Kovacheva Violeta N, Rajpoot Nasir M
Department of Systems Biology, University of Warwick, Coventry, CV4 7AL, UK.
Department of Computer Science, University of Warwick, Coventry, CV4 7AL, UK.
BMC Bioinformatics. 2016 Oct 22;17(1):430. doi: 10.1186/s12859-016-1243-y.
New bioimaging techniques capable of visualising the co-location of numerous proteins within individual cells have been proposed to study tumour heterogeneity of neighbouring cells within the same tissue specimen. These techniques have highlighted the need to better understand the interplay between proteins in terms of their colocalisation.
We recently proposed a cellular-level model of the healthy and cancerous colonic crypt microenvironments. Here, we extend the model to include detailed models of protein expression to generate synthetic multiplex fluorescence data. As a first step, we present models for various cell organelles learned from real immunofluorescence data from the Human Protein Atlas. Comparison between the distribution of various features obtained from the real and synthetic organelles has shown very good agreement. This has included both features that have been used as part of the model input and ones that have not been explicitly considered. We then develop models for six proteins which are important colorectal cancer biomarkers and are associated with microsatellite instability, namely MLH1, PMS2, MSH2, MSH6, P53 and PTEN. The protein models include their complex expression patterns and which cell phenotypes express them. The models have been validated by comparing distributions of real and synthesised parameters and by application of frameworks for analysing multiplex immunofluorescence image data.
The six proteins have been chosen as a case study to illustrate how the model can be used to generate synthetic multiplex immunofluorescence data. Further proteins could be included within the model in a similar manner to enable the study of a larger set of proteins of interest and their interactions. To the best of our knowledge, this is the first model for expression of multiple proteins in anatomically intact tissue, rather than within cells in culture.
能够可视化单个细胞内多种蛋白质共定位的新型生物成像技术已被提出，用于研究同一组织标本中相邻细胞的肿瘤异质性。这些技术凸显了从蛋白质共定位角度更好地理解蛋白质间相互作用的必要性。
我们最近提出了健康和癌性结肠隐窝微环境的细胞水平模型。在此，我们扩展该模型以纳入蛋白质表达的详细模型，从而生成合成多重荧光数据。第一步，我们展示了从人类蛋白质图谱的真实免疫荧光数据中学习到的各种细胞器模型。从真实细胞器和合成细胞器获得的各种特征分布之间的比较显示出非常好的一致性。这既包括作为模型输入一部分使用的特征，也包括未明确考虑的特征。然后，我们针对六种作为重要结直肠癌生物标志物且与微卫星不稳定性相关的蛋白质开发模型，即错配修复蛋白1（MLH1）、错配修复蛋白2（PMS2）、错配修复蛋白3（MSH2）、错配修复蛋白6（MSH6）、抑癌基因P53和抑癌基因PTEN。蛋白质模型包括它们复杂的表达模式以及哪些细胞表型表达它们。通过比较真实参数和合成参数的分布以及应用分析多重免疫荧光图像数据的框架，对模型进行了验证。
选择这六种蛋白质作为案例研究，以说明该模型如何用于生成合成多重免疫荧光数据。可以以类似方式在模型中纳入更多蛋白质，以便研究更大范围的感兴趣蛋白质及其相互作用。据我们所知，这是第一个用于解剖学完整组织而非培养细胞中多种蛋白质表达的模型。
