Filters








9 Hits in 4.9 sec

q2-sample-classifier: machine-learning tools for microbiome classification and regression [article]

Nicholas Bokulich, Matthew Dillon, Evan Bolyen, Benjamin D Kaehler, Gavin A Huttley, J Gregory Caporaso
2018 bioRxiv   pre-print
Random forest, extra trees, and gradient boosting models demonstrate the highest performance for both supervised classification and regression of microbiome data.  ...  We additionally present q2-sample-classifier, a plugin for the QIIME 2 microbiome bioinformatics framework, that facilitates application of the scikit-learn classifiers to microbiome data.  ...  This project was funded in part by NSF Award 1565100 to JGC, and by the Partnership for Native American Cancer Prevention (NIH/NCI U54CA143924 and U54CA143925) to JGC.  ... 
doi:10.1101/306167 fatcat:4gabzunohfd53bro2xk7t3b6ri

q2-sample-classifier: machine-learning tools for microbiome classification and regression

Nicholas Bokulich, Matthew Dillon, Evan Bolyen, Benjamin Kaehler, Gavin Huttley, J Caporaso
2018 Journal of Open Source Software  
q2-sample-classifier is a plugin for the QIIME 2 microbiome bioinformatics platform that facilitates access, reproducibility, and interpretation of supervised learning (SL) methods for a broad audience  ...  Acknowledgments The authors thank Jai Ram Rideout for his input and assistance integrating q2-sampleclassifier with QIIME 2.  ...  This work was supported by the National Science Foundation [1565100 to JGC], and by the National Institutes of Health / National Cancer Institute Partnership for Native American Cancer Prevention [U54CA143924  ... 
doi:10.21105/joss.00934 pmid:31552137 pmcid:PMC6759219 fatcat:bdc6fg5hobfhzjtuvhuvrtwk3q

q2-sample-classifier: machine-learning tools for microbiome classification and regression

Nicholas A. Bokulich, Matthew R. Dillon, Evan Bolyen, Benjamin D. Kaehler, Gavin A. Huttley, J. Gregory Caporaso
2018
q2-sample-classifier is a plugin for the QIIME 2 microbiome bioinformatics platform that facilitates access, reproducibility, and interpretation of supervised learning (SL) methods for a broad audience  ...  Bokulich et al., (2018). q2-sample-classifier: machine-learning tools for microbiome classification and regression. Journal of Open Source Software, 3(30), 934. https://doi.org/10.21105/joss.00934  ...  Acknowledgments The authors thank Jai Ram Rideout for his input and assistance integrating q2-sampleclassifier with QIIME 2.  ... 
doi:10.3929/ethz-b-000431152 fatcat:owxqgaekxfdb7f4mxsz7l2atua

Multi-omics data integration reveals metabolome as the top predictor of the cervicovaginal microenvironment

Nicholas A. Bokulich, Paweł Łaniewski, Anja Adamov, Dana M. Chase, J. Gregory Caporaso, Melissa M. Herbst-Kralovetz, Nicola Segata
2022 PLoS Computational Biology  
Multi-omics integration methods, including neural networks (mmvec) and Random Forest supervised learning, were utilized to explore potential interactions and develop predictive models.  ...  Different feature classes were important for prediction of different phenotypes.  ...  Dominique Barnes and Alison Goulder for the assistance with clinical sample and data collection.  ... 
doi:10.1371/journal.pcbi.1009876 pmid:35196323 pmcid:PMC8901057 fatcat:jlnyy2kdrvbhfo6c2xyypiztem

Predicting microbiomes through a deep latent space

Beatriz García-Jiménez, Jorge Muñoz, Sara Cabello, Joaquín Medina, Mark D Wilkinson, Jonathan Wren
2020 Bioinformatics  
Finally, via transfer learning, we predict microbial composition in a distinct scenario with only a hundred sequences, and distinct environmental features.  ...  Results Integrating Deep Learning techniques with microbiome data, we propose an artificial neural network architecture based on heterogeneous autoencoders to condense the long vector of microbial abundance  ...  Funding Research was supported by the"Severo Ochoa Program for Centres of Excellence in R&D"from the Agencia Estatal de Investigación of Spain (grant SEV-2016(grant SEV- -0672 (2017(grant SEV- -2021) to  ... 
doi:10.1093/bioinformatics/btaa971 pmid:33289510 pmcid:PMC8208755 fatcat:opbrnrnwmbhpbaknyevdyctkd4

