Abiraterone acetate preferentially enriches for the gut commensal Akkermansia muciniphila in castrate-resistant prostate cancer patients

Abstract

Abiraterone acetate (AA) is an inhibitor of androgen biosynthesis, though this cannot fully explain its efficacy against androgen-independent prostate cancer. Here, we demonstrate that androgen deprivation therapy depletes androgen-utilizing Corynebacterium spp. in prostate cancer patients and that oral AA further enriches for the health-associated commensal, Akkermansia muciniphila. Functional inferencing elucidates a coinciding increase in bacterial biosynthesis of vitamin K2 (an inhibitor of androgen dependent and independent tumor growth). These results are highly reproducible in a host-free gut model, excluding the possibility of immune involvement. Further investigation reveals that AA is metabolized by bacteria in vitro and that breakdown components selectively impact growth. We conclude that A. muciniphila is a key regulator of AA-mediated restructuring of microbial communities, and that this species may affect treatment response in castrate-resistant cohorts. Ongoing initiatives aimed at modulating the colonic microbiota of cancer patients may consider targeted delivery of poorly absorbed selective bacterial growth agents.

Fig. 1. Rectal swab microbiota from prostate cancer patients receiving no treatment CTRL, ADT, or ADT + AA.

a Principal component analysis (PCA) plot of the microbiota from patient samples. Sequence variants were collapsed at genus-level identification, with clr-transformed Aitchison distances used as input values for PCA analysis. The distance between points represent differences in microbiota composition. Strength of association for taxa are depicted by the length of red arrows shown. Ellipses indicate 95% confidence intervals for each group. b, c Percent relative abundance of the two largest influencers of microbiota separation based on treatment. Data represent the median (line in box), IQR (box), and minimum/maximum (whiskers) for CTRL (n = 33), ADT (n = 21), and ADT + AA (n = 14) patient samples. Statistics shown are derived from multivariate analysis performed using MaAsLin2 additive generalized linear models with log₁₀ clr-transformed input values. d, e ALDEx2 strip charts showing differential abundances of taxa between different patient groups. Positive values indicate increased relative abundance, while negative values indicate decreased relative abundance in the specified treatment groups (ADT or ADT + AA) relative to the CTRL samples. Statistical analysis performed with ALDEx2 and MaAsLin2 software. Features are colored red if ALDEx2 effect size differences (>1) and MaAsLin2 p value (<0.05) thresholds are exceeded, and blue if effect size difference (>2) and p value (<0.05) thresholds are exceeded. **P = 0.0030, ***p = 0.0007, ****p < 0.0001, and n.s. = not significant.

Fig. 2. In vitro incubation of patient fecal samples with abiraterone acetate (AA).

Freshly collected fecal samples from donors not receiving any form of prostate cancer treatment (n = 8) were transferred to BHI media supplemented with 100 μg/mL of abiraterone acetate (AA) or vehicle (EtOH). Samples were incubated anaerobically at 37 °C for 48 h prior to 16S rRNA gene sequencing. a Alpha diversity was measured via Shannon’s H index and b beta diversity was measured via Aitchison distance between samples within the same group. Data represent the median (line in box), IQR (box), and minimum/maximum (whiskers) of n = 4 low Akkermansia and n = 4 high Akkermansia samples. Statistical comparisons shown for separate Wilcoxon’s matched-pairs tests with multiple comparisons corrected using the Benjamini–Hochberg FDR method. c Differences in Akkermansia abundances following incubation with AA compared to vehicle. Data shown represent log₁₀ clr-transformed relative abundances normalized to the vehicle group for each sample. Statistics shown are derived from differential abundance analysis using ALDEx2 software in R. ***P = 0.0005, *p = 0.0358, and n.s. = not significant.

Fig. 3. AA exposure promotes A. muciniphila in a simulated model of the human distal gut microbiota.

a Simplified schematic providing a detailed overview of experimental methodology. Servier Medical Art images were used and modified under the Creative Commons Attribution 3.0 Unported License. b Bar plot representing the microbiota compositions of gut model samples from before, during, and after AA exposure as determined by sequencing of the V4 region of the bacterial 16S rRNA gene. c PCA plot of time-course collected gut model samples matching the days shown. Aitchison distance of genus-level microbiota compositions were used as input values and strength of association for taxa are depicted by the length of arrows shown. d qPCR-based quantification of total bacteria, Enterobacteriaceae, and A. muciniphila in the gut model over time. e Relative amount of AA remaining in bacterial culture supernatants following 24 h incubation in 100 ppm. AA-supplemented media. Data shown represent the mean ± standard deviation (one-way ANOVA with Sidak’s multiple comparisons) for n = 3 biological replicates performed in technical triplicate for each bacterial strain. f Co-occurrence network visually illustrating the significant interactions between taxa in the gut model. g, h Representative growth curves and i carrying capacity (k) of bacteria in 0.25 mM AA and acetate-supplemented media. Data represent mean ± standard deviation (one-way ANOVA with Sidak’s multiple comparisons) of n = 3 biological replicates performed in technical triplicate for each bacterial strain. j, k Temporal overlay graphs showing A. muciniphila and Enterobacteriaceae abundances in the gut model over time alongside predicted menaquinone (vitamin K2) biosynthesis-related pathway abundances. RA = relative abundance. ****P < 0.0001 and n.s. = not significant.

Fig. 4. Abiraterone acetate (AA) exerts a reproducible effect on the human gut microbiota in vivo and in vitro.

a Differentially abundant pathways in patients receiving AA compared to those who were not. Multiclass analysis with the LEfSe algorithm was used to discriminate between AA effects overlapping systemic ADT exposure (LDA score >2 and p < 0.05 for all pathways shown). b–e Relative abundance of predicted pathways that were statistically increased in AA-treated patients. Data represent the median (line in box), IQR (box), and minimum/maximum (whiskers) of CTRL (n = 33), ADT (n = 21), and ADT + AA (n = 14) patient samples. Statistics shown for Kruskal–Wallis tests with multiple comparisons corrected using the Benjamini–Hochberg FDR method. f–i Relative abundance of predicted pathways in AA-exposed gut model samples. j Relevant bacterial contribution to each menaquinone biosynthesis pathway. Predicted pathways were inferenced using an exact amplicon sequence variant approach with the PICRUSt2 software and annotated using the MetaCyc metabolic pathway database. n.s. = not significant.