Search

ObjectivesThis study aimed to explore the effects of an isocaloric Mediterranean diet (MD) intervention on metabolic health, gut microbiome and systemic metabolome in subjects with lifestyle risk factors for metabolic disease.DesignEighty-two healthy overweight and obese subjects with a habitually low intake of fruit and vegetables and a sedentary lifestyle participated in a parallel 8-week randomised controlled trial. Forty-three participants consumed an MD tailored to their habitual energy intakes (MedD), and 39 maintained their regular diets (ConD). Dietary adherence, metabolic parameters, gut microbiome and systemic metabolome were monitored over the study period.ResultsIncreased MD adherence in the MedD group successfully reprogrammed subjects’ intake of fibre and animal proteins. Compliance was confirmed by lowered levels of carnitine in plasma and urine. Significant reductions in plasma cholesterol (primary outcome) and faecal bile acids occurred in the MedD compared with the ConD group. Shotgun metagenomics showed gut microbiome changes that reflected individual MD adherence and increase in gene richness in participants who reduced systemic inflammation over the intervention. The MD intervention led to increased levels of the fibre-degrading Faecalibacterium prausnitzii and of genes for microbial carbohydrate degradation linked to butyrate metabolism. The dietary changes in the MedD group led to increased urinary urolithins, faecal bile acid degradation and insulin sensitivity that co-varied with specific microbial taxa.ConclusionSwitching subjects to an MD while maintaining their energy intake reduced their blood cholesterol and caused multiple changes in their microbiome and metabolome that are relevant in future strategies for the improvement of metabolic health.

First responders and recovery planners need accurate and quickly derived information about the status of buildings as well as newly built ones to both help victims and to make decisions for reconstruction processes after a disaster. Deep learning and, in particular, convolutional neural network (CNN)-based approaches have recently become state-of-the-art methods to extract information from remote sensing images, in particular for image-based structural damage assessment. However, they are predominantly based on manually extracted training samples. In the present study, we use pre-disaster OpenStreetMap building data to automatically generate training samples to train the proposed deep learning approach after the co-registration of the map and the satellite images. The proposed deep learning framework is based on the U-net design with residual connections, which has been shown to be an effective method to increase the efficiency of CNN-based models. The ResUnet is followed by a Conditional Random Field (CRF) implementation to further refine the results. Experimental analysis was carried out on selected very high resolution (VHR) satellite images representing various scenarios after the 2013 Super Typhoon Haiyan in both the damage and the recovery phases in Tacloban, the Philippines. The results show the robustness of the proposed ResUnet-CRF framework in updating the building map after a disaster for both damage and recovery situations by producing an overall F1-score of 84.2%.

Background Water springs provide important ecosystem services including drinking water supply, recreation, and balneotherapy, but their microbial communities remain largely unknown. In this study, we characterized the spring water microbiome of Comano Terme (Italy) at four sampling points of the thermal spa, including natural (spring and well) and human-built (storage tank, bathtubs) environments. We integrated large-scale culturing and metagenomic approaches, with the aim of comprehensively determining the spring water taxonomic composition and functional potential. Results The groundwater feeding the spring hosted the most atypical microbiome, including many taxa known to be recalcitrant to cultivation. The core microbiome included the orders Sphingomonadales, Rhizobiales, and Caulobacterales, and the families Bradyrhizobiaceae and Moraxellaceae. A comparative genomic analysis of 72 isolates and 30 metagenome-assembled genomes (MAGs) revealed that most isolates and MAGs belonged to new species or higher taxonomic ranks widely distributed in the microbial tree of life. Average nucleotide identity (ANI) values calculated for each isolated or assembled genome showed that 10 genomes belonged to known bacterial species (> 95% ANI), 36 genomes (including 1 MAG) had ANI values ranging 85–92.5% and could be assigned as undescribed species belonging to known genera, while the remaining 55 genomes had lower ANI values (

The body-wide human microbiome plays a role in health, but its full diversity remains uncharacterized, particularly outside of the gut and in international populations. We leveraged 9,428 metagenomes to reconstruct 154,723 microbial genomes (45% of high quality) spanning body sites, ages, countries, and lifestyles. We recapitulated 4,930 species-level genome bins (SGBs), 77% without genomes in public repositories (unknown SGBs [uSGBs]). uSGBs are prevalent (in 93% of well-assembled samples), expand underrepresented phyla, and are enriched in non-Westernized populations (40% of the total SGBs). We annotated 2.85 M genes in SGBs, many associated with conditions including infant development (94,000) or Westernization (106,000). SGBs and uSGBs permit deeper microbiome analyses and increase the average mappability of metagenomic reads from 67.76% to 87.51% in the gut (median 94.26%) and 65.14% to 82.34% in the mouth. We thus identify thousands of microbial genomes from yet-to-be-named species, expand the pangenomes of human-associated microbes, and allow better exploitation of metagenomic technologies.The human microbiome harbors many unidentified species. By large-scale metagenomic assembly of samples from diverse populations, we uncovered >150,000 microbial genomes that are recapitulated in 4,930 species. Many species (77%) were never described before, increase the mappability of metagenomes, and expand our understanding of global body-wide human microbiomes., This work was supported by EU-H2020 (DiMeTrack-707345) to E.P.; by NIH NHGRI (R01HG005220), NIDDK (R24DK110499), NIDDK (U54DE023798), CMIT (6935956) to C.H.; and by ERC (MetaPG-716575), MIUR (RBFR13EWWI), EU-FP7 (PCIG13-GA-2013-618833), CARITRO (2013.0239), and LEO Pharma Foundation to N.S. Madagascar data and sample collection was supported by the Rockefeller Foundation to C.D.G.

