Dataset Information

Mixture models for analysis of the taxonomic composition of metagenomes.

ABSTRACT: MOTIVATION: Inferring the taxonomic profile of a microbial community from a large collection of anonymous DNA sequencing reads is a challenging task in metagenomics. Because existing methods for taxonomic profiling of metagenomes are all based on the assignment of fragmentary sequences to phylogenetic categories, the accuracy of results largely depends on fragment length. This dependence complicates comparative analysis of data originating from different sequencing platforms or resulting from different preprocessing pipelines. RESULTS: We here introduce a new method for taxonomic profiling based on mixture modeling of the overall oligonucleotide distribution of a sample. Our results indicate that the mixture-based profiles compare well with taxonomic profiles obtained with other methods. However, in contrast to the existing methods, our approach shows a nearly constant profiling accuracy across all kinds of read lengths and it operates at an unrivaled speed. AVAILABILITY: A platform-independent implementation of the mixture modeling approach is available in terms of a MATLAB/Octave toolbox at http://gobics.de/peter/taxy. In addition, a prototypical implementation within an easy-to-use interactive tool for Windows can be downloaded.

SUBMITTER: Meinicke P

PROVIDER: S-EPMC3106201 | biostudies-other | 2011 Jun

REPOSITORIES: biostudies-other

ACCESS DATA

Publications

Mixture models for analysis of the taxonomic composition of metagenomes.

Meinicke Peter P Asshauer Kathrin Petra KP Lingner Thomas T

Bioinformatics (Oxford, England) 20110505 12

<h4>Motivation</h4>Inferring the taxonomic profile of a microbial community from a large collection of anonymous DNA sequencing reads is a challenging task in metagenomics. Because existing methods for taxonomic profiling of metagenomes are all based on the assignment of fragmentary sequences to phylogenetic categories, the accuracy of results largely depends on fragment length. This dependence complicates comparative analysis of data originating from different sequencing platforms or resulting ...[more]

PMID: 21546400

Similar Datasets

Project description:Microbial communities play key roles in ocean ecosystems through regulation of biogeochemical processes such as carbon and nutrient cycling, food web dynamics, and gut microbiomes of invertebrates, fish, reptiles, and mammals. Assessments of marine microbial diversity are therefore critical to understanding spatiotemporal variations in microbial community structure and function in ocean ecosystems. With recent advances in DNA shotgun sequencing for metagenome samples and computational analysis, it is now possible to access the taxonomic and genomic content of ocean microbial communities to study their structural patterns, diversity, and functional potential. However, existing taxonomic classification tools depend upon manually curated phylogenetic trees, which can create inaccuracies in metagenomes from less well-characterized communities, such as from ocean water. Herein, we explore the utility of deep learning tools-DeepMicrobes and a novel Residual Network architecture-that leverage natural language processing and convolutional neural network architectures to map input sequence data (k-mers) to output labels (taxonomic groups) without reliance on a curated taxonomic tree. We trained both models using metagenomic reads simulated from marine microbial genomes in the MarRef database. The performance of both models (accuracy, precision, and percent microbe predicted) was compared with the standard taxonomic classification tool Kraken2 using 10 complex metagenomic data sets simulated from MarRef. Our results demonstrate that time, compute power, and microbial genomic diversity still pose challenges for machine learning (ML). Moreover, our results suggest that high genome coverage and rectification of class imbalance are prerequisites for a well-trained model, and therefore should be a major consideration in future ML work. IMPORTANCE Taxonomic profiling of microbial communities is essential to model microbial interactions and inform habitat conservation. This work develops approaches in constructing training/testing data sets from publicly available marine metagenomes and evaluates the performance of machine learning (ML) approaches in read-based taxonomic classification of marine metagenomes. Predictions from two models are used to test accuracy in metagenomic classification and to guide improvements in ML approaches. Our study provides insights on the methods, results, and challenges of deep learning on marine microbial metagenomic data sets. Future machine learning approaches can be improved by rectifying genome coverage and class imbalance in the training data sets, developing alternative models, and increasing the accessibility of computational resources for model training and refinement.

Project description:BackgroundEstimation of the frequency of latent tuberculosis infection (LTBI) is difficult in areas with low tuberculosis infection rates and high exposure to non-tuberculous mycobacteria (NTM), including BCG vaccination. The objective was to assess LTBI and M avium infection and to estimate their probability based on skin tests responses in an infant population from a region with the aforementioned characteristics.MethodsA population-based tuberculin skin test (TST) and sensitin (M avium) survey was conducted on seven years old infants in Biscay, a province from The Basque Country (Spain). 2268 schoolchildren received sensitin and 5277 TST. Participation rate was 89%. Commonly used estimation methods were compared with a method based on the fit of mixture models using the Expectation Maximization algorithm. Functions estimating the probabilities of LTBI and M avium infection given the observed skin tests responses were developed for vaccinated and unvaccinated children.ResultsLTBI prevalences varied widely according to the estimation method. The mixture model provided prevalences higher than expected although intermediates between those obtained by currently recommended approaches. Exposure to previous BCG vaccine produces an upward shift of an average of about 3 mm on the induration size to attain the same probability of infection.ConclusionOur results confirm the commonplace exposure to NTM which effect should be taken into account when performing and assessing tuberculin surveys. The use of mixture analysis under the empirical Bayes framework allows to better estimate the probability of LTBI in settings with presence of other NTM and high BCG-vaccination coverage. An estimation of the average effect of BCG vaccination on TST induration is also provided. These models maximise information coming from classical tuberculin surveys and could be used together with the newly developed blood tests to improve survey's specificity and cost-effectiveness.

Dataset Information

Mixture models for analysis of the taxonomic composition of metagenomes.

Publications

Mixture models for analysis of the taxonomic composition of metagenomes.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets