Embed and annotate single-cell expression data with the scGPT foundation model.
npx skills add https://github.com/PKU-YuanGroup/OpenAI4S --skill scgpt-pku-yuangroup
Please help me install this Agent Skill. Skill: scgpt Source: https://github.com/PKU-YuanGroup/OpenAI4S/tree/main/skills/scgpt Command: npx skills add https://github.com/PKU-YuanGroup/OpenAI4S --skill scgpt-pku-yuangroup
scgpt helps users embed and annotate single-cell expression data using a foundation model for single-cell biology, streamlining data analysis and cell type annotation.
Use the scgpt skill to embed data from 'dataset.h5ad' and produce embeddings.
High-intent search queries and answers about installing and using this skill.
To annotate cell types in single-cell RNA sequencing data, you can use the scGPT foundation model to apply zero-shot or fine-tuned cell-type annotation directly to your AnnData objects.
To generate embeddings for single-cell expression data, you process your AnnData files through the scGPT foundation model to produce representations suitable for clustering and data integration.
Single-cell data annotation with scGPT requires access to a CUDA-capable GPU for processing. This hardware is necessary to run the scGPT foundation model for embedding and annotation tasks.
You can extract gene-level representations for perturbation and GRN tasks from AnnData using the scGPT foundation model. This provides specific gene representations suited for downstream single-cell biology analysis.
The best way to cluster single-cell data using a foundation model is to generate embeddings from your dataset.h5ad file using scGPT. These embeddings can then be used directly for clustering and integration.
jackspaceManage annotated data matrices with AnnData for single-cell genomics analysis.
nahisahoIntegrates multi-batch scRNA-seq data using scVI-tools to produce unified latent representations and annotations.
tassiovaleStandardize single-cell RNA-seq workflows with Scanpy for QC, clustering, and annotation.
StarlitnightlyGenerate cell embeddings and annotate single-cell data using 22 foundation models via omicverse's unified API.
