Metadata-Version: 2.1
Name: LVPocket
Version: 0.2.4
Summary: A Protein Binding Pocket Prediction Methods.
Home-page: https://github.com/ZRF-ZRF/LVpocket.git
Author: CPU-409
Author-email: 3221051463@stu.cpu.edu.cn
License: UNKNOWN
Keywords: protein binding pockets prediction,lvnet
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3.6
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Development Status :: 2 - Pre-Alpha
Requires-Python: >=3.6, <=3.7
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: h5py
Requires-Dist: numpy (>=1.12)
Requires-Dist: scipy
Requires-Dist: keras (>=2.0)
Requires-Dist: tensorflow-gpu (<2.0)
Requires-Dist: biopython
Requires-Dist: scikit-learn
Requires-Dist: numpy
Requires-Dist: pandas
Requires-Dist: scikit-image

We proposed LVPocket, a novel method that synergistically captures both local and global information of protein data through the integration of Transformer encoders, which help the model achieve better performance in binding pockets prediction. And then we tailored prediction models for data of four distinct structural classes of proteins using the transfer learning. The four fine-tuned models were trained on the baseline LVPocket model which was trained on the sc-PDB dataset. LVPocket exhibits superior performance on three independent datasets compared to current state-of-the-art methods. Additionally, the fine-tuned model outperforms the baseline model in terms of performance.