Added note about top 200 genes for model training
Browse files
README.md
CHANGED
@@ -1,3 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
# Overview
|
2 |
This is the C2S-Pythia-410m-cell-type-prediction model, based on the Pythia-410m architecture developed by EleutherAI,
|
3 |
fine-tuned using Cell2Sentence (C2S) on a diverse set of single-cell RNA sequencing (scRNA-seq) datasets from CellxGene
|
@@ -11,6 +20,8 @@ This model was trained on over 57 million human and mouse cells gathered from ov
|
|
11 |
datasets from CellxGene and the Human Cell Atlas. This dataset covers a broad range of cell types and conditions
|
12 |
from multiple tissues in both human and mouse.
|
13 |
|
|
|
|
|
14 |
# Tasks
|
15 |
This model is designed for:
|
16 |
- Cell type prediction: Predicting the cell type based on the "cell sentence" generated from scRNA-seq data.
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
base_model: EleutherAI/pythia-410m
|
5 |
+
library_name: transformers
|
6 |
+
tags:
|
7 |
+
- biology
|
8 |
+
- scRNAseq
|
9 |
+
---
|
10 |
# Overview
|
11 |
This is the C2S-Pythia-410m-cell-type-prediction model, based on the Pythia-410m architecture developed by EleutherAI,
|
12 |
fine-tuned using Cell2Sentence (C2S) on a diverse set of single-cell RNA sequencing (scRNA-seq) datasets from CellxGene
|
|
|
20 |
datasets from CellxGene and the Human Cell Atlas. This dataset covers a broad range of cell types and conditions
|
21 |
from multiple tissues in both human and mouse.
|
22 |
|
23 |
+
This model was trained with the top 200 genes per cell sentence.
|
24 |
+
|
25 |
# Tasks
|
26 |
This model is designed for:
|
27 |
- Cell type prediction: Predicting the cell type based on the "cell sentence" generated from scRNA-seq data.
|