A noise-robust deep clustering of biomolecular ions improves interpretability of mass spectrometric images.
A noise-robust deep clustering of biomolecular ions improves interpretability of mass spectrometric images.
复制标题
DOI：
10.1093/bioinformatics/btad067
复制
发表时间：
2023-02-03
期刊：
影响因子：
--
通讯作者：
中科院分区：
文献类型：
--
作者：
质谱成像（MSI）分析复杂的生物样品，如组织。它同时以质谱的形式表征组织中存在的离子，并以离子图像的形式表征离子在组织中的空间分布。离子图像的无监督聚类通过识别具有相似空间分布的离子组来促进谱域中的解释。不幸的是，许多用于聚类离子图像的当前方法忽略了图像的空间特征，并且因此不能学习这些特征以用于聚类目的。替代方法使用在自然图像任务上预先训练的深度神经网络来提取空间特征;然而，这通常是不够的，因为离子图像比自然图像噪声大得多。我们贡献了一个深聚类方法的离子图像，占空间背景特征和噪声。在对模拟数据集和不同组织类型的四个实验数据集的评估中，所提出的方法比现有方法更频繁地将来自同一源的离子分组到同一簇中。我们进一步证明，使用离子图像聚类作为预处理步骤，与使用所有离子或一次一个离子相比，有助于解释随后的空间分割。因此，所提出的方法促进了MSI数据在光谱域和空间域的可解释性。数据和代码可在https://github.com/DanGuo1223/mzClustering上获得。补充数据可在Bioinformatics在线获得。
Mass Spectrometry Imaging (MSI) analyzes complex biological samples such as tissues. It simultaneously characterizes the ions present in the tissue in the form of mass spectra, and the spatial distribution of the ions across the tissue in the form of ion images. Unsupervised clustering of ion images facilitates the interpretation in the spectral domain, by identifying groups of ions with similar spatial distributions. Unfortunately, many current methods for clustering ion images ignore the spatial features of the images, and are therefore unable to learn these features for clustering purposes. Alternative methods extract spatial features using deep neural networks pre-trained on natural image tasks; however, this is often inadequate since ion images are substantially noisier than natural images. We contribute a deep clustering approach for ion images that accounts for both spatial contextual features and noise. In evaluations on a simulated dataset and on four experimental datasets of different tissue types, the proposed method grouped ions from the same source into a same cluster more frequently than existing methods. We further demonstrated that using ion image clustering as a pre-processing step facilitated the interpretation of a subsequent spatial segmentation as compared to using either all the ions or one ion at a time. As a result, the proposed approach facilitated the interpretability of MSI data in both the spectral domain and the spatial domain. The data and code are available at https://github.com/DanGuo1223/mzClustering. Supplementary data are available at Bioinformatics online.
登录
查看更多内容
影响因子：
7.4
作者：
Hu H;Yin R;Brown HM;Laskin J
通讯作者：
Laskin J
影响因子：
3.8
作者：
通讯作者：
--
影响因子：
7.4
作者：
Race, Alan M.;Steven, Rory T.;Bunch, Josephine
通讯作者：
Bunch, Josephine
咖啡酸基质通过基质辅助激光解吸/电离质谱成像改善组织中分子量接近 200,000 Da 的蛋白质的原位检测和成像。
影响因子：
7.4
作者：
Liu，Haiqiang;Han，Manman;Wang，Xiaodong
通讯作者：
Wang，Xiaodong
影响因子：
4.4
作者：
Alexandrov, Theodore;Becker, Michael;Maass, Peter
通讯作者：
Maass, Peter