An engineered bacterial therapeutic lowers urinary oxalate in preclinical models and in silico simulations of enteric hyperoxaluria

Abstract

Enteric hyperoxaluria (EH) is a metabolic disease caused by excessive absorption of dietary oxalate leading to the formation of chronic kidney stones and kidney failure. There are no approved pharmaceutical treatments for EH. SYNB8802 is an engineered bacterial therapeutic designed to consume oxalate in the gut and lower urinary oxalate as a potential treatment for EH. Oral administration of SYNB8802 leads to significantly decreased urinary oxalate excretion in healthy mice and non-human primates, demonstrating the strain's ability to consume oxalate in vivo. A mathematical modeling framework was constructed that combines in vitro and in vivo preclinical data to predict the effects of SYNB8802 administration on urinary oxalate excretion in humans. Simulations of SYNB8802 administration predict a clinically meaningful lowering of urinary oxalate excretion in healthy volunteers and EH patients. Together, these findings suggest that SYNB8802 is a promising treatment for EH.

Keywords: engineered bacteria; enteric hyperoxaluria; in silico modeling; oxalate; synthetic biology.

Figure EV1. SYNB8802 in vitro evaluation

1. SYNB8802 vs. Oxalobacter formigenes. Left y‐axis: ¹³C₂‐oxalate in mM, ¹³C‐formate in mM, x‐axis: time in hours. Oxalobacter formigenes (black, triangle, solid line: oxalate, dotted line: formate). SYNB8802 (light blue, square, solid line: oxalate, dotted line: formate). The control EcN (pink, circle, solid line: oxalate, dotted line: formate). Biological triplicates were run and plotted separately.

2. Scaae3 is needed for oxalate degradation in EcN. Y‐axis shows oxalate in mM. X‐axis: time in hours. Wild type EcN (pink, circle). EcN expressing the OF genes oxdC, oxlT, and frc on p15a (orange, square). EcN expressing the OF genes including scaaE3 on p15a (light blue, triangle). Biological duplicates were run and plotted separately.

3. SYNB8802 vs. SYN1388. Y‐axis shows oxalate in mM. X‐axis: time in minutes. Wild type EcN (pink, circle). Prototype strain SYN1388 (blue, square). SYNB8802 (light blue, triangle). Biological duplicates were run and plotted separately.

4. Overexpression of individual pathway components. Y‐axis shows oxalate in mM. X‐axis: time in hours. SYNB8802 (blue, circle). SYNB8802, with added plasmid‐based expression of oxdC (orange, square). SYNB8802, with added plasmid‐based expression of oxlT (blue, triangle). SYNB8802, with added plasmid‐based expression of scaaE3 (pink, triangle). SYNB8802, with added plasmid‐based expression of frc (black, diamond). Biological duplicates were run and plotted separately.

Figure 1. SYNB8802 schematic and in vitro activity

1. Schematic depicting SYNB8802 oxalate degradation pathway Abbreviations: CO₂ = carbon dioxide; Frc = formyl‐CoA transferase; OxdC = oxalate decarboxylase; OxlT = oxalate/formate antiporter; ScaaE3 = oxalyl‐CoA synthetase.

2. In vitro activity. Left y‐axis: ¹³C₂‐oxalate in mM, right y‐axis: ¹³C‐formate in mM, x‐axis: time in minutes. SYNB8802 (blue, circles, solid line: oxalate, dotted line: formate). The control EcN (pink, triangle, solid line: oxalate, dotted line: formate). Three biological replicates were run and plotted separately.

3. In vitro simulation (IVS). Left y‐axis: Rate of oxalate degradation in μmol/h/10⁹ cells. X‐axis = time in hours. Left X‐axis 0–4 h, Right X‐axis 6–48 h. Three biological replicates were run and plotted separately. Data points in the orange box represent incubation in simulated gastric fluid. Data points in the light blue box represent incubation in simulated intestinal fluid. Data points in the pink box represent incubation in simulated colonic fluid.

Figure EV2. EcN and SYNB8802 intestinal distribution and fecal clearance in mice

1. EcN and SYNB8802^AbxR in vivo kinetics. Abundance of EcN or SYNB8802^AbxR in gut effluents of healthy mice following single oral dose of bacteria. Data represented as mean ± SEM, n = 4/group/timepoint. Full lines represent EcN and hatched lines represent SYNB8802^AbxR.

2. EcN and SYNB8802^AbxR fecal clearance. Abundance of EcN or SYNB8802^AbxR in fecal pellets of healthy mice following single oral dose of bacteria. Data represented as mean ± SEM, n = 5/group. Dark blue curve represents EcN and light blue curve represent SYNB8802^AbxR.

Figure 2. SYNB8802 in vivo activity

1. Acute mouse study design.

2. Acute mouse study of UOx lowering with SYNB8802. The y‐axis shows the urinary ¹³C₂‐oxalate normalized to creatine. The x‐axis shows the two groups, EcN (control, pink) versus SYNB8802^AbxR (light blue; n = 15 mice per group). Individual dots represent each metabolic cage (n = 3 mice per metabolic cage). Error bars are calculated as SEM (unpaired t‐test with Welch's correction, ****P < 0.0001).

3. Non‐human primate model development study design.

4. Non‐human primate model development study. The y‐axis shows urinary oxalate (UOx) normalized to creatine. X‐axis shows baseline UOx levels after overnight fast, and UOx measured 6 h post‐administration of either a spinach preparation (triangle, pink) or water (circle, blue) (n = 6 for each group). Individual dots represent individual animals. Error bars are calculated as SEM (two‐way ANOVA followed by Sidak's multiple comparison analysis, ****P < 0.0001).

