Skip to content

README.md

Latest commit

 

History

History
29 lines (27 loc) · 944 Bytes

README.md

File metadata and controls

29 lines (27 loc) · 944 Bytes

ncRNA-CUPID

ncRNA-CUPID is a ncRNA-ncRNA interaction classifier, based on a Transformer architecture.

Requirements

A CUDA environment, and a minimum VRAM of 8GB is required.

Dependencies

torch>=2.0
numpy
transformers==4.33.0.dev0
datasets==2.14.4
tqdm

Usage

Firstly, download the checkpoint of the foundational RNA Language model (GenerRNA)

Directory tree

.
├── LICENSE
├── README.md
├── model.pt         # to be downloaded
├── model.py         # define the architecture
├── tokenization.py  # preparete data
├── tokenizer        # BPE tokenizer of the foundational RNA LM
├── example_notebook.py # Example usage of ncRNA cupid for training on your set of ncRNA interaction sequences

Dataset

Dataset used for constructing CUPID: https://unimi2013-my.sharepoint.com/:u:/g/personal/marco_nicolini_unimi_it/IQADmEOosGc7TpxS5BH_nI5bAeO92MVs6xPdM_XYzfMBKaM?e=PYEgza