Fig. 1: Illustration of AGBT model.
From: Algebraic graph-assisted bidirectional transformers for molecular property prediction
For a given molecular structure and its SMILES strings, AG-FPs are generated from element-specific algebraic subgraphs module and BT-FPs are generated from a deep bidirectional transformer module, as shown inside the dashed rectangle, which contains the pre-training and fine-tuning processes, and then finally completes the feature extraction using task-specific SMILES as input. Then the random forest algorithm is used to fuse, rank, and select optimal fingerprints (AGBT-FPs) for machine learning.
