Predicting adverse drug reactions of two‐drug combinations using structural and transcriptomic drug representations to train an artificial neural network

Abstract

The most common definition, provided by the WHO, for an adverse drug reaction (ADR) is "A response to a drug which is noxious and unintended and which occurs at doses normally used in man for prophylaxis, diagnosis, or therapy of disease, or the modification of physiological function or noxious and unintended responses to drugs, when they are administered in their normal recommended dosages." This study focuses on the prediction of ADRs caused by the drug-drug interaction (DDI) of two-drug combinations. Apart from contributing to various productive drug design strategies such as drug repurposing (Zhou et al., 2015), coadministered drugs can exhibit synergistic DDIs (Liu et al., 2017), which comprises a new ADR that may be associated with either of the drugs or the aggravation of an existing ADR. In this study, we have proposed an artificial neural network (ANN) that predicts this specific subclass of ADRs using transcriptomic data, compound chemical fingerprint, and GO ontologies.

DeSIDE-DDI: interpretable prediction of drug-drug interactions using drug-induced gene expressions

“…Decagon shows a good performance in predicting unseen interactions, but it is not applicable to predict interactions with unseen drugs because unseen drugs are not connected to the network [ 21 ]. Meanwhile, the ANN model worked by Shankar et al could be implemented for case 2 and 3 [ 38 ]. However, it showed relatively poor performance with our dataset.…”

“…For evaluation, we compared the prediction performance with previous studies—one is the first paper for predicting polypharmacy side effects using graph convolutional networks, and the other utilized the L1000 data [ 21 , 28 ]. Especially we implemented the ANN model to predict with our dataset because the proposed architecture can be applied for ‘one-unseen’ and ‘both-unseen’ cases.…”

“…Transcriptome-level information is provided that describes detailed drug responses. A recent study proposed an artificial neural network (ANN) that uses L1000 data [ 28 ] for gene expression, gene ontology, and compound fingerprint information as features. Their proposal includes a multi-label classification ANN model with three simple hidden layers.…”

On the road to explainable AI in drug-drug interactions prediction: A systematic review

“…Network interaction mining [62] , [63] , [64] and molecular graph representations have also been used to describe substructures of drugs that come in distinctive shapes and sizes or the structural relations between entities [65] , [66] , [67] , [68] . Additionally, to overcome the lack of data overlap between chemical content and biological characteristics, the combined structure-based input that includes both chemical and biological data by hybridizing cheminformatics and bioinformatics techniques to link all chemical information and biological effects have also been applied to serve as a meaningful method for DDIs discovery in many studies [69] , [70] , [71] .…”

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

“…Lee and Chen 299 extensively discussed the role of ML approaches in detection and classification of side effects caused by drug–drug interactions in their review of previous studies. In a recent study, Shankar et al 300 predicted the adverse drug reactions of coadministered drug pairs using an ANN trained on transcriptomic data, compound chemical fingerprint, and Gene Ontologies 300 …”