Deep mining heterogeneous networks of biomedical linked data to predict novel drug–target associations

Zong, Nansu; Kim, Hyeoneui; Ngo, Victoria; Harismendy, Olivier

doi:10.1093/bioinformatics/btx160

Cited by 168 publications

(106 citation statements)

References 29 publications

Supporting

Mentioning

106

Contrasting

Order By: Relevance

“…(ii) based on association rules, drugs with similar chemical structures tend to bind similar proteins. It is based on heterogeneous networks of DTIs, using single or fusion similarity measures as features [23,31,32,58].…”

Section: Predictive Ability Of Different Types Of Featuresmentioning

confidence: 99%

“…Wang et al [29] employed a restricted Boltzmann machine to find the data distribution such that identifies DTIs relationship as well as drug modes of action. Based on meta-path-based topological features, Fu et al [30] employed random forest classifier to do prediction, and Zong et al [31] calculated it with SkipGram model. These methods are difficult to find new targets or drugs in known networks.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

DTI-CDF: a CDF model towards the prediction of DTIs based on hybrid features

Chu

Zhang

Wang

et al. 2019

Preprint

View full text Add to dashboard Cite

Drug-target interactions play a crucial role in target-based drug discovery and exploitation. Computational prediction of DTIs has become a popular alternative strategy to the experimental methods for identification of DTIs of which are both time and resource consuming. However, the performances of the current DTIs prediction approaches suffer from a problem of low precision and high false positive rate. In this study, we aimed to develop a novel DTIs prediction method, named DTI-CDF, for improving the prediction precision based on a cascade deep forest model which integrates hybrid features, including multiple similarity-based features extracted from the heterogeneous graph, fingerprints of drugs, and evolution information of target protein sequences.In the experiments, we built five replicates of 10 fold cross-validations under three different experimental settings of data sets, namely, corresponding DTIs values of certain drugs ( ), targets ( ), or drug-target pairs ( ) in the training set are missed, but existed in the test set. The experimental results show that our proposed approach DTI-CDF achieved significantly higher performance than the state-of-the-art methods.

show abstract

Section: Predictive Ability Of Different Types Of Featuresmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

DTI-CDF: a CDF model towards the prediction of DTIs based on hybrid features

Chu

Zhang

Wang

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…The model uses data points reconstructed from neighborhood to calculate the linear neighborhood similarity of drug-drug. Based on biomedical related data and Linked Tripartite Network (LTN), Zong et al [14] used the target-target and drug-drug similarities calculated by DeepWalk to predict DTIs. In addition, Peng et al [15] combines the biological information of targets and drugs with PCA-based convex optimization algorithms to predict new DTIs using semi-supervised inference method.…”

Section: Introductionmentioning

confidence: 99%

RFDTI: Using Rotation Forest with Feature Weighted for Drug-Target Interaction Prediction from Drug Molecular Structure and Protein Sequence

Wang

You

et al. 2020

Preprint

View full text Add to dashboard Cite

The identification and prediction of Drug-Target Interactions (DTIs) is the basis for screening drug candidates, which plays a vital role in the development of innovative drugs. However, due to the time-consuming and high cost constraints of biological experimental methods, traditional drug target identification technologies are often difficult to develop on a large scale. Therefore, in silico methods are urgently needed to predict drug-target interactions in a genome-wide manner. In this article, we design a new in silico approach, named RFDTI to predict the DTIs combine Feature weighted Rotation Forest (FwRF) classifier with protein amino acids information. This model has two outstanding advantages: a) using the fusion data of protein sequence and drug molecular fingerprint, which can fully carry information; b) using the classifier with feature selection ability, which can effectively remove noise information and improve prediction performance. More specifically, we first use Position-Specific Score Matrix (PSSM) to numerically convert protein sequences and utilize Pseudo Position-Specific Score Matrix (PsePSSM) to extract their features.Then a unified digital descriptor is formed by combining molecular fingerprints representing drug information. Finally, the FwRF is applied to implement on Enzyme, Ion Channel, GPCR, and Nuclear Receptor data sets. The results of the five-fold cross-validation experiment show that the prediction accuracy of this approach reaches 91.68%, 88.11%, 84.72% and 78.33% on four benchmark data sets, respectively. To further validate the performance of the RFDTI, we compare it with other excellent methods and Support Vector Machine (SVM) model. In addition, 7 of the 10 highest predictive scores in predicting novel DTIs were validated by relevant databases. The experimental results of cross-validation indicated that RFDTI is feasible in predicting the relationship among drugs and target, and can provide help for the discovery of new candidate drugs.

