瘤类型的分类和候选癌症特异性生物标志物的发现通过半监督学习
Peng Chen1, Zhenlei Li1, Zhaolin Hong1
1School of Computer Science and Technology, University of Science and Technology of China, Hefei 230026, China.
Biophysics reports
|September 27, 2023
概括
一个新的深度学习模型,MSSL,通过整合多个数据集,准确地分类瘤类型并发现癌症生物标志物. 这种方法克服了数据的局限性,并提高了各种癌症的诊断和预后能力.
科学领域:
- 基因组学就是基因组学.
- 生物信息学是一种生物信息学.
- 机器学习 机器学习
背景情况:
- 识别与癌症相关的差异表达基因对于诊断,预后和治疗至关重要.
- 深度学习 (DL) 方法在基因差异表达分析方面表现有前途,但在有限的数据和数据异质性方面面临挑战.
- 现有的DL模型与小数据集,不同机构的数据质量不一致以及罕见癌症的代表性不足而扎.
研究的目的:
- 开发一个强大的基于多个数据集的半监督学习 (MSSL) 模型,用于瘤类型分类和癌症特异性生物标志物发现.
- 解决单一数据集方法的局限性,并有效地利用多样化,多机构的基因表达数据集.
- 为了改善DL性能,对于常见和罕见的癌症类型.
主要方法:
- 提出了一种用于多数据集集成的新型半监督学习模型 (MSSL).
- 应用MSSL到癌症基因组图谱 (TCGA) 和基因表达总汇 (GEO) 全癌症规范化RNA-seq数据.
- 利用分类结果对每个癌症类型的基因重要性进行排名.
主要成果:
- 获得了97.6%的最终分类准确度,比以前的方法显著提高了性能.
- 根据基因重要性确定并排列候选癌症特异性生物标志物.
- 验证了顶级基因对各种瘤的生物学意义和潜在生物标志物实用性.
结论:
- MSSL模型为多数据集瘤分类和生物标志物发现提供了强大而有效的方法.
- 这种方法克服了将DL应用于异质和有限的癌症基因组学数据的关键挑战.
- 这些已识别的基因有望成为癌症诊断和预后的临床相关生物标志物.
相关概念视频
lncRNA - Long Non-coding RNAs
8.6K
In humans, more than 80% of the genome gets transcribed. However, only around 2% of the genome codes for proteins. The remaining part produces non-coding RNAs which includes ribosomal RNAs, transfer RNAs, telomerase RNAs, and regulatory RNAs, among other types. A large number of regulatory non-coding RNAs have been classified into two groups depending upon their length – small non-coding RNAs, such as microRNA, which are less than 200 nucleotides in length, and long non-coding RNA...
8.6K
Cancer-Critical Genes II: Tumor Suppressor Genes
7.5K
Genes usually encode proteins necessary for the proper functioning of a healthy cell. Mutations can often cause changes to the gene expression pattern, thereby altering the phenotype.
When the function of certain critical genes, especially those involved in cell cycle regulation and cell growth signaling cascades, gets disrupted, it upsets the cell cycle progression. Such cells with unchecked cell cycles start proliferating uncontrollably and eventually develop into tumors.
Such genes that act...
When the function of certain critical genes, especially those involved in cell cycle regulation and cell growth signaling cascades, gets disrupted, it upsets the cell cycle progression. Such cells with unchecked cell cycles start proliferating uncontrollably and eventually develop into tumors.
Such genes that act...
7.5K
Cancer Survival Analysis
380
Cancer survival analysis focuses on quantifying and interpreting the time from a key starting point, such as diagnosis or the initiation of treatment, to a specific endpoint, such as remission or death. This analysis provides critical insights into treatment effectiveness and factors that influence patient outcomes, helping to shape clinical decisions and guide prognostic evaluations. A cornerstone of oncology research, survival analysis tackles the challenges of skewed, non-normally...
380


