ABSTRACT
BACKGROUND: Shotgun metagenome data sets of microbial communities are highly diverse, not only due to the natural variation of the underlying biological systems, but also due to differences in laboratory protocols, replicate numbers, and sequencing technologies. Accordingly, to effectively assess the performance of metagenomic analysis software, a wide range of benchmark data sets are required. RESULTS: We describe the CAMISIM microbial community and metagenome simulator. The software can model different microbial abundance profiles, multi-sample time series, and differential abundance studies, includes real and simulated strain-level diversity, and generates second- and third-generation sequencing data from taxonomic profiles or de novo. Gold standards are created for sequence assembly, genome binning, taxonomic binning, and taxonomic profiling. CAMSIM generated the benchmark data sets of the first CAMI challenge. For two simulated multi-sample data sets of the human and mouse gut microbiomes, we observed high functional congruence to the real data. As further applications, we investigated the effect of varying evolutionary genome divergence, sequencing depth, and read error profiles on two popular metagenome assemblers, MEGAHIT, and metaSPAdes, on several thousand small data sets generated with CAMISIM. CONCLUSIONS: CAMISIM can simulate a wide variety of microbial communities and metagenome data sets together with standards of truth for method evaluation. All data sets and the software are freely available at https://github.com/CAMI-challenge/CAMISIM.
Subject(s)
Computer Simulation , Gastrointestinal Microbiome/genetics , Metagenome/genetics , Metagenomics/methods , Algorithms , Animals , Humans , Mice , Models, Biological , Sequence Analysis, DNA/methods , SoftwareABSTRACT
Methods for assembly, taxonomic profiling and binning are key to interpreting metagenome data, but a lack of consensus about benchmarking complicates performance assessment. The Critical Assessment of Metagenome Interpretation (CAMI) challenge has engaged the global developer community to benchmark their programs on highly complex and realistic data sets, generated from â¼700 newly sequenced microorganisms and â¼600 novel viruses and plasmids and representing common experimental setups. Assembly and genome binning programs performed well for species represented by individual genomes but were substantially affected by the presence of related strains. Taxonomic profiling and binning programs were proficient at high taxonomic ranks, with a notable performance decrease below family level. Parameter settings markedly affected performance, underscoring their importance for program reproducibility. The CAMI results highlight current challenges but also provide a roadmap for software selection to answer specific research questions.
