A new algorithm developed by researchers at New York-based Mount Sinai School of Medicine aims to help scientists to better understand why different drugs have certain side effects on patients, the school announced. The algorithm assists researchers in building networks from data found in medical records by helping them to better understand interactions like gene-gene, protein-protein and drug side effects.
The researchers, led by Avi Ma'ayan, Ph.D., created 15 types of gene-gene networks using the algorithm. They also found unreported side effects of drugs through a network built via analysis of 1 million patient medical records consisting of common co-prescribed drugs, common side effects and relationships between side effects and drug combinations.
They found 32 severe side effects stemming from 53 cancer drugs using a network built via the algorithm, dubbed Genes2FANs (functional association networks), outlined earlier in the month in BMC Bioinformatics.
"Once high dimensional and complex data is converted to networks, we can understand the data better and discover new and significant relationships and focus on the important features of the data," Ma'ayan said in a statement.
Earlier this month, a study published in the journal Cancer Research outlined the development of new tools by the National Cancer Institute that will allow researchers to compare data from large collections of genomic information against thousands of drugs to find the most effective treatments for cancer.
What's more, research appearing in June in the journal Nature showed how computer models hold promise for predicting negative side effects in drugs.
To learn more:
- read the Mount Sinai School of Medicine announcement
- here's the BMC Bioinformatics study
- check out the tools that implement the approach here and here