本文介绍如何构建一套文本聚类流水线，将大语言模型嵌入与基于密度的聚类算法 HDBSCAN 相结合，在无标注文本数据中自动发现主题。 当前的生成式 AI热潮，表面上似乎主要集中在聊天界面与提示词工程，但大语言模型（LLM）的实际应用范围远不止于此。

Uniform Manifold Approximation and Projection (UMAP) is a dimension reduction technique that can be used for visualisation similarly to t-SNE, but also for general non-linear dimension reduction. The ...

Abstract: Dimensionality reduction methods are employed to decrease data dimensionality, either to enhance machine learning performance or to facilitate data visualization in two or three-dimensional ...

This Python program provides a comprehensive pipeline for processing ANNOVAR files, converting them into AnnData format, and generating UMAP visualizations along with various summary reports based on ...

Distortions from traditional dimensionality reduction methods obscure relationships in high-dimensional single-cell data, thus impeding biological insights. We introduce DTNE (diffusive topology ...

To understand the importance of eIF4F components, we employed computational methods on large public datasets to investigate the impact of positive selection on eIF4F dysregulation in cancer. By ...

Enteric methane from cow burps, which results from microbial fermentation of high-fiber feed in the rumen, is a significant contributor to greenhouse gas emissions. A promising strategy to address ...

Astrocytes are important regulators of blood flow and play a key role in the response to injury and disease in the central nervous system (CNS). Despite having an understanding that structural changes ...

Reduced-dimension or spatial in situ scatter plots are widely employed in bioinformatics papers analyzing single-cell data to present phenomena or cell-conditions of interest in cell groups. When ...