OBJECTIVES: To identify novel serum protein biomarkers and establish diagnostic pattern for rheumatoid arthritis (RA) by using proteomic technology. METHODS: Serum proteomic spectra were generated by matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF-MS) combined with weak cationic exchange magnetic beads. A training set of spectra, derived from analyzing sera from 22 patients with RA, 26 patients with other autoimmune diseases and 25 age- and sex-matched healthy volunteers, was used to train and develop a decision tree model with a machine learning algorithm called decision boosting. A blinded testing set, including 21 patients with RA, 24 patients with other autoimmune diseases and 25 healthy people, was used to examine the accuracy of the model. RESULTS: A decision tree model was established, consisting of four potential protein biomarkers whose m/z values were 4966.88, 5065.3, 5636.97 and 7766.87, respectively. In validation test, the decision tree model could differentiate RA from other autoimmune diseases and healthy people with the sensitivity of 85.71% and specificity of 87.76%, respectively. CONCLUSIONS: The present data suggested that MALDI-TOF-MS combined with magnetic beads could screen and identify some novel serum protein biomarkers related to RA. The proteomic pattern based on the four candidate biomarkers is of value for laboratory diagnosis of RA.
OBJECTIVES: To identify novel serum protein biomarkers and establish diagnostic pattern for rheumatoid arthritis (RA) by using proteomic technology. METHODS: Serum proteomic spectra were generated by matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF-MS) combined with weak cationic exchange magnetic beads. A training set of spectra, derived from analyzing sera from 22 patients with RA, 26 patients with other autoimmune diseases and 25 age- and sex-matched healthy volunteers, was used to train and develop a decision tree model with a machine learning algorithm called decision boosting. A blinded testing set, including 21 patients with RA, 24 patients with other autoimmune diseases and 25 healthy people, was used to examine the accuracy of the model. RESULTS: A decision tree model was established, consisting of four potential protein biomarkers whose m/z values were 4966.88, 5065.3, 5636.97 and 7766.87, respectively. In validation test, the decision tree model could differentiate RA from other autoimmune diseases and healthy people with the sensitivity of 85.71% and specificity of 87.76%, respectively. CONCLUSIONS: The present data suggested that MALDI-TOF-MS combined with magnetic beads could screen and identify some novel serum protein biomarkers related to RA. The proteomic pattern based on the four candidate biomarkers is of value for laboratory diagnosis of RA.
Authors: Benjamin A Neely; Jennifer L Soper; Denise J Greig; Kevin P Carlin; Elizabeth G Favre; Frances Md Gulland; Jonas S Almeida; Michael G Janech Journal: Proteome Sci Date: 2012-03-19 Impact factor: 2.480
Authors: Thong Huy Cao; Donald J L Jones; Paulene A Quinn; Daniel Chu Siong Chan; Narayan Hafid; Helen M Parry; Mohapradeep Mohan; Jatinderpal K Sandhu; Stefan D Anker; John G Cleland; Kenneth Dickstein; Gerasimos Filippatos; Hans L Hillege; Marco Metra; Piotr Ponikowski; Nilesh J Samani; Dirk J Van Veldhuisen; Faiez Zannad; Aeilko H Zwinderman; Adriaan A Voors; Chim C Lang; Leong L Ng Journal: Clin Proteomics Date: 2018-11-02 Impact factor: 3.988