Hyperspectral data are becoming more widely available via sensors on airborne and unmanned aerial vehicle (UAV) platforms, as well as proximal platforms. While space-based hyperspectral data continue to be limited in availability, multiple spaceborne Earth-observing missions on traditional platforms are scheduled for launch, and companies are experimenting with small satellites for constellations to observe the Earth, as well as for planetary missions. Land cover mapping via classification is one of the most important applications of hyperspectral remote sensing and will increase in significance as time series of imagery are more readily available. However, while the narrow bands of hyperspectral data provide new opportunities for chemistry-based modeling and mapping, challenges remain. Hyperspectral data are high dimensional, and many bands are highly correlated or irrelevant for a given classification problem. For supervised classification methods, the quantity of training data is typically limited relative to the dimension of the input space. The resulting Hughes phenomenon, often referred to as the curse of dimensionality, increases potential for unstable parameter estimates, overfitting, and poor generalization of classifiers. This is particularly problematic for parametric approaches such as Gaussian maximum likelihood–based classifiers that have been the backbone of pixel-based multispectral classification methods. This issue has motivated investigation of alternatives, including regularization of the class covariance matrices, ensembles of weak classifiers, development of feature selection and extraction methods, adoption of nonparametric classifiers, and exploration of methods to exploit unlabeled samples via semi-supervised and active learning. Data sets are also quite large, motivating computationally efficient algorithms and implementations. This chapter provides an overview of the recent advances in classification methods for mapping vegetation using hyperspectral data. Three data sets that are used in the hyperspectral classification literature (e.g., Botswana Hyperion satellite data and AVIRIS airborne data over both Kennedy Space Center and Indian Pines) are described in Section 3.2 and used to illustrate methods described in the chapter. An additional high-resolution hyperspectral data set acquired by a SpecTIR sensor on an airborne platform over the Indian Pines area is included to exemplify the use of new deep learning approaches, and a multiplatform example of airborne hyperspectral data is provided to demonstrate transfer learning in hyperspectral image classification. Classical approaches for supervised and unsupervised feature selection and extraction are reviewed in Section 3.3. In particular, nonlinearities exhibited in hyperspectral imagery have motivated development of nonlinear feature extraction methods in manifold learning, which are outlined in Section 3.3.1.4. Spatial context is also important in classification of both natural vegetation with complex textural patterns and large agricultural fields with significant local variability within fields. Approaches to exploit spatial features at both the pixel level (e.g., co-occurrence–based texture and extended morphological attribute profiles [EMAPs]) and integration of segmentation approaches (e.g., HSeg) are discussed in this context in Section 3.3.2. Recently, classification methods that leverage nonparametric methods originating in the machine learning community have grown in popularity. An overview of both widely used and newly emerging approaches, including support vector machines (SVMs), Gaussian mixture models, and deep learning based on convolutional neural networks is provided in Section 3.4. Strategies to exploit unlabeled samples, including active learning and metric learning, which combine feature extraction and augmentation of the pool of training samples in an active learning framework, are outlined in Section 3.5. Integration of image segmentation with classification to accommodate spatial coherence typically observed in vegetation is also explored, including as an integrated active learning system. Exploitation of multisensor strategies for augmenting the pool of training samples is investigated via a transfer learning framework in Section 3.5.1.2. Finally, we look to the future, considering opportunities soon to be provided by new paradigms, as hyperspectral sensing is becoming common at multiple scales from ground-based and airborne autonomous vehicles to manned aircraft and space-based platforms.

Several studies have investigated links between the gut microbiome and colorectal cancer (CRC), but questions remain about the replicability of biomarkers across cohorts and populations. We performed a meta-analysis of five publicly available datasets and two new cohorts and validated the findings on two additional cohorts, considering in total 969 fecal metagenomes. Unlike microbiome shifts associated with gastrointestinal syndromes, the gut microbiome in CRC showed reproducibly higher richness than controls (P

Faecalibacterium is prevalent in the human gut and a promising microbe for the development of next-generation probiotics (NGPs) or biotherapeutics. Analyzing reference Faecalibacterium genomes and almost 3,000 Faecalibacterium-like metagenome-assembled genomes (MAGs) reconstructed from 7,907 human and 203 non-human primate gut metagenomes, we identified the presence of 22 different Faecalibacterium-like species-level genome bins (SGBs), some further divided in different strains according to the subject geographical origin. Twelve SGBs are globally spread in the human gut and show different genomic potential in the utilization of complex polysaccharides, suggesting that higher SGB diversity may be related with increased utilization of plant-based foods. Moreover, up to 11 different species may co-occur in the same subject, with lower diversity in Western populations, as well as intestinal inflammatory states and obesity. The newly explored Faecalibacterium diversity will be able to support the choice of strains suitable as NGPs, guided by the consideration of the differences existing in their functional potential.

Summary Prevotella copri is a common human gut microbe that has been both positively and negatively associated with host health. In a cross-continent meta-analysis exploiting >6,500 metagenomes, we obtained >1,000 genomes and explored the genetic and population structure of P. copri. P. copri encompasses four distinct clades (>10% inter-clade genetic divergence) that we propose constitute the P. copri complex, and all clades were confirmed by isolate sequencing. These clades are nearly ubiquitous and co-present in non-Westernized populations. Genomic analysis showed substantial functional diversity in the complex with notable differences in carbohydrate metabolism, suggesting that multi-generational dietary modifications may be driving reduced prevalence in Westernized populations. Analysis of ancient metagenomes highlighted patterns of P. copri presence consistent with modern non-Westernized populations and a clade delineation time pre-dating human migratory waves out of Africa. These findings reveal that P. copri exhibits a high diversity that is underrepresented in Western-lifestyle populations., Graphical Abstract, Highlights • P. copri is not a monotypic species but composed of four distinct clades • The P. copri complex is more prevalent in populations with non-Westernized lifestyles • P. copri clades are frequently co-present within non-Westernized individuals • Ancient stool samples suggest Westernization leads to P. copri underrepresentation, Tett et al. find that the intestinal microbe Prevotella copri encompasses four distinct clades constituting the P. copri complex. The complex is prevalent in non-Westernized populations where co-presence of all clades is commonly observed within individuals. Analysis of ancient stool samples supports Westernization as contributing to reduced P. copri prevalence.

