Drug–target prediction utilizing heterogeneous bio-linked network embeddings

Abstract

To enable modularization for network-based prediction, we conducted a review of known methods conducting the various subtasks corresponding to the creation of a drug–target prediction framework and associated benchmarking to determine the highest-performing approaches. Accordingly, our contributions are as follows: (i) from a network perspective, we benchmarked the association-mining performance of 32 distinct subnetwork permutations, arranging based on a comprehensive heterogeneous biomedical network derived from 12 repositories; (ii) from a methodological perspective, we identified the best prediction strategy based on a review of combinations of the components with off-the-shelf classification, inference methods and graph embedding methods. Our benchmarking strategy consisted of two series of experiments, totaling six distinct tasks from the two perspectives, to determine the best prediction. We demonstrated that the proposed method outperformed the existing network-based methods as well as how combinatorial networks and methodologies can influence the prediction. In addition, we conducted disease-specific prediction tasks for 20 distinct diseases and showed the reliability of the strategy in predicting 75 novel drug–target associations as shown by a validation utilizing DrugBank 5.1.0. In particular, we revealed a connection of the network topology with the biological explanations for predicting the diseases, ‘Asthma’ ‘Hypertension’, and ‘Dementia’. The results of our benchmarking produced knowledge on a network-based prediction framework with the modularization of the feature selection and association prediction, which can be easily adapted and extended to other feature sources or machine learning algorithms as well as a performed baseline to comprehensively evaluate the utility of incorporating varying data sources.

BETA: a comprehensive benchmark for computational drug–target prediction

“…Based on the data sources used as the input, two types of algorithms were used: network-based methods and structure- and sequence-based methods: (i) Network-based methods are the methods that used any graphical information from the proposed benchmark as the input, which includes multiple types of biomedical entities, such as drugs, targets, diseases, side effects and pathways, and the corresponding information from multipartite (including drug–target bipartite) networks. In practice, we used three state-of-the-art network-based methods: DTINet [ 21 ], Bio-Linked Network Embeddings (bioLNE) [ 64 ] and NEural integration of neighbOr information for DTI prediction (NeoDTI) [ 65 ]. For DTINet and NeoDTI, we used drug–target, drug–disease, protein–disease, drug–side effect, protein–protein, drug–drug interaction as well as drug–drug similarity, and protein–protein similarity matrices as the input data.…”

Leveraging Genetic Reports and Electronic Health Records for the Prediction of Primary Cancers: Algorithm Development and Validation Study

“…In order to train a model with the features generated from the input RDF data, we adapted a methodology [21] that considered RDF graph as a network, G(V,E) with a set of vertices V and a set of edges E, where V has 7 types of vertices (ie, genetics, lab tests, diagnosis, medication, family historical records, demographics, and patients) and E represents associations between the 6 types of vertices (ie, genetics, lab tests, diagnosis, medication, family historical records, demographics) and patients. We used the graph embedding method to learn the features of the patients, where a patient could be represented by a vector embedded within the topological structure of the patient in the network G. Node2vec [30] is a state-of-art graph embedding method that vectorizes the vertices of a network based on the topology of the network by maximizing the probability of observing the neighborhood N(u) of each node u in G: where and f (•) was the feature representation of a node.…”

“…A network-based data model can be used to represent the association between data models with edges, and the potential patterns are embedded in the topological structure of the network. Predictions from network-based data representations have achieved promising results in diverse biomedical areas, such as drug-target prediction [ 21 ] and patient clustering [ 22 ]. Representing correlations among phenotypic and genetic data elements through network-based data modeling shows great potential in cancer prediction.…”

Computational drug repurposing based on electronic health records: a scoping review

“…Conversely, in-silico methods gain their popularity through the analysis of heterogeneous data based on Artificial intelligence (AI) methods 4 , such as genetic association analysis, pathway mapping, molecular docking, and signature profile matching 5 , as such methods allow for all analysis to be done computationally in a time and cost-efficient manner. Computational drug repurposing can utilize a diverse set of data resources, including omics data (e.g., gene and protein expression) 6 , biomedical association/relation knowledgebase 7 , biomedical literature 8 , and the electronic health record (EHRs) 6 . Big EHR datasets offer a real-world perspective rooted in clinical care that provides rich longitudinal diagnostic and pathophysiological patient data, which can facilitate the generation and validation of drug repurposing hypotheses (e.g., statistical significance) 3 .…”