A Gene Selection Method Based on Outliers for Breast Cancer Subtype Classification

Autor(es)

Mendonca-Neto, Rayol ; Li, Zhi ; Fenyo, David ; Silva, Claudio T. ; Nakamura, Fabiola G. ; Nakamura, Eduardo F.

• Tipo de documento: Artigo Científico
• Fonte: IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS; v. 19, n. 5, p. 13-pg., 2022-09-01.

Resumo

Breast cancer is the second most common cancer type and is the leading cause of cancer-related deaths worldwide. Since it is a heterogeneous disease, subtyping breast cancer plays an important role in performing a specific treatment. Gene expression data is a viable alternative to be employed on cancer subtype classification, as they represent the state of a cell at the molecular level, but generally has a relatively small number of samples compared to a large number of genes. Gene selection is a promising approach that addresses this uneven high-dimensional matrix of genes versus samples and plays an important role in the development of efficient cancer subtype classification. In this work, an innovative outlier-based gene selection (OGS) method is proposed to select relevant genes for efficiently and effectively classify breast cancer subtypes. Experiments show that our strategy presents an F-1 score of 1.0 for basal and 0.86 for her 2, the two subtypes with the worst prognoses, respectively. Compared to other methods, our proposed method outperforms in the F-1 score using 80% less genes. In general, our method selects only a few highly relevant genes, speeding up the classification, and significantly improving the classifier's performance. (AU)

• Processo FAPESP: 20/05173-4 - Uma abordagem multimodal para identificar viés em mídias sociais digitais
• Beneficiário: Altigran Soares da Silva
• Modalidade de apoio: Auxílio à Pesquisa - Regular
• Processo FAPESP: 20/09866-4 - Centro de Inovação em Inteligência Artificial para a Saúde (CIIA-Saúde)
• Beneficiário: Virgilio Augusto Fernandes Almeida
• Modalidade de apoio: Auxílio à Pesquisa - Programa Centros de Pesquisa Aplicada