Hello all,
Wani et al., 2024 scientific poster entitled "Prediction of Antimicrobial Peptides Using Machine Learning Approach," has been selected for the International Poster Presentation Competition in Peeref - a global communications platform tailored for scientific researchers.
Kindly vote through the link
https://lnkd.in/gnwrV3Ek
Kindly support us by voting for our poster for the competition. Thank you
please rate my research on antimicrobial peptide
Antimicrobial peptides (AMPs), also called host defense peptides (HDPs),
consist of 12 to 100 amino acids that are part of the innate immune system and
can be found among all classes of life including bacteria, fungi, plants,
invertebrates, and vertebrates. These AMPs have been found to be effective
against disease-causing pathogens. Identification of antimicrobial peptides
through in vitro and in vivo experiments on large number of peptides is an
expensive and time-consuming approach.
This study explores machine learning classifiers for predicting
antimicrobial peptides (AMPs) using a diverse set of AMPs (2638) and nonAMPs (3700). The RF classifier-based model outperformed other models in
both internal and external validations. It correctly predicted known AMPs and
non-AMPs, with ChargeD2001, PAAC12 (pseudo amino acid composition),
and polarity T13 being crucial features in AMPs' antimicrobial activity. The
developed RF-based classification model may be useful in designing and
predicting novel potential AMPs. https://www.peeref.com/poster-competition/202401?action=quick_vote&entry_id=1143
Webinar