AttentionDTA: prediction of drug–target binding affinity using attention model

Zhao, Qichang; Xiao, Fen; Yang, Mingzhu; Li, Yaohang; Wang, Jianxin

doi:10.1109/bibm47256.2019.8983125

Cited by 78 publications

(75 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With regard to the DAVIS dataset, it can be observed that the greater number of the scores are found in the range of [5,6] along the x-axis, principally because the score of 5 establishes more than half of the dataset. Additionally, there is a crowded area of KIBA scores lying in the range [11,14] along the x-axis, which shows similar behavior to the Davis dataset. Principally, for both datasets, the data instances are close to the red regression line which, in turn, demonstrates that the proposed architecture has a competitive prediction performance.…”

Section: Results and Comparisonsmentioning

confidence: 60%

“…Among these approaches, Attention-DTA and MT-DTI yielded best results with CI of 0.887, MSE of 0.245 on the Davis dataset; also, on the KIBA dataset, they both achieved CI of 0.882 and MSE of 0.220 and 0.162 respectively. This explains the effectiveness of the attention convolutional operation in learning sequential drug and target information in the case of Attention-DTA [14]; and also, the efficiency of the pre-trained BERT representation presented in MT-DTI.…”

Section: Results and Comparisonsmentioning

confidence: 88%

“…On the other hand, deep-learning techniques that automatically capture feature representation show great performance improvement. The * denote the proposed architecture The * denote the proposed architecture First, this paper considers a few recent textual representation approaches such as: DeepDTA [29], MT-DTI [32], Deep-CPI [28], WideDTA [7], GANsDTA [13], and Attention-DTA [14]. Among these approaches, Attention-DTA and MT-DTI yielded best results with CI of 0.887, MSE of 0.245 on the Davis dataset; also, on the KIBA dataset, they both achieved CI of 0.882 and MSE of 0.220 and 0.162 respectively.…”

Section: Results and Comparisonsmentioning

confidence: 99%

“…However, they did not address GAN training on a small dataset. Similarly, Zhao et al [14] introduced a CNN architecture accompanied by attentional mechanisms to determine which protein sequences are more significant for a drug and which drug SMILES sequences are more vital for a protein during its affinity estimation. However, all of these approaches transform drug compounds into a corresponding string representation that is not an effective method to characterize molecules.…”

Section: A Drug-target Interactionsmentioning

confidence: 99%

See 3 more Smart Citations

DeepH-DTA: Deep Learning for Predicting Drug-Target Interactions: A Case Study of COVID-19 Drug Repurposing

et al. 2020

View full text Add to dashboard Cite

The rapid spread of novel coronavirus pneumonia (COVID-19) has led to a dramatically increased mortality rate worldwide. Despite many efforts, the rapid development of an effective vaccine for this novel virus will take considerable time and relies on the identification of drug-target (DT) interactions utilizing commercially available medication to identify potential inhibitors. Motivated by this, we propose a new framework, called DeepH-DTA, for predicting DT binding affinities for heterogeneous drugs. We propose a heterogeneous graph attention (HGAT) model to learn topological information of compound molecules and bidirectional ConvLSTM layers for modeling spatio-sequential information in simplified molecular-input line-entry system (SMILES) sequences of drug data. For protein sequences, we propose a squeezed-excited dense convolutional network for learning hidden representations within amino acid sequences; while utilizing advanced embedding techniques for encoding both kinds of input sequences. The performance of DeepH-DTA is evaluated through extensive experiments against cutting-edge approaches utilising two public datasets (Davis, and KIBA) which comprise eclectic samples of the kinase protein family and the pertinent inhibitors. DeepH-DTA attains the highest Concordance Index (CI) of 0.924 and 0.927 and also achieved a mean square error (MSE) of 0.195 and 0.111 on the Davis and KIBA datasets respectively. Moreover, a study using FDA-approved drugs from the Drug Bank database is performed using DeepH-DTA to predict the affinity scores of drugs against SARS-CoV-2 amino acid sequences, and the results show that that the model can predict some of the SARS-Cov-2 inhibitors that have been recently approved in many clinical studies.

show abstract

Section: Results and Comparisonsmentioning

confidence: 60%

Section: Results and Comparisonsmentioning

confidence: 88%

Section: Results and Comparisonsmentioning

confidence: 99%

Section: A Drug-target Interactionsmentioning

confidence: 99%

See 2 more Smart Citations

DeepH-DTA: Deep Learning for Predicting Drug-Target Interactions: A Case Study of COVID-19 Drug Repurposing

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Gao et al [17] combined Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN) to obtain meaningful information from protein sequences and drug structures. Zhao et al [18] proposed an end-to-end model, associated with an attention mechanism, to predict the binding affinity of DTIs. Zhao et al [19] proposed a neural network, GANsDTA, which combined two Generative Adversarial Networks (GANs) and a regression network to predict binding affinity.…”

Section: Introductionmentioning

confidence: 99%

Autoencoders for Drug-Target Interaction Prediction

Chen

Zhou²

2020

Preprint

View full text Add to dashboard Cite

Background: Because it is so laborious and expensive to experimentally identify Drug-Target Interactions (DTIs), only a few DTIs have been verified. Computational methods are useful for identifying DTIs in biological studies of drug discovery and development. Results: For drug-target interaction prediction, we propose a novel neural network architecture, DAEi, extended from Denoising AutoEncoder (DAE). We assume that a set of verified DTIs is a corrupted version of the full interaction set. We use DAEi to learn latent features from corrupted DTIs to reconstruct the full input. Also, to better predict DTIs, we add some similarities to DAEi and adopt a new nonlinear method for calculation. Similarity information is very effective at improving the prediction of DTIs. Conclusion: Results of the extensive experiments we conducted on four real data sets show that our proposed methods are superior to other baseline approaches.Availability: All codes in this paper are open-sourced, and our projects are available at: https://github.com/XiuzeZhou/DAEi.

show abstract

Proteome‐Scale Drug‐Target Interaction Predictions: Approaches and Applications

MacKinnon¹,

Tonekaboni²,

Windemuth³

2021

Current Protocols

View full text Add to dashboard Cite

Drug‐Target interaction predictions are an important cornerstone of computer‐aided drug discovery. While predictive methods around individual targets have a long history, the application of proteome‐scale models is relatively recent. In this overview, we will provide the context required to understand advances in this emerging field within computational drug discovery, evaluate emerging technologies for suitability to given tasks, and provide guidelines for the design and implementation of new drug‐target interaction prediction models. We will discuss the validation approaches used, and propose a set of key criteria that should be applied to evaluate their validity. We note that we find widespread deficiencies in the existing literature, making it difficult to judge the practical effectiveness of some of the techniques proposed from their publications alone. We hope that this review may help remedy this situation and increase awareness of several sources of bias that may enter into commonly used cross‐validation methods. © 2021 Cyclica Inc. Current Protocols published by Wiley Periodicals LLC.

show abstract

AttentionDTA: prediction of drug–target binding affinity using attention model

Cited by 78 publications

References 21 publications

DeepH-DTA: Deep Learning for Predicting Drug-Target Interactions: A Case Study of COVID-19 Drug Repurposing

DeepH-DTA: Deep Learning for Predicting Drug-Target Interactions: A Case Study of COVID-19 Drug Repurposing

Autoencoders for Drug-Target Interaction Prediction

Proteome‐Scale Drug‐Target Interaction Predictions: Approaches and Applications

Contact Info

Product

Resources

About