Predicting the Role of the Human Gut Microbiome in Constipation Using Machine-Learning Methods: A Meta-Analysis

(1) Background: Constipation is a common condition that affects the health and the quality of life of patients. Recent studies have suggested that the gut microbiome is associated with constipation, but these studies were mainly focused on a single research cohort. Thus, we aimed to construct a classification model based on fecal bacterial and identify the potential gut microbes’ biomarkers. (2) Methods: We collected 3056 fecal amplicon sequence data from five research cohorts. The data were subjected to a series of analyses, including alpha- and beta-diversity analyses, phylogenetic profiling analyses, and systematic machine learning to obtain a comprehensive understanding of the association between constipation and the gut microbiome. (3) Results: The alpha diversity of the bacterial community composition was higher in patients with constipation. Beta diversity analysis evidenced significant partitions between the two groups on the base of gut microbiota composition. Further, machine learning based on feature selection was performed to evaluate the utility of the gut microbiome as the potential biomarker for constipation. The Gradient Boosted Regression Trees after chi2 feature selection was the best model, exhibiting a validation performance of 70.7%. (4) Conclusions: We constructed an accurate constipation discriminant model and identified 15 key genera, including Serratia, Dorea, and Aeromonas, as possible biomarkers for constipation.

Download Full-text

Retinitis pigmentosa is associated with shifts in the gut microbiome

Scientific Reports ◽

10.1038/s41598-021-86052-1 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Oksana Kutsyr ◽

Lucía Maestre-Carballa ◽

Mónica Lluesma-Gomez ◽

Manuel Martinez-Garcia ◽

Nicolás Cuenca ◽

...

Keyword(s):

Retinitis Pigmentosa ◽

Gut Microbiome ◽

Functional Decline ◽

Retinal Disease ◽

Photoreceptor Cells ◽

Amplicon Sequencing ◽

Rrna Gene ◽

Sequencing Data ◽

Alpha And Beta Diversity ◽

Potential Biomarker

AbstractThe gut microbiome is known to influence the pathogenesis and progression of neurodegenerative diseases. However, there has been relatively little focus upon the implications of the gut microbiome in retinal diseases such as retinitis pigmentosa (RP). Here, we investigated changes in gut microbiome composition linked to RP, by assessing both retinal degeneration and gut microbiome in the rd10 mouse model of RP as compared to control C57BL/6J mice. In rd10 mice, retinal responsiveness to flashlight stimuli and visual acuity were deteriorated with respect to observed in age-matched control mice. This functional decline in dystrophic animals was accompanied by photoreceptor loss, morphologic anomalies in photoreceptor cells and retinal reactive gliosis. Furthermore, 16S rRNA gene amplicon sequencing data showed a microbial gut dysbiosis with differences in alpha and beta diversity at the genera, species and amplicon sequence variants (ASV) levels between dystrophic and control mice. Remarkably, four fairly common ASV in healthy gut microbiome belonging to Rikenella spp., Muribaculaceace spp., Prevotellaceae UCG-001 spp., and Bacilli spp. were absent in the gut microbiome of retinal disease mice, while Bacteroides caecimuris was significantly enriched in mice with RP. The results indicate that retinal degenerative changes in RP are linked to relevant gut microbiome changes. The findings suggest that microbiome shifting could be considered as potential biomarker and therapeutic target for retinal degenerative diseases.

Download Full-text

Intelligent Detection of False Information in Arabic Tweets Utilizing Hybrid Harris Hawks Based Feature Selection and Machine Learning Models

Symmetry ◽

10.3390/sym13040556 ◽

2021 ◽

Vol 13 (4) ◽

pp. 556

Author(s):

Thaer Thaher ◽

Mahmoud Saheb ◽

Hamza Turabieh ◽

Hamouda Chantar

Keyword(s):

