Skip to content

Commit 58a7562

Browse files
committed
Update README.md.
1 parent 7f8d58f commit 58a7562

File tree

1 file changed

+42
-2
lines changed

1 file changed

+42
-2
lines changed

README.md

Lines changed: 42 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,13 +1,53 @@
11
# BarcodeMAE
22

3-
A pre-trained transformer model for inference on insect DNA barcoding data.
3+
A PyTorch implementation of BarcodeMAE, a model for enhancing DNA foundation models to address masking inefficiencies.
44

55
<p align="center">
66
<img src ="Figures/Arch_mae.png" alt="drawing" width="800"/>
77
</p>
88

99
* Check out our [paper](https://arxiv.org/pdf/2502.18405)
1010

11-
#### Model checkpoint is available here:
11+
#### Model checkpoint is available here: [BarcodeMAE](https://drive.google.com/file/d/18TqKC_gLYYDZEFfkMBRvWTHTT8Vb74Wv/view?usp=drive_link)
1212

13+
### Using the model
1314

15+
To be completed...
16+
17+
### Reproducing the results from the paper
18+
19+
0. Clone this repository and install the required libraries by running
20+
21+
```shell
22+
pip install -e .
23+
```
24+
25+
1. Download the [BIOSCAN-5M dataet from the git repo](https://github.com/bioscan-ml/BIOSCAN-5M)
26+
27+
2. Pretrain BarcodeMAE
28+
29+
To be completed...
30+
31+
32+
## Citation
33+
34+
If you find BarcodeMAE useful in your research please consider citing:
35+
36+
```bibtex
37+
@article{safari2025barcodemae,
38+
title={Enhancing DNA Foundation Models to Address Masking Inefficiencies},
39+
author={Monireh Safari
40+
and Pablo Millan Arias
41+
and Scott C. Lowe
42+
and Lila Kari
43+
and Angel X. Chang
44+
and Graham W. Taylor
45+
},
46+
journal={arXiv preprint arXiv:2502.18405}
47+
year={2025},
48+
eprint={2502.18405},
49+
archivePrefix={arXiv},
50+
primaryClass={cs.LG},
51+
doi={10.48550/arxiv.2311.02401},
52+
}
53+
```

0 commit comments

Comments
 (0)