers Limited, part of Springer Nature
%M DZNE-2024-00612
%P 11861
%D 2024
%X The Integrative Cluster subtypes (IntClusts) provide a framework for the classification of breast cancer tumors into 10 distinct groups based on copy number and gene expression, each with unique biological drivers of disease and clinical prognoses. Gene expression data is often lacking, and accurate classification of samples into IntClusts with copy number data alone is essential. Current classification methods achieve low accuracy when gene expression data are absent, warranting the development of new approaches to IntClust classification. Copy number data from 1980 breast cancer samples from METABRIC was used to train multiclass XGBoost machine learning algorithms (CopyClust). A piecewise constant fit was applied to the average copy number profile of each IntClust and unique breakpoints across the 10 profiles were identified and converted into   500 genomic regions used as features for CopyClust. These models consisted of two approaches: a 10-class model with the final IntClust label predicted by a single multiclass model and a 6-class model with binary reclassification in which four pairs of IntClusts were combined for initial multiclass classification. Performance was validated on the TCGA dataset, with copy number data generated from both SNP arrays and WES platforms. CopyClust achieved 81
%K Humans
%K Breast Neoplasms: genetics
%K Breast Neoplasms: classification
%K Machine Learning
%K Female
%K DNA Copy Number Variations: genetics
%K Algorithms
%K Cluster Analysis
%K Gene Expression Profiling: methods
%F PUB:(DE-HGF)16
%9 Journal Article
%$ pmid:38789621
%2 pmc:PMC11126405
%R 10.1038/s41598-024-62724-6
%U https://pub.dzne.de/record/269770