在癌症和转移中对整合素表达模式的基于机器学习的调查
bioRxiv : the preprint server for biology
|October 10, 2024
概括
机器学习揭示了整合素表达模式在各个组织之间存在显著差异,并因癌症而改变. 这些独特的整合素 (细胞粘附分子) 配置文件可以根据组织类型或疾病状况对样品进行分类.
科学领域:
- 分子生物学分子生物学
- 生物信息学是一种生物信息学.
- 癌症研究 癌症研究
背景情况:
- 整合素是细胞粘附和信号传递至关重要的跨膜受体.
- 它们在癌症发展和转移中的作用是复杂的,需要进一步阐明.
- 对转录组数据的机器学习分析提供了一种有前途的方法来理解癌症中的整合素表达模式.
研究的目的:
- 在各种健康组织及其相应的瘤中调查整合素表达模式的变化.
- 应用机器学习技术来识别与不同组织类型和癌症状态相关的关键整合素.
- 分析癌症如何影响整合素联合表达网络,并比较原发性瘤表达与转移性部位.
主要方法:
- 利用公开可用的RNA-Seq数据对8个健康组织和匹配的瘤样本,以及转移性乳腺癌数据.
- 使用t-SNE可视化和随机森林分类来进行整数表达式的机器学习分析.
- 根据组织来源或疾病状况对样本分类至关重要的特定整合素.
主要成果:
- 在组织之间,健康和癌症样本之间,以及转移性疾病中,观察到整合素表达的显著变化.
- 机器学习模型成功地使用整合素表达形状将样本按组织类型和疾病状态分类.
- 确定ITGA7作为分类乳腺癌样本的关键整体蛋白.
- 揭示了癌症重新连接大多数整合蛋白共同表达网络,尽管仍保留了一些关系.
- 与转移相比,在初级乳腺瘤中观察到明显的整合蛋白表达,在肝转移中表达减少.
结论:
- 整蛋白表达模式表现出相当大的组织特异性变异性,并受到癌症的深刻影响.
- 机器学习有效地利用这些整数表达模式进行准确的样本分类.
- 了解癌症中的整合蛋白变化,可以了解疾病进展和潜在的治疗点.
更多相关视频
07:03Discovery of Metastatic Regulators using a Rapid and Quantitative Intravital Chick Chorioallantoic Membrane Model
Published on: February 3, 2021
2.6K
06:27A 3D Spheroid Model as a More Physiological System for Cancer-Associated Fibroblasts Differentiation and Invasion In Vitro Studies
Published on: August 8, 2019
8.8K
相关概念视频
Integrins
3.8K
Animal and protozoan cells do not have cell walls to help maintain shape and provide structural stability. Instead, these eukaryotic cells secrete a sticky mass of carbohydrates and proteins into the spaces between adjacent cells. This network of proteins and molecules is called an extracellular matrix or ECM.
Some ECM proteins assemble into a basement membrane to which the remaining components adhere. Proteoglycans typically form the bulk of the ECM while fibrous proteins, like collagen,...
Some ECM proteins assemble into a basement membrane to which the remaining components adhere. Proteoglycans typically form the bulk of the ECM while fibrous proteins, like collagen,...
3.8K
Activation of Integrins
3.3K
Integrins bind ligands and transmit information from outside the cell to inside or vice-versa through an "outside-in signaling" or "inside-out signaling."
In "outside-in signaling," external factors in the extracellular space bind to exposed ligand binding sites on integrins. This causes the inactive protein to undergo a conformational change to become active. Integrins are often clustered on the cell membrane. Repetitive and regularly spaced ligand binding...
In "outside-in signaling," external factors in the extracellular space bind to exposed ligand binding sites on integrins. This causes the inactive protein to undergo a conformational change to become active. Integrins are often clustered on the cell membrane. Repetitive and regularly spaced ligand binding...
3.3K
Intracellular Signaling Affects Focal Adhesions
2.6K
Integrins act both as extracellular input receivers and as intracellular processing activators. As their name suggests, integrins are entirely integrated into the membrane structure. Their hydrophobic membrane-spanning regions interact with the phospholipid bilayer's hydrophobic region. These membrane receptors provide extracellular attachment sites for effectors like hormones and growth factors. They activate intracellular response cascades when their effectors are bound and active.
Some...
Some...
2.6K
Metastasis
5.5K
Metastasis is the spread of cancer cells from the original site to distant locations in the body. Cancer cells can spread via blood vessels (hematogenous) as well as lymph vessels in the body.
Epithelial-to-Mesenchymal Transition
The epithelial-to-mesenchymal transition or EMT is a developmental process commonly observed in wound healing, embryogenesis, and cancer metastasis. EMT is induced by transforming growth factor-beta (TGF-β) or receptor tyrosine kinase (RTK) ligands, which further...
Epithelial-to-Mesenchymal Transition
The epithelial-to-mesenchymal transition or EMT is a developmental process commonly observed in wound healing, embryogenesis, and cancer metastasis. EMT is induced by transforming growth factor-beta (TGF-β) or receptor tyrosine kinase (RTK) ligands, which further...
5.5K