Bacterial community acquisition in the infant gut impacts immune education and disease susceptibility. We compared bacterial strains across and within families in a prospective birth cohort of 44 infants and their mothers, sampled longitudinally in the first months of each child's life. We identified mother-to-child bacterial transmission events and describe the incidence of family-specific antibiotic resistance genes. We observed two inheritance patterns across multiple species, where often the mother's dominant strain is transmitted to the child, but occasionally her secondary strains colonize the infant gut. In families where the secondary strain of B. uniformis was inherited, a starch utilization gene cluster that was absent in the mother's dominant strain was identified in the child, suggesting the selective advantage of a mother's secondary strain in the infant gut. Our findings reveal mother-to-child bacterial transmission events at high resolution and give insights into early colonization of the infant gut. Using longitudinal metagenomic sequencing from 44 mother/child pairs, Yassour et al. characterized mother-to-child strain transmission patterns. While mothers' dominant strains were often inherited, nondominant secondary strain transmissions were also observed. Microbial functional analysis reveals that inherited maternal secondary strains may have a selective advantage to colonize infant guts., National Institutes of Health (Grant 1DP3DK094338–01)

BackgroundFew studies, based on a limited number of patients using non-uniform therapeutic protocols, have analyzed Methicillin-resistant Staphylococcus aureus (MRSA) eradication.MethodsIn a randomized multicenter trial conducted on patients with new-onset MRSA infection we evaluated the efficacy of an early eradication treatment (arm A) compared with an observational group (B). Arm A received oral rifampicin and trimethoprim/sulfamethoxazole (21 days). Patients' microbiological status, FEV1, BMI, pulmonary exacerbations and use of antibiotics were assessed.ResultsSixty-one patients were randomized. Twenty-nine (47.5%) patients were assigned to active arm A and 32 (52.5%) patients to observational arm B. Twenty-nine (47.5%) patients, 10 patients in arm A and 19 in arm B, dropped out of the study. At 6 months MRSA was eradicated in 12 (63.2%) out of 19 patients in arm A while spontaneous clearance was observed in 5 (38.5%) out of 13 patients in arm B. A per-protocol analysis showed a 24.7% difference in the proportion of MRSA clearance between the two groups (z = 1.37, P(Z>z) = 0.08). Twenty-seven patients, 15 (78.9%) out of 19 in arm A and 12 (92.3%) out of 13 in arm B, were able to perform spirometry. The mean (±SD) FEV1 change from baseline was 7.13% (±14.92) in arm A and -1.16% (±5.25) in arm B (p = 0.08). In the same period the BMI change (mean ±SD) from baseline was 0.54 (±1.33) kg/m2 in arm A and -0.38 (±1.56) kg/m2 in arm B (p = 0.08). At 6 months no statistically significant differences regarding the number of pulmonary exacerbations, days spent in hospital and use of antibiotics were observed between the two arms.ConclusionsAlthough the statistical power of the study is limited, we found a 24.7% higher clearance of MRSA in the active arm than in the observational arm at 6 months. Patients in the active arm A also had favorable FEV1 and BMI tendencies.

Summary The role of intestinal Prevotella species in human health is controversial, with both positive and negative associations. Strain-level diversity may contribute to discrepancies in genus and species associations with health and disease. We dissected the gut metagenomes of Italians with varying dietary habits, investigating the presence of distinct Prevotella copri strains. Fiber-rich diets were linked to P. copri types with enhanced potential for carbohydrate catabolism. P. copri strains associated with an omnivore diet had a higher prevalence of the leuB gene—involved in branched-chain amino acid biosynthesis—a risk factor for glucose intolerance and type 2 diabetes. These P. copri pangenomes were compared to existing cohorts, providing evidence of distinct gene repertoires characterizing different P. copri populations, with drug metabolism and complex carbohydrate degradation significantly associated with Western and non-Western individuals, respectively. Strain-level P. copri diversity in gut microbiomes is affected by diet and should be considered when examining host-microbe associations.

Freshwater ecosystems represent 0.01% of the water on Earth, but they support 6% of global biodiversity that is still mostly uncharacterized. Here, we describe the genome sequences of three strains belonging to novel species in the Pseudomonas , Flavobacterium , and Sediminibacterium genera recovered from a water sample of Lake Garda, Italy.

Summary The acquisition and development of the infant microbiome are key to establishing a healthy host-microbiome symbiosis. The maternal microbial reservoir is thought to play a crucial role in this process. However, the source and transmission routes of the infant pioneering microbes are poorly understood. To address this, we longitudinally sampled the microbiome of 25 mother-infant pairs across multiple body sites from birth up to 4 months postpartum. Strain-level metagenomic profiling showed a rapid influx of microbes at birth followed by strong selection during the first few days of life. Maternal skin and vaginal strains colonize only transiently, and the infant continues to acquire microbes from distinct maternal sources after birth. Maternal gut strains proved more persistent in the infant gut and ecologically better adapted than those acquired from other sources. Together, these data describe the mother-to-infant microbiome transmission routes that are integral in the development of the infant microbiome., Graphical Abstract, Highlights • Strain-resolved metagenomics was used to track mother-to-infant microbiome transfer • Microbial strains from multiple maternal body sites transfer to the infant microbiome • The early microbial diversity in the infant gut is rapidly shaped by niche selection • The maternal gut microbiome is the source of the majority of transmitted strains, Ferretti et al. use metagenomics with strain-resolved computational profiling to characterize the transfer of microbes from mothers to their infants during their first 4 months of life. Multiple maternal body sites contribute to the developing infant microbiome, with maternal gut strains providing the largest contribution of colonizing microorganisms.

