Bioinformatical evaluation of modified nucleosides as biomedical markers in diagnosis of breast cancer

• Published in: Analytica chimica acta 2008-06, Vol.618 (1), p.29-34
• Main Authors: Bullinger, Dino, Fröhlich, Holger, Klaus, Fabian, Neubauer, Hans, Frickenschmidt, Antje, Henneges, Carsten, Zell, Andreas, Laufer, Stefan, Gleiter, Christoph H., Liebich, Hartmut, Kammerer, Bernd
• Format: Article
• Language: English
• Subjects: Adolescent; Adult; Aged; Aged, 80 and over; Analytical chemistry; Biological and medical sciences; Biomarkers, Tumor - chemistry; Biomarkers, Tumor - urine; Breast cancer; Breast Neoplasms - diagnosis; Chemistry; Chromatographic methods and physical methods associated with chromatography; Chromatography, High Pressure Liquid - instrumentation; Chromatography, High Pressure Liquid - methods; Computational Biology - methods; Exact sciences and technology; Female; Gynecology. Andrology. Obstetrics; High performance liquid chromatography with ultraviolett detection (HPLC-UV); Humans; k-Nearest-neighbor classifier (k-NN); Mammary gland diseases; Medical sciences; Metabolomics; Middle Aged; Molecular Conformation; Nucleosides; Nucleosides - chemistry; Nucleosides - urine; Other chromatographic methods; Reproducibility of Results; Sensitivity and Specificity; Stereoisomerism; Support Vector Machine (SVM); Tumors
• ISSN: 0003-2670; 1873-4324
• DOI: 10.1016/j.aca.2008.04.048

It is known that patients suffering from cancer diseases excrete increased amounts of modified nucleosides with their urine. Especially methylated nucleosides have been proposed to be potential tumor markers for early diagnosis of cancer. For determination of nucleosides in randomly collected urine samples, the nucleosides were extracted using affinity chromatography and then analyzed via reversed phase high-performance liquid chromatography (HPLC) with UV-detection. Eleven nucleosides were quantified in urine samples from 51 breast cancer patients and 65 healthy women. The measured concentrations were used to train a Support Vector Machine (SVM) and a k-nearest-neighbor classifier (k-NN) to discriminate between healthy control subjects and patients suffering from breast cancer. Evaluations of the learned models by computing the leave-one-out error and the prediction error on an independent test set of 29 subjects (15 healthy, 14 breast cancer patients) showed that by using the eleven nucleosides, the occurrence of breast cancer could be forecasted with 86% specificity and 94% sensitivity when using an SVM and 86% for both specificity and sensitivity with the k-NN model.