Graph Convolutional Autoencoder and Generative Adversarial Network-Based Method for Predicting Drug-Target Interactions

Sun, Chang; Xuan, Ping; Zhang, Tiangang; Ye, Yilin

doi:10.1109/tcbb.2020.2999084

Cited by 47 publications

(9 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the AUC and AUPR are usually adequate metrics for evaluating the performance of a model for DTI prediction [ 40 ]. Many similar studies have used these two metrics to evaluate the performance of methods for predicting DTIs [ 26 , 28 , 41 – 43 ]. As biologists often select drug-target pairs with high prediction scores for subsequent wet experiment validation, the recall rates of the top (5%, 10%, 15%, 20%, and 30%) proportion of candidate targets predicted by the model were selected.…”

Section: Resultsmentioning

confidence: 99%

“…To further evaluate the performance of SDGAE, we compared it with several other state-of-the-art methods, including GRMF [ 8 ], DTINet [ 9 ], GANDTI [ 28 ], NGDTP [ 7 ], MolTrans [ 19 ], and GADTI [ 26 ]. The hyperparameters of these methods were selected based on ranges recommended in the literature.…”

Section: Resultsmentioning

confidence: 99%

“…The encoder in this model consists of the combination of a GCN and an RWR, which provides more information to the nodes, and DisMult [ 27 ] was used as the decoder. The GANDTI model proposed by Sun et al [ 28 ] also uses a GCN to encode the drug and target features, but it then uses a generative adversarial network (GAN) to enhance the robustness and reduce the noise of feature vectors. However, most of these methods do not maintain invariant neighbour relationships during representation learning.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Drug-target interaction prediction based on spatial consistency constraint and graph convolutional autoencoder

Chen

Zheng

2023

BMC Bioinformatics

View full text Add to dashboard Cite

Background Drug-target interaction (DTI) prediction plays an important role in drug discovery and repositioning. However, most of the computational methods used for identifying relevant DTIs do not consider the invariance of the nearest neighbour relationships between drugs or targets. In other words, they do not take into account the invariance of the topological relationships between nodes during representation learning. It may limit the performance of the DTI prediction methods. Results Here, we propose a novel graph convolutional autoencoder-based model, named SDGAE, to predict DTIs. As the graph convolutional network cannot handle isolated nodes in a network, a pre-processing step was applied to reduce the number of isolated nodes in the heterogeneous network and facilitate effective exploitation of the graph convolutional network. By maintaining the graph structure during representation learning, the nearest neighbour relationships between nodes in the embedding space remained as close as possible to the original space. Conclusions Overall, we demonstrated that SDGAE can automatically learn more informative and robust feature vectors of drugs and targets, thus exhibiting significantly improved predictive accuracy for DTIs.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Drug-target interaction prediction based on spatial consistency constraint and graph convolutional autoencoder

Chen

Zheng

2023

BMC Bioinformatics

View full text Add to dashboard Cite

show abstract

“…The generative adversarial network was utilized to regulate the encoder so that the low dimensional feature vector generated by the encoder is followed the Gaussian distribution to ensure the feature vector's robustness. In terms of DTI prediction, the model adopts an integrated learning method and used the drugs and target proteins' low dimensional features to predict the interaction possibility [5]. The prediction method based on molecular sequence (such as AEFS) ignores the similarity relationship between drugs (or targets), and the prediction method based on heterogeneous network structure (such as GRMF, DDR) ignores the attributes of nodes themselves.…”

Section: Introductionmentioning

confidence: 99%

A Graph Convolutional Network-based Method for Drug-Target Interaction Prediction Running title: GCNDTI

Jin

2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Studying the interaction between drugs and targets is the key step of drug repositioning. Through machine learning methods, we can provide reliable drug-target pairs for drug-target interaction (DTI) identification for wet-lab experiments and improve its efficiency. Previous methods did not combine node attributes and relationships of drug and target, which limited the performance of those methods. To this end, we propose a prediction method that takes into account both node attributes and topology information and named it GCNDTI. Using a graph neural network, the low-dimensional feature vectors of drugs and targets are obtained. Utilizing the nonlinear graph neural network model, the drugs and targets’s abstract feature are obtained. The experimental results confirm that compared with added methods, our method shows superior achievement in DTI prediction.

show abstract

“…The method WideDTA [20] adapts the word-based sequence representation for compounds and proteins, and utilizes two extra features LMCS (ligand max common structures) and PDM (protein motifs and domains) to improve model performance and prediction accuracy. From the perspective that compound structure is regarded as molecular graph, the methods CPI-GNN [21] and Graph-DTA [22] use graph neural networks (GNNs) [23], [24] and graph convolutional neural networks (GCNs) [25] to learn representation of compounds, the model GANDTI integrates a graph convolutional autoencoder and generative adversarial network (GAN) to deeply learn the feature vectors for drugs and targets [26]. Regarding both compounds and proteins as sequence data, recurrent neural networks (RNNs) are used to extract feature vectors of compounds and proteins in DeepAffinity [27] and Zheng's work [28].…”

mentioning

confidence: 99%

FMGNN: A Method to Predict Compound-Protein Interaction With Pharmacophore Features and Physicochemical Properties of Amino Acids

Tang

Zhong

Wang

et al. 2023

IEEE/ACM Trans. Comput. Biol. and Bioinf.

View full text Add to dashboard Cite

Identifying interactions between compounds and proteins is an essential task in drug discovery. To recommend compounds as new drug candidates, applying the computational approaches has a lower cost than conducting the wet-lab experiments. Machine learning-based methods, especially deep learning-based methods, have advantages in learning complex feature interactions between compounds and proteins. However, deep learning models will over-generalize and lead to the problem of predicting less relevant compound-protein pairs when the compound-protein feature interactions are high-dimensional sparse. This problem can be overcome by learning both low-order and high-order feature interactions. In this paper, we propose a novel hybrid model with Factorization Machines and Graph Neural Network called FMGNN to extract the low-order and high-order features, respectively. Then, we design a compound-protein interactions (CPIs) prediction method with pharmacophore features of compound and physicochemical properties of amino acids. The pharmacophore features can ensure that the prediction results much more fit the expectation of biological experiment and the physicochemical properties of amino acids are loaded into the embedding layer to improve the convergence speed and accuracy of protein feature learning. The experimental results on several datasets, especially on an imbalanced large-scale dataset, showed that our proposed method outperforms other existing methods for CPI prediction. The western blot experiment results on wogonin and its candidate target proteins also showed that our proposed method is effective and accurate for finding target proteins. The computer program of implementing the model FMGNN is available at https://github.com/tcygxu2021/FMGNN.

show abstract

Graph Convolutional Autoencoder and Generative Adversarial Network-Based Method for Predicting Drug-Target Interactions

Cited by 47 publications

References 47 publications

Drug-target interaction prediction based on spatial consistency constraint and graph convolutional autoencoder

Drug-target interaction prediction based on spatial consistency constraint and graph convolutional autoencoder

A Graph Convolutional Network-based Method for Drug-Target Interaction Prediction Running title: GCNDTI

FMGNN: A Method to Predict Compound-Protein Interaction With Pharmacophore Features and Physicochemical Properties of Amino Acids

Contact Info

Product

Resources

About