Multi-cancer samples clustering via graph regularized low-rank representation method under sparse and symmetric constraints

Table 2 The distribution of the six datasets

Datasets	The number of samples of each type of cancer	Total number of samples	subspace number
CO-CH	262–36	298	2
PA-ES	176–183	359	2
CH-HN-CO	36–398-262	696	3
ES-CH-HN	183–36-398	617	3
CO-CH-ES-HN	262–36–183-398	879	4
ES-CO-PA-HN	183–262–176-398	1019	4

Note: The datasets represent different integrated datasets. The characteristics of each dataset are described in the previous passage

ISSN: 1471-2105