Current advances in ligand‐based target prediction

• DOI: 10.1002/wcms.1504
• Publication Date: 2020-10-15T06:48:09Z
• Authors: Su‐Qing Yang; Qing Ye; Jun‐Jie Ding; Ming‐Zhu Yin; Ai‐Ping Lu; Xiang Chen; Ting‐Jun Hou; Dong‐Sheng Cao
• Keywords: Cheminformatics; Identification; Repurposing; Similarity (geometry); Drug target; Predictive modelling; Drug Development

Abstract Target identification for bioactive molecules augments modern drug discovery efforts in a range of applications, from the elaboration mode‐of‐action drugs to repurposing even knowledge side‐effects and further optimization. However, traditional labor‐intensive time‐consuming experiment methods obstructed development. Driven by massive bioactivity data deposited chemogenomic databases, computational alternatives have been proposed widely developed expedite validation process. By screening compound against protein database, it is possible identify potential target candidates that fit with this specific subsequent experimental validation. In particular, ligand‐based prediction made tremendous progress past decade due their flexibility, relatively low cost, remarkable predictive performance, are still moving forward. review, we present comprehensive overview including similarity searching, machine learning algorithm stacking, strategies validate these methods. We also discuss strength weakness existing sources model development outline challenges prospects prediction. It expected topic discussed review should guide application be interest audiences wider scientific community. This article categorized under: Data Science > Chemoinformatics