Development of a human skin commensal microbe for bacteriotherapy of atopic dermatitis and use in a phase 1 randomized clinical trial

Abstract

Staphylococcus aureus colonizes patients with atopic dermatitis (AD) and exacerbates disease by promoting inflammation. The present study investigated the safety and mechanisms of action of Staphylococcus hominis A9 (ShA9), a bacterium isolated from healthy human skin, as a topical therapy for AD. ShA9 killed S. aureus on the skin of mice and inhibited expression of a toxin from S. aureus (psmα) that promotes inflammation. A first-in-human, phase 1, double-blinded, randomized 1-week trial of topical ShA9 or vehicle on the forearm skin of 54 adults with S. aureus-positive AD (NCT03151148) met its primary endpoint of safety, and participants receiving ShA9 had fewer adverse events associated with AD. Eczema severity was not significantly different when evaluated in all participants treated with ShA9 but a significant decrease in S. aureus and increased ShA9 DNA were seen and met secondary endpoints. Some S. aureus strains on participants were not directly killed by ShA9, but expression of mRNA for psmα was inhibited in all strains. Improvement in local eczema severity was suggested by post-hoc analysis of participants with S. aureus directly killed by ShA9. These observations demonstrate the safety and potential benefits of bacteriotherapy for AD.

Extended Data Fig. 1 |

Low levels of bacteria are detected after topical application of bacteria on mice with inflamed skin. Colony forming units (CFU) of S. aureus and CoNS were measured from the spleen of OVA-sensitized FLG^ft/ft Balb/c mice that were colonized by S. aureus for 4 days and treated by ShA9 for 3 days. Spleens (50–100 mg) were surgically excised and homogenized in 1 mL PBS. Live S. aureus and CoNS CFU were counted on mannitol salt agar with egg yolk and CFU counts adjusted based on wet weight of the excised spleens. Data represent mean ± SEM of biological replicates in individual mouse (n = 8). No statistical difference was detected by two-tailed unpaired parametric t-test.

Extended Data Fig. 2 |

Gating strategy for flow cytometry to identify CD4 +, IL4 + or CD4 +, IL17A + cells associated with experiments in Fig. 2g–i.

Extended Data Fig. 3 |

a-b, Flow diagram of participants (a) and illustration of measurements conducted for the clinical trial (b). ^§ One individual withdrew due to inability to keep the time commitments of the study and was excluded from data analysis according to our study protocol. ^† This individual reported <75% of treatment being applied and was excluded from data analysis according to our study protocol. ^‡ This individual was lost to follow up due to personal reasons but completed the study. He/she was included to data analysis according to our study protocol.

Extended Data Fig. 4 |. Change in abundance of S. aureus mprF mRNA on the lesional skin of subjects treated by ShA9.

Each dot represent data from individual subject. Data are shown as mean±95% confidence interval (n = 32 independent subjects). Data at each time point was compared by two-tailed paired parametric t-test and no change was detected.

Extended Data Fig. 5 |

a, Minimal inhibitory concentration (MIC) of ShA9 supernatant to inhibit growth of S. aureus isolated from each subject is correlated with change in local EASI at the indicated time points after treatment with ShA9. S. aureus resistant to ShA9 was defined as its MIC > 100% of conditioned media. Statistical analysis for correlation was carried out by two-tailed t distribution (n = 32 independent subjects). Dotted line represents detection limit of the assay. b, Correlation between relative change in live S. aureus abundance and change in local EASI scores from baseline at indicated time points for subjects treated with ShA9 (top row, blue) or vehicle (bottom row, red). Statistical analysis for correlation was carried out by two-tailed t distribution (ShA9: n = 35; Vehicle: n = 17 independent subjects).

Extended Data Fig. 6 |

a-c, Abundance of DNA for ShA9 lantibiotic-a (a), S. hominis-specific gap gene (b) and universal 16 S rRNA (c) on the lesional and nonlesional skin of patients treated by ShA9 or vehicle at indicated time points. Data represent Mean ± 95% confidence interval (ShA9: n = 35; Vehicle: n = 17 independent subjects) (a-c). A linear mixed-model approach was used to take into account the repeated aspect of the trial (a-c).