Background The microbial communities populating human and natural environments have been extensively characterized with shotgun metagenomics, which provides an in-depth representation of the microbial diversity within a sample. Microbes thriving in urban environments may be crucially important for human health, but have received less attention than those of other environments. Ongoing efforts started to target urban microbiomes at a large scale, but the most recent computational methods to profile these metagenomes have never been applied in this context. It is thus currently unclear whether such methods, that have proven successful at distinguishing even closely related strains in human microbiomes, are also effective in urban settings for tasks such as cultivation-free pathogen detection and microbial surveillance. Here, we aimed at a) testing the currently available metagenomic profiling tools on urban metagenomics; b) characterizing the organisms in urban environment at the resolution of single strain and c) discussing the biological insights that can be inferred from such methods. Results We applied three complementary methods on the 1614 metagenomes of the CAMDA 2017 challenge. With MetaMLST we identified 121 known sequence-types from 15 species of clinical relevance. For instance, we identified several Acinetobacter strains that were close to the nosocomial opportunistic pathogen A. nosocomialis. With StrainPhlAn, a generalized version of the MetaMLST approach, we inferred the phylogenetic structure of Pseudomonas stutzeri strains and suggested that the strain-level heterogeneity in environmental samples is higher than in the human microbiome. Finally, we also probed the functional potential of the different strains with PanPhlAn. We further showed that SNV-based and pangenome-based profiling provide complementary information that can be combined to investigate the evolutionary trajectories of microbes and to identify specific genetic determinants of virulence and antibiotic resistances within closely related strains. Conclusion We show that strain-level methods developed primarily for the analysis of human microbiomes can be effective for city-associated microbiomes. In fact, (opportunistic) pathogens can be tracked and monitored across many hundreds of urban metagenomes. However, while more effort is needed to profile strains of currently uncharacterized species, this work poses the basis for high-resolution analyses of microbiomes sampled in city and mass transportation environments. Reviewers This article was reviewed by Alexandra Bettina Graf, Daniel Huson and Trevor Cickovski. Electronic supplementary material The online version of this article (10.1186/s13062-018-0211-z) contains supplementary material, which is available to authorized users.

One of the exceptional advantages of spaceborne remote sensors is their regular scanning of the Earth surface, resulting thus in Satellite Image Time Series (SITS), extremely useful to monitor natural or man-made phenomena on the ground. In this chapter, after providing a brief overview of the most recent methods proposed to process and/or analyze time series of remotely sensed data, we describe methods handling two issues: the unsupervised exploration of SITS and the reconstruction of multispectral images. In particular, we first present data mining methods for extracting spatiotemporal patterns in an unsupervised way and illustrate this approach on time series of displacement measurements derived from multitemporal InSAR images. Then we present two methods which aim to reconstruct multispectral images contaminated by the presence of clouds. The first one is based on a linear contextual prediction mode that reproduces the local spectro-temporal relationships characterizing a given time series of images. The second method tackles the image reconstruction problem within a compressive sensing formulation and with different implementation strategies. A rich set of illustrations on real and simulated examples is provided and discussed.

a b s t r a c t Classification of electrocardiographic (ECG) signals can be deteriorated by the presence in the training set of mislabeled samples. To alleviate this issue we propose a new approach that aims at assisting the human user (cardiologist) in his/her work of labeling by removing in an automatic way the training samples with potential mislabeling problems. The proposed method is based on a genetic optimiza- tion process, in which each chromosome represents a candidate solution for validating/invalidating the training samples. Moreover, the optimization process consists of optimizing jointly two different crite- ria, which are the maximization of the statistical separability among classes and the minimization of the number of invalidated samples. Experimental results obtained on real ECG signals extracted from the MIT-BIH arrhythmia database confirm the effectiveness of the proposed solution.

Background The correct establishment of the human gut microbiota represents a crucial development that commences at birth. Different hypotheses propose that the infant gut microbiota is derived from, among other sources, the mother’s fecal/vaginal microbiota and human milk. Results The composition of bifidobacterial communities of 25 mother-infant pairs was investigated based on an internal transcribed spacer (ITS) approach, combined with cultivation-mediated and genomic analyses. We identified bifidobacterial strains/communities that are shared between mothers and their corresponding newborns. Notably, genomic analyses together with growth profiling assays revealed that bifidobacterial strains that had been isolated from human milk are genetically adapted to utilize human milk glycans. In addition, we identified particular bacteriophages specific of bifidobacterial species that are common in the viromes of mother and corresponding child. Conclusions This study highlights the transmission of bifidobacterial communities from the mother to her child and implies human milk as a potential vehicle to facilitate this acquisition. Furthermore, these data represent the first example of maternal inheritance of bifidobacterial phages, also known as bifidophages in infants following a vertical transmission route. Electronic supplementary material The online version of this article (doi:10.1186/s40168-017-0282-6) contains supplementary material, which is available to authorized users.

