scholarly journals Investigation of Adiposity Measures and Operational Taxonomic unit (OTU) Data Transformation Procedures in Stool Samples from a German Cohort Study Using Machine Learning Algorithms

2020 ◽  
Vol 8 (4) ◽  
pp. 547
Author(s):  
Martina Troll ◽  
Stefan Brandmaier ◽  
Sandra Reitmeier ◽  
Jonathan Adam ◽  
Sapna Sharma ◽  
...  
Keyword(s):  
Predictive Performance ◽  
Operational Taxonomic Unit ◽  
Data Transformation ◽  
Amplicon Sequencing ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Rrna Gene ◽  
Substantial Impact ◽  
Stool Samples ◽  
Log Ratio

The analysis of the gut microbiome with respect to health care prevention and diagnostic purposes is increasingly the focus of current research. We analyzed around 2000 stool samples from the KORA (Cooperative Health Research in the Region of Augsburg) cohort using high-throughput 16S rRNA gene amplicon sequencing representing a total microbial diversity of 2089 operational taxonomic units (OTUs). We evaluated the combination of three different components to assess the reflection of obesity related to microbiota profiles: (i) four prediction methods (i.e., partial least squares (PLS), support vector machine regression (SVMReg), random forest (RF), and M5Rules); (ii) five OTU data transformation approaches (i.e., no transformation, relative abundance without and with log-transformation, as well as centered and isometric log-ratio transformations); and (iii) predictions from nine measurements of obesity (i.e., body mass index, three measures of body shape, and five measures of body composition). Our results showed a substantial impact of all three components. The applications of SVMReg and PLS in combination with logarithmic data transformations resulted in considerably predictive models for waist circumference-related endpoints. These combinations were at best able to explain almost 40% of the variance in obesity measurements based on stool microbiota data (i.e., OTUs) only. A reduced loss in predictive performance was seen after sex-stratification in waist–height ratio compared to other waist-related measurements. Moreover, our analysis showed that the contribution of OTUs less prevalent and abundant is minor concerning the predictive power of our models.

Detection of misinformation on garlic and COVID-19 in Twitter: A machine learning-based approach (Preprint)

2021 ◽  
Author(s):  
Myeong Gyu Kim ◽  
Jae Hyun Kim ◽  
Kyungim Kim
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Latent Dirichlet Allocation ◽  
Predictive Performance ◽  
Machine Learning Algorithms ◽  
Training Dataset ◽  
Polynomial Kernel ◽  
Support Vector ◽  
Accurate Information ◽  
Probability Number

BACKGROUND Garlic-related misinformation is prevalent whenever a virus outbreak occurs. Again, with the outbreak of coronavirus disease 2019 (COVID-19), garlic-related misinformation is spreading through social media sites, including Twitter. Machine learning-based approaches can be used to detect misinformation from vast tweets. OBJECTIVE This study aimed to develop machine learning algorithms for detecting misinformation on garlic and COVID-19 in Twitter. METHODS This study used 5,929 original tweets mentioning garlic and COVID-19. Tweets were manually labeled as misinformation, accurate information, and others. We tested the following algorithms: k-nearest neighbors; random forest; support vector machine (SVM) with linear, radial, and polynomial kernels; and neural network. Features for machine learning included user-based features (verified account, user type, number of followers, and follower rate) and text-based features (uniform resource locator, negation, sentiment score, Latent Dirichlet Allocation topic probability, number of retweets, and number of favorites). A model with the highest accuracy in the training dataset (70% of overall dataset) was tested using a test dataset (30% of overall dataset). Predictive performance was measured using overall accuracy, sensitivity, specificity, and balanced accuracy. RESULTS SVM with the polynomial kernel model showed the highest accuracy of 0.670. The model also showed a balanced accuracy of 0.757, sensitivity of 0.819, and specificity of 0.696 for misinformation. Important features in the misinformation and accurate information classes included topic 4 (common myths), topic 13 (garlic-specific myths), number of followers, topic 11 (misinformation on social media), and follower rate. Topic 3 (cooking recipes) was the most important feature in the others class. CONCLUSIONS Our SVM model showed good performance in detecting misinformation. The results of our study will help detect misinformation related to garlic and COVID-19. It could also be applied to prevent misinformation related to dietary supplements in the event of a future outbreak of a disease other than COVID-19.

scholarly journals Comparative Analysis of Fecal Microbiota Composition Between Rheumatoid Arthritis and Osteoarthritis Patients

