Commit ·
d0de36b
1
Parent(s): 02a8f7d
update readme
Browse files
README.md
CHANGED
|
@@ -13,7 +13,7 @@ tags:
|
|
| 13 |
|
| 14 |
# SeqScreen Frozen
|
| 15 |
|
| 16 |
-
This model corresponds to the SeqScreen finetuning configuration, in which ESM2 T36 and the projection layers are trained.
|
| 17 |
|
| 18 |
\[[Github Repo](https://github.com/pcdslab/SeqScreen)\] | \[[Dataset on HuggingFace](https://huggingface.co/datasets/SaeedLab/SeqScreen)\] | \[[Model Collection](https://huggingface.co/collections/SaeedLab/seqscreen)\] | \[[Cite](#citation)\]
|
| 19 |
|
|
@@ -36,6 +36,12 @@ Two configurations are available in this collection:
|
|
| 36 |
|
| 37 |
SeqScreen computes cosine similarities between protein and molecule embeddings, which can be used to rank candidate molecules for a given target protein.
|
| 38 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
### Similarity
|
| 40 |
|
| 41 |
```python
|
|
|
|
| 13 |
|
| 14 |
# SeqScreen Frozen
|
| 15 |
|
| 16 |
+
This model corresponds to the SeqScreen finetuning configuration, in which ESM2 T36 and the projection layers are trained on filtered ChEMBL.
|
| 17 |
|
| 18 |
\[[Github Repo](https://github.com/pcdslab/SeqScreen)\] | \[[Dataset on HuggingFace](https://huggingface.co/datasets/SaeedLab/SeqScreen)\] | \[[Model Collection](https://huggingface.co/collections/SaeedLab/seqscreen)\] | \[[Cite](#citation)\]
|
| 19 |
|
|
|
|
| 36 |
|
| 37 |
SeqScreen computes cosine similarities between protein and molecule embeddings, which can be used to rank candidate molecules for a given target protein.
|
| 38 |
|
| 39 |
+
### Dependencies
|
| 40 |
+
|
| 41 |
+
```bash
|
| 42 |
+
pip install peft
|
| 43 |
+
```
|
| 44 |
+
|
| 45 |
### Similarity
|
| 46 |
|
| 47 |
```python
|