Aminu Muhammad, Zhu Bo, Vokes Natalie, Chen Hong, Hong Lingzhi, Li Jianrong, Fujimoto Junya, Yang Yuqui, Wang Tao, Wang Bo, Poteete Alissa, Nilsson Monique B, Le Xiuning, Tina Cascone, Jaffray David, Navin Nick, Byers Lauren A, Gibbons Don, Heymach John, Chen Ken, Cheng Chao, Zhang Jianjun, Wu Jia
Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA.
These authors contributed equally: Muhammad Aminu, Bo Zhu, Natalie Vokes.
Res Sq. 2024 May 20:rs.3.rs-4359834. doi: 10.21203/rs.3.rs-4359834/v1.
Traditional feature dimension reduction methods have been widely used to uncover biological patterns or structures within individual spatial transcriptomics data. However, these methods are designed to yield feature representations that emphasize patterns or structures with dominant high variance, such as the normal tissue spatial pattern in a precancer setting. Consequently, they may inadvertently overlook patterns of interest that are potentially masked by these high-variance structures. Herein we present our graph contrastive feature representation method called CoCo-ST (Comparing and Contrasting Spatial Transcriptomics) to overcome this limitation. By incorporating a background data set representing normal tissue, this approach enhances the identification of interesting patterns in a target data set representing precancerous tissue. Simultaneously, it mitigates the influence of dominant common patterns shared by the background and target data sets. This enables discerning biologically relevant features crucial for capturing tissue-specific patterns, a capability we showcased through the analysis of serial mouse precancerous lung tissue samples.
传统的特征降维方法已被广泛用于揭示单个空间转录组学数据中的生物学模式或结构。然而，这些方法旨在生成强调具有主导高方差的模式或结构的特征表示，例如癌前环境中的正常组织空间模式。因此，它们可能会无意中忽略那些可能被这些高方差结构掩盖的感兴趣的模式。在此，我们提出了一种名为CoCo-ST（比较和对比空间转录组学）的图对比特征表示方法来克服这一限制。通过纳入代表正常组织的背景数据集，该方法增强了在代表癌前组织的目标数据集中对感兴趣模式的识别。同时，它减轻了背景和目标数据集共享的主导共同模式的影响。这使得能够辨别对于捕获组织特异性模式至关重要的生物学相关特征，我们通过对系列小鼠癌前肺组织样本的分析展示了这一能力。