We present curatedMetagenomicData, a Bioconductor and command-line resource providing thousands of metagenomic profiles from the Human Microbiome Project and other publicly available datasets, and ExperimentHub, for convenient cloud-based distribution of data to the R desktop. curatedMetagenomicData provides standardized per-participant metadata linked to bacterial, fungal, archaeal, and viral taxonomic abundances, as well as quantitative metabolic functional profiles, generated by the HUMAnN2 and MetaPhlAn2 pipelines. The resulting datasets can be immediately analyzed with a wide range of statistical methods, requiring a minimum of bioinformatic expertise and no preprocessing of data. We demonstrate exploratory data analysis, an investigation of gut "enterotypes", and a comparison of the accuracy of disease classification from different data types. These documented analyses can be reproduced efficiently on a laptop, without the barriers of working with large-scale, raw sequencing data. The development of curatedMetagenomicData will continue with the addition, curation, and analysis of further microbiome datasets.

Among the human health conditions linked to microbial communities, phenotypes are often associated with only a subset of strains within causal microbial groups. Although it has been critical for decades in microbial physiology to characterize individual strains, this has been challenging when using culture-independent high-throughput metagenomics. We introduce StrainPhlAn, a novel metagenomic strain identification approach, and apply it to characterize the genetic structure of thousands of strains from more than 125 species in more than 1500 gut metagenomes drawn from populations spanning North and South American, European, Asian, and African countries. The method relies on per-sample dominant sequence variant reconstruction within species-specific marker genes. It identified primarily subject-specific strain variants (70% of species). Microbial population structure was correlated in several distinct ways with the geographic structure of the host population. In some cases, discrete subspecies (e.g., for Eubacterium rectale and Prevotella copri) or continuous microbial genetic variations (e.g., for Faecalibacterium prausnitzii) were associated with geographically distinct human populations, whereas few strains occurred in multiple unrelated cohorts. We further estimated the genetic variability of gut microbes, with Bacteroides species appearing remarkably consistent (0.45% median number of nucleotide variants between strains), whereas P. copri was among the most plastic gut colonizers. We thus characterize here the population genetics of previously inaccessible intestinal microbes, providing a comprehensive strain-level genetic overview of the gut microbial diversity.

We describe here the draft genome sequence of the cyanobacterium Tychonema bourrellyi , assembled from a metagenome of a nonaxenic culture. The strain (FEM_GT703) was isolated from a freshwater sample taken from Lake Garda, Italy. The draft genome sequence represents the first assembled T. bourrellyi strain.

Psoriasis is an immune-mediated inflammatory skin disease that has been associated with cutaneous microbial dysbiosis by culture-dependent investigations and rRNA community profiling. We applied, for the first time, high-resolution shotgun metagenomics to characterise the microbiome of psoriatic and unaffected skin from 28 individuals. We demonstrate psoriatic ear sites have a decreased diversity and psoriasis is associated with an increase in Staphylococcus, but overall the microbiomes of psoriatic and unaffected sites display few discriminative features at the species level. Finer strain-level analysis reveals strain heterogeneity colonisation and functional variability providing the intriguing hypothesis of psoriatic niche-specific strain adaptation or selection. Furthermore, we accessed the poorly characterised, but abundant, clades with limited sequence information in public databases, including uncharacterised Malassezia spp. These results highlight the skins hidden diversity and suggests strain-level variations could be key determinants of the psoriatic microbiome. This illustrates the need for high-resolution analyses, particularly when identifying therapeutic targets. This work provides a baseline for microbiome studies in relation to the pathogenesis of psoriasis., Psoriasis: investigating microbial diversity Analysing microbial populations on the skin provides an insight into the diversity of microbes associated with psoriasis. Nicola Segata and colleagues at the University of Trento, Italy, used genetic analysis to compare the microbial populations on regions of skin affected and unaffected by psoriasis. Staphylococcus bacteria were more prevalent in psoriasis, but there was little clearly defined difference in microbial species on psoriasis-affected and unaffected skin. There was, however, decreased microbial diversity on psoriatic ear sites. Deeper strain-level computational analysis suggested that psoriasis could offer niche locations for colonisation by specific strains of staphylococci and propionibacteria. The results highlight the diversity of microbial populations on the skin, and the need for larger cohorts to build on the baseline data now established. Further studies might help identify targets for treating skin bacteria associated with psoriasis.

In the last few years active learning has been gaining growing interest in the remote sensing community in optimizing the process of training sample collection for supervised image classification. Current strategies formulate the active learning problem in the spectral domain only. However remote sensing images are intrinsically defined both in the spectral and spatial domains. In this paper we explore this fact by proposing a new active learning approach for support vector machine classification. In particular we suggest combining spectral and spatial information directly in the iterative process of sample selection. For this purpose three criteria are proposed to favor the selection of samples distant from the samples already composing the current training set. In the first strategy the Euclidean distances in the spatial domain from the training samples are explicitly computed whereas the second one is based on the Parzen window method in the spatial domain. Finally the last criterion involves the concept of spatial entropy. Experiments on two very high resolution images show the effectiveness of regularization in spatial domain for active learning purposes. © 2013 IEEE.

In the remote sensing field, ground-truth design for collecting training samples represents a tricky and critical problem since it has a direct impact on most of the subsequent image processing and analysis steps. In this paper, we propose a novel framework for assisting a human user in designing ground-truth by photointerpretation for optical remote sensing image classification. The proposed approach is (almost) completely automatic and comprehensive since it aims at assisting the human user from the first to the last step of the process. It is based on unsupervised methods of segmentation and clustering, in order to investigate both the spatial and the spectral information in the process of ground-truth design. The resulting ground-truth is classifier-free and can be further improved by making it classifier-driven through an active learning process. To validate the proposed framework, an experimental study was conducted on very high spatial resolution and hyperspectral images acquired by the IKONOS and the Reflective Optics System Imaging Spectrometer sensors, respectively. The obtained results show the usefulness and effectiveness of the proposed approach.

