The rapid development of machine learning (ML) techniques has opened up the data-dense field of microbiome research for novel therapeutic, diagnostic, and prognostic applications targeting a wide range of disorders, which could substantially improve healthcare practices in the era of precision medicine. However, several challenges must be addressed to exploit the benefits of ML in this field fully. In particular, there is a need to establish "gold standard" protocols for conducting ML analysis experiments and improve interactions between microbiome researchers and ML experts. The Machine Learning Techniques in Human Microbiome Studies (ML4Microbiome) COST Action CA18131 is a European network established in 2019 to promote collaboration between discovery-oriented microbiome researchers and data-driven ML experts to optimize and standardize ML approaches for microbiome analysis. This perspective paper presents the key achievements of ML4Microbiome, which include identifying predictive and discriminatory 'omics' features, improving repeatability and comparability, developing automation procedures, and defining priority areas for the novel development of ML methods targeting the microbiome. The insights gained from ML4Microbiome will help to maximize the potential of ML in microbiome research and pave the way for new and improved healthcare practices.

• Publikační typ
• časopisecké články MeSH

Proteins belonging to the DHH family, a member of the phosphoesterase superfamily, are produced by most bacterial species. While some of these proteins are well studied in Bacillus subtilis and Escherichia coli, their functions in Streptococcus pneumoniae remain unclear. Recently, the highly conserved DHH subfamily 1 protein PapP (SP1298) has been reported to play an important role in virulence. Here, we provide a plausible explanation for the attenuated virulence of the papP mutant. Recombinant PapP specifically hydrolyzed nucleotides 3'-phosphoadenosine-5'-phosphate (pAp) and 5'-phosphoadenylyl-(3'->5')-adenosine (pApA). Deletion of papP, potentially leading to pAp/pApA accumulation, resulted in morphological defects and mis-localization of several cell division proteins. Incubation with both polar solvent and detergent led to robust killing of the papP mutant, indicating that membrane integrity is strongly affected. This is in line with previous studies showing that pAp inhibits the ACP synthase, an essential enzyme involved in lipid precursor production. Remarkably, partial inactivation of the lipid biosynthesis pathway, by inhibition of FabF or depletion of FabH, phenocopied the papP mutant. We conclude that pAp and pApA phosphatase activity of PapP is required for maintenance of membrane lipid homeostasis providing an explanation how inactivation of this protein may attenuate pneumococcal virulence.

• MeSH
• adeninnukleotidy metabolismus   MeSH
• bakteriální proteiny genetika   metabolismus   MeSH
• DEAD-box RNA-helikasy metabolismus   MeSH
• fosfatasy genetika   metabolismus   MeSH
• homeostáza MeSH
• membránové lipidy metabolismus   MeSH
• mutace MeSH
• nukleotidy genetika   metabolismus   MeSH
• sekvenční delece MeSH
• Streptococcus pneumoniae enzymologie   genetika   metabolismus   patogenita   MeSH
• vazba proteinů MeSH
• vazebná místa MeSH
• virulence MeSH
• vztahy mezi strukturou a aktivitou MeSH
• Publikační typ
• časopisecké články MeSH