Microbiome meta-analysis and cross-disease comparison enabled by the SIAMCAT machine learning toolbox

Wirbel, Jakob; Zych, Konrad; Essex, Morgan; Karcher, Nicolai; Kartal, Ece; Salazar, Guillem; Bork, Peer; Sunagawa, Shinichi; Zeller, Georg

doi:10.1186/s13059-021-02306-1

Cited by 168 publications

(165 citation statements)

References 109 publications

Supporting

Mentioning

160

Contrasting

Order By: Relevance

“…Differential abundance between time points and statistical analysis of the changes over time was obtained with siamcat [ 36 ]. Time points analysed were at consecutive weeks from the start ( t 0): t 0, t 2, t 4, t 6, t 8 and t 10.…”

Section: Resultsmentioning

confidence: 99%

“…siamcat [ 36 ] was employed to determine differentially abundant GTDB clustered MAGs between groups. The data were normalized by proportions prior to analysis with siamcat .…”

Section: Methodsmentioning

confidence: 99%

“…For the installation and management of environments, conda [ 47 ] was used (v4.7.12). R [ 48 ] and the following R packages were used for the data analysis and visualization: ape [ 49 ], circlize [ 50 ], cluster [ 51 ], cowplot [ 52 ], data.table [ 53 ], dplyr [ 54 ], EnvStats [ 55 ], factoextra [ 56 ], forcats [ 57 ], ggbiplot [ 58 ], ggplot2 [ 58 ], ggpubr [ 59 ], ggrepel [ 60 ], gplots [ 61 ], gridExtra [ 62 ], magrittr [ 63 ], matrixStats [ 64 ], microbiome [ 65 ], openxlsx [ 66 ], pheatmap [ 67 ], phyloseq [ 35 ], plyr [ 68 ], purr [ 69 ], RColorBrewer [ 70 ], readr [ 71 ], readxl [ 72 ], reshape [ 73 ], robCompositions [ 74 ], scales [ 75 ], seqinr [ 76 ], siamcat [ 36 ], splitstackshape [ 77 ], stringr [ 78 ], tidyr [ 79 ] and tidyverse [ 80 ].…”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Post-weaning shifts in microbiome composition and metabolism revealed by over 25 000 pig gut metagenome-assembled genomes

et al. 2021

View full text Add to dashboard Cite

Using a previously described metagenomics dataset of 27 billion reads, we reconstructed over 50 000 metagenome-assembled genomes (MAGs) of organisms resident in the porcine gut, 46.5 % of which were classified as >70 % complete with a <10 % contamination rate, and 24.4 % were nearly complete genomes. Here, we describe the generation and analysis of those MAGs using time-series samples. The gut microbial communities of piglets appear to follow a highly structured developmental programme in the weeks following weaning, and this development is robust to treatments including an intramuscular antibiotic treatment and two probiotic treatments. The high resolution we obtained allowed us to identify specific taxonomic ‘signatures’ that characterize the gut microbial development immediately after weaning. Additionally, we characterized the carbohydrate repertoire of the organisms resident in the porcine gut. We tracked the abundance shifts of 294 carbohydrate active enzymes, and identified the species and higher-level taxonomic groups carrying each of these enzymes in their MAGs. This knowledge can contribute to the design of probiotics and prebiotic interventions as a means to modify the piglet gut microbiome.

show abstract

Section: Resultsmentioning

confidence: 99%

“…siamcat [ 36 ] was employed to determine differentially abundant GTDB clustered MAGs between groups. The data were normalized by proportions prior to analysis with siamcat .…”

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Post-weaning shifts in microbiome composition and metabolism revealed by over 25 000 pig gut metagenome-assembled genomes

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Differential abundance analysis was performed by Wilcoxon rank sum test and Analysis of Composition of Microbiomes ( ANCOM ) [32] . Random forest machine learning models were performed using the randomForest package ( SIAMCAT package [33] ) in which five-fold cross-validation was performed with 100 iterations. Microbiome regression analyses were performed using the MaAsLin2 package.…”

Section: Methodsmentioning

confidence: 99%

The fecal microbiome and rotavirus vaccine immunogenicity in rural Zimbabwean infants

