Premium
Proteomic patterns for classification of ovarian cancer and CTCL serum samples utilizing peak pairs indicative of post‐translational modifications
Author(s) -
Liu Chenwei,
Shea Nancy,
Rucker Sally,
Harvey Linda,
Russo Paul,
Saul Richard,
Lopez Mary F.,
Mikulskis Alvydas,
Kuzdzal Scott,
Golenko Eva,
Fishman David,
Vonderheid Eric,
Booher Susan,
Cowen Edward W.,
Hwang Sam T.,
Whiteley Gordon R.
Publication year - 2007
Publication title -
proteomics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.26
H-Index - 167
eISSN - 1615-9861
pISSN - 1615-9853
DOI - 10.1002/pmic.200601044
Subject(s) - ovarian cancer , cancer , computational biology , biology , posttranslational modification , cancer research , oncology , bioinformatics , medicine , genetics , biochemistry , enzyme
Proteomic patterns as a potential diagnostic technology has been well established for several cancer conditions and other diseases. The use of machine learning techniques such as decision trees, neural networks, genetic algorithms, and other methods has been the basis for pattern determination. Cancer is known to involve signaling pathways that are regulated through PTM of proteins. These modifications are also detectable with high confidence using high‐resolution MS. We generated data using a prOTOF™ mass spectrometer on two sets of patient samples: ovarian cancer and cutaneous t‐cell lymphoma (CTCL) with matched normal samples for each disease. Using the knowledge of mass shifts caused by common modifications, we built models using peak pairs and compared this to a conventional technique using individual peaks. The results for each disease showed that a small number of peak pairs gave classification equal to or better than the conventional technique that used multiple individual peaks. This simple peak picking technique could be used to guide identification of important peak pairs involved in the disease process.