Shotgun metagenomic analysis of the human associated microbiome provides a rich set of microbial features for prediction and biomarker discovery in the context of human diseases and health conditions. However, the use of such high-resolution microbial features presents new challenges, and validated computational tools for learning tasks are lacking. Moreover, classification rules have scarcely been validated in independent studies, posing questions about the generality and generalization of disease-predictive models across cohorts. In this paper, we comprehensively assess approaches to metagenomics-based prediction tasks and for quantitative assessment of the strength of potential microbiome-phenotype associations. We develop a computational framework for prediction tasks using quantitative microbiome profiles, including species-level relative abundances and presence of strain-specific markers. A comprehensive meta-analysis, with particular emphasis on generalization across cohorts, was performed in a collection of 2424 publicly available metagenomic samples from eight large-scale studies. Cross-validation revealed good disease-prediction capabilities, which were in general improved by feature selection and use of strain-specific markers instead of species-level taxonomic abundance. In cross-study analysis, models transferred between studies were in some cases less accurate than models tested by within-study cross-validation. Interestingly, the addition of healthy (control) samples from other studies to training sets improved disease prediction capabilities. Some microbial species (most notably Streptococcus anginosus) seem to characterize general dysbiotic states of the microbiome rather than connections with a specific disease. Our results in modelling features of the “healthy” microbiome can be considered a first step toward defining general microbial dysbiosis. The software framework, microbiome profiles, and metadata for thousands of samples are publicly available at http://segatalab.cibio.unitn.it/tools/metaml., Author Summary The human microbiome–the entire set of microbial organisms associated with the human host–interacts closely with host immune and metabolic functions and is crucial for human health. Significant advances in the characterization of the microbiome associated with healthy and diseased individuals have been obtained through next-generation DNA sequencing technologies, which permit accurate estimation of microbial communities directly from uncultured human-associated samples (e.g., stool). In particular, shotgun metagenomics provide data at unprecedented species- and strain- levels of resolution. Several large-scale metagenomic disease-associated datasets are also becoming available, and disease-predictive models built on metagenomic signatures have been proposed. However, the generalization of resulting prediction models on different cohorts and diseases has not been validated. In this paper, we comprehensively assess approaches to metagenomics-based prediction tasks and for quantitative assessment of microbiome-phenotype associations. We consider 2424 samples from eight studies and six different diseases to assess the independent prediction accuracy of models built on shotgun metagenomic data and to compare strategies for practical use of the microbiome as a prediction tool.

Augmenting spectral data with spatial information for image classification has recently gained significant attention, as classification accuracy can often be improved by extracting spatial information from neighboring pixels. In this paper, we propose a new framework in which active learning (AL) and hierarchical segmentation (HSeg) are combined for spectral–spatial classification of hyperspectral images. The spatial information is extracted from a best segmentation obtained by pruning the HSeg tree using a new supervised strategy. The best segmentation is updated at each iteration of the AL process, thus taking advantage of informative labeled samples provided by the user. The proposed strategy incorporates spatial information in two ways: 1) concatenating the extracted spatial features and the original spectral features into a stacked vector and 2) extending the training set using a self-learning-based semi-supervised learning (SSL) approach. Finally, the two strategies are combined within an AL framework. The proposed framework is validated with two benchmark hyperspectral datasets. Higher classification accuracies are obtained by the proposed framework with respect to five other state-of-the-art spectral–spatial classification approaches. Moreover, the effectiveness of the proposed pruning strategy is also demonstrated relative to the approaches based on a fixed segmentation.

Classification of remotely sensed hyperspectral images via supervised approaches is typically affected by high dimensionality of the spectral data and a limited number of labeled samples. Dimensionality reduction via feature extraction and active learning (AL) are two approaches that researchers have investigated independently to deal with these two problems. In this paper, we propose a new method in which the feature extraction and AL steps are combined into a unique framework. The idea is to learn and update a reduced feature space in a supervised way at each iteration of the AL process, thus taking advantage of the increasing labeled information provided by the user. In particular, the computation of the reduced feature space is based on the large-margin nearest neighbor (LMNN) metric learning principle. This strategy is applied in conjunction with $k$ -nearest neighbor ( $k$ -NN) classification, for which a new sample selection strategy is proposed. The methodology is validated experimentally on four benchmark hyperspectral data sets. Good improvements in terms of classification accuracy and computational time are achieved with respect to the state-of-the-art strategies that do not combine feature extraction and AL.

The classification of hyperspectral and multimodal remote sensing data is affected by two key problems: the high dimensionality of the input data and the limited number of the labeled samples. In this letter, a multimetric learning approach that combines feature extraction and active learning (AL) is introduced to deal with these two issues simultaneously. In particular, distinct metrics are assigned to different types of features and then learned jointly. In this way, multiple features are projected into a common feature space, in which AL is then performed in conjunction with $k$ - nearest neighbor classification to enrich the set of labeled samples. Experiments on two sets of remote sensing data illustrate the effectiveness of the proposed framework in terms of both classification accuracy and computational requirements.

In this article, the task of remote-sensing image classification is tackled with local maximal margin approaches. First, we introduce a set of local kernel-based classifiers that alleviate the computational limitations of local support vector machines (SVMs), maintaining at the same time high classification accuracies. Such methods rely on the following idea: (a) during training, build a set of local models covering the considered data and (b) during prediction, choose the most appropriate local model for each sample to evaluate. Additionally, we present a family of operators on kernels aiming to integrate the local information into existing (input) kernels in order to obtain a quasi-local (QL) kernel. To compare the performances achieved by the different local approaches, an experimental analysis was conducted on three distinct remote-sensing data sets. The obtained results show that interesting performances can be achieved in terms of both classification accuracy and computational cost.

