The data of the article"RLsite: Integrating 3D-CNN and BiLSTM for RNA-ligand binding site prediction''

The data folder contains the test datasets used to evaluate the model's performance, while the demo folder provides feature descriptors and example inputs utilized during the feature generation process.

Predicted results from the model are saved in the Output directory. The pkl folder includes the pre-trained model parameter files required for inference. Among the source code files, dataPre.py handles data preprocessing and formatting; main.py serves as the primary script for executing testing workflows; model.py defines the architecture of the RLsite model, combining 3D-CNN and BiLSTM modules; predict.py is responsible for loading the trained model and performing predictions; and subfunction.py contains a set of auxiliary functions that support various tasks throughout the pipeline.