摘要
由一名新闻记者-机器人与机器学习的工作人员新闻编辑每日新闻-生物技术的新研究-生物信息学是一篇报道的主题。根据NewsRx编辑在泰国Khon Kae N的新闻报道，研究表明：“肾细胞癌(RCC)，占所有肾癌的90%，根据Cu rent NCN指南，分为透明细胞RCC(ccRCC)和非透明细胞RCC(non-ccRCC)进行治疗。因此，分类将与治疗意义相关。”这项研究的财政支持来自Khon Kaen大学。本研究旨在利用生物信息学和机器学习技术，从TCGA中获得CRCC和非CRCC亚型（包括乳头状RCC(pRCC)和嫌色细胞RCC(chRCC)）的基因表达谱，并鉴定出差异表达基因(DEGs)。利用Venn图对CRCC和非CRCC的特异性DEG进行基因本体分析和路径富集分析,选取CRCC中表达最多的前10个基因进行机器学习分析,通过特征选择确定最小的高效基因集来构建预测模型,并利用DAV ID对最优基因集的表达进行验证。免疫组织化学技术，随后利用H-评分建立了诊断肾癌的机器学习模型，在CRCC、pRCC和chRCC中分别有910、415和835个DEG显著特异性基因，CRCC中特异性DEG丰富于免疫系统中的PD-1信号、免疫系统和细胞因子信号，而TCA循环和呼吸信号、胰岛素受体信号。基于决策树分类的特征选择模型准确率为98.89%,基于H值NDUFA4L2和DAT的监督分类模型准确率为82%,AUC为0.9. NDUFA4L2表达与淋巴血管浸润有关。"ccRCC病理分期及pT分期."
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Biotechnology-Bioinf ormatics is the subject of a report. According to news reporting out of Khon Kae n, Thailand, by NewsRx editors, research stated, "Renal cell carcinoma (RCC), ac counting for 90% of all kidney cancer, is categorized into clear c ell RCC (ccRCC) and non-clear cell RCC (non-ccRCC) for treatment based on the cu rrent NCCN Guidelines. Thus, the classification will be associated with therapeu tic implications." Financial support for this research came from Khon Kaen University. Our news journalists obtained a quote from the research from Khon Kaen Universit y, "This study aims to identify novel biomarkers to differentiate ccRCC from non -ccRCC using bioinformatics and machine learning. The gene expression profiles o f ccRCC and non-ccRCC subtypes (including papillary RCC (pRCC) and chromophobe R CC (chRCC)), were obtained from TCGA. Differential expression genes (DEGs) were identified, and specific DEGs for ccRCC and non-ccRCC were explored using a Venn diagram. Gene Ontology and pathway enrichment analysis were performed using DAV ID. The top ten expressed genes in ccRCC were then selected for machine learning analysis. Feature selection was operated to identify a minimum highly effective gene set for constructing a predictive model. The expression of best-performing gene set was validated on tissue samples from RCC patients using immunohistoche mistry techniques. Subsequently, machine learning models for diagnosing RCC were developed using H-scores. There were 910, 415, and 835 genes significantly spec ific for DEGs in ccRCC, pRCC, and chRCC, respectively. Specific DEGs in ccRCC en riched in PD-1 signaling, immune system, and cytokine signaling in the immune sy stem, whereas TCA cycle and respiratory, signaling by insulin receptor, and meta bolism were enriched in chRCC. Feature selection based on Decision Tree Classifi er revealed that the model with two genes, including NDUFA4L2 and DAT, had an ac curacy of 98.89%. Supervised classification models based on H-score of NDUFA4L2, and DAT revealed that Decision Tree models showed the best perform ance with 82 % accuracy and 0.9 AUC. NDUFA4L2 expression was associ ated with lymphovascular invasion, pathologic stage and pT stage in ccRCC."
NETL
NSTL