DADA2: High-resolution sample inference from Illumina amplicon data

Abstract

We present the open-source software package DADA2 for modeling and correcting Illumina-sequenced amplicon errors (https://github.com/benjjneb/dada2). DADA2 infers sample sequences exactly and resolves differences of as little as 1 nucleotide. In several mock communities, DADA2 identified more real variants and output fewer spurious sequences than other methods. We applied DADA2 to vaginal samples from a cohort of pregnant women, revealing a diversity of previously undetected Lactobacillus crispatus variants.

Figure 1. Sequence variants inferred by DADA2 compared to the OTUs constructed by UPARSE

The merged sequences output by DADA2 are plotted for three Illumina amplicon datasets: (a) Balanced, (b) HMP, and (c) Extreme. Frequency is plotted on the y-axis; Hamming distance to the closest more-abundant sequence on the x-axis. Shapes represent accuracy (Methods). When variants are well separated from other members of the community the sequence variants inferred by DADA2 largely coincide with the OTUs output by UPARSE (black). However, DADA2 resolves additional variation (blue), especially within the UPARSE's OTU radius (dashed line), while outputting fewer spurious sequences (One Off and Other).

Figure 2. Lactobacillus crispatus sequence variants in the human vaginal community during pregnancy

DADA2 identified six Lactobacillus crispatus 16S rRNA sequence variants present in multiple samples and a significant fraction of all reads (L1: 19.7%, L2: 11.1%, L3: 6.5%, L4: 3.1%, L5: 1.3%, L6: 0.4%). (a) The frequency of L1–L6 in each sample. Black bars at the bottom link samples from the same subject. The frequency of (b) L1 vs. L2, and (c) L1 vs. L3, by sample. The dashed line indicates a total frequency of 1.