本文關(guān)鍵詞： GBM 生存模型 LASSO SPCA SSLC算法　出處：《西南大學(xué)學(xué)報(自然科學(xué)版)》2017年10期 　論文類型：期刊論文

【摘要】：多形性膠質(zhì)母細(xì)胞瘤(GBM)是一種最常見且致死率極高的腦部腫瘤.為了解決傳統(tǒng)生存模型不能處理變量p遠(yuǎn)大于樣本數(shù)n的基因表達數(shù)據(jù)的缺點,本文構(gòu)建了一個關(guān)鍵基因篩選算法——SSLC算法.該算法結(jié)合限制性優(yōu)化算法和生存模型篩選出了與生存時間相關(guān)的GBM關(guān)鍵基因,并通過比較證明了此算法優(yōu)于傳統(tǒng)經(jīng)典算法,最后通過文獻查找證明篩選出的部分基因是已經(jīng)證實的和GBM高度相關(guān)的基因,為GBM的靶向制藥打下基礎(chǔ).
[Abstract]:Glioblastoma pleomorphic (GBM) is one of the most common and highly lethal brain tumors. In order to solve the traditional survival model can not deal with the variables p is far larger than the number of samples n gene expression data shortcomings. In this paper, a key gene screening algorithm, SSLC algorithm, is constructed, which combines the restrictive optimization algorithm and the survival model to screen the key genes related to the survival time of GBM. It is proved by comparison that this algorithm is superior to the traditional classical algorithm. Finally, it is proved by literature search that the selected genes are highly related to GBM, which lays the foundation for the targeted pharmaceutical of GBM.
【作者單位】： 西南大學(xué)經(jīng)濟管理學(xué)院;西南大學(xué)數(shù)學(xué)與統(tǒng)計學(xué)院;
【基金】：國家自然科學(xué)基金項目(20130695)
【分類號】：R739.41
【正文快照】： 癌癥是一大類疾病的總稱,其共同點是失去控制的細(xì)胞增殖.在眾多的癌癥疾病中,多形性膠質(zhì)母細(xì)胞瘤(GBM)是一種神經(jīng)膠質(zhì)瘤,是最常見且致死率極高的腦部腫瘤,這種腦瘤具有高侵潤性,可大范圍轉(zhuǎn)移.同時,該腫瘤細(xì)胞對放療不甚敏感,非常容易復(fù)發(fā).據(jù)文獻報道神經(jīng)膠質(zhì)瘤的中位生存時間，

本文編號：1444304