Genes ◽  
2019 ◽  
Vol 10 (10) ◽  
pp. 748 ◽  
Author(s):  
Jin-Young Lee ◽  
Mohamed Mannaa ◽  
Yunkyung Kim ◽  
Jehun Kim ◽  
Geun-Tae Kim ◽  
...  
Keyword(s):  
Rheumatoid Arthritis ◽  
Gut Microbiota ◽  
Gut Microbiome ◽  
Bacterial Species ◽  
Amplicon Sequencing ◽  
Fecal Microbiota ◽  
Rrna Gene ◽  
Microbiota Composition ◽  
Stool Samples ◽  
Gut Microbiota Composition

The aim of this study was to investigate differences between the gut microbiota composition in patients with rheumatoid arthritis (RA) and those with osteoarthritis (OA). Stool samples from nine RA patients and nine OA patients were collected, and DNA was extracted. The gut microbiome was assessed using 16S rRNA gene amplicon sequencing. The structures and differences in the gut microbiome between RA and OA were analyzed. The analysis of diversity revealed no differences in the complexity of samples. The RA group had a lower Bacteroidetes: Firmicutes ratio than did the OA group. Lactobacilli and Prevotella, particularly Prevotella copri, were more abundant in the RA than in the OA group, although these differences were not statistically significant. The relative abundance of Bacteroides and Bifidobacterium was lower in the RA group. At the species level, the abundance of certain bacterial species was significantly lower in the RA group, such as Fusicatenibacter saccharivorans, Dialister invisus, Clostridium leptum, Ruthenibacterium lactatiformans, Anaerotruncus colihominis, Bacteroides faecichinchillae, Harryflintia acetispora, Bacteroides acidifaciens, and Christensenella minuta. The microbial properties of the gut differed between RA and OA patients, and the RA dysbiosis revealed results similar to those of other autoimmune diseases, suggesting that a specific gut microbiota pattern is related to autoimmunity.

scholarly journals Monitoring forest health using hyperspectral imagery: Does feature selection improve the performance of machine-learning techniques?

2020 ◽  
Author(s):  
Patrick Schratz ◽  
Jannes Muenchow ◽  
Eugenia Iturritxa ◽  
José Cortés ◽  
Bernd Bischl ◽  
...  
Keyword(s):  
Feature Selection ◽  
Predictive Performance ◽  
Environmental Modeling ◽  
Gradient Boosting ◽  
Support Vector ◽  
Substantial Impact ◽  
Feature Sets ◽  
Filter Methods ◽  
Extreme Gradient Boosting ◽  
Feature Importance

This study analyzed highly-correlated, feature-rich datasets from hyperspectral remote sensing data using multiple machine and statistical-learning methods.<br> The effect of filter-based feature-selection methods on predictive performance was compared.<br> Also, the effect of multiple expert-based and data-driven feature sets, derived from the reflectance data, was investigated.<br> Defoliation of trees (%) was modeled as a function of reflectance, and variable importance was assessed using permutation-based feature importance.<br> Overall support vector machine (SVM) outperformed others such as random forest (RF), extreme gradient boosting (XGBoost), lasso (L1) and ridge (L2) regression by at least three percentage points.<br> The combination of certain feature sets showed small increases in predictive performance while no substantial differences between individual feature sets were observed.<br> For some combinations of learners and feature sets, filter methods achieved better predictive performances than the unfiltered feature sets, while ensemble filters did not have a substantial impact on performance.<br><br> Permutation-based feature importance estimated features around the red edge to be most important for the models.<br> However, the presence of features in the near-infrared region (800 nm - 1000 nm) was essential to achieve the best performances.<br><br> More training data and replication in similar benchmarking studies is needed for more generalizable conclusions.<br> Filter methods have the potential to be helpful in high-dimensional situations and are able to improve the interpretation of feature effects in fitted models, which is an essential constraint in environmental modeling studies.

scholarly journals Trikafta therapy alters the CF lung mucus metabolome reshaping microbiome niche space

2021 ◽  
Author(s):  
Lauren Sosinski ◽  
Christian Martin-Hernandez ◽  
Kerri A Neugebauer ◽  
Lydia-Ann J Ghuneim ◽  
Douglas V Guzior ◽  
...  
Keyword(s):  
Drug Effects ◽  
Amplicon Sequencing ◽  
Kynurenine Pathway ◽  
Rrna Gene ◽  
Structural Modifications ◽  
Lung Microbiome ◽  
Fda Approval ◽  
Significant Difference ◽  
Before And After ◽  
Log Ratio

