Heuristic principal component analysis-based unsupervised feature extraction applied to gene expression analysis of amyotrophic lateral sclerosis data sets

• Item type: SIG Technical Reports(1)
• 公開日: 2015-09-05
• タイトル: Heuristic principal component analysis-based unsupervised feature extraction applied to gene expression analysis of amyotrophic lateral sclerosis data sets
• タイトル / 言語: en
• タイトル: Heuristic principal component analysis-based unsupervised feature extraction applied to gene expression analysis of amyotrophic lateral sclerosis data sets
• 言語: eng
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_18gh
• 資源タイプ: technical report
• 著者所属: Department of Physics, Chuo University
• 著者所属: Department of Biological Science, Chuo University
• 著者所属: Department of Biological Science, Chuo University
• 著者所属(英): en
• 著者所属(英): Department of Physics, Chuo University
• 著者所属(英): en
• 著者所属(英): Department of Biological Science, Chuo University
• 著者所属(英): en
• 著者所属(英): Department of Biological Science, Chuo University
• 著者名: Y-H., Taguchi; Mitsuo, Iwadate; Hideaki, Umeyama
• 著者名(英): Y-H., Taguchi; Mitsuo, Iwadate; Hideaki, Umeyama
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: We applied principal component analysis (PCA)-based unsupervised feature extraction (FE) to amyotrophic lateral sclerosis (ALS) gene expression profiles. ALS is a debilitating neurodegenerative disorder with no effective therapy. The relevant gene expression profiles contained a small number of samples (from a few to tens) with a large number of features (several tens of thousands). Although it is important to recognize critical genes from gene expression profiles, a small-sample-large-feature situation makes FE difficult. In PCA-based unsupervised FE, features rather than samples are embedded into a low dimensional space, and critical genes are identified as outliers that are supposed to obey group-oriented behavior. The 29 candidate genes identified as critical for ALS by this methodology turned out to be biologically feasible based on comparisons with numerous previous studies. Together, they formed a collected gene regulation/protein binding network within which the known, but not explicitly identified in this study, three ALS-causing genes, SOD1, TDP-43, and SETX, could be naturally placed/embedded. Among the 29 genes, the translated chemokine receptor CCR6 protein was considered to be a potential therapy target and its antagonists/agonists were identified using the in silico drug discovery software ChooseLD. The ten top-ranked antagonists/agonists shared structures with many compounds that were previously known to bind to various proteins [This paper is the digest version of a conference paper [1]. For more details, see the conference paper version].
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: We applied principal component analysis (PCA)-based unsupervised feature extraction (FE) to amyotrophic lateral sclerosis (ALS) gene expression profiles. ALS is a debilitating neurodegenerative disorder with no effective therapy. The relevant gene expression profiles contained a small number of samples (from a few to tens) with a large number of features (several tens of thousands). Although it is important to recognize critical genes from gene expression profiles, a small-sample-large-feature situation makes FE difficult. In PCA-based unsupervised FE, features rather than samples are embedded into a low dimensional space, and critical genes are identified as outliers that are supposed to obey group-oriented behavior. The 29 candidate genes identified as critical for ALS by this methodology turned out to be biologically feasible based on comparisons with numerous previous studies. Together, they formed a collected gene regulation/protein binding network within which the known, but not explicitly identified in this study, three ALS-causing genes, SOD1, TDP-43, and SETX, could be naturally placed/embedded. Among the 29 genes, the translated chemokine receptor CCR6 protein was considered to be a potential therapy target and its antagonists/agonists were identified using the in silico drug discovery software ChooseLD. The ten top-ranked antagonists/agonists shared structures with many compounds that were previously known to bind to various proteins [This paper is the digest version of a conference paper [1]. For more details, see the conference paper version].
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AA12055912
• 書誌情報: 研究報告バイオ情報学（BIO）; 巻 2015-BIO-43, 号 6, p. 1-6, 発行日 2015-09-05
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 2188-8590
• Notice: SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc.
• 出版者 / 言語: ja
• 出版者: 情報処理学会