Prediction of Thermal Conductance of Complex Networks with Deep Learning

Predicting thermal conductance of complex networks poses a formidable challenge in the field of materials science and engineering. This challenge arises due to the intricate interplay between the parameters of network structure and thermal conductance, encompassing connectivity, network topology, network geometry, node inhomogeneity, and others. Our understanding of how these parameters specifically influence heat transfer performance remains limited. Deep learning offers a promising approach for addressing such complex problems. We find that the well-established convolutional neural network models AlexNet can predict the thermal conductance of complex network efficiently. Our approach further optimizes the calculation efficiency by reducing the image recognition in consideration that the thermal transfer is inherently encoded within the Laplacian matrix.Intriguingly, our findings reveal that adopting a simpler convolutional neural network architecture can achieve a comparable prediction accuracy while requiring less computational time. This result facilitates a more efficient solution for predicting the thermal conductance of complex networks and serves as a reference for machine learning algorithm in related domains.

Response of Salmonella enterica serovar Typhimurium to alginate oligosaccharides fermented with fecal inoculum:integrated transcriptomic and metabolomic analyses

Alginate oligosaccharides(AOS),extracted from marine brown algae,are a common functional feed additive;however,it remains unclear whether they modulate the gut microbiota and microbial metabolites.The response of Salmonella enterica serovar Typhimurium,a common poultry pathogen,to AOS fermented with chicken fecal inocula was investigated using metabolomic and transcriptomic analyses.Single-strain cultivation tests showed that AOS did not directly inhibit the growth of S.Typhimurium.However,when AOS were fermented by chicken fecal microbiota,the supernatant of fermented AOS(F-AOS)exhibited remarkable antibacterial activity against S.Typhimurium,decreasing the abundance ratio of S.Typhimurium in the fecal microbiota from 18.94 to 2.94%.Transcriptomic analyses showed that the 855 diferentially expressed genes induced by F-AOS were mainly enriched in porphyrin and chlorophyll metabolism,oxidative phosphorylation,and Salmonella infection-related pathways.RT-qPCR confrmed that F-AOS downregulated key genes involved in fagellar assembly and the type III secretory system of S.Typhimurium,indicating metabolites in F-AOS can infuence the growth and metabolism of S.Typhimurium.Metabolomic analyses showed that 205 microbial metabolites were signifcantly altered in F-AOS.Among them,the increase in indolelactic acid and 3-indolepropionic acid levels were further confrmed using HPLC.This study provides a new perspective for the application of AOS as a feed additive against pathogenic intestinal bacteria.