Multichannel bacterial discrimination based on recognition and disintegration disparity of short antimicrobial peptides

MMDB: Multimodal dual-branch model for multi-functional bioactive peptide prediction

Bioactive peptides can hinder oxidative processes and microbial spoilage in foodstuffs and play important roles in treating diverse diseases and disorders. While most of the methods focus on single-functional bioactive peptides and have obtained promising prediction performance, it is still a significant challenge to accurately detect complex and diverse functions simultaneously with the quick increase of multi-functional bioactive peptides. In contrast to previous research on multi-functional bioactive peptide prediction based solely on sequence, we propose a novel multimodal dual-branch (MMDB) lightweight deep learning model that designs two different branches to effectively capture the complementary information of peptide sequence and structural properties. Specifically, a multi-scale dilated convolution with Bi-LSTM branch is presented to effectively model the different scales sequence properties of peptides while a multi-layer convolution branch is proposed to capture structural information. To the best of our knowledge, this is the first effective extraction of peptide sequence features using multi-scale dilated convolution without parameter increase. Multimodal features from both branches are integrated via a fully connected layer for multi-label classification. Compared to state-of-the-art methods, our MMDB model exhibits competitive results across metrics, with a 9.1% Coverage increase and 5.3% and 3.5% improvements in Precision and Accuracy, respectively.

Gold nanoparticles-mediated fluorescent chemical nose sensor for pathogenic diagnosis and phenotype

Pathogens are one of the important factors affecting national economic construction. An ideal detection system for pathogen control with excellent sensitivity, high specificity, and time-saving is needed. Here, we reported a method for bacterial detection using gold nanoparticles-mediated fluorescent "chemical nose" sensors (GFCEs). The technique consists of gold nanoparticles-coated magnetic particle using benzaldehyde, octyl aldehyde, and pyrimidine-4-formaldehyde modified, respectively. And these positively charged nanocompound interacting with three different fluorescent proteins (FPs) to form three kinds of GFCEs, respectively, named GFCE1, GFCE2, and GFCE3. Upon binding with pathogenic cells, functionalized gold nanoparticles could identify patches on hydrophobic/functional surfaces of microorganisms, and self-assemble with living bacteria by complementary electrostatic interactions. The binding ability between GFCEs and bacteria determines the change of fluorescence response of three FPs from GFCEs. These feature fluorescent level are pathogen-specific, highly repeatable, and can be analyzed by Linear Discriminant Analysis (LDA). The combination of GFCE1 and GFCE2 has the best performance when detecting pathogens with concentrations of 10⁶  cfu mL^-1 . The first discriminant within 15 minutes is 93.8%, which could be used for subsequent identification of unknown samples. The commonly applicable system provides a simple way for the rapid bacterial detection without preprocessing procedures.

Array-Based Biosensors for Bacteria Detection: From the Perspective of Recognition

Array-based biosensors have shown as effective and powerful tools to distinguish intricate mixtures with infinitesimal differences among analytes such as nucleic acids, proteins, microorganisms, and other biomolecules. In array-based bacterial sensing, the recognition of bacteria is the initial step that can crucially influence the analytical performance of a biosensor array. Bacteria recognition as well as the signal readout and mathematical analysis are indispensable to ensure the discrimination ability of array-based biosensors. Strategies for bacteria recognition mainly include the specific interaction between biomolecules and the corresponding receptors on bacteria, the noncovalent interaction between materials and bacteria, and the specific targeting of bacterial metabolites. In this review, recent advances in array-based bacteria sensors are discussed from the perspective of bacteria recognition relying on the characteristics of different bacteria. Principles of bacteria recognition and signal readout for bacteria detection are highlighted as well as the discussion on future trends in array-based biosensors.