Robertson

Church

Edens³

et al. 2021

Vaccine

View full text Add to dashboard Cite

Background Oral rotavirus vaccine (RVV) immunogenicity is considerably lower in low- versus high-income populations; however, the mechanisms underlying this remain unclear. Previous evidence suggests that the gut microbiota may contribute to differences in oral vaccine efficacy. Methods We performed whole metagenome shotgun sequencing on stool samples and measured anti-rotavirus immunoglobulin A in plasma samples from a subset of infants enrolled in a cluster randomized 2 × 2 factorial trial of improved water, sanitation and hygiene and infant feeding in rural Zimbabwe (SHINE trial: NCT01824940). We examined taxonomic microbiome composition and functional metagenome features using random forest models, differential abundance testing and regression analyses to explored associations with RVV immunogenicity. Results Among 158 infants with stool samples and anti-rotavirus IgA titres, 34 were RVV seroconverters. The median age at stool collection was 43 days (IQR: 35–68), corresponding to a median of 4 days before the first RVV dose. The infant microbiome was dominated by Bifidobacterium longum . The gut microbiome differed significantly between early (≤42 days) and later samples (>42 days) however, we observed no meaningful differences in alpha diversity, beta diversity, species composition or functional metagenomic features by RVV seroconversion status. Bacteroides thetaiotaomicron was the only species associated with anti-rotavirus IgA titre. Random forest models poorly classified seroconversion status by both composition and functional microbiome variables. Conclusions RVV immunogenicity is low in this rural Zimbabwean setting, however it was not associated with the composition or function of the early-life gut microbiome in this study. Further research is warranted to examine the mechanisms of poor oral RVV efficacy in low-income countries.

show abstract

“…To generate the machine learning models, taxonomic features were used in the form of ASV tables collapsed to specieslevel. For the classification, we used the workflow provided in "Siamcat, " which provides a machine learning toolbox for metagenome analysis through state-of-the-art machine learning methods (Wirbel et al, 2019(Wirbel et al, , 2021. The data were separately processed for fungi and bacteria and sample-wise relative abundance for the microbiome quantitative profiles was used as input data to maintain the uniformity.…”

Section: Machine Learning Analysismentioning

confidence: 99%

Characterization of Supragingival Plaque and Oral Swab Microbiomes in Children With Severe Early Childhood Caries

et al. 2021

View full text Add to dashboard Cite

The human oral cavity harbors one of the most diverse microbial communities with different oral microenvironments allowing the colonization of unique microbial species. This study aimed to determine which of two commonly used sampling sites (dental plaque vs. oral swab) would provide a better prediction model for caries-free vs. severe early childhood caries (S-ECC) using next generation sequencing and machine learning (ML). In this cross-sectional study, a total of 80 children (40 S-ECC and 40 caries-free) < 72 months of age were recruited. Supragingival plaque and oral swab samples were used for the amplicon sequencing of the V4-16S rRNA and ITS1 rRNA genes. The results showed significant differences in alpha and beta diversity between dental plaque and oral swab bacterial and fungal microbiomes. Differential abundance analyses showed that, among others, the cariogenic species Streptococcus mutans was enriched in the dental plaque, compared to oral swabs, of children with S-ECC. The fungal species Candida dubliniensis and C. tropicalis were more abundant in the oral swab samples of children with S-ECC compared to caries-free controls. They were also among the top 20 most important features for the classification of S-ECC vs. caries-free in oral swabs and for the classification of dental plaque vs. oral swab in the S-ECC group. ML approaches revealed the possibility of classifying samples according to both caries status and sampling sites. The tested site of sample collection did not change the predictability of the disease. However, the species considered to be important for the classification of disease in each sampling site were slightly different. Being able to determine the origin of the samples could be very useful during the design of oral microbiome studies. This study provides important insights into the differences between the dental plaque and oral swab bacteriome and mycobiome of children with S-ECC and those caries-free.

show abstract

Microbiome meta-analysis and cross-disease comparison enabled by the SIAMCAT machine learning toolbox

Cited by 168 publications

References 109 publications

Post-weaning shifts in microbiome composition and metabolism revealed by over 25 000 pig gut metagenome-assembled genomes

Post-weaning shifts in microbiome composition and metabolism revealed by over 25 000 pig gut metagenome-assembled genomes

The fecal microbiome and rotavirus vaccine immunogenicity in rural Zimbabwean infants

Characterization of Supragingival Plaque and Oral Swab Microbiomes in Children With Severe Early Childhood Caries

Contact Info

Product

Resources

About