One of the major limitations of passive sensors is their high sensitivity to weather conditions during the image acquisition process. The resulting images are frequently subject to the presence of clouds, which makes the image partly useless for assessing landscape properties. The common approach to cope with this problem attempts to remove the clouds by substituting them with cloud-free estimations. The cloud removal problem can be viewed as an image reconstruction/restoration issue, in which it is aimed at recovering an original scene from degraded or missing observations. Two cloud removal approaches are detailed and discussed in this chapter. The first one is a single-channel method for the reconstruction in a sequence of temporal optical images. Given a contaminated image of the sequence, each area of missing measurements is recovered by means of a contextual prediction process that reproduces the local spectro-temporal relationships. The second approach exploits the Compressive Sensing (CS) theory, which offers the capability to recover an unknown sparse signal with a linear combination of a small number of elementary samples. The two reconstruction approaches are evaluated experimentally on a real multitemporal multispectral remote sensing image.

Identifying microbial strains and characterizing their functional potential is essential for pathogen discovery, epidemiology and population genomics. We present pangenome-based phylogenomic analysis (PanPhlAn; http://segatalab.cibio.unitn.it/tools/panphlan), a tool that uses metagenomic data to achieve strain-level microbial profiling resolution. PanPhlAn recognized outbreak strains, produced the largest strain-level population genomic study of human-associated bacteria and, in combination with metatranscriptomics, profiled the transcriptional activity of strains in complex communities.

Incorporating disparate features from multiple sources can provide valuable diverse information for remote sensing data analysis. However, multisource remote sensing data require large quantities of labeled data to train robust supervised classifiers, which are often difficult and expensive to acquire. A mixture-of-kernel approach can facilitate the construction of an effective formulation for acquiring useful samples via active learning (AL). In this paper, we propose an ensemble multiple kernel active learning (EnsembleMKL-AL) framework that incorporates different types of features extracted from multisensor remote sensing data (hyperspectral imagery and LiDAR data) for robust classification. An ensemble of probabilistic multiple kernel classifiers is embedded into a maximum disagreement-based AL system, which adaptively optimizes the kernel for each source during the AL process. At the end of each learning step, a decision fusion strategy is implemented to make a final decision based on the probabilistic outputs. The proposed framework is tested in a multisource environment, including different types of features extracted from hyperspectral and LiDAR data. The experimental results validate the efficacy of the proposed approach. In addition, we demonstrate that using ensemble classifiers and a large number of disparate but relevant features can further improve the performance of an AL-based classification approach.

In this letter, we show how active learning can be particularly promising for classifying remote sensing images at large scales. The classification model constructed on samples extracted from a limited region of the image, called source domain, exhibits generally poor accuracies when used to predict the samples of a different region, called target domain, due to possible changes in class distributions throughout the image. To alleviate this problem, we suggest selecting and labeling additional samples from the new domain in order to improve generalization capabilities of the model. We propose to implement an initialization strategy based on clustering before applying the traditional active learning method in order to cope with distribution changes and better explore the feature space of the target domain. Experiments on a MODIS dataset for the generation of a land-cover map at European scale show good capabilities of the proposed approach for this purpose.

Acquiring current, accurate land-use information is critical for monitoring and understanding the impact of anthropogenic activities on natural environments. Remote sensing technologies are of increasing importance because of their capability to acquire information for large areas in a timely manner, enabling decision makers to be more effective in complex environments. Although optical imagery has demonstrated to be successful for land cover classification, active sensors, such as light detection and ranging (LiDAR), have distinct capabilities that can be exploited to improve classification results. However, utilization of LiDAR data for land cover classification has not been fully exploited. Moreover, spatial-spectral classification has recently gained significant attention since classification accuracy can be improved by extracting additional information from the neighboring pixels. Although spatial information has been widely used for spectral data, less attention has been given to LiDAR data. In this work, a new framework for land cover classification using discrete return LiDAR data is proposed. Pseudo-waveforms are generated from the LiDAR data and processed by hierarchical segmentation. Spatial features are extracted in a region-based way using a new unsupervised strategy for multiple pruning of the segmentation hierarchy. The proposed framework is validated experimentally on a real dataset acquired in an urban area. Better classification results are exhibited by the proposed framework compared to the cases in which basic LiDAR products such as digital surface model and intensity image are used. Moreover, the proposed region-based feature extraction strategy results in improved classification accuracies in comparison with a more traditional window-based approach.

In this paper, we face the problem of collecting training samples for regression problems under an active learning perspective. In particular, we propose various active learning strategies specifically developed for regression approaches based on Gaussian processes (GPs) and support vector machines (SVMs). For GP regression, the first two strategies are based on the idea of adding samples that are dissimilar from the current training samples in terms of covariance measure, while the third one uses a pool of regressors in order to select the samples with the greater disagreements between the different regressors. Finally, the last strategy exploits an intrinsic GP regression outcome to pick up the most difficult and hence interesting samples to label. For SVM regression, the method based on the pool of regressors and two additional strategies based on the selection of the samples distant from the current support vectors in the kernel-induced feature space are proposed. The experimental results obtained on simulated and real data sets show that the proposed strategies exhibit a good capability to select samples that are significant for the regression process, thus opening the way to the active learning approach for remote-sensing regression problems.

Active learning is showing to be a useful approach to improve the efficiency of the classification process for remote sensing images. This letter introduces a new active learning strategy specifically developed for support vector machine (SVM) classification. It relies on the idea of the following: 1) reformulating the original classification problem into a new problem where it is needed to discriminate between significant and nonsignificant samples, according to a concept of significance which is proper to the SVM theory; and 2) constructing the corresponding significance space to suitably guide the selection of the samples potentially useful to better deal with the original classification problem. Experiments were conducted on both multi- and hyperspectral images. Results show interesting advantages of the proposed method in terms of convergence speed, stability, and sparseness.

