|
|
--- |
|
|
license: cc-by-nc-nd-4.0 |
|
|
--- |
|
|
**FusOn-pLM: A Fusion Oncoprotein-Specific Language Model via Focused Probabilistic Masking** |
|
|
 |
|
|
In this work, we introduce **FusOn-pLM**, a novel pLM that fine-tunes state-of-the-art ESM-2 embeddings on fusion oncoprotein sequences, those that drive a large portion of pediatric cancers but are heavily disordered and undruggable, via masked language modeling (MLM). We specifically introduce a novel MLM strategy, employing a binding-site probability predictor to focus masking on key amino acid residues, thereby generating more optimal fusion oncoprotein-aware embeddings. Our model improves performance on both fusion oncoprotein-specific benchmarks and disorder prediction tasks in comparison to baseline ESM-2 representations, as well as manually-constructed biophysical embeddings, motivating downstream usage of FusOn-pLM embeddings for therapeutic design tasks targeting these fusions. |
|
|
|
|
|
|
|
|
# How to Use FusOn-pLM |
|
|
|
|
|
``` |
|
|
# Load model directly |
|
|
from transformers import AutoTokenizer, AutoModelForMaskedLM |
|
|
|
|
|
tokenizer = AutoTokenizer.from_pretrained("ChatterjeeLab/FusOn-pLM") |
|
|
model = AutoModelForMaskedLM.from_pretrained("ChatterjeeLab/FusOn-pLM") |
|
|
``` |
