Detecting drug-drug interactions using artificial neural networks and classic graph similarity measures

Abstract

Drug-drug interactions are preventable causes of medical injuries and often result in doctor and emergency room visits. Computational techniques can be used to predict potential drug-drug interactions. We approach the drug-drug interaction prediction problem as a link prediction problem and present two novel methods for drug-drug interaction prediction based on artificial neural networks and factor propagation over graph nodes: adjacency matrix factorization (AMF) and adjacency matrix factorization with propagation (AMFP). We conduct a retrospective analysis by training our models on a previous release of the DrugBank database with 1,141 drugs and 45,296 drug-drug interactions and evaluate the results on a later version of DrugBank with 1,440 drugs and 248,146 drug-drug interactions. Additionally, we perform a holdout analysis using DrugBank. We report an area under the receiver operating characteristic curve score of 0.807 and 0.990 for the retrospective and holdout analyses respectively. Finally, we create an ensemble-based classifier using AMF, AMFP, and existing link prediction methods and obtain an area under the receiver operating characteristic curve of 0.814 and 0.991 for the retrospective and the holdout analyses. We demonstrate that AMF and AMFP provide state of the art results compared to existing methods and that the ensemble-based classifier improves the performance by combining various predictors. Additionally, we compare our methods with multi-source data-based predictors using cross-validation. In the multi-source data comparison, our methods outperform various ensembles created using 29 different predictors based on several data sources. These results suggest that AMF, AMFP, and the proposed ensemble-based classifier can provide important information during drug development and regarding drug prescription given only partial or noisy data. Additionally, the results indicate that the interaction network (known DDIs) is the most useful data source for identifying potential DDIs and that our methods take advantage of it better than the other methods investigated. The methods we present can also be used to solve other link prediction problems. Drug embeddings (compressed representations) created when training our models using the interaction network have been made public.

Drug-Drug Interaction Prediction on a Biomedical Literature Knowledge Graph

“…Authors in [18] present KMR, a procedure for similarity computation based on chemical structure and side effects. On the other hand, Shtar et al [19] employ adjacency matrix factorization to embed the drugs based on their interactivity as derived by DrugBank. Finally, authors in [6] also construct a biomedical Knowledge Graph from structured data (i.e.…”

Drug-Drug Interaction Prediction Based on Knowledge Graph Embeddings and Convolutional-LSTM Network

“…Since DDIs form a complex network in which nodes refer to drugs and links refer to potential interactions, we approach the DDIs prediction task as a link prediction problem similar to Shtar et al [38]. Given a directed DDI KG as G = (V , E) in which each edge e = (u, v) ∈ E represents an interaction between drugs u and v. Let N denotes the number of drugs, we can define the DDIs matrix Y ∈ {0, 1} N x N as follows:…”

“…In eq. (1), a value of 1 for y u,v indicates an existing interaction between drugs u and v. However, a value of 0 does not mean that an interaction does not exist in the KG, but it could be that the interaction has not yet been discovered [38]. Next, we proceed to DDIs extraction to be followed by KG construction.…”

“…ADRs are a significant threat to public health, as shown in a study by Shtar et al They found that about 6.7% of hospital readmission occurred because of ADRs with a fatality rate of 0.32% in the USA in 2014. In that year, as many as 807,270 cases of serious ADRs were reported in the United States, resulting in 123,927 lost lives [38].…”

MTDDI: a graph convolutional network framework for predicting Multi-Type Drug-Drug Interactions

“…Various machine learning methods have been proved as a promising method to provide a preliminary screening of DDIs for further experimental validation with the advantages of both high efficiency and low costs. Generally, the machine learning-based methods [4][5][6][7][8][9][10][11][12][13][14][15] use the approved DDIs training the predictive models to infer the potential DDIs among massive unlabeled drug pairs by extracting the drug features from diverse drug property source, such as chemical structure [4,[6][7][8][9], targets [4][5][6][7], anatomical taxonomy [5,8,10] and phenotypic observation [5,7,9,10], or extracting the drug similarity features [5,6,9,10,[16][17][18], or training the deep learning models to extract better features from raw features [19][20][21]. However, most of these existing methods focus on whether a drug interacts with another or not.…”