In this paper, we present three active learning strategies for the classification of electrocardiographic (ECG) signals. Starting from a small and suboptimal training set, these learning strategies select additional beat samples from a large set of unlabeled data. These samples are labeled manually, and then added to the training set. The entire procedure is iterated until the construction of a final training set representative of the considered classification problem. The proposed methods are based on support vector machine classification and on the: 1) margin sampling; 2) posterior probability; and 3) query by committee principles, respectively. To illustrate their performance, we conducted an experimental study based on both simulated data and real ECG signals from the MIT-BIH arrhythmia database. In general, the obtained results show that the proposed strategies exhibit a promising capability to select samples that are significant for the classification process, i.e., to boost the accuracy of the classification process while minimizing the number of involved labeled samples.

Recently, a promising pattern-recognition system has been presented to deal with the extraction of buried-object characteristics in ground-penetrating-radar images. In particular, it allows the detecting of buried objects by means of a search method based on genetic algorithms and the recognizing of the material type of the identified objects through a classification approach based on support vector machines. In this letter, we propose to extend the processing capabilities of this system by addressing the issue of the detected buried-object size estimation. This problem is viewed as a regression issue where it is aimed at reproducing the relationship between a set of opportunely extracted features and the object size. For such purpose, it is formulated within a Gaussian process (GP) regression approach. A detailed experimental study is reported, showing encouraging object-size-estimation accuracies even when buried objects are close to each other.

In this paper, we propose a novel pattern-recognition system to identify and classify buried objects from ground-penetrating radar (GPR) imagery. The entire process is subdivided into four steps. After a preprocessing step, the GPR image is thresholded to put under light the regions containing potential objects. The third step of the system consists of automatically detecting the objects in the obtained binary image by means of a search of linear/hyperbolic patterns formulated within a genetic optimization framework. In the genetic optimizer, each chromosome models the apex position and the curvature associated with the candidate pattern, while the fitness function expresses the Hamming distance between that pattern and the binary image content. Finally, in the fourth step, the problem of the recognition of the material type of the identified objects is approached as a classification issue, which is solved by means of an opportune feature-extraction strategy and a support vector machine classifier. To illustrate the performances of the proposed system, we conducted a thorough experimental study based on GPR images generated by a GPR simulator based on the finite-difference time-domain method so as to construct different acquisition scenarios by varying the number of buried objects, their position, their size, their shape, and their material type. In general, the obtained experimental results show that the proposed system exhibits promising performances both in terms of object detection and material recognition.

This work presents a novel pattern recognition approach for the automatic analysis of ground penetrating radar (GPR) images. The developed system comprises pre-processing, segmentation, object detection and material recognition stages. Object detection is done using an innovative unsupervised strategy based on genetic algorithms (GA) that allows to localize linear/hyperbolic patterns in GPR images. Object material recognition is approached as a classification issue, which is solved by means of a support vector machine (SVM) classifier. Results on synthetic images show that the proposed system exhibits promising performances both in terms of object detection and material recognition.

The genus Prevotella includes more than 50 characterized species that occur in varied natural habitats, although most Prevotella spp. are associated with humans. In the human microbiome, Prevotella spp. are highly abundant in various body sites, where they are key players in the balance between health and disease. Host factors related to diet, lifestyle and geography are fundamental in affecting the diversity and prevalence of Prevotella species and strains in the human microbiome. These factors, along with the ecological relationship of Prevotella with other members of the microbiome, likely determine the extent of the contribution of Prevotella to human metabolism and health. Here we review the diversity, prevalence and potential connection of Prevotella spp. in the human host, highlighting how genomic methods and analysis have improved and should further help in framing their ecological role. We also provide suggestions for future research to improve understanding of the possible functions of Prevotella spp. and the effects of the Western lifestyle and diet on the host–Prevotella symbiotic relationship in the context of maintaining human health. Prevotella is a genus of bacteria that commonly associate with humans, in various body sites. In this Review, Segata, Ercolini and colleagues discuss Prevotella diversity and the evidence for the involvement of these bacteria in human health and disease.

The influence of unicellular eukaryotic microorganisms on human gut health and disease is still largely unexplored. Blastocystis spp. commonly colonize the gut, but its clinical significance and ecological role are currently unsettled. We have developed a high-sensitivity bioinformatic pipeline to detect Blastocystis subtypes (STs) from shotgun metagenomics, and applied it to 12 large data sets, comprising 1689 subjects of different geographic origin, disease status and lifestyle. We confirmed and extended previous observations on the high prevalence the microrganism in the population (14.9%), its non-random and ST-specific distribution, and its ability to cause persistent (asymptomatic) colonization. These findings, along with the higher prevalence observed in non-westernized individuals, the lack of positive association with any of the disease considered, and decreased presence in individuals with dysbiosis associated with colorectal cancer and Crohn’s disease, strongly suggest that Blastocystis is a component of the healthy gut microbiome. Further, we found an inverse association between body mass index and Blastocystis, and strong co-occurrence with archaeal organisms (Methanobrevibacter smithii) and several bacterial species. The association of specific microbial community structures with Blastocystis was confirmed by the high predictability (up to 0.91 area under the curve) of the microorganism colonization based on the species-level composition of the microbiome. Finally, we reconstructed and functionally profiled 43 new draft Blastocystis genomes and discovered a higher intra subtype variability of ST1 and ST2 compared with ST3 and ST4. Altogether, we provide an in-depth epidemiologic, ecological, and genomic analysis of Blastocystis, and show how metagenomics can be crucial to advance population genomics of human parasites.