Potential role of intratumor bacteria in mediating tumor resistance to the chemotherapeutic drug gemcitabine

Abstract

Growing evidence suggests that microbes can influence the efficacy of cancer therapies. By studying colon cancer models, we found that bacteria can metabolize the chemotherapeutic drug gemcitabine (2',2'-difluorodeoxycytidine) into its inactive form, 2',2'-difluorodeoxyuridine. Metabolism was dependent on the expression of a long isoform of the bacterial enzyme cytidine deaminase (CDD_L), seen primarily in Gammaproteobacteria. In a colon cancer mouse model, gemcitabine resistance was induced by intratumor Gammaproteobacteria, dependent on bacterial CDD_L expression, and abrogated by cotreatment with the antibiotic ciprofloxacin. Gemcitabine is commonly used to treat pancreatic ductal adenocarcinoma (PDAC), and we hypothesized that intratumor bacteria might contribute to drug resistance of these tumors. Consistent with this possibility, we found that of the 113 human PDACs that were tested, 86 (76%) were positive for bacteria, mainly Gammaproteobacteria.

Fig. 1. M. hyorhinis contributes to gemcitabine resistance in colon carcinoma models

(A) Green fluorescent protein (GFP)-labeled RKO human colorectal carcinoma cells were cultured alone (medium control), with HDFs, HDF-conditioned medium (HDF-CM), HDFs treated with antibiotics (G418) (Supplementary methods), or filtered (0.45 μm) HDF-conditioned medium. Wells were treated with 0.01 μM gemcitabine or with dimethylsulphoxide (DMSO) control. The relative proliferation was calculated by normalizing the number of cells (as determined by GFP fluorescence) after 7 days of treatment to the number of cells (GFP) in the DMSO control wells. Bars represent standard deviation between 2 biological replicates, each containing 4 technical replicates. (B) A subcutaneous model of colon carcinoma was generated by injecting M. hyorhinis-positive or -negative luciferase-tagged MC-26 mouse colon carcinoma cells subcutaneously into the flanks of immunocompetent BALB/c mice. Gemcitabine was administered intraperitoneally [150 mg of drug per kg of body weight (mg/kg)] on days 0, 4, and 9. Tumor size was monitored using an in vivo imaging system (IVIS) for detection of firefly luciferase activity. Tumor size was normalized to the tumor size on day 0. Bars represent standard error between replicates (N=7 mice in each group). (C) Gemcitabine (0.64μM) was incubated for 24 hours at 37°C with HDF-conditioned medium or with Dulbecco's modified Eagle's medium (DMEM) control. HPLC-MS/MS was used to assess gemcitabine levels at the end of the experiment. Bars represent standard deviation between five biological replicates (P<0.001 by two-tailed paired Student's t test).

Fig. 2. The long isoform of bacterial CDD mediates gemcitabine metabolism

(A) Histogram of CDD DNA sequence length across all bacteria in the KEGG database. bp, base pair (B) Gemcitabine (4 μM) was incubated with 10⁷ bacteria in M9 minimal salts medium. Bacteria were filtered from the media at different time points, and the remaining gemcitabine was detected by HPLC-MS/MS. Bars represent the standard deviation between two biological replicates, each containing two technical repeats. (C) WT (wild-type parental) E. coli strain K-12 (long CDD), CDD knockout (Δ) strains of the parental E. coli, and bacteria-free media were each incubated with different gemcitabine concentrations for 4 hours. Bacteria were then filtered out, and the flow-through media were added to GFP-labeled AsPC1 human pancreatic adenocarcinoma cells. The growth of AsPC1 cells after 7 days, as measured by GFP, was normalized to a no-drug control. Bars represent standard deviation between 4 replicates.

Fig. 3. Antibiotics enhance the anti-cancer activity of gemcitabine in a mouse model of colon carcinoma

(A) A subcutaneous model of colon carcinoma (MC-26 cells) was established in immunocompetent BALB/c mice. Bacteria expressing luciferase were injected intravenously and selectively detected in the tumors with IVIS. (B and C) E. coli Nissle 1917 (5×10⁶ bacteria) were injected into the tail vein of mice with MC-26 tumors. The antibiotic ciprofloxacin (Cipro) (150 mg/kg) was administered intraperitoneally (every 12 hours), and gemcitabine (Gem) (150 mg/kg) was administered on days 0 and 4. The antibiotic prevented bacterial growth (B) and increased the efficacy of the chemotherapy [(C) Left panel, no significant difference; right panel, ***P<0.001 by two-way analysis of variance (ANOVA) with a Bonferroni adjustment]. N=16 to 18 mice (groups without Cipro) and 9 to 13 mice (groups with Cipro). Tumor size was normalized to the tumor size on day 0. Bars represent standard error of the mean. (D) WT E. coli or CDD-deficient E. coli (ΔCDD) were injected into the tail vein of mice with MC-26 tumors. Gemcitabine was administered intraperitoneally (150mg/kg) on days 0 and 4. Gemcitabine significantly inhibited tumor growth when ΔCDD bacteria rather than WT bacteria were administered (*P<0.05 by two-way ANOVA with a Bonferroni adjustment). N=15 mice (WT –Gem), 6 to 8 mice (WT +Gem), 10 mice (ΔCDD –Gem), and 4 to 6 mice (ΔCDD +Gem). Tumor size was normalized to the tumor size on day 0. Bars represent standard error of the mean. (E) Devices for local intra-tumor release of drug microdoses were used to release gemcitabine and antibiotics, alone and in combination, directly into the microenvironment of bacteria-colonized tumors to assess in vivo efficacy (13). Histological staining by cleaved caspase 3 shows significantly more apoptosis when gemcitabine is released in combination with antibiotics (ii and iv) but less apoptosis when gemcitabine (i) or ampicillin (iii) is administrated alone. Scale bars, 200 μm. (F) Graph comparing the percentage of apoptotic cells in tumor regions near reservoirs containing the treatment agents (gemcitabine and/or antibiotics). The increase in apoptosis achieved by delivering gemcitabine with antibiotics compared to delivering gemcitabine or antibiotics alone is statistically significant (P <0.001, Student's t test). N=8 mice per treatment group.

Fig. 4. Characterization of bacteria in human pancreatic ductal adenocarcinomas

(A) The presence of bacteria in human pancreatic tumors or in healthy pancreatic tissue from organ donors was assessed by bacterial 16S rDNA qPCR. A calibration curve, generated by spiking bacterial DNA into human DNA, was used to estimate bacterial numbers (fig. S13). Bars represent the mean. (B) Fluorescence in situ hybridization was used to detect bacterial 16S rRNA sequences in a human PDAC tumor (red). Cell nuclei were stained with 4′,6-diamidino-2-phenylindole (DAPI) (blue). Four sections from one tumor are presented. Scale bars, 10 μm. (C) Immunohistochemistry of a human PDAC tumor using an anti-bacterial LPS antibody. Arrows point to LPS staining in the tumor tissue. Scale bar, 20 μm. (D) Distribution of family-level phylotypes in 65 human PDAC tumors. Relative abundance (%) is plotted for each tumor.