Source:

@ARTICLE{Su2001,

author = {A. I. Su and J. B. Welsh and L. M. Sapinoso and S. G. Kern and P. Dimitrov and H. Lapp and P. G. Schultz and S. M. Powell and C. A. Moskaluk and H. F. Frierson and G. M. Hampton},

title = {Molecular classification of human carcinomas by use of gene expression signatures.},

journal = {Cancer Res},

year = {2001},

volume = {61},

pages = {7388--7393},

number = {20},

month = {Oct},

}

Original data: http://public.gnf.org/cancer/epican/

Description:

Classification of human tumors according to their primary anatomical site of origin is fundamental for the optimal treatment of patients with cancer. The authors describe the use of large-scale RNA profiling and supervised machine learning algorithms to construct a first-generation molecular classification scheme for carcinomas of the prostate (PR), breast (BR), lung (LU), ovary (OV), colorectum (CO), kidney (KI), liver (LI), pancreas (PA), bladder/ureter (BL), and gastroesophagus (GA), which collectively account for approximately 70% of all cancer-related deaths in the United States.

• Su: .26 PR, 8 BL, 26 BR, 23 CO, 12 GA, 11 KI, 7 LI, 27 OV, 6 PA and 28 LU.

Parameters used in our filter:

• Su: l=3 and c=22