Novel small molecule therapies for cystic fibrosis (CF) are showing promising efficacy and becoming more widely available since recent FDA approval. The newest of these is a triple therapy of Elexacaftor-Tezacaftor-Ivacaftor (ETI). Little is known about how these drugs will affect polymicrobial lung infections, which are the leading cause of morbidity and mortality among people with CF (pwCF). We analyzed the sputum microbiome and metabolome from pwCF (n=24) before and after TKT therapy using 16S rRNA gene amplicon sequencing and untargeted metabolomics. The lung microbiome diversity, particularly its evenness, was increased (p = 0.044) and the microbiome profiles were different between individuals before and after therapy (PERMANOVA F=1.92, p=0.044). Despite these changes, the microbiomes were more similar within an individual than across the sampled population. There were no specific microbial taxa that were different in abundance before and after therapy, but collectively, the log-ratio of anaerobes to pathogens significantly decreased. The sputum metabolome also showed changes due to TKT. Beta-diversity increased after therapy (PERMANOVA F=4.22, p=0.022) and was characterized by greater variation across subjects while on treatment. This significant difference in the metabolome was driven by a decrease in peptides, amino acids, and metabolites from the kynurenine pathway. Metabolism of the three small molecules that make up TKT was extensive, including previously uncharacterized structural modifications. This study shows that TKT therapy affects both the microbiome and metabolome of airway mucus. This effect was stronger on sputum biochemistry, which may reflect changing niche spaces for microbial residency in lung mucus as the drug effects take hold, which then leads to changing microbiology.

scholarly journals Growth and Population Dynamics of the Anaerobic Fe(II)-Oxidizing and Nitrate-Reducing Enrichment Culture KS

2018 ◽  
Vol 84 (9) ◽  
Author(s):  
Claudia Tominski ◽  
Helene Heyer ◽  
Tina Lösekann-Behrens ◽  
Sebastian Behrens ◽  
Andreas Kappler
Keyword(s):  
16S Rrna ◽  
16S Rrna Gene ◽  
Community Composition ◽  
Enrichment Culture ◽  
Operational Taxonomic Unit ◽  
Amplicon Sequencing ◽  
Rrna Gene ◽  
Organic Substrates ◽  
Content Type ◽  
Heterotrophic Denitrification

ABSTRACTMost isolated nitrate-reducing Fe(II)-oxidizing microorganisms are mixotrophic, meaning that Fe(II) is chemically oxidized by nitrite that forms during heterotrophic denitrification, and it is debated to which extent Fe(II) is enzymatically oxidized. One exception is the chemolithoautotrophic enrichment culture KS, a consortium consisting of a dominant Fe(II) oxidizer,Gallionellaceaesp., and less abundant heterotrophic strains (e.g.,Bradyrhizobiumsp.,Nocardioidessp.). Currently, this is the only nitrate-reducing Fe(II)-oxidizing culture for which autotrophic growth has been demonstrated convincingly for many transfers over more than 2 decades. We used 16S rRNA gene amplicon sequencing and physiological growth experiments to analyze the community composition and dynamics of culture KS with various electron donors and acceptors. Under autotrophic conditions, an operational taxonomic unit (OTU) related to known microaerophilic Fe(II) oxidizers within the familyGallionellaceaedominated culture KS. With acetate as an electron donor, most 16S rRNA gene sequences were affiliated withBradyrhizobiumsp.Gallionellaceaesp. not only was able to oxidize Fe(II) under autotrophic and mixotrophic conditions but also survived over several transfers of the culture on only acetate, although it then lost the ability to oxidize Fe(II).Bradyrhizobiumspp. became and remained dominant when culture KS was cultivated for only one transfer under heterotrophic conditions, even when conditions were reverted back to autotrophic in the next transfer. This study showed a dynamic microbial community in culture KS that responded to changing substrate conditions, opening up questions regarding carbon cross-feeding, metabolic flexibility of the individual strains in KS, and the mechanism of Fe(II) oxidation by a microaerophile in the absence of O2.IMPORTANCENitrate-reducing Fe(II)-oxidizing microorganisms are present in aquifers, soils, and marine and freshwater sediments. Most nitrate-reducing Fe(II) oxidizers known are mixotrophic, meaning that they need organic carbon to continuously oxidize Fe(II) and grow. In these microbes, Fe(II) was suggested to be chemically oxidized by nitrite that forms during heterotrophic denitrification, and it remains unclear whether or to what extent Fe(II) is enzymatically oxidized. In contrast, the enrichment culture KS was shown to oxidize Fe(II) autotrophically coupled to nitrate reduction. This culture contains the designated Fe(II) oxidizerGallionellaceaesp. and several heterotrophic strains (e.g.,Bradyrhizobiumsp.). We showed that culture KS is able to metabolize Fe(II) and a variety of organic substrates and is able to adapt to dynamic environmental conditions. When the community composition changed andBradyrhizobiumbecame the dominant community member, Fe(II) was still oxidized byGallionellaceaesp., even when culture KS was cultivated with acetate/nitrate [Fe(II) free] before being switched back to Fe(II)/nitrate.