Machine Learning ◽

Social Media ◽

Feature Selection ◽

Language Processing ◽

User Profile ◽

Vital Role ◽

Classification Model ◽

Fake News ◽

False Information ◽

Social Media Platforms

Fake or false information on social media platforms is a significant challenge that leads to deliberately misleading users due to the inclusion of rumors, propaganda, or deceptive information about a person, organization, or service. Twitter is one of the most widely used social media platforms, especially in the Arab region, where the number of users is steadily increasing, accompanied by an increase in the rate of fake news. This drew the attention of researchers to provide a safe online environment free of misleading information. This paper aims to propose a smart classification model for the early detection of fake news in Arabic tweets utilizing Natural Language Processing (NLP) techniques, Machine Learning (ML) models, and Harris Hawks Optimizer (HHO) as a wrapper-based feature selection approach. Arabic Twitter corpus composed of 1862 previously annotated tweets was utilized by this research to assess the efficiency of the proposed model. The Bag of Words (BoW) model is utilized using different term-weighting schemes for feature extraction. Eight well-known learning algorithms are investigated with varying combinations of features, including user-profile, content-based, and words-features. Reported results showed that the Logistic Regression (LR) with Term Frequency-Inverse Document Frequency (TF-IDF) model scores the best rank. Moreover, feature selection based on the binary HHO algorithm plays a vital role in reducing dimensionality, thereby enhancing the learning model’s performance for fake news detection. Interestingly, the proposed BHHO-LR model can yield a better enhancement of 5% compared with previous works on the same dataset.

Download Full-text

Gut Microbiome in Psoriasis: An Updated Review

Pathogens ◽

10.3390/pathogens9060463 ◽

2020 ◽

Vol 9 (6) ◽

pp. 463

Author(s):

Mariusz Sikora ◽

Albert Stec ◽

Magdalena Chrabaszcz ◽

Aleksandra Knot ◽

Anna Waskiel-Burnat ◽

...

Keyword(s):

Gut Microbiome ◽

Beta Diversity ◽

Large Scale ◽

Skin Diseases ◽

Intestinal Barrier ◽

Alpha Diversity ◽

Current Data ◽

Intestinal Microbiome ◽

Microbial Composition ◽

Alpha And Beta Diversity

(1) Background: A growing body of evidence highlights that intestinal dysbiosis is associated with the development of psoriasis. The gut–skin axis is the novel concept of the interaction between skin diseases and microbiome through inflammatory mediators, metabolites and the intestinal barrier. The objective of this study was to synthesize current data on the gut microbial composition in psoriasis. (2) Methods: We conducted a systematic review of studies investigating intestinal microbiome in psoriasis, using the PRISMA checklist. We searched MEDLINE, EMBASE, and Web of Science databases for relevant published articles (2000–2020). (3) Results: All of the 10 retrieved studies reported alterations in the gut microbiome in patients with psoriasis. Eight studies assessed alpha- and beta-diversity. Four of them reported a lack of change in alpha-diversity, but all confirmed significant changes in beta-diversity. At the phylum-level, at least two or more studies reported a lower relative abundance of Bacteroidetes, and higher Firmicutes in psoriasis patients versus healthy controls. (4) Conclusions: There is a significant association between alterations in gut microbial composition and psoriasis; however, there is high heterogeneity between studies. More unified methodological standards in large-scale studies are needed to understand microbiota’s contribution to psoriasis pathogenesis and its modulation as a potential therapeutic strategy.

Download Full-text

Machine Learning-Based Identification of Potentially Novel Non-Alcoholic Fatty Liver Disease Biomarkers

Biomedicines ◽

10.3390/biomedicines9111636 ◽

2021 ◽

Vol 9 (11) ◽

pp. 1636

Author(s):

Roshan Shafiha ◽

Basak Bahcivanci ◽

Georgios V. Gkoutos ◽

Animesh Acharjee

Keyword(s):

