Deep learning methods for molecular representation and property prediction

Li, Zhen; Jiang, Mingjian; Wang, Shuang; Zhang, Shuguang

doi:10.1016/j.drudis.2022.103373

Cited by 100 publications

(40 citation statements)

References 89 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…220 Li et al introduced an alternative approach to generating graph-level representation using GCN by introducing a dummy super node. 221 The early spectral GCN fixed graph structure without training, but Li et al constructed graph convolution that accepts flexible graph inputs and learned additional topology information for each input graph. 221 The previous frameworks were all built on spatial graph convolution, while spectral graph convolution was less employed in QSAR tasks.…”

Section: Gnnmentioning

confidence: 99%

A Review on the Recent Applications of Deep Learning in Predictive Drug Toxicological Studies

Sinha¹,

Ghosh²,

Sil

2023

Chem. Res. Toxicol.

View full text Add to dashboard Cite

Drug toxicity prediction is an important step in ensuring patient safety during drug design studies. While traditional preclinical studies have historically relied on animal models to evaluate toxicity, recent advances in deep-learning approaches have shown great promise in advancing drug safety science and reducing animal use in preclinical studies. However, deep-learning-based approaches also face challenges in handling large biological data sets, model interpretability, and regulatory acceptance. In this review, we provide an overview of recent developments in deep-learning-based approaches for predicting drug toxicity, highlighting their potential advantages over traditional methods and the need to address their limitations. Deep-learning models have demonstrated excellent performance in predicting toxicity outcomes from various data sources such as chemical structures, genomic data, and high-throughput screening assays. The potential of deep learning for automated feature engineering is also discussed. This review emphasizes the need to address ethical concerns related to the use of deep learning in drug toxicity studies, including the reduction of animal use and ensuring regulatory acceptance. Furthermore, emerging applications of deep learning in drug toxicity prediction, such as predicting drug–drug interactions and toxicity in rare subpopulations, are highlighted. The integration of deep-learning-based approaches with traditional methods is discussed as a way to develop more reliable and efficient predictive models for drug safety assessment, paving the way for safer and more effective drug discovery and development. Overall, this review highlights the critical role of deep learning in predictive toxicology and drug safety evaluation, emphasizing the need for continued research and development in this rapidly evolving field. By addressing the limitations of traditional methods, leveraging the potential of deep learning for automated feature engineering, and addressing ethical concerns, deep-learning-based approaches have the potential to revolutionize drug toxicity prediction and improve patient safety in drug discovery and development.

show abstract

Section: Gnnmentioning

confidence: 99%

A Review on the Recent Applications of Deep Learning in Predictive Drug Toxicological Studies

Sinha¹,

Ghosh²,

Sil

2023

Chem. Res. Toxicol.

View full text Add to dashboard Cite

show abstract

“…However, the majority of the proposed chemical language models (CLMs) have a significant shortcoming in that they use SMILES notations to represent molecules. Problems with SMILES-based representations can be listed as; (1) there are a number of ways to write the same molecule in a non-canonical way, which decreases the uniqueness of molecular strings; (2) a valid SMILES string might have invalid chemical properties such as exceeding the natural valency of an atom (Wigh et al 2022); (3) SMILES cannot fully capture spatial information; and (4) SMILES alone may not be sufficient to capture molecular characteristics since it lacks syntactic and semantic robustness (Krenn et al 2022, Li et al, 2022b. These issues suggest a new research direction that may produce CLMs with a greater degree of generalizability.…”

Section: Introductionmentioning

confidence: 99%

SELFormer: molecular representation learning via SELFIES language models

Atakan

Ulusoy

Ünlü

et al. 2023

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

Automated computational analysis of the vast chemical space is critical for numerous fields of research such as drug discovery and material science. Representation learning techniques have recently been employed with the primary objective of generating compact and informative numerical expressions of complex data, for efficient usage in subsequent prediction tasks. One approach to efficiently learn molecular representations is processing string-based notations of chemicals via natural language processing (NLP) algorithms. Majority of the methods proposed so far utilize SMILES notations for this purpose, which is the most extensively used string-based encoding for molecules. However, SMILES is associated with numerous problems related to validity and robustness, which may prevent the model from effectively uncovering the knowledge hidden in the data. In this study, we propose SELFormer, a transformer architecture-based chemical language model that utilizes a 100% valid, compact and expressive notation, SELFIES, as input, in order to learn flexible and high-quality molecular representations. SELFormer is pre-trained on two million drug-like compounds and fine-tuned for diverse molecular property prediction tasks. Our performance evaluation has revealed that, SELFormer outperforms all competing methods, including graph learning-based approaches and SMILES-based chemical language models, on predicting aqueous solubility of molecules and adverse drug reactions, while producing comparable results for the remaining tasks. We also visualized molecular representations learned by SELFormer via dimensionality reduction, which indicated that even the pre-trained model can discriminate molecules with differing structural properties. We shared SELFormer as a programmatic tool, together with its datasets and pre-trained models. Overall, our research demonstrates the benefit of using the SELFIES notations in the context of chemical language modeling and opens up new possibilities for the design and discovery of novel drug candidates with desired features.

show abstract

“…Computer-aided drug design (CADD) [ 2 ] is a new approach that can reduce the time, cost, and risk factors involved in the process of drug design, with help of computer technology. The prediction of molecular properties [ 3 ] is an important task in CADD, which also is one of the key tasks in cheminformatics. As the data volume of molecular property prediction becomes larger and larger, how to fully utilize these data to improve the accuracy of prediction has received extensive attention.…”

Section: Introductionmentioning

confidence: 99%

Molecular Property Prediction by Combining LSTM and GAT

Pan

Xia

et al. 2023

Biomolecules

Self Cite

View full text Add to dashboard Cite

Molecular property prediction is an important direction in computer-aided drug design. In this paper, to fully explore the information from SMILE stings and graph data of molecules, we combined the SALSTM and GAT methods in order to mine the feature information of molecules from sequences and graphs. The embedding atoms are obtained through SALSTM, firstly using SMILES strings, and they are combined with graph node features and fed into the GAT to extract the global molecular representation. At the same time, data augmentation is added to enlarge the training dataset and improve the performance of the model. Finally, to enhance the interpretability of the model, the attention layers of both models are fused together to highlight the key atoms. Comparison with other graph-based and sequence-based methods, for multiple datasets, shows that our method can achieve high prediction accuracy with good generalizability.

show abstract

Deep learning methods for molecular representation and property prediction

Cited by 100 publications

References 89 publications

A Review on the Recent Applications of Deep Learning in Predictive Drug Toxicological Studies

A Review on the Recent Applications of Deep Learning in Predictive Drug Toxicological Studies

SELFormer: molecular representation learning via SELFIES language models

Molecular Property Prediction by Combining LSTM and GAT

Contact Info

Product

Resources

About