What modalities are covered by this skill?

It covers a wide range of modalities including scRNA-seq, scATAC-seq, CITE-seq (protein+RNA), multi-omics, spatial transcriptomics, methylation, and flow cytometry.

Does it support GPU acceleration?

Absolutely. The skill provides guidance on utilizing PyTorch Lightning's accelerator settings to enable GPU support, which is highly recommended for large-scale single-cell datasets.

Does this skill work with raw or normalized counts?

scvi-tools models are specifically designed to work with raw, unnormalized counts. This skill follows best practices by ensuring data is registered correctly to leverage the underlying Poisson or Negative Binomial distributions.

How does it integrate with the Scanpy ecosystem?

It is fully AnnData-centric. The skill helps you register AnnData objects, train models, and store latent representations back into the object for seamless downstream analysis with Scanpy.

Can I use this for spatial transcriptomics?

Yes, the skill supports spatial analysis models including DestVI for deconvolution, Stereoscope, and Tangram for mapping single-cell data to spatial locations.

scvi-tools for Single-Cell Analysis

Name: scvi-tools for Single-Cell Analysis
Author: Activer007

byActiver007

データサイエンスとML

Performs probabilistic modeling and deep generative analysis for single-cell omics data using the scvi-tools framework.

概要

scvi-tools provides a comprehensive Python framework for analyzing single-cell genomics data through deep generative models built on PyTorch and PyTorch Lightning. This skill enables Claude to guide users through complex bioinformatics workflows including dimensionality reduction, batch correction, and multimodal data integration for modalities like scRNA-seq, scATAC-seq, and spatial transcriptomics. It automates the implementation of standardized API patterns, ensuring best practices like raw count utilization and proper covariate registration are followed for robust, scalable biological insights.

主な機能

Probabilistic modeling for scRNA-seq and scATAC-seq integration
0 GitHub stars
Standardized API patterns for model training and data registration
Deep generative models for batch correction and dimensionality reduction
Multimodal and spatial transcriptomics analysis (CITE-seq, multiome)
Probabilistic differential expression and cell type annotation

ユースケース

Integrating heterogeneous single-cell datasets from different studies or batches
Analyzing joint single-cell RNA and protein expression with totalVI
Deconvolving spatial transcriptomics data to map cell types to tissue locations

概要

主な機能

Probabilistic modeling for scRNA-seq and scATAC-seq integration
0 GitHub stars
Standardized API patterns for model training and data registration
Deep generative models for batch correction and dimensionality reduction
Multimodal and spatial transcriptomics analysis (CITE-seq, multiome)
Probabilistic differential expression and cell type annotation

ユースケース

Integrating heterogeneous single-cell datasets from different studies or batches
Analyzing joint single-cell RNA and protein expression with totalVI
Deconvolving spatial transcriptomics data to map cell types to tissue locations