Machine Learning ◽

Feature Selection ◽

Liver Disease ◽

Fatty Liver Disease ◽

Complement Pathway ◽

Alcoholic Fatty Liver ◽

Potential Biomarker ◽

Processing Step ◽

Biological Interpretation ◽

Alcoholic Fatty Liver Disease

Non-alcoholic fatty liver disease (NAFLD) is a chronic liver disease that presents a great challenge for treatment and prevention.. This study aims to implement a machine learning approach that employs such datasets to identify potential biomarker targets. We developed a pipeline to identify potential biomarkers for NAFLD that includes five major processes, namely, a pre-processing step, a feature selection and a generation of a random forest model and, finally, a downstream feature analysis and a provision of a potential biological interpretation. The pre-processing step includes data normalising and variable extraction accompanied by appropriate annotations. A feature selection based on a differential gene expression analysis is then conducted to identify significant features and then employ them to generate a random forest model whose performance is assessed based on a receiver operating characteristic curve. Next, the features are subjected to a downstream analysis, such as univariate analysis, a pathway enrichment analysis, a network analysis and a generation of correlation plots, boxplots and heatmaps. Once the results are obtained, the biological interpretation and the literature validation is conducted over the identified features and results. We applied this pipeline to transcriptomics and lipidomic datasets and concluded that the C4BPA gene could play a role in the development of NAFLD. The activation of the complement pathway, due to the downregulation of the C4BPA gene, leads to an increase in triglyceride content, which might further render the lipid metabolism. This approach identified the C4BPA gene, an inhibitor of the complement pathway, as a potential biomarker for the development of NAFLD.

Download Full-text

Evidence supporting the microbiota–gut–brain axis in a songbird

Biology Letters ◽

10.1098/rsbl.2020.0430 ◽

2020 ◽

Vol 16 (11) ◽

pp. 20200430

Author(s):

Morgan C. Slevin ◽

Jennifer L. Houtz ◽

David J. Bradshaw ◽

Rindy C. Anderson

Keyword(s):

Gut Microbiome ◽

Beta Diversity ◽

Alpha Diversity ◽

Cloacal Swab ◽

Cognitive Tasks ◽

Captive Population ◽

Wild Populations ◽

Alpha And Beta Diversity ◽

Microbiome Research ◽

Host Development

Recent research in mammals supports a link between cognitive ability and the gut microbiome, but little is known about this relationship in other taxa. In a captive population of 38 zebra finches ( Taeniopygia guttata ), we quantified performance on cognitive tasks measuring learning and memory. We sampled the gut microbiome via cloacal swab and quantified bacterial alpha and beta diversity. Performance on cognitive tasks related to beta diversity but not alpha diversity. We then identified differentially abundant genera influential in the beta diversity differences among cognitive performance categories. Though correlational, this study provides some of the first evidence of an avian microbiota–gut–brain axis, building foundations for future microbiome research in wild populations and during host development.

Download Full-text

PSVI-16 Fecal microbiome of nursery pigs fed phytogenics and antibiotics

Journal of Animal Science ◽

10.1093/jas/skz258.418 ◽

2019 ◽

Vol 97 (Supplement_3) ◽

pp. 203-203

Author(s):

Huyen Tran ◽

Timothy J Johnson

Keyword(s):