Extended Data Fig. 7 |

a, Abundance of ShA9 lantibiotic-α mRNA recovered by skin swabs from lesional skin at indicated time points for subjects treated with ShA9 or vehicle. Data represent Mean ± 95% confidence interval (ShA9: n = 35; Vehicle: n = 17 independent subjects). A linear mixed-model approach was used to take into account the repeated aspect of the trial (a). b-c, Correlation between abundance of ShA9 lantibiotic-α mRNA (b) or ShA9 AIP mRNA (c) and S. hominis DNA on the lesional skin of subjects with ShA9 at indicated time points. Statistical analysis for correlation was carried out by t distribution. Dotted line represents detection limit of the assay. Statistical analysis for correlation was carried out by two-tailed t distribution (n = 35 independent subjects) (b,c).

Extended Data Fig. 8 |. AIP activity from ShA9 against S. aureus psmα expression is independent from antimicrobial activity of ShA9.

MIC of ShA9 conditioned media (CM) against each patient’s S. aureus was correlated with relative change in S. aureus psmα expression from base line (BL) at indicated time point. CM was precipitated from ShA9 culture supernatant by 70% ammonium sulfate and % calculated from the original volume of medium. Statistical analysis for correlation was carried out by t distribution. Dotted line represents detection limit of the assay. Statistical analysis for correlation was carried out by two-tailed t distribution (n = 35 independent subjects).

Extended Data Fig. 9 |

Change in S. aureus psmα expression after ShA9 treatment does not correlate with a decrease in S. aureus survival on AD lesional skin. Statistical analysis for correlation was carried out by two-tailed t distribution (n = 35 independent subjects).

Extended Data Fig. 10 |. AIP activity of ShA9 on S. aureus isolates that resistant to ShA9 lantibiotics.

All 11 isolates of S. aureus identified by analyses in Fig. 3d,f,g were cultured in TSB with ShA9 conditioned media (25%) or TSB (Vehicle) at 30 °C for 18 hrs. Abundance in mRNA for Psmα was measured as described in Fig. 2j. Data represent mean of 2 technical replicates in independent bacterial culture.

Fig. 1 |. Preclinical validation of the activity of ShA9 on mice.

a–f, Analysis of mouse skin after twice-daily topical applications of ShA9 or vehicle for 3 d on OVA-sensitized FLG^ft/ft Balb/c mice that were colonized by S. aureus for 4 d. Live S. aureus recovered from lesional back skin by swab (a), skin inflammation (b), and relative abundance of mRNA of indicated cytokines (c), Camp (d), mDB14 (e) and mBD4 (f) in skin. Data represent mean ± s.e.m. of biological replicates from independent mice (mock/vehicle: n = 6; S. aureus/vehicle: n = 7; S. aureus/ShA9: n = 7; mock/ShA9: n = 6) (a–f). Mouse images represent similar results from indicated biological replicates (b). g, Time course change in severity of local skin inflammation during extended topical application of ShA9 or vehicle for 1 week on FLG^ft/ft Balb/c mice treated as in a–f. All data represent mean ± s.e.m. of biological replicates from independent mice (ShA9: n = 9; vehicle: n = 8). h, TEWL of targeted site at day 7. Data represent mean ± s.e.m. of biological replicates from independent mice (ShA9: n = 9; vehicle: n = 7). The P value was calculated using a two-tailed, unpaired, parametric Student’s t-test (a, g and h) or a two-tailed Mann–Whitney U-test (c and d–f).

