TransVAE-DTA: Transformer and variational autoencoder network for drug-target binding affinity prediction

Zhou, Changjian; Li, Zhongzheng; Song, Jia; Xiang, Wensheng

doi:10.1016/j.cmpb.2023.108003

Cited by 11 publications

(8 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the future, it is imperative to delve into DTA prediction methods based on deep learning from three key perspectives: Performance analysis of multiple state-of-the-art methods based on KIBA dataset. The evaluation metric values of these methods in the figure are sourced from References (Bi et al, 2023;Xia et al, 2023;Tian et al, 2024;Wu et al, 2024;Zhou et al, 2024). Performance analysis of multiple state-of-the-art methods based on Davis dataset.…”

Section: Discussionmentioning

confidence: 99%

“…Figure 1 highlights PDBbind, KIBA, and Davis datasets as commonly used datasets for predicting DTA using deep learning. We summarized the performance evaluation metrics values of several state-of-the-art methods on PDBbind, KIBA, and Davis datasets, as reported in recently published literatures ( Wang et al, 2023a ; Zhu et al, 2023a ; Bi et al, 2023 ; Xia et al, 2023 ; Tian et al, 2024 ; Wu et al, 2024 ; Zhou et al, 2024 ), without considering the specific partitioning of the corresponding datasets by these methods. Although the statistical results ( Tables 4 , 5 ; Figures 5 – 7 ) showed that these methods have achieved good prediction performance for DTA on commonly used benchmark datasets, the further improvement in DTA prediction still faces challenges.…”

Section: Performance Analysis Of Multiple State-of-the-art Methods Ba...mentioning

confidence: 99%

“… Performance analysis of multiple state-of-the-art methods based on Davis dataset. The evaluation metric values of these methods in the figure are sourced from References ( Bi et al, 2023 ; Xia et al, 2023 ; Tian et al, 2024 ; Wu et al, 2024 ; Zhou et al, 2024 ). …”

Section: Performance Analysis Of Multiple State-of-the-art Methods Ba...mentioning

confidence: 99%

“…Sequence-based methods ( Öztürk et al, 2018 ; Karimi et al, 2019 ; Wang et al, 2021a ; Li et al, 2022b ; Ghimire et al, 2022 ; Zhao et al, 2022 ; Gim et al, 2023 ; Jin et al, 2023 ; Kalemati et al, 2023 ; Ru et al, 2023 ; Zhou et al, 2024 ) aim to extract implicit sequence features from drug SMILES (Simplified Molecular Input Line Entry System) ( Weininger, 1988 ) and target sequences using deep learning models. These methods leverage various sequence deep learning models such as Convolutional Neural Networks (CNNs) ( LeCun et al, 2015 ), Recurrent Neural Networks (RNNs) ( Zaremba et al, 2015 ), and Transformers ( Vaswani et al, 2017 ).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A comprehensive review of the recent advances on predicting drug-target affinity based on deep learning

Zeng,

Li,

et al. 2024

Front. Pharmacol.

View full text Add to dashboard Cite

Accurate calculation of drug-target affinity (DTA) is crucial for various applications in the pharmaceutical industry, including drug screening, design, and repurposing. However, traditional machine learning methods for calculating DTA often lack accuracy, posing a significant challenge in accurately predicting DTA. Fortunately, deep learning has emerged as a promising approach in computational biology, leading to the development of various deep learning-based methods for DTA prediction. To support researchers in developing novel and highly precision methods, we have provided a comprehensive review of recent advances in predicting DTA using deep learning. We firstly conducted a statistical analysis of commonly used public datasets, providing essential information and introducing the used fields of these datasets. We further explored the common representations of sequences and structures of drugs and targets. These analyses served as the foundation for constructing DTA prediction methods based on deep learning. Next, we focused on explaining how deep learning models, such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Transformer, and Graph Neural Networks (GNNs), were effectively employed in specific DTA prediction methods. We highlighted the unique advantages and applications of these models in the context of DTA prediction. Finally, we conducted a performance analysis of multiple state-of-the-art methods for predicting DTA based on deep learning. The comprehensive review aimed to help researchers understand the shortcomings and advantages of existing methods, and further develop high-precision DTA prediction tool to promote the development of drug discovery.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Performance Analysis Of Multiple State-of-the-art Methods Ba...mentioning

confidence: 99%

Section: Performance Analysis Of Multiple State-of-the-art Methods Ba...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A comprehensive review of the recent advances on predicting drug-target affinity based on deep learning

Zeng,

Li,

et al. 2024

Front. Pharmacol.

View full text Add to dashboard Cite

show abstract

“…Evaluated interpretability of downstream DTA predictions are obtained from the attention scores. To better capture structural information, which is essential for DTA, several recent methods such as GTAMP-DTA, 117 AttentionMGT-DTA, 118 and TransVAE-DTA 119 turn to graph representations, representing molecules and proteins as molecular graph and protein pocket graphs and processing them via graph transformers. These models obtain strong performances on DTA predictions.…”

Section: Applications Of Transformers In Cheminformaticsmentioning

confidence: 99%

Application of Transformers in Cheminformatics

Luong,

Singh

2024

J. Chem. Inf. Model.

View full text Add to dashboard Cite

By accelerating time-consuming processes with high efficiency, computing has become an essential part of many modern chemical pipelines. Machine learning is a class of computing methods that can discover patterns within chemical data and utilize this knowledge for a wide variety of downstream tasks, such as property prediction or substance generation. The complex and diverse chemical space requires complex machine learning architectures with great learning power. Recently, learning models based on transformer architectures have revolutionized multiple domains of machine learning, including natural language processing and computer vision. Naturally, there have been ongoing endeavors in adopting these techniques to the chemical domain, resulting in a surge of publications within a short period. The diversity of chemical structures, use cases, and learning models necessitate a comprehensive summarization of existing works. In this paper, we review recent innovations in adapting transformers to solve learning problems in chemistry. Because chemical data is diverse and complex, we structure our discussion based on chemical representations. Specifically, we highlight the strengths and weaknesses of each representation, the current progress of adapting transformer architectures, and future directions.

show abstract