Accurate noise-robust classification of Bacillus species from MALDI-TOF MS spectra using a denoising autoencoder

Bacillus strains are ubiquitous in the environment and are widely used in the microbiological industry as valuable enzyme sources, as well as in agriculture to stimulate plant growth. The Bacillus genus comprises several closely related groups of species. The rapid classification of these remains challenging using existing methods. Techniques based on MALDI-TOF MS data analysis hold significant promise for fast and precise microbial strains classification at both the genus and species levels. In previous work, we proposed a geometric approach to Bacillus strain classification based on mass spectra analysis via the centroid method (CM). One limitation of such methods is the noise in MS spectra. In this study, we used a denoising autoencoder (DAE) to improve bacteria classification accuracy under noisy MS spectra conditions. We employed a denoising autoencoder approach to convert noisy MS spectra into latent variables representing molecular patterns in the original MS data, and the Random Forest method to classify bacterial strains by latent variables. Comparison of the DAE-RF with the CM method using the artificially noisy test samples showed that DAE-RF offers higher noise robustness. Hence, the DAE-RF method could be utilized for noise-robust, fast, and neat classification of Bacillus species according to MALDI-TOF MS data.

Diversity and Metabolism of Microbial Communities in a Hypersaline Lake along a Geochemical Gradient

In the south of western Siberia (Russia), there are many unique and unexplored soda, saline, and freshwater lakes. In this study, the results are presented on microbial diversity, its metabolic potential, and their relation with a set of geochemical parameters for a hypersaline lake ecosystem in the Novosibirsk region (Oblast). The metagenomic approach used in this work allowed us to determine the composition and structure of a floating microbial community, the upper layer of silt, and the strata of bottom sediments in a natural saline lake via two bioinformatic approaches, whose results are in good agreement with each other. In the floating microbial community and in the upper layers of the bottom sediment, bacteria of the Proteobacteria (Gammaproteobacteria), Cyanobacteria, and Bacteroidetes phyla were found to predominate. The lower layers were dominated by Proteobacteria (mainly Deltaproteobacteria), Gemmatimonadetes, Firmicutes, and Archaea. Metabolic pathways were reconstructed to investigate the metabolic potential of the microbial communities and other hypothetical roles of the microbial communities in the biogeochemical cycle. Relations between different taxa of microorganisms were identified, as was their potential role in biogeochemical transformations of C, N, and S in a comparative structural analysis that included various ecological niches.

Metagenomics dataset used to characterize microbiome in water and sediments of the lake Solenoe (Novosibirsk region, Russia)

This is data on the microbial diversity in the floating cyanobacterial community and sediment samples from the lake Solenoe (Novosibirsk region, Russia) obtained by metagenomic methods. Such a detailed data of the microbial diversity of the Novosibirsk oblast lake ecosystem was carried out for the first time. The purpose of our work was to reveal microbial taxonomic diversity and abundance, metabolic pathways and new enzyme findings the studied lake ecosystem using the next-generation sequencing (NGS) technology and metagenomic analysis. The data was obtained using metagenomics DNA whole genome sequencing (WGS) on Illumina NextSeq and NovaSeq. The raw sequence data used for analysis is available in NCBI under the Sequence Read Archive (SRA) with the BioProjects and SRA accession numbers: PRJNA493912 (SRR7943696), PRJNA493952 (SRR7943839) and PRJNA661775 (SRR12601635, SRR12601634, SRR12601633) corresponding to floating cyanobacterial community and sediment layers samples, respectively.