Fig. 2 |. Anti-inflammatory action of ShA9 is mediated by mechanisms independent of antimicrobial activity against S. aureus.

a, Radial diffusion assay of S. aureus growth with WT ShA9 and lantibiotic knockout mutant of ShA9 (ShA9-Δlanti). b–f, Live S. aureus recovered from lesional back skin by swab (b) and relative abundance of mRNA of Il-4 (c), Il-13 (d), Il-17a (e) and cathelicidin antimicrobial peptide in skin (f) of Flg^ft/ft Balb/c mice treated as in Fig. 1a–c with ShA9 WT, ShA9-Δlanti or vehicle. Data represent the mean ± s.e.m. of biological replicates from independent mice (vehicle: n = 8; ShA9-Δlanti: n = 8; ShA9 WT: n = 9). Expression of each gene was normalized to that of Gapdh (c–f). g, FACS analysis of IL-4+ CD4+ and IL-17A+ CD4+ cells isolated from the skin of mice treated as in Fig. 1a–f after twice-daily topical application of ShA9 WT, ShA9-Δlanti or vehicle for 3 d. Gating strategy for this analysis is shown in Extended Data Fig. 2. h,i, Quantification of numbers of CD4+IL-4+ (h) and CD4+IL-17A+ (i) cells shown in g. Data represent mean ± s.e.m. of biological replicates from independent mice (n = 3). j, Inhibition of psmα mRNA expression by S. aureus (USA300Lac) in culture after exposure to indicated dilutions of conditioned medium (CM) from ShA9 WT or ShA9-Δlanti for 18 h. USA300Lac was resistant to antimicrobial activity from ShA9. Data were normalized against the gyrB gene. Data represent mean ± s.e.m. of technical replicates from individual bacterial cultures (n = 3). The P value was calculated using one-way ANOVA (b–f, h and i). No significant difference was found using the two-tailed Mann–Whitney U-test (P > 0.05) (j).

Fig. 3 |. Efficacy of ShA9 correlates with sensitivity to lantibiotics.

a, Actions of ShA9 include anti-quorum sensing and selective antimicrobial action against S. aureus. b, Study design for topical application of ShA9 on adults with AD colonized by S. aureus. c, Live S. aureus colony-forming units recovered by swab at baseline (BL), 1 h after initial application, during treatment or after the last dose (off-treatment). Data represent mean ± 95% confidence interval (CI) (ShA9: n = 35; vehicle: n = 17 independent subjects). d, Minimal inhibitory concentration (MIC) of ShA9 CM against S. aureus isolated from each participant compared with change in S. aureus colony-forming units from the BL on lesional skin treated with ShA9. CM was precipitated by ammonium sulfate and the percentage calculated from the original volume of medium. The dotted line represents the detection limit of the assay. The change in S. aureus survival at each time point correlated to the MIC of S. aureus isolated from BL swabs, to show how S. aureus that originally colonized participants at BL responds to ShA9 (ShA9: n = 32; vehicle: n = 16 independent subjects). e, Radial diffusion assay for activity of ShA9 WT and the ShA9-Δlanti mutant against S. aureus WT and ΔmprF mutant. The arrow shows the zone of inhibition of S. aureus. f, The expression of mprF in S. aureus that was sensitive or resistant to ShA9. Data represent mean ± 95% CI of data from independent S. aureus strains from distinct subjects (sensitive to ShA9: n = 21; resistant to ShA9: n = 11). g, Abundance of S. aureus mprF mRNA on the surface of lesional skin of participants with S. aureus sensitive or resistant to ShA9. Data represent mean ± 95% CI (sensitive to ShA9: n = 21; resistant to ShA9: n = 11 independent subjects). h, Pearson’s correlation between relative change in live S. aureus abundance and change in local EASI from BL at day 7, for participants treated with ShA9 (blue) or vehicle (red) (ShA9: n = 35, vehicle: n = 17 independent subjects). Participants with S. aureus killed by ShA9 are shown in green and those with high MIC in black. Data at all time points are shown in Extended Data Fig. 5b. i,j, Change in local EASI (i) and SCORAD score (j) in all participants, and in those participants with S. aureus that was sensitive to direct killing by ShA9 compared with participants treated with vehicle. Data represent mean ± 95% CI (all ShA9: n = 35; ShA9 with S. aureus sensitive to ShA9 lantibiotic: n = 21; vehicle: n = 17 independent subjects). A linear mixed-model approach was used to take into account the repeated aspect of the trial (c). Statistical analysis for correlation was carried out by two-tailed, Student’s t-test distribution. The P value was calculated using a two-tailed, unpaired, parametric Student’s t-test (f, and g) or a random-effects linear model (i and j).

