Research Article

Classification of Cancer Primary Sites Using Machine Learning and Somatic Mutations

Table 5

Summary of genes and samples used in the primary tumor site prediction.

Primary tumor siteNumber of genesNumber of true positives

Large intestine18,066555
Liver19,778287
Skin10,898113
Pancreas3,364170
Lung18,423724
Endometrium18,234137
Kidney10,601302
Haematopoietic and lymphoid tissue14,545723
Breast6,327486
Central nervous system2,773192
Ovary8,169238
Prostate5,875132
Autonomic ganglia1,42562
Oesophagus6,20034
Urinary tract3,28810
Upper aerodigestive tract1,0135
Stomach863