Prediction of Dansgaard-Oeschger events using machine learning

2021 ◽  
Author(s):  
Nuno Moniz ◽  
Susana Barbosa
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Prediction Models ◽  
Learning Algorithms ◽  
Ice Core ◽  
Model Performance ◽  
Predictive Performance ◽  
Oxygen Isotopic Composition ◽  
Machine Learning Algorithms ◽  
Support Vector

&lt;p&gt;The Dansgaard-Oeschger (DO) events are one of the most striking examples of abrupt climate change in the Earth's history, representing temperature oscillations of about 8 to 16 degrees Celsius within a few decades. DO events have been studied extensively in paleoclimatic records, particularly in ice core proxies. Examples include the Greenland NGRIP record of oxygen isotopic composition.&lt;br&gt;This work addresses the anticipation of DO events using machine learning algorithms. We consider the NGRIP time series from 20 to 60 kyr b2k with the GICC05 timescale and 20-year temporal resolution. Forecasting horizons range from 0 (nowcasting) to 400 years. We adopt three different machine learning algorithms (random forests, support vector machines, and logistic regression) in training windows of 5 kyr. We perform validation on subsequent test windows of 5 kyr, based on timestamps of previous DO events' classification in Greenland by Rasmussen et al. (2014). We perform experiments with both sliding and growing windows.&lt;br&gt;Results show that predictions on sliding windows are better overall, indicating that modelling is affected by non-stationary characteristics of the time series. The three algorithms' predictive performance is similar, with a slightly better performance of random forest models for shorter forecast horizons. The prediction models' predictive capability decreases as the forecasting horizon grows more extensive but remains reasonable up to 120 years. Model performance deprecation is mostly related to imprecision in accurately determining the start and end time of events and identifying some periods as DO events when such is not valid.&lt;/p&gt;

scholarly journals The Effects of Dietary Pattern during Intensified Training on Stool Microbiota of Elite Race Walkers

Nutrients ◽  
2019 ◽  
Vol 11 (2) ◽  
pp. 261 ◽  
Author(s):  
Nida Murtaza ◽  
Louise Burke ◽  
Nicole Vlahovich ◽  
Bronwen Charlesson ◽  
Hayley O’ Neill ◽  
...  
Keyword(s):  
Gut Microbiota ◽  
Amplicon Sequencing ◽  
Post Treatment ◽  
Rrna Gene ◽  
Diet Patterns ◽  
Selective Pressures ◽  
Low Carbohydrate ◽  
Stool Samples ◽  
Stool Microbiota ◽  
Sedentary Subjects

We investigated extreme changes in diet patterns on the gut microbiota of elite race walkers undertaking intensified training and its possible links with athlete performance. Numerous studies with sedentary subjects have shown that diet and/or exercise can exert strong selective pressures on the gut microbiota. Similar studies with elite athletes are relatively scant, despite the recognition that diet is an important contributor to sports performance. In this study, stool samples were collected from the cohort at the beginning (baseline; BL) and end (post-treatment; PT) of a three-week intensified training program during which athletes were assigned to a High Carbohydrate (HCHO), Periodised Carbohydrate (PCHO) or ketogenic Low Carbohydrate High Fat (LCHF) diet (post treatment). Microbial community profiles were determined by 16S rRNA gene amplicon sequencing. The microbiota profiles at BL could be separated into distinct “enterotypes,” with either a Prevotella or Bacteroides dominated enterotype. While enterotypes were relatively stable and remained evident post treatment, the LCHF diet resulted in a greater relative abundance of Bacteroides and Dorea and a reduction of Faecalibacterium. Significant negative correlations were observed between Bacteroides and fat oxidation and between Dorea and economy test following LCHF intervention.

scholarly journals Virtual Screening of Conjugated Polymers for Organic Photovoltaic Devices Using Support Vector Machines and Ensemble Learning

2019 ◽  
Vol 2019 ◽  
pp. 1-7
Author(s):  
Fang-Chung Chen
Keyword(s):  
Virtual Screening ◽  
Conjugated Polymers ◽  
Ensemble Learning ◽  
High Performance ◽  
Learning Algorithm ◽  
Predictive Performance ◽  
Machine Learning Algorithms ◽  
Organic Photovoltaic ◽  
Support Vector ◽  
Learning Approaches

