Correcting for Microbial Blooms in Fecal Samples during Room-Temperature Shipping

Abstract

The use of sterile swabs is a convenient and common way to collect microbiome samples, and many studies have shown that the effects of room-temperature storage are smaller than physiologically relevant differences between subjects. However, several bacterial taxa, notably members of the class Gammaproteobacteria, grow at room temperature, sometimes confusing microbiome results, particularly when stability is assumed. Although comparative benchmarking has shown that several preservation methods, including the use of 95% ethanol, fecal occult blood test (FOBT) and FTA cards, and Omnigene-GUT kits, reduce changes in taxon abundance during room-temperature storage, these techniques all have drawbacks and cannot be applied retrospectively to samples that have already been collected. Here we performed a meta-analysis using several different microbiome sample storage condition studies, showing consistent trends in which specific bacteria grew (i.e., "bloomed") at room temperature, and introduce a procedure for removing the sequences that most distort analyses. In contrast to similarity-based clustering using operational taxonomic units (OTUs), we use a new technique called "Deblur" to identify the exact sequences corresponding to blooming taxa, greatly reducing false positives and also dramatically decreasing runtime. We show that applying this technique to samples collected for the American Gut Project (AGP), for which participants simply mail samples back without the use of ice packs or other preservatives, yields results consistent with published microbiome studies performed with frozen or otherwise preserved samples. IMPORTANCE In many microbiome studies, the necessity to store samples at room temperature (i.e., remote fieldwork) and the ability to ship samples without hazardous materials that require special handling training, such as ethanol (i.e., citizen science efforts), is paramount. However, although room-temperature storage for a few days has been shown not to obscure physiologically relevant microbiome differences between comparison groups, there are still changes in specific bacterial taxa, notably, in members of the class Gammaproteobacteria, that can make microbiome profiles difficult to interpret. Here we identify the most problematic taxa and show that removing sequences from just a few fast-growing taxa is sufficient to correct microbiome profiles.

Keywords: 16S rRNA; DNA sequencing; bioinformatics.

FIG 1

A small number of bacteria showed high levels of growth in the storage studies. (A to D) The log₂ fold change of an OTU relative to time zero within the Mayo Clinic fecal stability study and the preservation study by Song et al. (1). A minimum read threshold of 10 reads per sample was used, and OTUs present below this threshold in both samples are not shown. (A and B) Mayo Clinic fecal stability study (2) at day 1 (A) and day 4 (B). (C and D) Results of fecal preservation study by Song et al. (1) at day 7 (C) and day 14 (D). The numbers (and percentages of total bacteria) showing at least 4-fold change in the room-temperature storage compared to day 0 were 11 (1.6%), 21 (3.1%), 49 (7.1%), and 144 (19%) for days 1, 2, 7, and 14, respectively. (E) A topology plot of the maximal (max.) fold change in the two storage studies whose results are shown in panels A to D (x axis) and minimal (min.) fold change in the AGP fecal samples compared to data reported in references and and PGP (unpublished), studies in which samples were immediately frozen (y axis). Red circles denote 14 bacterial samples selected as potentially blooming (>2-fold change in both axes or >50-fold change in the storage studies). Six bacterial samples showing >2-fold change in AGP compared to results of all studies using fresh-frozen samples that were not present in the storage studies are also added to the potential blooming list (Table S1).

FIG 2

Effect of bloom filtering on American Gut data. (A and B) PCoA of Bray-Curtis distances from a random subset of 200 American Gut Project samples (AGP [unpublished]; colored pink) compared to 3 studies containing fresh-frozen fecal samples: Personal Genome Project (PGP [unpublished]; colored green); whole-grain feces (EWF [6]; colored orange); and UK Twins ([7]; colored purple), respectively. The PCoA data shown represent results obtained before (A) and after (B) applying the filter for blooms to all samples. The size of a sphere is scaled by the amount of candidate bloom bacteria in a sample prior to filtering. (C and D) Mean taxonomy distribution for the same studies before (C) and after (D) filtering for blooms. (E and F) The well-known effect of age on alpha diversity and how the effect is observed only after the removal of bloom reads. The Kruskal-Wallis test statistic (E) and corresponding –log(P value) (F) are shown for different numbers of bacteria used for the filtering before applying the test. A value of 0 on the x axis indicates no filtering. The x axis is ordered by decreasing severity score of the bloom where bloom 1 represents greater severity than bloom 2, and each point on the x axis includes the prior blooms (e.g., position 5 includes bloom sOTUs 1 through 5).