Predicting microbiomes through a deep latent space [article]

Beatriz García-Jiménez, Jorge Muñoz, Sara Cabello, Joaquín Medina, Mark D Wilkinson
2020 bioRxiv   pre-print
Finally, via transfer learning, we predict microbial composition in a distinct scenario with only a hundred sequences, and distinct environmental features.  ...  Results: Integrating Deep Learning techniques with microbiome data, we propose an artificial neural network architecture based on heterogeneous autoencoders to condense the long vector of microbial abundance  ...  Acknowledgements Thanks to the authors of Walters et al. (2018) for kindly sharing their datasets with us.  ... 
doi:10.1101/2020.04.27.063974 fatcat:5tcknhcydffmjntsqt6wgsumke

Multi-omics approach reveals new insights into the gut microbiome of Galleria mellonella (Lepidoptera:Pyralidae) exposed to polyethylene diet [article]

Samuel Latour, Gregoire Noel, Laurent Serteyn, Abdoul Razack Sare, Sebastien Massart, Delvigne Frank, Frederic Francis
2021 bioRxiv   pre-print
Gut microbiome samples were processed by high throughput 16S rRNA sequencing, and Enterococcaceae and Oxalobacteraceae were found to be the major bacterial families.  ...  At low polyethylene dose, we detect no bacterial community change and no amplicon sequence variant associated with the polyethylene diet suggesting microbiome resilience.  ...  Bokulich NA, Dillon M, Evan B, et al (2018) q2-sample-classifier: machine-learning tools for 386 microbiome classification and regression. 5485: 387 25.  ... 
doi:10.1101/2021.06.04.446152 fatcat:wuznuf5jgrgmhkq6zksfiitaum

QIIME 2 Enables Comprehensive End‐to‐End Analysis of Diverse Microbiome Data and Comparative Studies with Publicly Available Data

Mehrbod Estaki, Lingjing Jiang, Nicholas A. Bokulich, Daniel McDonald, Antonio González, Tomasz Kosciolek, Cameron Martino, Qiyun Zhu, Amanda Birmingham, Yoshiki Vázquez‐Baeza, Matthew R. Dillon, Evan Bolyen (+2 others)
2020 Current Protocols in Bioinformatics  
We also show how plug-ins developed by the community to add analysis capabilities can be installed and used with QIIME 2, enhancing various aspects of microbiome analyses-e.g., improving taxonomic classification  ...  For more information about QIIME 2, see https://qiime2.org.  ...  The QIIME 2 plugin q2-sample-classifier ; https:// library.qiime2.org/ plugins/ q2-sample-classifier/ ) contains methods for performing supervised classification/regression and feature selection using  ... 
doi:10.1002/cpbi.100 pmid:32343490 fatcat:i2ssiyaxvbartoaarja5p7f5dq

Non-Celiac Gluten/Wheat Sensitivity: Clinical Characteristics and Microbiota and Mycobiota Composition by Response to the Gluten Challenge Test

Valentina Ponzo, Ilario Ferrocino, Ilaria Goitre, Marianna Pellegrini, Mauro Bruno, Marco Astegiano, Gianni Cadario, Eleonora Castellana, Fabio Bioletto, Maria Rita Corvaglia, Patrizia Malfa, Luca Cocolin (+2 others)
2021 Nutrients  
For Bacteroides (p = 0.05) and Parabacteroides (p = 0.007), the frequency of amplicon sequence variants was lower, and that for Blautia (p = 0.009) and Streptococcus (p = 0.004) was higher in NCGS individuals  ...  at multiple regression analyses.  ...  Acknowledgments: We are grateful to Lucia Fransos, Martina Oddenino, Silvia Marcolin, Lucia Ferraris, and Sara Pellegrino for their precious contribution to this study.  ... 
doi:10.3390/nu13041260 pmid:33921293 fatcat:wx7cbfeupvgvbdd3737y5kkqdy