Multiclass Cancer Diagnosis Using Tumor Gene Expression Signatures

• Published in: Proceedings of the National Academy of Sciences - PNAS Vol. 98; no. 26; pp. 15149 - 15154
• Main Authors: Ramaswamy, Sridhar, Tamayo, Pablo, Rifkin, Ryan, Mukherjee, Sayan, Yeang, Chen-Hsiang, Angelo, Michael, Ladd, Christine, Reich, Michael, Latulippe, Eva, Mesirov, Jill P., Poggio, Tomaso, Gerald, William, Loda, Massimo, Lander, Eric S., Golub, Todd R.
• Format: Journal Article
• Language: English
• Published: United States National Academy of Sciences 18-12-2001; National Acad Sciences; National Academy of Sciences, Washington, DC (United States); The National Academy of Sciences
• Subjects: Adenocarcinoma; BASIC BIOLOGICAL SCIENCES; Biological Sciences; Biomarkers, Tumor; Cancer; Cluster Analysis; Datasets; Gene expression; Gene Expression Profiling; Genes; Humans; Hyperplanes; Medical diagnosis; Multigene Family; Neoplasms - classification; Neoplasms - diagnosis; Neoplasms - genetics; Ova; Pathology; Tumors
• ISSN: 0027-8424; 1091-6490
• DOI: 10.1073/pnas.211566398

The optimal treatment of patients with cancer depends on establishing accurate diagnoses by using a complex combination of clinical and histopathological data. In some instances, this task is difficult or impossible because of atypical clinical presentation or histopathology. To determine whether the diagnosis of multiple common adult malignancies could be achieved purely by molecular classification, we subjected 218 tumor samples, spanning 14 common tumor types, and 90 normal tissue samples to oligonucleotide microarray gene expression analysis. The expression levels of 16,063 genes and expressed sequence tags were used to evaluate the accuracy of a multiclass classifier based on a support vector machine algorithm. Overall classification accuracy was 78%, far exceeding the accuracy of random classification (9%). Poorly differentiated cancers resulted in low-confidence predictions and could not be accurately classified according to their tissue of origin, indicating that they are molecularly distinct entities with dramatically different gene expression patterns compared with their well differentiated counterparts. Taken together, these results demonstrate the feasibility of accurate, multiclass molecular cancer classification and suggest a strategy for future clinical implementation of molecular cancer diagnostics.