The identification of drug-target interactions is a crucial issue in drug discovery. In recent years, researchers have made great efforts on the drug-target interaction predictions, and developed databases, software and computational methods. In the paper, we review the recent advances of machine learning-based drug-target interaction prediction. First, we briefly introduce the datasets and data, and summarize features for drugs and targets which can be extracted from different data. Since drug-drug similarity and target-target similarity are important for many machine learning prediction models, we introduce how to calculate similarities based on data or features. Different machine learning-based drug-target interaction prediction methods can be proposed by using different features or information. Thus, we summarize, analyze and compare different machine learning-based prediction methods. This study provides the guide to the development of computational methods for the drug-target interaction prediction.
Alzheimer’s disease (AD) is the prevalent cause of dementia in the ageing world population. Apolipoprotein E4 (ApoE4) allele is the key genetic risk factor for AD, although the mechanisms linking ApoE4 with neurocognitive impairments and aberrant metabolism remains to be fully characterised. We discovered a significant increase in the ApoE4 content of serum exosomes in old healthy subjects and AD patients carrying ApoE4 allele as compared with healthy adults. Elevated exosomal ApoE4 demonstrated significant inverse correlation with serum level of thyroid hormones and cognitive function. We analysed effects of ApoE4-containing peripheral exosomes on neural cells and neurological outputs in aged or thyroidectomised young mice. Ageing-associated hypothyroidism as well as acute thyroidectomy augmented transport of liver-derived ApoE4 reach exosomes into the brain, where ApoE4 activated nucleotide-binding oligomerisation domain-like receptor family pyrin domain-containing 3 (NLRP3) inflammasome by increasing cholesterol level in neural cells. This, in turn, affected cognition, locomotion and mood. Our study reveals pathological potential of exosomes-mediated relocation of ApoE4 from the periphery to the brain, this process can represent potential therapeutic target.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.