scCulturePredict

Description

A simple R package to build a phenotypic fingerprint and subsequentially predict cell culture based on gene expression and biological pathways from single-cell transcriptomics data: a dual functionality in BUILD and PREDICT modes. The first generates transferable transcriptomic fingerprints from labeled training data using KEGG pathway analysis and trains both similarity-based and SVM prediction models. The latter applies these pre-built fingerprints to unlabeled datasets for culture condition prediction. Supports both CSV and 10X Genomics data formats, integrates with Seurat workflows, and provides comprehensive visualisation tools for model evaluation and prediction confidence assessment.

Code

Code metrics have not been computed for this package yet.

Topics

People

• Niccolò Bianchi author maintainer