Drug-Target Interaction Prediction via Graph Auto-Encoder and Multi-Subspace Deep Neural Networks

Ye, Qing; Zhang, Xiaolong; Lin, Xiaojie

doi:10.1109/tcbb.2022.3206907

Cited by 11 publications

(2 citation statements)

References 69 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This model is suitable for nonlinear fitting, because of a lot of parameters. Many research proved that MLP methods are suitable for drug‐target interaction prediction 29,30 . When the number of training data is big, the deep learning models based on multilayer perceptron could always have good prediction results 31 …”

Section: Methodsmentioning

confidence: 99%

“…Many research proved that MLP methods are suitable for drug-target interaction prediction. 29,30 When the number of training data is big, the deep learning models based on multilayer perceptron could always have good prediction results. 31 Random forest (RF) is an ensemble method consisting of many individual decisions.…”

Section: Logistic Regression (Lr) Is An Algorithm Which Uses Least Sq...mentioning

confidence: 99%

See 1 more Smart Citation

Multiple machine learning methods aided virtual screening of Na_V1.5 inhibitors

Zhu

Huang

Peng

et al. 2022

J Cellular Molecular Medi

View full text Add to dashboard Cite

Na v 1.5 sodium channels contribute to the generation of the rapid upstroke of the myocardial action potential and thereby play a central role in the excitability of myocardial cells. At present, the patch clamp method is the gold standard for ion channel inhibitor screening. However, this method has disadvantages such as high technical difficulty, high cost and low speed. In this study, novel machine learning models to screen chemical blockers were developed to overcome the above shortage. The data from the ChEMBL Database were employed to establish the machine learning models. Firstly, six molecular fingerprints together with five machine learning algorithms were used to develop 30 classification models to predict effective inhibitors. A validation and a test set were used to evaluate the performance of the models. Subsequently, the privileged substructures tightly associated with the inhibition of the Na v 1.5 ion channel were extracted using the bioalerts Python package. In the validation set, the RF‐Graph model performed best. Similarly, RF‐Graph produced the best result in the test set in which the Prediction Accuracy (Q) was 0.9309 and Matthew's correlation coefficient was 0.8627, further indicating the model had high classification ability. The results of the privileged substructures indicated Sulfa structures and fragments with large Steric hindrance tend to block Na v 1.5. In the unsupervised learning task of identifying sulfa drugs, MACCS and Graph fingerprints had good results. In summary, effective machine learning models have been constructed which help to screen potential inhibitors of the Na v 1.5 ion channel and key privileged substructures with high affinity were also extracted.

show abstract

Section: Methodsmentioning

confidence: 99%