The number of microbiome-related studies has notably increased the availability of data on human microbiome composition and function. These studies provide the essential material to deeply explore host-microbiome associations and their relation to the development and progression of various complex diseases. Improved data-analytical tools are needed to exploit all information from these biological datasets, taking into account the peculiarities of microbiome data, i.e., compositional, heterogeneous and sparse nature of these datasets. The possibility of predicting host-phenotypes based on taxonomy-informed feature selection to establish an association between microbiome and predict disease states is beneficial for personalized medicine. In this regard, machine learning (ML) provides new insights into the development of models that can be used to predict outputs, such as classification and prediction in microbiology, infer host phenotypes to predict diseases and use microbial communities to stratify patients by their characterization of state-specific microbial signatures. Here we review the state-of-the-art ML methods and respective software applied in human microbiome studies, performed as part of the COST Action ML4Microbiome activities. This scoping review focuses on the application of ML in microbiome studies related to association and clinical use for diagnostics, prognostics, and therapeutics. Although the data presented here is more related to the bacterial community, many algorithms could be applied in general, regardless of the feature type. This literature and software review covering this broad topic is aligned with the scoping review methodology. The manual identification of data sources has been complemented with: (1) automated publication search through digital libraries of the three major publishers using natural language processing (NLP) Toolkit, and (2) an automated identification of relevant software repositories on GitHub and ranking of the related research papers relying on learning to rank approach.

DNA sequences accumulating in the International Nucleotide Sequence Databases (INSD) form a rich source of information for taxonomic and ecological meta-analyses. However, these databases include many erroneous entries, and the data itself is poorly annotated with metadata, making it difficult to target and extract entries of interest with any degree of precision. Here we describe the web-based workbench PlutoF, which is designed to bridge the gap between the needs of contemporary research in biology and the existing software resources and databases. Built on a relational database, PlutoF allows remote-access rapid submission, retrieval, and analysis of study, specimen, and sequence data in INSD as well as for private datasets though web-based thin clients. In contrast to INSD, PlutoF supports internationally standardized terminology to allow very specific annotation and linking of interacting specimens and species. The sequence analysis module is optimized for identification and analysis of environmental ITS sequences of fungi, but it can be modified to operate on any genetic marker and group of organisms. The workbench is available at http://plutof.ut.ee .

A literature analysis of 158 papers published in international peer-reviewed journals indexed by the Thomson Reuters Web of Knowledge from 1994 to 2013 showed that CO2C emission was significantly lower in free water surface (FWS) constructed wetlands (CW) than in subsurface flow (SF) CWs (median values from 95.8 to 137.0 mg m−2h−1, respectively). In vertical subsurface flow (VSSF) CWs the CH4Cemission was significantly lower than in horizontal subsurface flow (HSSF) CWs (median values 3.0, 6.4,and 4.0 mg m−2h−1, respectively). There were no significant differences in N2O N emission in various Cw types (median for FWS, VSSF and HSSF CWs: 0.09, 0.12, and 0.13 mg m−2h−1correspondingly).The highest value of emission factor (EF) of CH4((CH4C/inflow TOCin) * 100%) was found for FWSCWs (median 18.0%), followed by HSSF CWs (3.8%), and VSSF CWs (1.28%). Median values of N2O EFs((N2O N/inflow TNin) * 100%) differed significantly in all three CW types: 0.34% for HSSF, 0.11% for FWS,and 0.018% for VSSF CWs.We found a significant correlation between TOCin and CH4C emission and between the TNinandN2O N emission values for all of the types of CWs we studied.Hybrid CWs (e.g., the subsequent combination of VSSF, HSSF and FWS CWs) are beneficial from thepoint of view of both water purification and minimization of greenhouse gas (GHG) emissions. Likewise,intermittent loading in VSSF CWs and macrophyte harvesting in HSSF and FWS CWs can mitigate GH Gemissions.201