Improved Protein-ligand Binding Affinity Prediction with Structure-Based Deep Fusion Inference
This work addresses a key problem in drug discovery by enhancing binding affinity prediction, but it is incremental as it builds on existing neural network approaches.
The paper tackles the challenge of predicting protein-ligand binding affinity in drug discovery by proposing fusion models that combine complementary features from two neural network models, resulting in improved overall prediction and greater computational efficiency compared to individual models and biophysics-based methods, as demonstrated on the PDBBind 2016 dataset.
Predicting accurate protein-ligand binding affinity is important in drug discovery but remains a challenge even with computationally expensive biophysics-based energy scoring methods and state-of-the-art deep learning approaches. Despite the recent advances in the deep convolutional and graph neural network based approaches, the model performance depends on the input data representation and suffers from distinct limitations. It is natural to combine complementary features and their inference from the individual models for better predictions. We present fusion models to benefit from different feature representations of two neural network models to improve the binding affinity prediction. We demonstrate effectiveness of the proposed approach by performing experiments with the PDBBind 2016 dataset and its docking pose complexes. The results show that the proposed approach improves the overall prediction compared to the individual neural network models with greater computational efficiency than related biophysics based energy scoring functions. We also discuss the benefit of the proposed fusion inference with several example complexes. The software is made available as open source at https://github.com/llnl/fast.