Photo Credit: Ipopba

The following is a summary of “Machine learning study of the extended drug–target interaction network informed by pain related voltage-gated sodium channels,” published in the April 2024 issue of Pain by Chen et al. 

Pain is a significant global health issue. However, current treatment options lack in terms of effectiveness, side effects, and potential for addiction, raising the need for improved treatment and the development of new drugs. 

Researchers conducted a prospective study identifying potential drug candidates for pain management by targeting Voltage-gated sodium channels (Nav1.3, Nav1.7, Nav1.8, Nav1.9). 

They constructed a protein-protein interaction (PPI) network based on pain-related sodium channels and drug-target networks. From over 1,000 targets, 111 inhibitor data sets were selected, and machine learning (ML) was employed to select candidates using a natural language process. 

The results showed 150,000 drug candidates for side effects, repurposing potential, and ADMET (absorption, distribution, metabolism, excretion, and toxicity)  properties of candidates. 

Investigators concluded an innovative platform for the pharmacological development of pain treatments, potentially offering improved efficacy and reduced side effects.

Source: journals.lww.com/pain/abstract/2024/04000/machine_learning_study_of_the_extended_drug_target.17.aspx