Longitudinal study of stool-associated microbial taxa in sibling pairs with and without autism spectrum disorder

Tataru, Christine; Martin, Austin; Dunlap, Kaitlyn; Peras, Marie; Chrisman, Brianna; Rutherford, Erica; Deitzler, Grace E.; Phillips, Alexandra; Yin, Xiaochen; Sabino, Kayleen; Hannibal, Roberta L.; Hartono, Wiputra; Lin, Michelle; Raack, Edward; Wu, Yonggan; DeSantis, Todd Z.; Iwai, Shoko; Wall, Dennis P.; David, Maude M.

doi:10.1038/s43705-021-00080-6

Cited by 5 publications

(5 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Random forest models were trained on the M3 dataset and tested on the Pilot dataset (see Test Dataset Descriptions) Tataru et al (2021) , David et al (2021) to classify the phenotype of participants with autism spectrum disorder and their typically developing siblings. While the full model outperformed other models during training, it obtained an F1 score of 0.56 in testing, while the GloVe_50, GloVe_100 models obtained higher F1 scores of 0.67, 0.66 respectively ( Figure 4 ; Table 4 ).…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

GMEmbeddings: An R Package to Apply Embedding Techniques to Microbiome Data

Tataru¹,

Eaton²,

David³

2022

Front. Bioinform.

View full text Add to dashboard Cite

Large-scale microbiome studies investigating disease-inducing microbial roles base their findings on differences between microbial count data in contrasting environments (e.g., stool samples between cases and controls). These microbiome survey studies are often impeded by small sample sizes and database bias. Combining data from multiple survey studies often results in obvious batch effects, even when DNA preparation and sequencing methods are identical. Relatedly, predictive models trained on one microbial DNA dataset often do not generalize to outside datasets. In this study, we address these limitations by applying word embedding algorithms (GloVe) and PCA transformation to ASV data from the American Gut Project and generating translation matrices that can be applied to any 16S rRNA V4 region gut microbiome sequencing study. Because these approaches contextualize microbial occurrences in a larger dataset while reducing dimensionality of the feature space, they can improve generalization of predictive models that predict host phenotype from stool associated gut microbiota. The GMEmbeddings R package contains GloVe and PCA embedding transformation matrices at 50, 100 and 250 dimensions, each learned using ∼15,000 samples from the American Gut Project. It currently supports the alignment, matching, and matrix multiplication to allow users to transform their V4 16S rRNA data into these embedding spaces. We show how to correlate the properties in the new embedding space to KEGG functional pathways for biological interpretation of results. Lastly, we provide benchmarking on six gut microbiome datasets describing three phenotypes to demonstrate the ability of embedding-based microbiome classifiers to generalize to independent datasets. Future iterations of GMEmbeddings will include embedding transformation matrices for other biological systems. Available at: https://github.com/MaudeDavidLab/GMEmbeddings.

show abstract

Section: Resultsmentioning

confidence: 99%

“…The M3 dataset Tataru et al (2021) consists of 432 total samples from 72 age-matched sibling pairs. The pairs included one sibling diagnosed with ASD and the other who is developing typically (TD).…”

Section: Methodsmentioning

confidence: 99%

GMEmbeddings: An R Package to Apply Embedding Techniques to Microbiome Data

Tataru¹,

Eaton²,

David³

2022

Front. Bioinform.

View full text Add to dashboard Cite

show abstract

“…Children were all from families with two siblings, one previously diagnosed with Autism by a health care provider and one typically developing. Dietary, lifestyle, demographic, and host health information were reported by parents of guardians via a questionnaire for each child (see Tataru et al (2021) ). Parents and guardians also filled out a Mobile Autism Risk Assessment (MARA) to document autism-associated behaviors in their children with the Autism diagnosis Duda et al (2017) .…”

Section: Methodsmentioning

confidence: 99%

Topic modeling for multi-omic integration in the human gut microbiome and implications for Autism

Tataru

Peras

Rutherford

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Multi-omic analysis of gut microbiomes promises to improve understanding of microbial processes that influence human health, especially in complex conditions such as Autism. However, the vast heterogeneity of both the human gut microbiome environment and the omic techniques make integrating these data challenging. Latent Dirichlet Allocation (LDA), a form of topic modeling, is a promising natural language processing technique that identifies topics in heterogeneous documents. Here, we apply LDA to multi-omic microbial data (stool 16S rRNA, metagenomic, metatranscriptomic, and metabolomic sequencing) from 81 children with and without Autism. We identify topics, or microbial landscapes, that summarize complex phenomena occurring within these microbial communities. We then subset stool samples by topic distribution into groups that share broad microbial landscapes, and identify metabolites, specifically neurotransmitter precursors and fatty acid derivatives, that differ significantly between children with and without Autism. We identify clusters of topics, deemed "cross-omic topics", which we hypothesize are representative of generalizable microbial processes observable at every level of the central dogma of biology. Interpreting topics, we find each represents a particular diet, and we heuristically label each cross-omic topic as: healthy/general function, age-associated function, transcriptional regulation, and opportunistic pathogenesis.

show abstract

“…Children were all from families with two siblings, one previously diagnosed with Autism by a health care provider and one typically developing. Dietary, lifestyle, demographic, and host health information were reported by parents of guardians via a questionnaire for each child (see 104 ). Parents and guardians also filled out a Mobile Autism Risk Assessment (MARA) to document autism-associated behaviors in their children with the Autism diagnosis 105 .…”

Section: Cohort and Metadatamentioning

confidence: 99%

Topic modeling for multi-omic integration in the human gut microbiome and implications for Autism

Tataru

Peras

Rutherford

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

While healthy gut microbiomes are critical to human health, pertinent microbial processes remain largely undefined, partially due to differential bias among profiling techniques. By simultaneously integrating multiple profiling methods, multi-omic analysis can define generalizable microbial processes, and is especially useful in understanding complex conditions such as Autism. Challenges with integrating heterogeneous data produced by multiple profiling methods can be overcome using Latent Dirichlet Allocation (LDA), a promising natural language processing technique that identifies topics in heterogeneous documents. In this study, we apply LDA to multi-omic microbial data (16S rRNA amplicon, shotgun metagenomic, shotgun metatranscrip-tomic, and untargeted metabolomic profiling) from the stool of 81 children with and without Autism. We identify topics, or microbial processes, that summarize complex phenomena occurring within gut microbial communities. We then subset stool samples by topic distribution, and identify metabolites, specifically neurotransmitter precursors and fatty acid derivatives, that differ significantly between children with and without Autism. We identify clusters of topics, deemed "cross-omic topics", which we hypothesize are representative of generalizable microbial processes observable regardless of profiling method. Interpreting topics, we find each represents a particular diet, and we heuristically label each cross-omic topic as: healthy/general function, age-associated function, transcriptional regulation, and opportunistic pathogenesis.

show abstract

Longitudinal study of stool-associated microbial taxa in sibling pairs with and without autism spectrum disorder

Cited by 5 publications

References 64 publications

GMEmbeddings: An R Package to Apply Embedding Techniques to Microbiome Data

GMEmbeddings: An R Package to Apply Embedding Techniques to Microbiome Data

Topic modeling for multi-omic integration in the human gut microbiome and implications for Autism

Topic modeling for multi-omic integration in the human gut microbiome and implications for Autism

Contact Info

Product

Resources

About