MEGAN analysis of metagenomic data

Abstract

Metagenomics is the study of the genomic content of a sample of organisms obtained from a common habitat using targeted or random sequencing. Goals include understanding the extent and role of microbial diversity. The taxonomical content of such a sample is usually estimated by comparison against sequence databases of known sequences. Most published studies use the analysis of paired-end reads, complete sequences of environmental fosmid and BAC clones, or environmental assemblies. Emerging sequencing-by-synthesis technologies with very high throughput are paving the way to low-cost random "shotgun" approaches. This paper introduces MEGAN, a new computer program that allows laptop analysis of large metagenomic data sets. In a preprocessing step, the set of DNA sequences is compared against databases of known sequences using BLAST or another comparison tool. MEGAN is then used to compute and explore the taxonomical content of the data set, employing the NCBI taxonomy to summarize and order the results. A simple lowest common ancestor algorithm assigns reads to taxa such that the taxonomical level of the assigned taxon reflects the level of conservation of the sequence. The software allows large data sets to be dissected without the need for assembly or the targeting of specific phylogenetic markers. It provides graphical and statistical output for comparing different data sets. The approach is applied to several data sets, including the Sargasso Sea data set, a recently published metagenomic data set sampled from a mammoth bone, and several complete microbial genomes. Also, simulations that evaluate the performance of the approach for different read lengths are presented.

Figure 1.

For a given sample of organisms, a randomly selected collection of DNA fragments is sequenced. The resulting reads are then compared with one or more reference databases using an appropriate sequence comparison program such as BLAST (Altschul et al. 1990). The resulting data are processed by MEGAN to produce an interactive analysis of the taxonomical content of the sample.

Figure 2.

On the right, we list the three BLASTX matches obtained for a specific read r from the mammoth data set, to sequences representing Campylobacter lari, Helicobacter hepaticus, and Wolinella, respectively. The LCA-assignment algorithm assigns r to the taxon Campylobacterales, shown on the left, as it is the lowest-common taxonomical ancestor of the three matched species.

Figure 3.

Phylogenetic diversity of the Sargasso Sea sequences computed by MEGAN. The microheterogeneity of Sample 1 was investigated by comparing it to pooled Samples 2, 3, and 4 (Venter et al. 2004). (A) Analysis of 10,000 reads randomly chosen from Sample 1. (B) Analysis of 10,000 reads randomly chosen from Sample 2. (C,D) A more detailed view of Sample 1 and Samples 2–4, respectively, illustrating a significant difference of relative frequencies of Shewanella and Burkholderia species in the two data sets. In all such figures, each circle represents a taxon in the NCBI taxonomy and is labeled by its name and the number of reads that are assigned either directly to the taxon, or indirectly via one of its subtaxa. The size of the circle is scaled logarithmically to represent the number of reads assigned directly to the taxon.

Figure 4.

The distribution of reads from Sample 1, pooled Samples 2–4, and the weighted average of these two data sets, over 16 major phylogenetic groups, as computed by MEGAN. For the sake of comparison, the diagram also shows the relative contribution of organisms to these groups, as estimated from Venter et al. (2004) by averaging over the values for all six genes that are reported there.

Figure 5.

High-level summary of a MEGAN analysis of the mammoth data set, based on a BLASTX comparison of the 302,692 reads against the NCBI-NR database.

Figure 6.

A low level view of the MEGAN analysis of the mammoth data set.

Figure 7.

MEGAN analysis of 2000 reads collected from E. coli K12 using Roche GS20 sequencing, based on a BLASTX comparison with the NCBI-NR database.

Figure 8.

MEGAN analysis of 2000 reads collected from B. bacteriovorus HD100 using Roche GS20 sequencing. (A) Analysis based on a BLASTX comparison with NCBI-NR. (B) The same analysis, but with all hits matching database sequences representing the B. bacteriovorus HD100 genome removed, mimicking the situation in which the reads originate from a genome that is not represented in NCBI-NR.

Figure 9.

(A) MEGAN provides a Find tool to search for specific taxa of interest. (B) The result of a search is highlighted in a detailed summary of the analysis. (C) MEGAN provides an Inspector tool to view the individual sequence comparisons upon which the assignment of a particular read to a particular taxon is based.