jorgebotas commited on
Commit
bfbb3fa
Β·
verified Β·
1 Parent(s): 18eda53

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +29 -13
README.md CHANGED
@@ -1,14 +1,14 @@
1
  ---
2
  license: mit
3
  language:
4
- - en
5
  tags:
6
- - biology
7
- - single-cell
8
- - scFM
9
- - Drosophila
10
- - foundation-model
11
- - cell-type-annotation
12
  ---
13
 
14
  <div align="start">
@@ -17,18 +17,34 @@ tags:
17
  </div>
18
 
19
  **Lemur** is a single-cell foundation model developed specifically for *Drosophila melanogaster*. It achieves fine-tuning-free cell-type annotation using two key innovations:
20
-
21
  - **Comprehensive Pre-training:** Trained on an integrated whole-organism atlas with a unified cell-type annotation schema.
22
  - **Hierarchical Decoding:** Employs a transformer-based hierarchical cell-type decoder to generate consistent predictions at multiple levels of granularity.
23
 
24
- ### Highlights
 
25
  - **Fine-Tuning-Free Annotation:** No extra training required on new datasets.
26
  - **Robust Across Conditions:** Consistent performance across various tissue types, experimental conditions, and sequencing platforms.
27
  - **Zero-Shot Batch-Effect Correction:** Automatically corrects batch effects without further adjustments.
28
  - **Broad Applications:** Tailored for the fly research community with potential implications for aging and neurodegenerative disease studies in humans.
29
 
30
- ### Status & Availability
31
- - **Model Weights:** Available now on the Hugging Face Hub.
32
- - **Code:** Will be made public alongside our preprint πŸ“„.
 
 
 
 
 
 
 
33
 
34
- Happy modeling! πŸš€
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: mit
3
  language:
4
+ - en
5
  tags:
6
+ - biology
7
+ - single-cell
8
+ - scFM
9
+ - Drosophila
10
+ - foundation-model
11
+ - cell-type-annotation
12
  ---
13
 
14
  <div align="start">
 
17
  </div>
18
 
19
  **Lemur** is a single-cell foundation model developed specifically for *Drosophila melanogaster*. It achieves fine-tuning-free cell-type annotation using two key innovations:
20
+
21
  - **Comprehensive Pre-training:** Trained on an integrated whole-organism atlas with a unified cell-type annotation schema.
22
  - **Hierarchical Decoding:** Employs a transformer-based hierarchical cell-type decoder to generate consistent predictions at multiple levels of granularity.
23
 
24
+ ### Highlights ⚑️
25
+
26
  - **Fine-Tuning-Free Annotation:** No extra training required on new datasets.
27
  - **Robust Across Conditions:** Consistent performance across various tissue types, experimental conditions, and sequencing platforms.
28
  - **Zero-Shot Batch-Effect Correction:** Automatically corrects batch effects without further adjustments.
29
  - **Broad Applications:** Tailored for the fly research community with potential implications for aging and neurodegenerative disease studies in humans.
30
 
31
+ ### Status & Availability πŸš€
32
+
33
+ - **Model Weights:** Available now on the Hugging Face Hub πŸ‹πŸ»β€β™‚οΈ.
34
+ - **Code:** Soon to be released. Stay tuned! πŸ”₯πŸ‘€
35
+
36
+ ### Publication & Citation πŸ“šπŸ”—
37
+
38
+ We're excited to share our manuscript, *Lemur: A Single-Cell Foundation Model with Fine-Tuning-Free Hierarchical Cell-Type Generation for* *Drosophila melanogaster*, which is now available as a preprint on [bioRxiv: 10.1101/123456](https://www.biorxiv.org/content/10.1101/123456)! πŸš€βœ¨
39
+
40
+ If you find our work helpful, please consider citing our preprint as follows:
41
 
42
+ ```bibtex
43
+ @article{your_citation_key,
44
+ title={Lemur: A Single-Cell Foundation Model with Fine-Tuning-Free Hierarchical Cell-Type Generation for *Drosophila melanogaster*},
45
+ author={Doe, John and Smith, Jane and Collaborators},
46
+ journal={bioRxiv},
47
+ year={2025},
48
+ doi={10.1101/123456}
49
+ }
50
+ ```