Beta Diversity ◽

Sequence Data ◽

Alpha Diversity ◽

Illumina Miseq ◽

Amplicon Sequencing ◽

Fecal Microbiome ◽

Nursery Pigs ◽

Alpha And Beta Diversity ◽

Family Level ◽

Dietary Treatments

Abstract The objective of this study was to evaluate effects of feeding two phytogenic products (PHY1 and PHY2; blends of essential oils and plant extracts) in diets with or without antibiotics (AureoMix S 10-10; AB) on fecal microbiome of nursery pigs. A total of 400 nursery pigs (6.8 kg BW; 20 d of age) were fed one of the six dietary treatments (9 pens/treatment), including: control (0% AB; 0% phytogenics), 0.5% AB, phytogenics (0.02% PHY1 or 0.03% PHY2) or the combination of phytogenic and AB (PHY1 x AB or PHY2 x AB). On d 46 postweaning, 48 fecal samples were collected (1 pig/pen; 7–9 pigs/treatment) and were subjected to the analyses of microbial communities by using 16S rRNA V4 amplicon sequencing with Illumina MiSeq. The sequence data were analyzed by using Qiime and the rarefied OTU table was submitted to Calypso to evaluate the alpha and beta diversity, taxonomic classification, and the differential taxa associated to the dietary treatments. There were differences among treatments on alpha diversity, where the control and PHY2 pigs had lower OTU richness (P = 0.05) and chao1 index (P < 0.10) compared to pigs fed AB alone or AB with phytogenics. There were also differences among treatments on microbial beta diversity of pigs (P < 0.01). The most abundant phyla included Firmicute, Bacteroidetes, Actinobacteria, Tenericutes, Proteobacteria, Spirochaetes, and TM7. At family level, pigs fed AB had greater Ruminococcaceae compared to the control, but lower Coriobacteriaceae and Erysipelotrichaceae compared to PHY1 or PHY2 group (P < 0.05). Feature selection by LEfSe indicated that dominant genus associated to AB treatment was Unclassified RF39, while dominant genera associated to PHY2 treatment were Cantenibacterium, unclassified Coriobacteriaceae, Blautia, Eubacterium, and Collinsella. In conclusion, feeding AB and phytogenic products had different impacts on the fecal bacteria of nursery pigs.

Download Full-text

The Horse Gut Microbiome Responds in a Highly Individualized Manner to Forage Lignification

10.21203/rs.3.rs-27270/v1 ◽

2020 ◽

Author(s):

Andres Gomez ◽

Ashok Kumar Sharma ◽

Amanda Grev ◽

Craig Sheaffer ◽

Krishona Martinson

Keyword(s):

Gut Microbiome ◽

Community Dynamics ◽

Lignin Content ◽

Bacterial Community Composition ◽

Neutral Detergent Fiber ◽

Fecal Microbiome ◽

Alpha And Beta Diversity ◽

Dry Matter Digestibility ◽

Acid Detergent Lignin ◽

The Impact

Abstract Background: Although contributions of the equine gut microbiome to forage utilization are well recognized, the impact of alfalfa lignification on the equine gut microbiome remains unknown. Here, we characterized microbial community dynamics in the equine distal gut when feeding reduced lignin (RL) and reference alfalfa hays (CON-control) ( Medicago sativa L.) to adult stock-type horses. Hay from RL and CON cultivars were similar in crude protein, neutral detergent fiber, and equine digestible energy, but differed in acid detergent lignin content (RL:74 g kg -1 vs. CON: 81 g kg -1 ). Dietary treatments were fed to six horses in a crossover study. Experimental periods consisted of a 9-d dietary adaptation phase followed by a 5-d total fecal collection phase, during which horses were housed in individual box stalls and manure was removed on a continuous 24-h basis. At 12-h intervals, feces were thoroughly mixed, frozen, and used for bacterial community composition analyses via V4, 16S rRNA amplicon MiSeq sequencing.Results: RL alfalfa did not result in specific fecal microbiome composition across all horses. However, upon incorporating individual horse in the model, it was shown that the microbiome of each subject did respond to hay lignin content in an individualized manner over time, in terms of alpha and beta diversity. Closer inspection of specific taxonomic changes upon feeding the two diets also revealed horse-specific trends, with unique amplicon sequence variants classified as Akkermansia , Fibrobacter succinogenes , Treponema, and Paludibacter fluctuating significantly in abundance when RL alfalfa was fed, depending on horse. Along these lines, horse-specific associations between individual gut microbiome traits and characteristics of the digested CON or RL alfalfa were observed, mainly in regards to dry matter digestibility and mean feed particle size.Conclusions: These results indicate that the horse gut microbiome responds in an individualized manner to small changes in the amount of acid detergent lignin in alfalfa hay, potentially impacting several feed digestibility characteristics. The implications of horse-specific responses to forage quality in regards to metabolic health and performance remain to be elucidated.

Download Full-text

Machine learning analysis on American Gut Project microbiome data to identify subjects with cancer both with and without chemotherapy exposure.

