慢动作人：一款用于在二维嵌入中沿着用户绘制的轨迹发现重要特征的网络应用程序。
SlowMoMan: a web app for discovery of important features along user-drawn trajectories in 2D embeddings.
作者信息
Deol Kiran, Weber Griffin M, Yu Yun William
机构信息
Department of Computer Science, University of Alberta, Edmonton, Alberta T6G 2R3, Canada.
Department of Biomedical Informatics, Harvard Medical School, Boston, MA 02115, United States.
出版信息
Bioinform Adv. 2024 Jun 21;4(1):vbae095. doi: 10.1093/bioadv/vbae095. eCollection 2024.
MOTIVATION
Nonlinear low-dimensional embeddings allow humans to visualize high-dimensional data, as is often seen in bioinformatics, where datasets may have tens of thousands of dimensions. However, relating the axes of a nonlinear embedding to the original dimensions is a nontrivial problem. In particular, humans may identify patterns or interesting subsections in the embedding, but cannot easily identify what those patterns correspond to in the original data.
RESULTS
Thus, we present SlowMoMan (SLOW Motions on MANifolds), a web application which allows the user to draw a one-dimensional path onto a 2D embedding. Then, by back-projecting the manifold to the original, high-dimensional space, we sort the original features such that those most discriminative along the manifold are ranked highly. We show a number of pertinent use cases for our tool, including trajectory inference, spatial transcriptomics, and automatic cell classification.
AVAILABILITY AND IMPLEMENTATION
Software: https://yunwilliamyu.github.io/SlowMoMan/; Code: https://github.com/yunwilliamyu/SlowMoMan.
动机
非线性低维嵌入使人类能够可视化高维数据，这在生物信息学中经常出现，其中数据集可能有成千上万的维度。然而，将非线性嵌入的轴与原始维度相关联是一个不平凡的问题。特别是，人类可能会在嵌入中识别出模式或有趣的子部分，但无法轻易识别这些模式在原始数据中对应的是什么。
结果
因此，我们展示了SlowMoMan（流形上的慢动作），这是一个网络应用程序，允许用户在二维嵌入上绘制一维路径。然后，通过将流形反向投影到原始高维空间，我们对原始特征进行排序，使得那些在流形上最具区分性的特征排名靠前。我们展示了我们工具的一些相关用例，包括轨迹推断、空间转录组学和自动细胞分类。
可用性和实现
软件：https://yunwilliamyu.github.io/SlowMoMan/；代码：https://github.com/yunwilliamyu/SlowMoMan。
Zotero 插件