gokceuludogan
commited on
Commit
•
8915165
1
Parent(s):
3a9fe37
Update README.md
Browse files
README.md
CHANGED
@@ -10,9 +10,10 @@ tags:
|
|
10 |
---
|
11 |
## WarmMolGenTwo
|
12 |
|
13 |
-
A target-specific molecule generator model which is warm started (i.e. initialized) from pretrained biochemical language models and trained on interacting protein-compound pairs, viewing targeted molecular generation as a translation task between protein and molecular languages. It was introduced in
|
|
|
14 |
|
15 |
-
WarmMolGenTwo is a Transformer-based encoder-decoder model initialized with [Protein RoBERTa](https://github.com/PaccMann/paccmann_proteomics) and [ChemBERTaLM](https://huggingface.co/gokceuludogan/ChemBERTaLM) checkpoints, and then, trained on interacting protein-compound pairs filtered from [BindingDB](https://www.bindingdb.org/rwd/bind/index.jsp). The model takes a protein sequence as
|
16 |
|
17 |
## How to use
|
18 |
|
|
|
10 |
---
|
11 |
## WarmMolGenTwo
|
12 |
|
13 |
+
A target-specific molecule generator model which is warm started (i.e. initialized) from pretrained biochemical language models and trained on interacting protein-compound pairs, viewing targeted molecular generation as a translation task between protein and molecular languages. It was introduced in the paper, "Exploiting pretrained biochemical language models for
|
14 |
+
targeted drug design", which has been accepted for publication in *Bioinformatics* Published by Oxford University Press and first released in [this repository](https://github.com/boun-tabi/biochemical-lms-for-drug-design).
|
15 |
|
16 |
+
WarmMolGenTwo is a Transformer-based encoder-decoder model initialized with [Protein RoBERTa](https://github.com/PaccMann/paccmann_proteomics) and [ChemBERTaLM](https://huggingface.co/gokceuludogan/ChemBERTaLM) checkpoints, and then, trained on interacting protein-compound pairs filtered from [BindingDB](https://www.bindingdb.org/rwd/bind/index.jsp). The model takes a protein sequence as an input and outputs a SMILES sequence.
|
17 |
|
18 |
## How to use
|
19 |
|