Impact of training sets on classification of high-throughput bacterial 16s rRNA gene surveys

By J. Werner, Omry Koren, Philip Hugenholtz, Todd Z. DeSantis, William Walters, J. Gregory Caporaso, Largus T. Angenent, Rob Knight, Ruth E. Ley. The ISME Journal, 2011

578 citations recorded by the source corpus.

Taxonomic classification of the thousands–millions of 16S rRNA gene sequences generated in microbiome studies is often achieved using a naïve Bayesian classifier (for example, the Ribosomal Database Project II (RDP) classifier), due to favorable trade-offs among automation, speed and accuracy. The resulting classification depends on the reference sequences and taxonomic hierarchy used to train the model; although the influence of primer sets and classification algorithms have been explored in detail, the influence of training set has not been characterized. We compared classification results obtained using three different publicly available databases as training sets, applied to five different bacterial 16S rRNA gene pyrosequencing data sets generated (from human body, mouse gut, python gut, soil and anaerobic digester samples). We observed numerous advantages to using the largest, most diverse training set available, that we constructed from the Greengenes (GG) bacterial/archaeal 16S rRNA gene sequence database and the latest GG taxonomy. Phylogenetic clusters of previously unclassified experimental sequences were identified with notable improvements (for example, 50% reduction in reads unclassified at the phylum level in mouse gut, soil and anaerobic digester samples), especially for phylotypes belonging to specific phyla (Tenericutes, Chloroflexi, Synergistetes and Candidate phyla TM6, TM7). Trimming the reference sequences to the primer region resulted in systematic improvements in classification depth, and greatest gains at higher confidence thresholds. Phylotypes unclassified at the genus level represented a greater proportion of the total community variation than classified operational taxonomic units in mouse gut and anaerobic digester samples, underscoring the need for greater diversity in existing reference databases.

Subfields: Ecology, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/d9dc800fe046c31715ff9c7a1b7e8242cb53e669

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Ecology

In Molecular Biology

Citations in the corpus

An improved Greengenes taxonomy with explicit ranks for ecological and evolutionary analyses of bacteria and archaea (2011, methodology): “Further, the updated Greengenes taxonomy performed well in a test of reference taxonomies using a naı̈ve Bayesian classifier (Werner et al., 2011).”
Ribosomal Database Project: data and tools for high throughput rRNA analysis (2013, background): “These features have allowed researchers to retrain the RDP Classifier on a broader range of sequences, including ones from environmental clades (25), on honeybee gut specific 16S rRNA sequences (26) and on fungal LSU sequences (4).”
Vineyard soil bacterial diversity and composition revealed by 16S rRNA genes: Differentiation by geographic features (2015, methodology): “…classified taxonomically using a QIIME-based wrapper of the Ribosomal Database Project (RDP) classifier (Wang et al., 2007) and the Greengenes 16S rRNA gene reference database (13_5 release) (McDonald et al., 2012; Werner et al., 2012), using a 0.80 confidence threshold for taxonomic assignment.”
Taxonomic Classification of Bacterial 16S rRNA Genes Using Short Sequencing Reads: Evaluation of Effective Study Designs (2013, methodology): “[40] observed improved performance of the training set when trimming reference sequences to the region tested, compared to using the full 16S rRNA gene sequence as reference.”
Conducting a Microbiome Study (2014, background): “If there is little or no overlap between sequence reads, both can be used in the downstream analyses, with at best modest performance enhancements over using just one of the two sets (Soergel et al., 2012; Werner et al., 2012b).”
Diversity and heritability of the maize rhizosphere microbiome under field conditions (2013, methodology): “Taxonomy was subsequently assigned to each representative OTUs using the Greengenes database classifier with a minimum support threshold of 80% (5, 8).”
Strengths and Limitations of 16S rRNA Gene Amplicon Sequencing in Revealing Temporal Microbial Community Dynamics (2014, background): “contigs, likely due to the region of the 16S rRNA gene chosen [54,55] and the high conservation of the 16S rRNA gene, which can mask important level of micro-heterogeneity.”
Vineyard soil bacterial diversity and composition revealed by 16S rRNA genes: Differentiation by vineyard management (2016, methodology): “…classified taxonomically using a QIIME-based wrapper of the Ribosomal Database Project (RDP) classifier (Wang et al., 2007) and the Greengenes 16S rRNA gene reference database (13_5 release) (McDonald et al., 2012; Werner et al., 2012), using a 0.80 confidence threshold for taxonomic assignment.”
Applications of Machine Learning in Human Microbiome Studies: A Review on Feature Selection, Biomarker Identification, Disease Prediction and Treatment (2021, methodology): “Firstly, to support the taxonomic representation and differentiation in microbiology, models were developed to support the classification of microbial features (Cai and Sun, 2011; Bonder et al., 2012; Werner et al., 2012; Vervier et al., 2016).”