Meta-analysis of 16S rRNA microbial data identified alterations of the gut microbiota in COVID-19 patients during the acute and recovery phases

Abstract

Background: Dozens of studies have demonstrated gut dysbiosis in COVID-19 patients during the acute and recovery phases. However, a consensus on the specific COVID-19 associated bacteria is missing. In this study, we performed a meta-analysis to explore whether robust and reproducible alterations in the gut microbiota of COVID-19 patients exist across different populations.

Methods: A systematic review was conducted for studies published prior to May 2022 in electronic databases. After review, we included 16 studies that comparing the gut microbiota in COVID-19 patients to those of controls. The 16S rRNA sequence data of these studies were then re-analyzed using a standardized workflow and synthesized by meta-analysis.

Results: We found that gut bacterial diversity of COVID-19 patients in both the acute and recovery phases was consistently lower than non-COVID-19 individuals. Microbial differential abundance analysis showed depletion of anti-inflammatory butyrate-producing bacteria and enrichment of taxa with pro-inflammatory properties in COVID-19 patients during the acute phase compared to non-COVID-19 individuals. Analysis of microbial communities showed that the gut microbiota of COVID-19 recovered patients were still in unhealthy ecostates.

Conclusions: Our results provided a comprehensive synthesis to better understand gut microbial perturbations associated with COVID-19 and identified underlying biomarkers for microbiome-based diagnostics and therapeutics.

Keywords: 16S rRNA; Acute phase; COVID-19; Gut microbiota; Recovery phase.

Fig. 1

Forest plot showing differences in alpha diversity between COV and non-COV by (a) Shannon’s diversity index, and (b) observed species. COV, samples derived from COVID-19 patients; non-COV, samples derived from non-COVID-19 individuals

Fig. 2

Differences in alpha diversity between RP/post-RP and non-COV. (a) Forest plot of the differences in Shannon’s diversity index between RP/post-RP and non-COV. (b) Forest plot of the differences in observed species between RP/post-RP and non-COV. (c) Boxplots showing standardized Shannon’s diversity index by SARS-CoV-2 infection status (red = COV, purple = RP, blue = post-RP, and green = non-COV). COV, samples derived from COVID-19 patients; RP, samples derived from COVID-19 recovered patients who with clearance of SARS-CoV-2 RNA (negative conversion of viral RNA) within one month; those with negative conversion of viral RNA more than three months were especially grouped as post-RP; non-COV, samples derived from non-COVID-19 individuals

Fig. 3

Differential gut microbial composition between COV and non-COV (a) at genus level, and (b) at species level. Heatmap showed log (OR) of relative abundances of bacterial taxa between COV and non-COV across each study. The bacterial taxa unavailable in a particular study were in white in heatmap. Forest plot indicated pooled log (OR) estimate and 95% CI of relative abundances of bacterial taxa between COV and non-COV across all studies included. Log (OR) estimates were from GAMLSS-BEZI and Random Effects Meta-analysis. Only bacterial taxa with pooled P of pooled log (OR) estimates below 0.05 were displayed. Pooled log (OR) estimates with FDR-adjusted pooled P < 0.1 were showed as red triangles. Log (OR) > 0 denoted an increase and log (OR) < 0 denoted a decrease of taxa relative abundance in COV compared with non-COV. COV, samples derived from COVID-19 patients; non-COV, samples derived from non-COVID-19 individuals

Fig. 4

Differential gut microbial composition between RP/post-RP and non-COV (a) at genus level, and (b) at species level. Heatmap showed log (OR) of relative abundances of bacterial taxa between RP/post-RP and non-COV across each study. The bacterial taxa unavailable in a particular study were in white in heatmap. Forest plot indicated pooled log (OR) estimate and 95% CI of relative abundances of bacterial taxa between RP/post-RP and non-COV across all studies included. Log (OR) estimates were from GAMLSS-BEZI and Random Effects Meta-analysis. Only bacterial taxa with pooled P of pooled log (OR) estimates below 0.05 were displayed. Pooled log (OR) estimates with FDR-adjusted pooled P < 0.1 were showed as red triangles. Log (OR) > 0 denoted an increase and log (OR) < 0 denoted a decrease of taxa relative abundance in RP/post-RP compared with non-COV. RP, samples derived from COVID-19 recovered patients who with clearance of SARS-CoV-2 RNA (negative conversion of viral RNA) within one month; those with negative conversion of viral RNA more than three months were especially grouped as post-RP; non-COV, samples derived from non-COVID-19 individuals