Please share if anyone is working on ML to identify antimicrobial peptides and their experimental validation.
The abuse of antibiotics in medicine, agriculture, and animal husbandry, especially in developing countries, has led to a serious increase in antimicrobial resistance. The WHO reported median rates of 42% for third-generation cephalosporin-resistant E. coli and 35% for methicillin-resistant Staphylococcus aureus in 76 countries, which are major concerns.
Typically, peptides can be encoded in the genome as short open reading frames or derived from larger proteins by proteolysis. However, predicting the therapeutic value of these peptides poses challenges due to high false positive rates. A recent article in Cell (July 11, 2024) describes a unique computational approach using machine learning to identify antimicrobial peptides. This study identified 79 peptides, with 63 targeting pathogens, and validated the results both in vitro and in vivo.
Santos-Júnior CD, Torres MD, Duan Y, Del Río ÁR, Schmidt TS, Chong H, Fullam A, Kuhn M, Zhu C, Houseman A, Somborski J. Discovery of antimicrobial peptides in the global microbiome with machine learning. Cell. 2024 Jun 5. (Open access)
------------------------------
Sudip Das, MPharm, PhD
Distinguished Faculty, Butler University
Professor of Pharmaceutics & Drug Delivery
4600 Sunset Avenue, Indianapolis, IN 46208-3485
E-mail:
[email protected]Webpage:
https://research.butler.edu/nanomedicine/LinkedIn:
http://www.linkedin.com/in/sudipkdasDisclaimer: Opinions expressed are solely my own and do not express the views or opinions of my employer.
------------------------------