show abstract

“…Different from the binary judgement made based on the classification models, inference-based models often utilize interactions, similarities and correlations between drugs and targets to predict a confidence score for a potential drug-target association. In general, the methods can be categorized to: 1) "guilt-by-association"based (Alaimo, et al, 2013;Cheng, et al, 2012;Wang, et al, 2013;Zong, et al, 2017), 2) random walk-based (Cheng, et al, 2012;Seal, et al, 2015), 3) similarity-based (Cheng, et al, 2012), and 4) statistical analysis-based (Cheng, et al, 2016). Since the information used in the inference-based methods can be easily pulled from networks, heterogeneous networks often serve as the input (Alaimo, et al, 2013;Cheng, et al, 2012;Cheng, et al, 2016;Luo, et al, 2017;Seal, et al, 2015;Wang, et al, 2013;Zong, et al, 2017).…”

Section: Introductionmentioning

confidence: 99%

“…Therefore, scalable and robust solutions that can process large heterogeneous datasets to yield precious prediction for new drugs/targets need to be studied. The existing machine learning-based works, including our previously proposed network-based (Linked Tripartite Network) solution (Zong, et al, 2017), have three essentials: 1) heterogeneous data, 2) feature learning methods, and 3) prediction generation methods. Therefore, the improvement for the three essentials are the main focus of our study to advance the prediction.…”

Section: Introductionmentioning

confidence: 99%

Scalable and Accurate Drug–target Prediction Based on Heterogeneous Bio-linked Network Mining

Zong¹,

Wong²,

Ngo³

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

Motivation:Despite the existing classification-and inference-based machine learning methods that show promising results in drug-target prediction, these methods possess inevitable limitations, where: 1) results are often biased as it lacks negative samples in the classification-based methods, and 2) novel drug-target associations with new (or isolated) drugs/targets cannot be explored by inference-based methods. As big data continues to boom, there is a need to study a scalable, robust, and accurate solution that can process large heterogeneous datasets and yield valuable predictions. Results: We introduce a drug-target prediction method that improved our previously proposed method from the three aspects: 1) we constructed a heterogeneous network which incorporates 12 repositories and includes 7 types of biomedical entities (#20,119 entities , # 194,296 associations), 2) we enhanced the feature learning method with Node2Vec, a scalable state-of-art feature learning method, 3) we integrate the originally proposed inference-based model with a classification model, which is further fine-tuned by a negative sample selection algorithm. The proposed method shows a better result for drug-target association prediction: 95.3% AUC ROC score compared to the existing methods in the 10-fold cross-validation tests. We studied the biased learning/testing in the network-based pairwise prediction, and conclude a best training strategy. Finally, we conducted a disease specific prediction task based on 20 diseases. New drug-target associations were successfully predicted with AUC ROC in average, 97.2% (validated based on the DrugBank 5.1.0). The experiments showed the reliability of the proposed method in predicting novel drug-target associations for the disease treatment.

show abstract

Deep mining heterogeneous networks of biomedical linked data to predict novel drug–target associations

Abstract: Supplementary data are available at Bioinformatics online.

Cited by 168 publications

References 29 publications

DTI-CDF: a CDF model towards the prediction of DTIs based on hybrid features

DTI-CDF: a CDF model towards the prediction of DTIs based on hybrid features

RFDTI: Using Rotation Forest with Feature Weighted for Drug-Target Interaction Prediction from Drug Molecular Structure and Protein Sequence

Scalable and Accurate Drug–target Prediction Based on Heterogeneous Bio-linked Network Mining

Contact Info

Product

Resources

About