36 lines
1.6 KiB
Markdown
36 lines
1.6 KiB
Markdown
---
|
|
language:
|
|
- en
|
|
base_model: EleutherAI/pythia-410m
|
|
library_name: transformers
|
|
tags:
|
|
- biology
|
|
- scRNAseq
|
|
license: cc-by-4.0
|
|
---
|
|
# Overview
|
|
This is the C2S-Pythia-410m-cell-type-prediction model, based on the Pythia-410m architecture developed by EleutherAI,
|
|
fine-tuned using Cell2Sentence (C2S) on a diverse set of single-cell RNA sequencing (scRNA-seq) datasets from CellxGene
|
|
and the Human Cell Atlas. Cell2Sentence is an innovative approach for adapting large language models (LLMs) to
|
|
single-cell biology by transforming scRNA-seq data into "cell sentences"—sequences of gene names ordered by
|
|
expression levels. This transformation enables LLMs to leverage their natural language processing capabilities for
|
|
various single-cell tasks, with a focus on cell type prediction in this model.
|
|
|
|
# Training Data
|
|
This model was trained on over 57 million human and mouse cells gathered from over 800 single-cell RNA sequencing
|
|
datasets from CellxGene and the Human Cell Atlas. This dataset covers a broad range of cell types and conditions
|
|
from multiple tissues in both human and mouse.
|
|
|
|
This model was trained with the top 200 genes per cell sentence.
|
|
|
|
# Tasks
|
|
This model is designed for:
|
|
- Cell type prediction: Predicting the cell type based on the "cell sentence" generated from scRNA-seq data.
|
|
|
|
# Cell2Sentence Links
|
|
- GitHub: https://github.com/vandijklab/cell2sentence (Note: Codebase has Apache 2.0 license, weights shared on HuggingFace are CC-by-4.0)
|
|
- Paper: https://www.biorxiv.org/content/10.1101/2023.09.11.557287v3
|
|
|
|
# Pythia Links
|
|
- Paper: https://arxiv.org/pdf/2304.01373
|
|
- Hugging Face: https://huggingface.co/EleutherAI/pythia-410m |