Welcome to the official documentation for scGenAI, a comprehensive Python package designed for the prediction and analysis of single-cell RNA sequencing (scRNA-seq) data using transformer-based large language models (LLMs). The package enables users to train, fine-tune, and perform predictions on scRNA-seq datasets utilizing models such as LLaMA, GPT, BigBird, and scGenT, with multi-GPU support via PyTorch's DistributedDataParallel (DDP) framework.
scGenAI offers an advanced framework for researchers and bioinformaticians working on single-cell transcriptomics data analysis. By leveraging LLMs, this package brings state-of-the-art machine learning techniques to single-cell gene expression data. This documentation provides detailed instructions on how to install, use, and configure scGenAI, as well as how to train, fine-tune, and predict cellular states, cell type and genotype.
To begin, please proceed to the Installation Guide.