Identification of Drug-Disease Associations Using Information of Molecular Structures and Clinical Symptoms via Deep Convolutional Neural Network

  title={Identification of Drug-Disease Associations Using Information of Molecular Structures and Clinical Symptoms via Deep Convolutional Neural Network},
  author={Zhanchao Li and Qixing Huang and Xingyu Chen and Yang Wang and Jinlong Li and Yun Xie and Zong Dai and Xiaoyong Zou},
  journal={Frontiers in Chemistry},
Identifying drug-disease associations is helpful for not only predicting new drug indications and recognizing lead compounds, but also preventing, diagnosing, treating diseases. Traditional experimental methods are time consuming, laborious and expensive. Therefore, it is urgent to develop computational method for predicting potential drug-disease associations on a large scale. Herein, a novel method was proposed to identify drug-disease associations based on the deep learning technique… 

Figures and Tables from this paper

Predicting drug-disease associations through layer attention graph convolutional network
This study reveals that embeddings from different convolution layers can reflect the proximities of different orders, and combining theembeddings by the attention mechanism can improve the prediction performances.
Identification of Potential Parkinson’s Disease Drugs Based on Multi-Source Data Fusion and Convolutional Neural Network
Some of the predicted potential PD therapeutics through molecular docking further proved that they can exert their efficacy by acting on the known targets of PD, and may be potential PD therapeutic drugs for further experimental research.
Drug Repositioning with GraphSAGE and Clustering Constraints Based on Drug and Disease Networks
A new method based on GraphSAGE and clustering constraints (DRGCC) to investigate the potential therapeutic properties of drugs for drug repositioning and predict drugs that may be effective for the novel coronavirus disease 2019 (COVID-19).
Meta-Path Based Gene Ontology Profiles for Predicting Drug-Disease Associations
An ensemble learning method with Meta-path based Gene ontology Profiles for predicting Drug-Disease Associations (MGP-DDA), which outperforms the state-of-the-art methods and yields the precision of 88.6%.
A New Framework for Discovering Protein Complex and Disease Association via Mining Multiple Databases.
  • Lei XueXu-Qing Tang
  • Computer Science
    Interdisciplinary sciences, computational life sciences
  • 2021
A new framework including protein-protein networks, disease-gene associations and disease-complex pairs to cluster protein complexes and infer disease associations is proposed and can provide clinical scholars and medical practitioners with new ideas on disease identification and treatment.
A Discovery Strategy for Active Compounds of Chinese Medicine Based on the Prediction Model of Compound-Disease Relationship
A new method is proposed that integrates the molecular descriptors of compounds and the symptom descriptor of diseases to build a CDR two-dimensional matrix to predict candidate active compounds in Chinese medicine.
Graph Convolutional Autoencoder and Fully-Connected Autoencoder with Attention Mechanism Based Method for Predicting Drug-Disease Associations
GFPred, a method based on a graph convolutional autoencoder and a fully-connected autoen coder with an attention mechanism, to predict drug-related diseases and achieves better performance than several state-of-the-art prediction methods.


A Network-Based Classification Model for Deriving Novel Drug-Disease Associations and Assessing Their Molecular Actions
An integrative genetic network is generated using combinations of interactions, including protein-protein interactions and gene regulatory network datasets to find new drug-disease associations and identifies and visualized the topological modules of predicted drug indications for certain types of cancers, and for Alzheimer’s disease.
LRSSL: predict and interpret drug‐disease associations based on data integration using sparse subspace learning
This research presents a novel method for indication prediction of both new drugs and approved drugs based on Laplacian regularized sparse subspace learning (LRSSL), which integrates drug chemical information, drug target domain information and target annotation information.
PREDICT: a method for inferring novel drug indications with application to personalized medicine
A novel method for the large‐scale prediction of drug indications (PREDICT) that can handle both approved drugs and novel molecules and lays the computational foundation for future personalized drug treatments, where gene expression signatures from individual patients would replace the disease‐specific signatures.
Drug Repositioning by Kernel-Based Integration of Molecular Structure, Molecular Activity, and Phenotype Data
A new method for drug repositioning, PreDR (Predict Drug Repositioning), to integrate molecular structure, molecular activity, and phenotype data is proposed and can serve as a useful tool in drug discovery to efficiently identify novel drug-disease interactions.
Scoring multiple features to predict drug disease associations using information fusion and aggregation
The purpose of this study was to investigate the effect of drug and disease features as well as data fusion to predict drug–disease interactions and proposed a computational method named scored mean kernel fusion (SMKF), which uses a new method to score the average aggregation operator called scored mean.
Drug-Disease Association and Drug-Repositioning Predictions in Complex Diseases Using Causal Inference-Probabilistic Matrix Factorization
Modified causal inference included in CI-PMF outperformed existing causal inference with a higher AUC (area under receiver operating characteristic curve) score and greater precision and performed better than single modified causal inference in predicting therapeutic drug-disease associations.
Predicting drug-disease associations by using similarity constrained matrix factorization
A user-friendly web server is developed by using known associations collected from the CTD database, available at, which makes use of known drug-disease associations, drug features and disease semantic information.
Inferring drug-disease associations from integration of chemical, genomic and phenotype data using network propagation
The feasibility and benefits of using network-based analyses of chemical, genomic and phenotype data to reveal drug-disease associations are clearly demonstrated and provide new perspectives for toxicogenomics and drug reposition evaluation.
Inferring drug-disease associations based on known protein complexes
A novel methodology that discover the drug-disease association based on protein complexes by constructing an integrated heterogeneous network consisting of drugs, protein complexes, and disease, which can be directly reinforced by existing biomedical literature, suggesting that the proposed method obtains higher specificity and sensitivity.