High Performance of Gradient Boosting in Binding Affinity Prediction
Not on the map. Why?
Abstract (arXiv)
Prediction of protein-ligand (PL) binding affinity remains the key to drug discovery. Popular approaches in recent years involve graph neural networks (GNNs), which are used to learn the topology and geometry of PL complexes. However, GNNs are computationally heavy and have poor scalability to graph sizes. On the other hand, traditional machine learning (ML) approaches, such as gradient-boosted decision trees (GBDTs), are lightweight yet extremely efficient for tabular data. We propose to use PL interaction features along with PL graph-level features in GBDT. We show that this combination outperforms the existing solutions.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 12 of its 33 references that are in the map. First posted on arXiv 14 May 2022.
Builds on
12 of 33 references.
References · 12
- 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,455
- 2021Revisiting Deep Learning Models for Tabular Datacited by 725
- 2016Molecular Graph Convolutions: Moving Beyond Fingerprintscited by 238
- 2018CatBoost: gradient boosting with categorical features supportcited by 208
- 2019A Survey on Graph Kernelscited by 148
- 2020Hybrid Models for Learning to Branchcited by 95
- 2021Structure-aware Interactive Graph Neural Networks for the Prediction of Protein-Ligand Binding Affinitycited by 60
- 2018Anonymous Walk Embeddingscited by 46
- 2021Boost then Convolve: Gradient Boosting Meets Graph Neural Networkscited by 42
- 2020Improved Protein-ligand Binding Affinity Prediction with Structure-Based Deep Fusion Inferencecited by 35
- 2020PIGNet: A physics-informed deep learning model toward generalized drug-target interaction predictionscited by 31
- 2020A Lagrangian Approach to Information Propagation in Graph Neural Networkscited by 4
Built on by
Citing papers per year: 2022: 1.
1 paper.