FP-GNN: a versatile deep learning architecture for enhanced molecular property prediction

TL;DR

The paper introduces FP-GNN, a novel deep learning architecture that combines molecular graphs and fingerprints to improve the accuracy of molecular property prediction across diverse datasets.

Contribution

FP-GNN is a new deep learning model that integrates molecular graphs and fingerprints, achieving state-of-the-art results in molecular property prediction.

Findings

FP-GNN outperforms existing models on multiple datasets.

Analysis shows the importance of combining graphs and fingerprints.

FP-GNN demonstrates strong anti-noise and interpretability capabilities.

Abstract

Deep learning is an important method for molecular design and exhibits considerable ability to predict molecular properties, including physicochemical, bioactive, and ADME/T (absorption, distribution, metabolism, excretion, and toxicity) properties. In this study, we advanced a novel deep learning architecture, termed FP-GNN, which combined and simultaneously learned information from molecular graphs and fingerprints. To evaluate the FP-GNN model, we conducted experiments on 13 public datasets, an unbiased LIT-PCBA dataset, and 14 phenotypic screening datasets for breast cell lines. Extensive evaluation results showed that compared to advanced deep learning and conventional machine learning algorithms, the FP-GNN algorithm achieved state-of-the-art performance on these datasets. In addition, we analyzed the influence of different molecular fingerprints, and the effects of molecular graphs and molecular fingerprints on the performance of the FP-GNN model. Analysis of the anti-noise ability and interpretation ability also indicated that FP-GNN was competitive in real-world situations.