Machine learning toolkit can improve odds of drug development success
Southwest Research Institute (SwRI) is using a generative artificial intelligence (AI) tool to improve pharmaceutical development outcomes. The SwRI-developed GAMES, or Generative Approaches for Molecular Encodings, uses large language models (LLMs) to produce text strings representing chemical structures.
Southwest Research Institute (SwRI) has developed a machine learning tool called GAMES, or Generative Approaches for Molecular Encodings, to enhance the drug development process. GAMES employs large language models (LLMs) and machine learning to generate text strings that represent chemical structures, providing chemists with informed decision-making capabilities.
Dr. Jonathan Bohmann, one of GAMES' inventors, explains that the tool can identify viable paths forward when preclinical development encounters roadblocks such as instability or toxicity issues.
GAMES complements SwRI's computer-aided drug design platform, Rhodium, by integrating a ranking system that evaluates compound structures based on the properties of FDA-approved drugs. The model is trained to avoid issues like solubility, toxicity, and off-target effects, generating viable compound structures with a higher likelihood of FDA approval.
SwRI scientists have already used GAMES to advance drug development projects, including the identification of 18 antiviral candidates for treating filovirus infections like Ebola. These candidates ranked in the top 10% of ranked candidates, with over a quarter considered for follow-on studies.
Written by urgent.news from Medical Xpress's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