Journal of Clinical Oncology ◽

10.1200/jco.2020.38.15_suppl.e14069 ◽

2020 ◽

Vol 38 (15_suppl) ◽

pp. e14069-e14069

Author(s):

Oguz Akbilgic ◽

Ibrahim Karabayir ◽

Hakan Gunturkun ◽

Joseph F Pierre ◽

Ashley C Rashe ◽

...

Keyword(s):

Machine Learning ◽

Cancer Patients ◽

Test Data ◽

Gut Microbiome ◽

Classification Model ◽

Outcome Variable ◽

Gradient Boosting ◽

Healthy Controls ◽

Extreme Gradient Boosting ◽

Significant Difference

e14069 Background: There is growing interest in the links between cancer and the gut microbiome. However, the effect of chemotherapy upon the gut microbiome remains unknown. We studied whether machine learning can: 1) accurately classify subjects with cancer vs healthy controls and 2) whether this classification model is affected by chemotherapy exposure status. Methods: We used the American Gut Project data to build a extreme gradient boosting (XGBoost) model to distinguish between subjects with cancer vs healthy controls using data on simple demographics and published microbiome. We then further explore the selected features for cancer subjects based on chemotherapy exposure. Results: The cohort included 7,685 subjects consisting of 561 subjects with cancer, 52.5% female, 87.3% White, and average age of 44.7 (SD 17.7). The binary outcome variable represents cancer status. Among 561 subjects with cancer, 94 of them were treated with chemotherapy agents before sampling of microbiomes. As predictors, there were four demographic variables (sex, race, age, BMI) and 1,812 operational taxonomic units (OTUs) each found in at least 2 subjects via RNA sequencing. We randomly split data into 80% training and 20% hidden test. We then built an XGBoost model with 5-fold cross-validation using only training data yielding an AUC (with 95% CI) of 0.79 (0.77, 0.80) and obtained the almost the same AUC on the hidden test data. Based on feature importance analysis, we identified 12 most important features (Age, BMI and 12 OTUs; 4C0d-2, Brachyspirae, Methanosphaera, Geodermatophilaceae, Bifidobacteriaceae, Slackia, Staphylococcus, Acidaminoccus, Devosia, Proteus) and rebuilt a model using only these features and obtained AUC of 0.80 (0.77, 0.83) on the hidden test data. The average predicted probabilities for controls, cancer patients who were exposed to chemotherapy, and cancer patients who were not were 0.071 (0.070,0.073), 0.125 (0.110, 0.140), 0.156 (0.148, 0.164), respectively. There was no statistically significant difference on levels of these 12 OTUs between cancer subjects treated with and without chemotherapy. Conclusions: Machine learning achieved a moderately high accuracy identifying patients’ cancer status based on microbiome. Despite the literature on microbiome and chemotherapy interaction, the levels of 12 OTUs used in our model were not significantly different for cancer patients with or without chemotherapy exposure. Testing this model on other large population databases is needed for broader validation.

Download Full-text

The power of microbiome studies: some considerations on which alpha and beta metrics to use and how to report analysis the results

10.21203/rs.3.rs-698991/v1 ◽

2021 ◽

Author(s):

Jannigje Gerdien Kers ◽

Edoardo Saccenti

Keyword(s):

