Analyzing Learned Molecular Representations for Property Prediction

Abstract

Advancements in neural machinery have led to a wide range of algorithmic solutions for molecular property prediction. Two classes of models in particular have yielded promising results: neural networks applied to computed molecular fingerprints or expert-crafted descriptors, and graph convolutional neural networks that construct a learned molecular representation by operating on the graph structure of the molecule. However, recent literature has yet to clearly determine which of these two methods is superior when generalizing to new chemical space. Furthermore, prior research has rarely examined these new models in industry research settings in comparison to existing employed models. In this paper, we benchmark models extensively on 19 public and 16 proprietary industrial datasets spanning a wide variety of chemical endpoints. In addition, we introduce a graph convolutional model that consistently matches or outperforms models using fixed molecular descriptors as well as previous graph neural architectures on both public and proprietary datasets. Our empirical findings indicate that while approaches based on these representations have yet to reach the level of experimental reproducibility, our proposed model nevertheless offers significant improvements over models currently used in industrial workflows.

Cited by in corpus (11)

• Molecular Contrastive Learning of Representations via Graph Neural Networks
• Accelerating high-throughput virtual screening through molecular pool-based active learning
• Transfer learning for solvation free energies: from quantum chemistry to experiments
• Quantum chemistry-augmented neural networks for reactivity prediction: Performance, generalizability and interpretability
• Improving Molecular Contrastive Learning via Faulty Negative Mitigation and Decomposed Fragment Contrast
• KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction
• Convolutional Neural Nets in Chemical Engineering: Foundations, Computations, and Applications
• BatmanNet: Bi-branch Masked Graph Transformer Autoencoder for Molecular Representation
• Improving Compound Activity Classification via Deep Transfer and Representation Learning
• Grouping-matrix based Graph Pooling with Adaptive Number of Clusters
• PACIA: Parameter-Efficient Adapter for Few-Shot Molecular Property Prediction