ABSTRACT
Proteins are complex biomolecules essential for numerous biological processes, making them crucial targets for advancements in molecular biology, medical research, and drug design. Understanding their intricate, hierarchical structures, and functions is vital for progress in these fields. To capture this complexity, we introduce Multimodal Protein Representation Learning (MPRL), a novel framework for symmetry-preserving multimodal pretraining that learns unified, unsupervised protein representations by integrating primary and tertiary structures. MPRL employs Evolutionary Scale Modeling (ESM-2) for sequence analysis, Variational Graph Auto-Encoders (VGAE) for residue-level graphs, and PointNet Autoencoder (PAE) for 3D point clouds of atoms, each designed to capture the spatial and evolutionary intricacies of proteins while preserving critical symmetries. By leveraging Auto-Fusion to synthesize joint representations from these pretrained models, MPRL ensures robust and comprehensive protein representations. Our extensive evaluation demonstrates that MPRL significantly enhances performance in various tasks such as protein-ligand binding affinity prediction, protein fold classification, enzyme activity identification, and mutation stability prediction. This framework advances the understanding of protein dynamics and facilitates future research in the field. Our source code is publicly available at https://github.com/HySonLab/Protein_Pretrain.
ABSTRACT
The purpose of this study was to further characterize the multi-antimicrobial resistance and antibiotic resistance gene expression associated with multi-drug resistance (MDR) in Salmonella spp. isolates from retail meats in Hanoi, Vietnam. A total of 14 Salmonella spp. belonging to 9 serotypes (e.g., Warragul, London, Derby, Indiana, Meleagridis, Give, Rissen, Assine, and Typhimurium) were tested for sensitivity to 8 antibiotics. Resistance to at least one antibiotic was shown in 13 strains (92.85%). The multiple antimicrobial resistances accounted for 64.29% of isolates (9/14). One hundred percent of MDR isolates possessed antibiotic resistant genes, in which 17, 16 and 11 genes were found in Salmonella (Salm) Typhimurium S360, S384, S181 respectively; 12 genes in each strain as Indiana, Warragul, and Meleagridis; 11 genes in Give, 8 genes in Derby and 6 genes in Rissen. Three antibiotic resistance genes (ssaQ, aadA, and gyrB) were present in all isolates, whereas Cephalosporin-resistant gene (e.g., CTX-M3-like) was not detected in any isolates. The results suggest that retail meats could constitute a source of human exposure to multi-drug resistant Salmonella and future research should focus on the impact of these MDR source on the human genome. [Int Microbiol 20(2): 85-93 (2017)].
