HAC-Net v1.4.3

• minor bug fixes

HAC-Net v1.4.2

• Source code for updated version of HACNet Python package
• Includes function to predict pKd for a single protein-ligand complex from protein (PDB) and ligand (MOL2) files alone
• Tutorial notebook and demo video are linked in README
• In order to create a function to perform the entire HAC-Net prediction pipeline that is user-friendly and does not require any external programs, we introduce a few subtle discrepancies related to preprocessing the input files, although the original function is still available in HACNet/functions.py

HAC-Net v1.3.0

• optimized source code for HACNet Python package

HAC-Net v1.2.0

• tutorial notebooks demonstrating training and testing procedures
• link to all parameter files and train-test files
• lists of PDB IDs associated with each train-test split
• low-level cleaning of source code

HAC-Net v1.1.0

• Source code is optimized for speed, further commented, and organized in a simpler and more generalizable way
• 3D-CNN model contains a helper module for reshaping tensors
• GCN model code is much more straightforward
• test function can be applied to model subcomponents or hybrid model