Fig. 4 |. Survival of ShA9 on AD skin and correlations to autoinducing peptide expression.

a, Change in live CoNS recovered by skin swab from patient’s skin compared with baseline at indicated time points after application of ShA9 or vehicle. b, Abundance of ShA9 AIP mRNA recovered by skin swabs from lesional skin at indicated time points for participants treated with ShA9 or vehicle. Data represent mean ± 95% CI (ShA9: n = 35; vehicle: n = 17 independent subjects) (a and b). c, Correlation between absolute ShA9 AIP mRNA copy number and change in psmα mRNA on lesional skin of participants treated with ShA9 or vehicle at the indicated time points. d, Correlation between change in the local EASI and absolute abundance of psmα mRNA copy number on lesional skin of participants treated with ShA9 or vehicle at day 7 (ShA9: n = 35; vehicle: n = 17 independent subjects). Data from participants with S. aureus both sensitive to ShA9 (green dots) and resistant (black dots) are shown (c and d). The dotted line represents the detection limit of the assay (c and d). e–i, Representative S. aureus strains from participants with high expression of mprF (mprF^hi) or low expression (mprF^lo) were applied to Flg^ft/ft Balb/c mice treated with OVA. Survival of S. aureus recovered from lesional back skin by swab is measured by colony-forming units (e). Abundance of psmα mRNA recovered from lesional back skin by swab (f), expression of Il-4 mRNA (g) and Camp mRNA (h) extracted from whole skin, and skin inflammation observed in each group (i) are shown. Data represent mean ± s.e.m. with individual results shown for each mouse (mprF^hi, vehicle: n = 9; mprF^hi, ShA9: n = 8; mprF^Lo, vehicle: n = 7; mprF^Lo, ShA9: n = 7). Mouse images represent similar results from indicated biological replicates (i). A linear mixed-model approach was used to take into account the repeated aspect of the trial (a and b). Statistical analysis for correlation was carried out using a two-tailed, Student’s t-test distribution (c and d). The P value was calculated using two-tailed, unpaired, parametric Student’s t-test (e–h).

Fig. 5 |. Bacterial species on the skin of participants treated with ShA9.

a, Full-length 16S sequencing analysis of the relative abundance of bacterial species on lesional skin of AD participants at baseline (BL), after 1-week treatment with ShA9 or vehicle (day 7) and 96 h after the end of treatment (96-h f/u). b, PCA plot displaying composition of bacterial community at BL, day 7 and 96-h f/u. Statistical analyses were conducted by paired, parametric Student’s t-test on the relative distance of each dot. c, Relative proportion of bacterial species on individuals treated by ShA9 or vehicle is shown after subtraction of S. hominis. d, Individual subject data from c are averaged showing bacterial species on lesional skin at BL, day 7 and 96-h f/u. e,f, Relative abundance of S. aureus 16S rRNA gene (e) and S. epidermidis 16S rRNA gene (f) determined from c. Data represent average (a and d) or mean ± 95% CI (e and f) (ShA9, BL: n = 33; ShA9, day 7: n = 33; ShA9, 96-h f/u: n = 33; vehicle, BL: n = 16; vehicle, day 7: n = 17; vehicle, 96-h f/u: n = 17 independent subjects) (a–f). Only data from >1,000 contigs were shown and data with <1,000 contigs were excluded (a–f). The P value was calculated using the two-tailed, paired, parametric Student’s t-test (b, e and f).