Predicting Drug-Disease Associations via Using Gaussian Interaction Profile and Kernel-Based Autoencoder

Abstract

Computational drug repositioning, designed to identify new indications for existing drugs, significantly reduced the cost and time involved in drug development. Prediction of drug-disease associations is promising for drug repositioning. Recent years have witnessed an increasing number of machine learning-based methods for calculating drug repositioning. In this paper, a novel feature learning method based on Gaussian interaction profile kernel and autoencoder (GIPAE) is proposed for drug-disease association. In order to further reduce the computation cost, both batch normalization layer and the full-connected layer are introduced to reduce training complexity. The experimental results of 10-fold cross validation indicate that the proposed method achieves superior performance on Fdataset and Cdataset with the AUCs of 93.30% and 96.03%, respectively, which were higher than many previous computational models. To further assess the accuracy of GIPAE, we conducted case studies on two complex human diseases. The top 20 drugs predicted, 14 obesity-related drugs, and 11 drugs related to Alzheimer's disease were validated in the CTD database. The results of cross validation and case studies indicated that GIPAE is a reliable model for predicting drug-disease associations.

An effective drug-disease associations prediction model based on graphic representation learning over multi-biomolecular network

“…Random forest can avoid the problem of decision tree overfitting. Compared with other single classifiers, it usually has more stable prediction performance [ 48 ]. Since stability and accuracy are very important for large-scale prediction of drugs-diseases association, in this work, random forest was selected as the classifier to process the extracted features.…”

Artificial intelligence and machine learning‐aided drug discovery in central nervous system diseases: State‐of‐the‐arts and future directions

“…Various specially designed AI/ML models have been proposed for detecting novel drug indications. Here, we classify the ML applications for drug repositioning into the following three categories: (i) Similarity‐based methods that employ different types of classifiers like logistic regression, 305,306 SVM, 307–309 RF, 310,311 KNN, 312 and CNN, 313 (ii) feature vector‐based methods that utilize supervised 314–318 and semisupervised 319–321 learning algorithms, and (iii) network‐based methods that mainly use semisupervised learning algorithms (e.g., Laplacian regularized least square, 322–324 label propagation, 325 random walk, 326 and RF 310 ). We provide an in‐depth discussion of these three classes of AI‐based drug repositioning applications in the Supporting Information.…”

Micro Expression Recognition: Multi-scale Approach to Automatic Emotion Recognition by using Spatial Pyramid Pooling Module

“…The five convolutional layers have the kernel number of 96 for the first convolutional layer, 256 for the second convolutional layer, and 512 for the third, fourth, and fifth convolutional layer. Jiang et al [52] proposed the fully-connected layers have a kernel size of 128 for the first and second layers, while three nodes for the third fully-connected layer to reduce the complexity of the training process. Each convolutional and full-connected layer is coupled with the ReLu activation function except for the last fully-connected layer, which is coupled with the Softmax activation function.…”