Inferring anatomical therapeutic chemical (ATC) class of drugs using shortest path and random walk with restart algorithms

Abstract

The anatomical therapeutic chemical (ATC) classification system is a widely accepted drug classification scheme. This system comprises five levels and includes several classes in each level. Drugs are classified into classes according to their therapeutic effects and characteristics. The first level includes 14 main classes. In this study, we proposed two network-based models to infer novel potential chemicals deemed to belong in the first level of ATC classification. To build these models, two large chemical networks were constructed using the chemical-chemical interaction information retrieved from the Search Tool for Interactions of Chemicals (STITCH). Two classic network algorithms, shortest path (SP) and random walk with restart (RWR) algorithms, were executed on the corresponding network to mine novel chemicals for each ATC class using the validated drugs in a class as seed nodes. Then, the obtained chemicals yielded by these two algorithms were further evaluated by a permutation test and an association test. The former can exclude chemicals produced by the structure of the network, i.e., false positive discoveries. By contrast, the latter identifies the most important chemicals that have strong associations with the ATC class. Comparisons indicated that the two models can provide quite dissimilar results, suggesting that the results yielded by one model can be essential supplements for those obtained by the other model. In addition, several representative inferred chemicals were analyzed to confirm the reliability of the results generated by the two models. This article is part of a Special Issue entitled: Accelerating Precision Medicine through Genetic and Genomic Big Data Analysis edited by Yudong Cai & Tao Huang.

Inferring Novel Tumor Suppressor Genes with a Protein-Protein Interaction Network and Network Diffusion Algorithms

“… 79 This algorithm is also a type of network diffusion algorithm that has been successfully applied to identify novel genes, proteins, or chemicals in different networks. 71 , 72 , 80 , 81 The RWR algorithm simulates a walker starting from one seed node or a set of seed nodes and walking randomly on the network. Similar to the LHD algorithm, an initial probability distribution vector, , was constructed, which was the same as that in the LHD algorithm, and was repeatedly updated.…”

Use of Laplacian Heat Diffusion Algorithm to Infer Novel Genes With Functions Related to Uveitis

“…Inferring novel genes related to different diseases in network level has become quite popular ( Barabasi et al, 2011 ). Several classic network algorithms, such as shortest path algorithm ( Gormen et al, 1990 ; Gui et al, 2015 ; Chen et al, 2016a ; Zhang et al, 2016 ; Cai et al, 2017 , Chen et al, 2018a ), and RWR algorithm ( Chen et al, 2017a , 2018c ; Li et al, 2017 , 2018a ; Yuan and Lu, 2017 ; Zhang et al, 2017 ), have been applied to develop different computational methods in this regard. A recent publication ( Lu et al, 2017 ) proposed a RWR-based computational method to identify novel uveitis-related genes and reported several ones.…”

Prediction of Drug Side Effects with a Refined Negative Sample Selection Strategy

“…Drug Network. It has been reported in several studies that interacting chemicals are more likely to share similar properties [24][25][26][27][28][29]. It is feasible to adopt such information for investigating drug side effects because side effect is one of the important properties of drugs.…”

“…Walk with Restart Algorithm. The RWR algorithm is a powerful and widely used network ranking algorithm [20,27,[30][31][32][33]. In this algorithm, the walker randomly moves from a seed node set to other nodes in the network.…”