Improved Protein-Ligand Binding Affinity Prediction with Structure-Based Deep Fusion Inference

Predicting accurate protein-ligand binding affinities is an important task 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 application of deep convolutional and graph neural network-based approaches, it remains unclear what the relative advantages of each approach are and how they compare with physics-based methodologies that have found more mainstream success in virtual screening pipelines. We present fusion models that combine features and inference from complementary representations to improve binding affinity prediction. This, to our knowledge, is the first comprehensive study that uses a common series of evaluations to directly compare the performance of three-dimensional (3D)-convolutional neural networks (3D-CNNs), spatial graph neural networks (SG-CNNs), and their fusion. We use temporal and structure-based splits to assess performance on novel protein targets. To test the practical applicability of our models, we examine their performance in cases that assume that the crystal structure is not available. In these cases, binding free energies are predicted using docking pose coordinates as the inputs to each model. In addition, we compare these deep learning approaches to predictions based on docking scores and molecular mechanic/generalized Born surface area (MM/GBSA) calculations. Our results show that the fusion models make more accurate predictions than their constituent neural network models as well as docking scoring and MM/GBSA rescoring, with the benefit of greater computational efficiency than the MM/GBSA method. Finally, we provide the code to reproduce our results and the parameter files of the trained models used in this work. The software is available as open source at https://gichub.coirOini/fast . Model parameter files are available at ftp:/ /gdobioinforrnatics.ucllnl.orgi fast/pribbind2016_model_checkpoints/.

Automated summary

Accurately predicting protein-ligand binding affinities is crucial in drug discovery. While current methods face challenges, fusion models that combine features and inference from complementary representations show improved prediction accuracy. Comparative analysis reveals that fusion models perform better than individual neural network models, docking scoring, and MM/GBSA calculations, with the added benefit of greater computational efficiency.