Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# Model Card: algaGPT
|
| 2 |
|
| 3 |
## Overview
|
|
@@ -18,12 +31,15 @@
|
|
| 18 |
|
| 19 |
| Metric | Score |
|
| 20 |
|--------|-------|
|
|
|
|
|
|
|
| 21 |
| Recall | >99% |
|
| 22 |
-
| Speed vs BLASTP+ |
|
| 23 |
|
| 24 |
## Usage
|
| 25 |
|
| 26 |
-
Input a protein sequence; model generates a classification tag (algal/
|
|
|
|
| 27 |
|
| 28 |
## Citation
|
| 29 |
|
|
@@ -32,4 +48,4 @@ Nelson DR, Jaiswal AK, Ismail NS, Mystikou A, Salehi-Ashtiani K. Pan-microalgal
|
|
| 32 |
## Contact
|
| 33 |
|
| 34 |
Kourosh Salehi-Ashtiani
|
| 35 |
-
ksa3@nyu.edu
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- biology
|
| 5 |
+
- protein-classification
|
| 6 |
+
- microalgae
|
| 7 |
+
- genomics
|
| 8 |
+
- nanoGPT
|
| 9 |
+
datasets:
|
| 10 |
+
- custom
|
| 11 |
+
pipeline_tag: text-classification
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
# Model Card: algaGPT
|
| 15 |
|
| 16 |
## Overview
|
|
|
|
| 31 |
|
| 32 |
| Metric | Score |
|
| 33 |
|--------|-------|
|
| 34 |
+
| Algal F1 | >0.87 |
|
| 35 |
+
| Bacterial F1 | >0.89 |
|
| 36 |
| Recall | >99% |
|
| 37 |
+
| Speed vs BLASTP+ | ~10,701× faster |
|
| 38 |
|
| 39 |
## Usage
|
| 40 |
|
| 41 |
+
Input a protein sequence; model generates a classification tag (algal/conta (contaminant)) via next-token prediction.
|
| 42 |
+
|
| 43 |
|
| 44 |
## Citation
|
| 45 |
|
|
|
|
| 48 |
## Contact
|
| 49 |
|
| 50 |
Kourosh Salehi-Ashtiani
|
| 51 |
+
ksa3@nyu.edu
|