5. Study design for urinary recovery of oxalate in non‐human primates.

6. Urinary recovery of oxalate in non‐human primates. The y‐axis shows change in UOx from vehicle control. The x‐axis shows vehicle (control, grey) and increasing doses of SYNB8802^AbxR (n = 24 for vehicle, n = 6 for treatment groups). Individual dots represent normalized UOx for each individual animal. Error bars are calculated as SEM (One‐way ANOVA followed by Tukey's multiple comparison analysis, *P < 0.05).

7. Urinary recovery of ¹³C₂ oxalate in non‐human primates. The y‐axis shows change in urinary ¹³C₂‐oxalate from vehicle control. The x‐axis shows vehicle (control, grey) and increasing doses of SYNB8802^AbxR (n = 24 for vehicle, n = 6 for treatment groups). Individual dots represent normalized urinary ¹³C₂‐oxalate for each individual animal. Error bars are calculated as SEM (one‐way ANOVA followed by Tukey's multiple comparison analysis, **P < 0.01).

Figure 3. Enteric hyperoxaluria in silico simulation (ISS) schematic

1. Oxalate and SYNB8802 transit through the stomach, small intestine, and colon are modeled according to a physiological function of chyme progression. Oxalate absorption and consumption occur sequentially in as chyme transits through the three compartments.

2. SYNB8802 begins in the stomach and empties into the small intestine during the first 4 h post‐meal. From 4 to 8 h post‐meal, SYNB8802 empties from the small intestine into the colon. Approximately 36 h post‐meal, SYNB8802 begins to empty from the colon via fecal excretion.

3. ISS connects in vitro strain activity knowledge to host and disease biology. The strain‐side model (green) simulates the consumption of oxalate by SYNB8802 within the gastrointestinal physiology. The host‐side model (overall schematic) simulates the impact of consumption by SYNB8802 on the distribution of oxalate throughout the body.

Figure 4. In silico simulation (ISS) strain activity and pH inhibition model

1. Michaelis–Menten model of strain activity kinetics. Vmax defines the maximal strain activity velocity (consumption rate of oxalate by SYNB8802). Km defines the oxalate concentration at which half‐maximal strain activity velocity occurs. Vmax and Km were determined through in vitro simulation.

2. Simulated gastric pH as a function of time following a solid meal (dark blue). This function is a power exponential decay with a half‐life of 110 min and a shape parameter equal to 1.81. Likelihood of time spent in the stomach based on gastric residence time distribution (light blue). The distribution is truncated to a maximum of 4 h and the median gastric residence time is 110 min.

3. Simulated normalized SYNB8802 activity in the stomach as a function of time.

4. Simulated normalized SYNB8802 activity in the small intestine as a function of time previously spent in the stomach. Function is equivalent to gastric function with an upper limit imposed based on intestinal pH.

Figure EV3. SYNB8802 pH inhibition in vitro simulation

SYNB8802 activity as a function of exposure time to medium at pH ranging from 2.0 to 7.0. Points and error bars in black represent in vitro measurements (n = 3 replicate cultures per group; mean ± SD). Blue curves represent exponential decay models fit to in vitro measurements for each pH level.

Figure 5. In silico simulation (ISS) model validation and simulated urinary oxalate (UOx) lowering subsequent dietary oxalate removal by SYNB8802

1. Validation of simulated UOx excretion against clinical data. Simulated UOx on a free‐living diet and on 3 days of a high‐oxalate diet (dark blue). Observed UOx on a free‐living diet and on 3 days of a high‐oxalate, low‐calcium (HOLC) diet (light blue); points and error bars represent mean and standard deviation, respectively, across 30 simulated healthy subjects.

2. Simulated UOx and UOx reduction for healthy subjects consuming 200 mg/day dietary oxalate without SYNB8802 and with 1 × 10¹¹, 2 × 10¹¹, and 5 × 10¹¹ SYNB8802 cells TID over 10 days. Points represent simulations under a baseline assumption of dietary oxalate absorption in healthy subjects (Holmes et al, 2001) (See Materilas and Methods for a detailed description). Error bars represent a simulated range of dietary oxalate absorption (two simulations: 0.75× baseline and 1.25× baseline).

3. Simulated UOx and UOx reduction for enteric hyperoxaluria patients consuming 200 mg/day dietary oxalate without SYNB8802 and with 1 × 10¹¹, 2 × 10¹¹, and 5 × 10¹¹ SYNB8802 cells TID over 10 days. Points represent simulations under a baseline assumption of increased dietary oxalate absorption in HOX patients (4× healthy absorption). Error bars represent a simulated range of increased dietary oxalate absorption (two simulations: 3× healthy absorption and 5× healthy absorption).

4. Simulated UOx reduction for enteric hyperoxaluria patients after 5 days dosing with 1 × 10¹¹, 2 × 10¹¹, and 5 × 10¹¹ SYNB8802 cells TID as a function of dietary intake of oxalate. Solid curves represent simulations under a baseline assumption of increased dietary oxalate absorption in HOX patients (4× healthy absorption). Shaded regions represent a simulated range of increased dietary oxalate absorption (two simulations: 3× healthy absorption and 5× healthy absorption).

Figure EV4. Agarose gel of PCR verification for SYNB8802

Lane 1 shows insertion of agaI/rsmI:: P_FnrS ‐scaaE3‐oxdC‐frc. Lane 2 shows insertion of exo/cea::P_FnrS‐oxlT. Lane 3 shows knock out thyA.