[Detecting biomarkers from serum in nephroblastoma patients with support vector machine]

Abstract

Objective: To find new biomarkers and to establish serum protein fingerprint models for early detection and diagnosis of nephroblastoma by SELDI-TOF-MS and bioinformatics tools.

Methods: Seventy five serum samples from 35 nephroblastoma patients, 30 children's abdominal solid tumor patients, and 20 healthy children were bound to WCX2 protein chip and tested by surface enhanced laser desorption/ionization time of flight-mass spectrometry (SELDI-TOF-MS). The data of spectra were analyzed by support vector machine(SVM).

Results: Four peaks with m/z of 6984.5, 6455.5, 6914.0, 3256.7 were selected as potential biomarkers. The detective model combined with 2 biomarkers could separate nephroblastoma from the healthy group with a sensitivity of 100%, and a specificity of 100%. The diagnostic model combined with 2 biomarkers could separate nephroblastoma from other child's abdominal solid tumors with a sensitivity of 93.3%, and a specificity of 100%.

Conclusion: High sensitivity and specificity achieved by this method show great potential for early diagnosis of nephroblastoma, and screening for new tumor biomarkers.