Soft tissue sarcomas (STS) is a set of rare malignant
tumor originated from mesoderm. For the prognosis of
sarcoma, early diagnosis is important, however, currently no mature and non-invasive method for diagnosis exists.
MicroRNAs (
miRNAs) are a class of noncoding RNAs and their expression varies greatly, especially during
tumor activity. The purpose of this study was to construct a predictive model for the diagnosis of
sarcomas based on the relative expression level of
miRNA in serum.
miRNA array expression data of 677 samples including 402 malignant
sarcoma samples and 275 healthy samples was used to construct the prediction model. Based on 6 gene pairs, random generalized linear model (RGLM) was constructed, with an accuracy of 100% in the internal test dataset and of 74.3% in the merged external dataset in prediction whether a serum sample was obtained from a
sarcoma patient, with a specificity of 100% in the internal test dataset and 90.5% in the external dataset. In conclusion, our serum
miRNA-pair classifier has the potential to be used for the screening of
sarcoma with high accuracy and specificity.