Related Experiment Video
Updated: Jul 27, 2026

A Method for Targeted 16S Sequencing of Human Milk Samples
Published on: March 23, 2018
Discovery of milk-derived antimicrobial peptides in human milk by DeepMAMP based on peptidomics technology and deep
Wenhao Yu1, Xinchen Zhang2, Yang Yu1
1Division of Energy Research Resources, Dalian Institute of Chemical Physics, Chinese Academy of Sciences, Dalian, Liaoning 116023, China.
Abstract:
Milk-derived antimicrobial peptides (MAMPs) in human milk (HMAMPs) play an important role in the nutrition and the immune system construction of newborns. Current AMP prediction models cannot accurately predict HMAMPs, thus high-throughput and targeted methods are urgently needed. This study proposes a novel workflow for discovering HMAMPs by peptidomics technology and deep learning methods. We propose a novel MAMPs prediction model, DeepMAMP, with an accuracy of 81.4 % based on a combination of the Light Gradient Boosting Machine (LightGBM), Long Short-Term Memory (LSTM) and an attention mechanism. A total of 311 potential HMAMPs in human milk were predicted by DeepMAMP. Six predicted potential HMAMPs underwent antimicrobial assays, and five were experimentally verified as HMAMPs. The results demonstrated the HMAMPs' prediction effectiveness of DeepMAMP and provided a comprehensive method for screening novel HMAMPs, providing a strong support for the application of HMAMPs in functional foods and pharmaceuticals fields.
Related Concept Videos
MALDI-TOF Mass Spectrometry
Peptide Identification Using Tandem Mass Spectrometry
This technique helps gather information regarding the protein from which the peptide was obtained and to study the peptides’ amino acid sequence. Identifying peptides from a complex mixture is an important component of the growing field of...
Microorganisms in Medicine and Therapeutics
Development of Human Microbiota
Rapid Identification of Pathogens
Clinical Significance of Antibiotic Resistance

