MF-SuP-pKa: Multi-fidelity modeling with subgraph pooling mechanism for pKa prediction.
10.1016/j.apsb.2022.11.010
- Author:
Jialu WU
1
;
Yue WAN
2
;
Zhenxing WU
1
;
Shengyu ZHANG
2
;
Dongsheng CAO
3
;
Chang-Yu HSIEH
1
;
Tingjun HOU
1
Author Information
1. Innovation Institute for Artificial Intelligence in Medicine of Zhejiang University, College of Pharmaceutical Sciences, Zhejiang University, Hangzhou 310058, China.
2. Tencent Quantum Laboratory, Tencent, Shenzhen 518057, China.
3. Xiangya School of Pharmaceutical Sciences, Central South University, Changsha 410004, China.
- Publication Type:Journal Article
- Keywords:
Data augmentation;
Graph neural network;
Multi-fidelity learning;
Subgraph pooling;
pKa prediction
- From:
Acta Pharmaceutica Sinica B
2023;13(6):2572-2584
- CountryChina
- Language:English
-
Abstract:
Acid-base dissociation constant (pKa) is a key physicochemical parameter in chemical science, especially in organic synthesis and drug discovery. Current methodologies for pKa prediction still suffer from limited applicability domain and lack of chemical insight. Here we present MF-SuP-pKa (multi-fidelity modeling with subgraph pooling for pKa prediction), a novel pKa prediction model that utilizes subgraph pooling, multi-fidelity learning and data augmentation. In our model, a knowledge-aware subgraph pooling strategy was designed to capture the local and global environments around the ionization sites for micro-pKa prediction. To overcome the scarcity of accurate pKa data, low-fidelity data (computational pKa) was used to fit the high-fidelity data (experimental pKa) through transfer learning. The final MF-SuP-pKa model was constructed by pre-training on the augmented ChEMBL data set and fine-tuning on the DataWarrior data set. Extensive evaluation on the DataWarrior data set and three benchmark data sets shows that MF-SuP-pKa achieves superior performances to the state-of-the-art pKa prediction models while requires much less high-fidelity training data. Compared with Attentive FP, MF-SuP-pKa achieves 23.83% and 20.12% improvement in terms of mean absolute error (MAE) on the acidic and basic sets, respectively.