Herein, we report virtual screening of potential semiconductor polymers for high-performance organic photovoltaic (OPV) devices using various machine learning algorithms. We particularly focus on support vector machine (SVM) and ensemble learning approaches. We found that the power conversion efficiencies of the device prepared with the polymer candidates can be predicted with their structure fingerprints as the only inputs. In other words, no preliminary knowledge about material properties was required. Additionally, the predictive performance could be further improved by “blending” the results of the SVM and random forest models. The resulting ensemble learning algorithm might open up a new opportunity for more precise, high-throughput virtual screening of conjugated polymers for OPV devices.

scholarly journals Metagenomic analysis of bacterial community composition in Dhanaan: Ethiopian traditional fermented camel milk

2019 ◽  
Vol 366 (Supplement_1) ◽  
pp. i127-i132
Author(s):  
Tesfemariam Berhe ◽  
Richard Ipsen ◽  
Eyassu Seifu ◽  
Mohamed Y Kurtu ◽  
Angelina Fugl ◽  
...  
Keyword(s):  
Bacterial Community Composition ◽  
Safety Evaluation ◽  
Operational Taxonomic Unit ◽  
Amplicon Sequencing ◽  
Starter Cultures ◽  
Camel Milk ◽  
Rrna Gene ◽  
Food Grade ◽  
Streptococcus Species ◽  
Metagenomic Approach

ABSTRACT This study was conducted to evaluate the safety and bacterial profile of Dhanaan (Ethiopian traditional fermented camel milk). The composition of the microbial community in Dhanaan samples was analysed by a metagenomic approach of 16S rRNA gene amplicon sequencing. Metagenomic profiling identified 87 different bacterial microorganisms (OTUs) in six samples analysed. Although the Dhanaan samples contained various lactic acid bacteria (LAB), they also all contained undesirable microorganisms in large proportions. The following LAB genera were identified: Streptococcus, Lactococcus and Weissella. One Streptococcus species represented by OTU-1 (operational taxonomic unit) was found in all Dhanaan samples and the dominating species in four out of six samples. This common isolate was found to be closely related to S. lutetiensis and S. infantarius. Undesirable microorganisms from genera such as Escherichia, Klebsiella, Enterobacter, Acinetobacter and Clostridium were, however, also frequent, or even dominant in Dhanaan samples. Thus, this calls for a change in the Dahnaan manufacturing practice to an improved and safer production system. Starter cultures suitable for Dhanaan production might be developed from the Streptococcus, Weissella and Lactococcus microorganisms identified in this study. However, further safety evaluation and technological characterization need to be conducted on strains defined by OTU-1, OTU-2, OTU-3, OTU-8 and OTU-35 before they can be used as food grade starter cultures.

scholarly journals Adults with Prader–Willi syndrome exhibit a unique microbiota profile

2021 ◽  
Vol 14 (1) ◽  
Author(s):  
Wendy J. Dahl ◽  
Jérémie Auger ◽  
Zainab Alyousif ◽  
Jennifer L. Miller ◽  
Thomas A. Tompkins
Keyword(s):  
Adult Population ◽  
Geographical Location ◽  
Gastrointestinal Transit ◽  
Amplicon Sequencing ◽  
Fecal Microbiota ◽  
Machine Learning Algorithms ◽  
Rrna Gene ◽  
Prader Willi Syndrome ◽  
Microbiota Composition ◽  
Gastrointestinal Transit Time

Abstract Objective Adults with Prader–Willi syndrome (PWS) require less energy intake to maintain body weight than the general adult population. This, combined with their altered gastrointestinal transit time, may impact microbiota composition. The aim of the study was to determine if the fecal microbiota composition of adults with PWS differed from non-affected adults. Using usual diet/non-interventional samples, fecal microbiota composition was analyzed using 16S rRNA gene amplicon sequencing and data from adults with PWS were merged with four other adult cohorts that differed by geographical location and age. QIIME 2™ sample-classifier, machine learning algorithms were used to cross-train the samples and predict from which dataset the taxonomic profiles belong. Taxa that most distinguished between all datasets were extracted and a visual inspection of the R library PiratePlots was performed to select the taxa that differed in abundance specific to PWS. Results Fecal microbiota composition of adults with PWS showed low Blautia and enhanced RF39 (phyla Tenericutes), Ruminococcaceae, Alistipes, Erysipelotrichacaea, Parabacteriodes and Odoribacter. Higher abundance of Tenericutes, in particular, may be a signature characteristic of the PWS microbiota although its relationship, if any, to metabolic health is not yet known.

Sign in / Sign up

Export Citation Format

Share Document