Sample Size ◽

Beta Diversity ◽

Sequence Data ◽

Animal Experiments ◽

Simulated Data ◽

Alpha Diversity ◽

Data Sets ◽

Power Calculations ◽

Alpha And Beta Diversity ◽

Diversity Metrics

Abstract Since sequencing techniques become less expensive, larger sample sizes are applicable for microbiota studies. The aim of this study is to show how, and to what extent, different diversity metrics and different compositions of the microbiota influence the needed sample size to observed dissimilar groups. Empirical 16S rRNA amplicon sequence data obtained from animal experiments, observational human data, and simulated data was used to perform retrospective power calculations. A wide variation of alpha diversity and beta diversity metrics were used to compare the different microbiota data sets and the effect on the sample size. Our data showed that beta diversity metrics are most sensitive to observe differences compared to alpha diversity metrics. The structure of the data influenced which alpha metrics are most sensitive. Regarding beta diversity, the Bray-Curtis metric is in general most sensitive to observe differences between groups, resulting in lower sample size and potential publication bias. We recommend to perform power calculations and to use multiple diversity metrics as an outcome measure. To improve microbiota studies awareness needs to be raised on the sensitivity and bias for microbiota research outcomes created by the used metrics rather than biological differences. We have seen that different alpha and beta diversity metrics lead to different study power: on the basis of this observation, one could be naturally tempted to try all possible metrics until one or more are found that give a statistically significant test result, i.e. p-value < α. This way of proceeding is one of the many forms of the so-called p-value hacking. To this end, in our opinion, the only way to protect ourselves from (the temptation of) p-hacking would be to publish, and we stress here the word publish, a statistical plan before experiments are initiated: this practice is customary for clinical trials where a statistical plan describing the endpoints and the corresponding statistical analyses must be disclosed before the start of the study.

Download Full-text

Red Wheat Alters Colon Cancer Risk, Oxidative Stress, and the Gut Microbiome

Current Developments in Nutrition ◽

10.1093/cdn/nzab054_011 ◽

2021 ◽

Vol 5 (Supplement_2) ◽

pp. 1156-1156

Author(s):

Chelsey Fiecke ◽

Daniel Gallaher ◽

Senay Simsek ◽

Ashok Sharma

Keyword(s):

Oxidative Stress ◽

Colon Cancer ◽

Gut Microbiome ◽

Beta Diversity ◽

Precancerous Lesions ◽

Aberrant Crypt Foci ◽

Aleurone Layer ◽

Adaptation Period ◽

Colon Tissue ◽

Alpha And Beta Diversity

Abstract Objectives Red wheat, the class of wheat used to make yeast bread products, is associated with reductions in colon cancer biomarkers, regardless of refinement state. We hypothesized that red wheat as well as the phenol-rich aleurone and testa layers of red wheat would reduce colonic precancerous lesions and oxidative stress, and beneficially modulate the gut microbiome in rats with diet-induced obesity. Methods Rats were divided into seven groups (12/group) and fed a normal fat diet (NFD), high-fat diet (50% of total kcal as fat, HFD), whole red wheat + HFD (whR + HFD), refined red wheat + HFD (refR + HFD), refined white wheat + HFD (refW + HFD), aleurone layer + HFD (AL + HFD), or testa layer + HFD (TL + HFD). After a 14-day adaptation period, rats received two i.p. injections of the colon-specific carcinogen 1,2-dimethylhydrazine (DMH), administered one week apart. Sixty-three days after the second injection, colons were harvested and precancerous lesions (aberrant crypt foci, ACF) were enumerated. Staining intensity of 3-nitrotyrosine (3-NT) was determined immunohistochemically in distal colon tissue. Microbial DNA from cecal contents was sequenced using a 16S rRNA metagenomic approach. Differences in alpha and beta diversity, and microbial abundances were determined. Results Compared to the NFD, the HFD had a greater number of ACF, regardless of size (i.e., AC/ACF). The refR + HFD had significant reductions in medium ACF (3–5 AC/ACF; 2.62 vs. 4.28), large ACF (≥6 AC/ACF; 0.06 vs. 0.45), ACF multiplicity (1.58 vs. 2.01) and 3-NT (% positivity per ACF; 2.06% vs. 4.51%) compared to the HFD. All diets containing wheat reduced large ACF number. The TL + HFD and AL + HFD demonstrated trends for reducing ACF with 8 AC (0.06 vs. 0.18) and 3-NT (2.22% vs. 4.51%), respectively, compared to the HFD. Beta diversity significantly differed between diet groups (R2 = 0.27, P = 0.001), and there was greater abundance of Faecalitalea, Fusicatenibacter, and Lactobacillus in the cecal contents of rats fed wheat-containing diets. Conclusions Red wheat reduces precancerous lesions, oxidative stress, and beneficially modulates the gut microbiome relative to a non-wheat diet. The phenol-rich testa and aleurone layers alone had little influence on these outcomes. Funding Sources NDSU Collaborative Seed Grant Program.

Download Full-text