Novel computational model predicts effective drug combinations
A computational tool has accurately predicted a drug combination that inhibited triple-negative breast cancer in in vitro experiments.
Researchers at the Icahn School of Medicine at Mount Sinai (NY, USA) have developed a computational model that can predict synergistic drug combinations. They applied the tool to triple-negative breast cancer and found a drug combination that inhibited cancer cell growth more effectively than either drug individually.
Complex conditions such as cancer often involve multiple pathways and targets, so a combination of therapies is needed to treat the disease. However, with millions of potential drug combinations arising from thousands of available drugs, experimentally identifying effective drug combinations is costly and time-consuming.
To overcome this, the researchers developed a novel computational tool termed Identification of Drug Combinations via Multi-Set Operations (iDOMO). iDOMO is based on the idea that reversing disease gene expression changes would reverse disease-related phenotypes. It analyzes gene signatures of diseases and drug responses to predict the beneficial and detrimental effects of drug combinations.
ChromoGen: the AI tool predicting 3D genomic structures in minutes
A novel, freely available AI tool has cut the time it takes to determine chromatin structure from days to minutes.
“Our approach offers a more effective way to predict drug combinations that could serve as novel therapeutic options for treating human diseases,” commented senior author Bin Zhang. “This could significantly expand treatment options for clinicians and improve outcomes for patients who do not respond to standard therapies.”
The researchers applied iDOMO to find drug combinations that could be used for triple-negative breast cancer, an aggressive and difficult-to-treat form of cancer. The tool identified trifluridine and monobenzone as a promising combination. The researchers tested the combination in vitro on SUM159 cells and found that the combined drugs inhibited cancer cell growth more effectively than either drug alone.
“By leveraging computational approaches like iDOMO, we can prioritize the most promising drug combinations for further experimental validation, potentially accelerating the discovery of new treatments for a wide range of diseases,” commented Zhang.
Next, the researchers are going to apply iDOMO to other diseases, further refine the tool and integrate it into broader drug development pipelines.
