Ovarian cancer identification based on dimensionality reduction for high-throughput mass spectrometry data

• Published in: Bioinformatics 2005-05, Vol.21 (10), p.2200-2209
• Main Authors: Yu, J. S., Ongarello, S., Fiedler, R., Chen, X. W., Toffolo, G., Cobelli, C., Trajanoski, Z.
• Format: Article
• Language: English
• Subjects: Algorithms; Artificial Intelligence; Biological and medical sciences; Biomarkers, Tumor - analysis; Diagnosis, Computer-Assisted - methods; Female; Fundamental and applied biological sciences. Psychology; Gene Expression Profiling - methods; General aspects; Humans; Mathematics in biology. Statistical analysis. Models. Metrology. Data processing in biology (general aspects); Neoplasm Proteins - analysis; Ovarian cancer; Ovarian Neoplasms - classification; Ovarian Neoplasms - diagnosis; Ovarian Neoplasms - metabolism; Reproducibility of Results; Sensitivity and Specificity; Software; Spectrometry, Mass, Matrix-Assisted Laser Desorption-Ionization - methods
• ISSN: 1367-4803; 1460-2059; 1367-4811
• DOI: 10.1093/bioinformatics/bti370

Motivation: High-throughput and high-resolution mass spectrometry instruments are increasingly used for disease classification and therapeutic guidance. However, the analysis of immense amount of data poses considerable challenges. We have therefore developed a novel method for dimensionality reduction and tested on a published ovarian high-resolution SELDI-TOF dataset. Results: We have developed a four-step strategy for data preprocessing based on: (1) binning, (2) Kolmogorov–Smirnov test, (3) restriction of coefficient of variation and (4) wavelet analysis. Subsequently, support vector machines were used for classification. The developed method achieves an average sensitivity of 97.38% (sd = 0.0125) and an average specificity of 93.30% (sd = 0.0174) in 1000 independent k-fold cross-validations, where k = 2, …, 10. Availability: The software is available for academic and non-commercial institutions. Contact: [e-mail]