Advancing microbiome research with machine learning: key findings from the ML4Microbiome COST action.

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.

Genomic comparison of Escherichia coli serotype O103:H2 isolates with and without verotoxin genes: implications for risk assessment of strains commonly found in ruminant reservoirs.

INTRODUCTION: Escherichia coli O103:H2 occurs as verotoxigenic E. coli (VTEC) carrying only vtx 1 or vtx 2 or both variants, but also as vtx-negative atypical enteropathogenic E. coli (aEPEC). The majority of E. coli O103:H2 identified from cases of human disease are caused by the VTEC form. If aEPEC strains frequently acquire verotoxin genes and become VTEC, they must be considered a significant public health concern. In this study, we have characterized and compared aEPEC and VTEC isolates of E. coli O103:H2 from Swedish cattle. METHODS: Fourteen isolates of E. coli O103:H2 with and without verotoxin genes were collected from samples of cattle feces taken during a nationwide cattle prevalence study 2011-2012. Isolates were sequenced with a 2×100 bp setup on a HiSeq2500 instrument producing >100× coverage per isolate. Single-nucleotide polymorphism (SNP) typing was performed using the genome analysis tool kit (GATK). Virulence genes and other regions of interest were detected. Susceptibility to transduction by two verotoxin-encoding phages was investigated for one representative aEPEC O103:H2 isolate. RESULTS AND DISCUSSION: This study shows that aEPEC O103:H2 is more commonly found (64%) than VTEC O103:H2 (36%) in the Swedish cattle reservoir. The only verotoxin gene variant identified was vtx 1a . Phylogenetic comparison by SNP analysis indicates that while certain subgroups of aEPEC and VTEC are closely related and have otherwise near identical virulence gene repertoires, they belong to separate lineages. This indicates that the uptake or loss of verotoxin genes is a rare event in the natural cattle environment of these bacteria. However, a representative of a VTEC-like aEPEC O103:H2 subgroup could be stably lysogenized by a vtx-encoding phage in vitro.

2nd Combined Working Group and Management Committee Meeting of Urine and Kidney Proteomics COST Action 29-30 March 2009, Nafplio, Greece.

EuroKUP (Urine and Kidney Proteomics; www.eurokup.org) is a COST (European Cooperation in the field of Scientific and Technical research: www.cost.esf.org Action fostering a multi-disciplinary network of investigators from 25 countries and focusing on facilitating translational proteomic research in kidney diseases. Four Working Groups focusing respectively on defining clinically important research questions in kidney diseases, kidney tissue proteomics, urine proteomics and bioinformatics have been generated. The EuroKUP members had their second combined Working Group and Management Committee (MC) meeting in Nafplio, Greece from March 29 to 30, 2009. This report summarizes the main presentations, discussions and agreed action points during this meeting. These refer to the design of collaborative projects and clinical center networks for specific kidney diseases; establishment of guidelines for kidney tissue proteomics analysis by laser-based imaging- and laser capture microdissection-MS; development and characterization of a "standard" urine specimen to be used for assessment of platform capability and data comparability in clinical proteomics applications; definition of statistical requirements in biomarker discovery studies; and development of a specialized kidney and urine ontology. Various training activities are planned involving training schools on laser capture microdissection- and imaging-MS, workshops on ontologies as well as short-term travel grants for junior investigators.

EVALLER: a web server for in silico assessment of potential protein allergenicity.

Bioinformatics testing approaches for protein allergenicity, involving amino acid sequence comparisons, have evolved appreciably over the last several years to increased sophistication and performance. EVALLER, the web server presented in this article is based on our recently published 'Detection based on Filtered Length-adjusted Allergen Peptides' (DFLAP) algorithm, which affords in silico determination of potential protein allergenicity of high sensitivity and excellent specificity. To strengthen bioinformatics risk assessment in allergology EVALLER provides a comprehensive outline of its judgment on a query protein's potential allergenicity. Each such textual output incorporates a scoring figure, a confidence numeral of the assignment and information on high- or low-scoring matches to identified allergen-related motifs, including their respective location in accordingly derived allergens. The interface, built on a modified Perl Open Source package, enables dynamic and color-coded graphic representation of key parts of the output. Moreover, pertinent details can be examined in great detail through zoomed views. The server can be accessed at http://bioinformatics.bmc.uu.se/evaller.html.