Predicting Drug Targets in Human Cancers

Abstract

Introduction

A large amount of knowledge has accumulated regarding the pharmacology of most cancer types, including their side effects, and during the last decade, many novel agents have emerged, accompanied by increased costs for healthcare systems.

Aim

Artificial intelligence (AI) was applied in healthcare services, and the benefit of its use in the prediction of the targets of low molecular weight compounds that can affect biological processes was assessed (proportion of the top predicted targets, common name, target class and probability).

Method

Designing the chemical agent or molecule chosen and the program will give the protein target prediction immediately by AI. A tuning algorithm device, with new information input in the web application interface, was used.

Results

Information was arranged in order and fed to an in silico target prediction/Swiss TargetPrediction (STP). This tool is a computational method used to predict the most probable protein targets of small molecules, as well as to envisage what happens when many chemotherapy drugs are combined in cancer treatment. It aids in understanding some molecular processes controlling specific physical traits or biological activities to elucidate probable beneficial and adverse consequences. In addition, it helps to predict imprecision of defined molecules and pave the way to drug repositioning. Prediction is carried out employing the ligand-based drug design (LBDD), which enables comparison of the correlation between the molecule under examination and the known binding molecules of a large set of target proteins.

Conclusion

Target activity profiles enable a systematic repurposing process by extending the target profile of drugs, and then drug repurposing with AI provides a cost-effective strategy to reuse approved drugs for new medical indications and the availability of new treatments, reduces development costs and mitigates risks due to the cost of the cancer drug agents, coupled with high cancer disease prevalence, which means the current cost trajectory is untenable for most world healthcare systems.