PARMESAN: The Future of Genetic Disorder Treatments
Written by Shaveta Arora, Arushi Sharma
PARMESAN represents a visionary approach to genetic disorder treatments, heralding a new era in healthcare. Through groundbreaking research and cutting-edge therapies, we're rewriting the possibilities for those affected by genetic conditions.
Researchers looking for new treatments for genetic disorders must first thoroughly understand the existing literature in order to identify optimal gene/protein targets and promising drugs for testing. However, the rapidly expanding biomedical literature frequently contains contradictory data, making it increasingly difficult for scientists to conduct comprehensive and exhaustive reviews.
PARMESAN: Enhancing Genetic Research
The PARsing ModifiErS via Article aNnotations (PARMESAN) NLP tool can search for current information, compile it into a central knowledge base, and even predict potential medications to correct specific protein imbalances. The findings were published recently in the American Journal of Human Genetics.
"PARMESAN offers a wonderful opportunity for scientists to speed up the pace of their research and thus, accelerate drug discovery and development," Howard Hughes Medical Institute investigator, Dr. Huda Zoghbi, who is also the founding director of Duncan NRI and distinguished service professor at Baylor College, added.
This AI-powered tool scans public biomedical literature databases (PubMed and PubMed Central) to identify and rank descriptions of gene-gene and drug-gene regulatory relationships. What makes PARMESAN stand out is its unique capability to use curated information to predict undiscovered relationships.
"The unique feature of PARMESAN is that it not only identifies existing gene-gene or drug-gene interactions based on the available literature but also predicts putative novel drug-gene relationships by assigning an evidence-based score to each prediction," Dr. Zhandong Liu, Chief of Computation Sciences at Texas Children's Hospital and associate professor at Baylor College of Medicine, noted.
PARMESAN's AI algorithms analyze studies detailing the contributions of various players in a multistep genetic pathway. They assign a weighted numerical score to each reported interaction. Interactions consistently and frequently reported in the literature receive higher scores, while interactions weakly supported or contradicted in different studies get lower scores.
Currently, PARMESAN offers predictions for over 18,000 target genes, with benchmarking studies indicating over 95% accuracy for the highest-scoring predictions.
"By pinpointing the most promising gene and drug interactions, this tool will allow researchers to identify the most promising drugs at a faster rate and with greater accuracy," Cole Deisseroth, said.