license: apache-2.0
The model is trained using PyTorch on a custom dataset designed for protein sequence classification.
The first stage model, best_model_stage1.pth, classifies proteins into two categories: nucleic acid-binding proteins and non-nucleic acid-binding proteins.
The second stage model, best_model_stage2.pth, further classifies nucleic acid-binding proteins into DNA-binding proteins and RNA-binding proteins.
In addition to the trained models, we have uploaded a compressed package containing the executable version of DRBP_EDP. After downloading and extracting the package locally, it can be used directly.
The model folder in the DRBP_EDP(.exe).zip file already contains the following critical files, so you can avoid re-downloading them:
- esm2_t33_650M_UR50D (the model checkpoint file)
- best_model_stage1.pth
- best_model_stage2.pth
Please note that the first time you run it, there may be a slight delay as the model is loaded.
The directory structure of the extracted files is shown below. Please ensure that all necessary components are present to avoid any errors during execution.
Note: esm1b_t33_650M_UR50S.