A transcriptional biosensor to monitor single cancer cell therapeutic responses by bioluminescence microscopy

Plasmid and adenoviral constructions

Cell line culture

22Rv1, LNCaP, LNCaP-LN3, LNCaP-PRO5, V16D, MR42D, MR49F, CAMA-1 and ZR-75-1 were cultured in RPMI-1640 media containing 10% fetal bovine serum (FBS) (VWR, Radnor, PA, USA). LAPC4 was cultured in DMEM media (Wisent Bio Products, ST-BRUNO, QC, Canada) containing 10% FBS. PC-3, DU145, SW780, SW1710, RT4, MD-MB-231 and MCF-7 were cultured in eMEM (Wisent Bio Products) media containing 10% FBS. All the cells were incubated in a 37 °C incubator that provided 5% CO₂. Cells were passaged after the confluence reached 80-90%.

Adenoviral infection and treatment experiments for luciferase assays

Cancer cell lines were seeded in 24-well plates as follow: 22Rv1, LNCaP, LNCaP-LN3, LNCaP-PRO5 at 1 x 10⁵ cells/well; V16D, MR42D, MR49F, CAMA-1, ZR-75-1, MD-MB-231 and MCF-7 at 5 x 10⁴ cells/well; PC-3, DU-145, SW780, SW1710 and RT4 at 8 x 10⁴ cells/well. Twenty-four hours after seeding, adenoviruses were transduced at a multiplicity of infection (MOI) of 2. Seventy-two hours after infection, cells were lysed, and a luciferase assay was performed as described (Promega, Madison, WI, USA). Protein content was estimated by adding 250 μl of Bradford reagent (ThermoFisher Scientific, Waltham, ON, Canada) to 3 μl of total lysate. Absorbance was then read using an Infinite F50 absorbance microplate reader (TECAN, Mannedorf, Switzerland) at 595 nm. SV40-Luc virus was infected in parallel to normalize for infection efficiency between different cell lines. For androgen sensitivity assessment, cells were treated with 10 nM dihydrotestosterone (DHT) (Toronto Research Chemicals, Toronto, ON, CA) and 10 μM Bica (Sigma-Aldrich, St.Louis, MO, USA) in 10% charcoal-treated FBS (FBS-CT) (Wisent Bio Products), 24 h post-infection. Luciferase assays were performed after 48 h of treatment.

Transfection experiments for luciferase assays

LAPC4 (1 x 10⁵ cells/well) were seeded in 24-well plates. The following day, 100 ng of each plasmid was transfected into the cells along with 60 ng of pRL-null (Promega) using lipofectamine 2000 (Invitrogen). Seventy-two hours after transfection, the cells were lysed using passive lysis buffer and a luciferase assay was performed as described (Promega).

RT-qPCR technique

The 22Rv1 cells were infected with adenovirus expressing or not Cre recombinase. Cells were washed with PBS and trypsinized at each of the time points (6, 24, 48, 72, 96 h). Viral DNA was isolated from the infected cells using QIAmp® viral DNA isolation kit (Qiagen, Hilden, Germany). RT-qPCR reaction was performed with TaqMan probes (Applied Biosystems, Waltham, MA, USA) using two primer sets, one within the firefly luciferase (Luc) gene used as internal control (primer set 1) and one within the stop cassette to determine the cleavage (primer set 2) (Table S1). Standard curves for both the primer sets were determined using original plasmids as the template. Isolated viral DNA copy number at each time point was extrapolated on the standard curves.

Cell lines adenoviral infection and treatment for dynamic bioluminescence assays and imaging

LNCaP, LAPC4 and 22Rv1 cells (2,000 cells/well) were seeded in a 384-well black plate (Greiner Bio-One North America Inc., Monroe, NC, USA) in RPMI-1640 with 10% heat-inactivated FBS-CT and 1 nM DHT. The cells were then transduced with 1 x 10⁵ infectious viral particles (ivp) of PCA3-Cre-PSEBC-ITSTA adenovirus per well. The plate was kept on a shaker overnight and incubated at 37 °C. Seventy-two hours after infection, media was removed to leave 10 μl at the bottom of the wells. Ten microliters of Matrigel^TM Matrix High Concentration (Corning, Corning, NY, USA) diluted at 40% in cold RPMI-1640 (with 10% heat-inactivated FBS-CT and 1 nM DHT) was added in each well. The plate was rapidly centrifuged at 225 g for 3 min and incubated for 30 min at 37 °C in 5% CO₂. Following incubation, 30 μl of RPMI-1640 with 10% heat-inactivated FBS-CT and 1 nM DHT was added to each well and, in the presence of 3.5 mM of D-luciferin (Caliper Lifesciences, Hopkinton, MA, USA), wells were then read with a TriStar LB 941 (20 seconds exposure; Berthold, Bad Wildbad, Germany) or imaged. To further determine response to treatment for isolated cells, media over the Matrigel^TM layer was replaced with media containing 1 nM DHT, 1 nM DHT + 10 μM Bica or 1 nM DHT + 10 μM Enza (MedChem Express, NJ, USA) and reading or imaging was done 48 h later. D-luciferin (3.5 mM) was added 20 min before each imaging timepoint.

Patient samples

Samples were collected with ethical permission from the Institutional Review Board of the CHU de Quebec Hospital, Quebec, QC, Canada (A14-06-1976 and A12-12-1076). All patients gave written consent for their tissue to be used for research. Primary prostate samples were obtained from needle biopsy cores (18 G, 17 mm) of radical prostatectomy of naive patients. Sextants harboring adenocarcinoma on a previous transrectal biopsy were targeted. Urine samples were collected from mCRPC patients with primary tumor and established clinical status.

Isolation, infection and treatment of PCa cells isolated from urine samples

Ten milliliters of urine were collected post-digital rectal examination. Sampling was done twice for patient 8, the first and second sampling were done when the patient was on enzalutamide and bicalutamide, respectively. Urine samples were centrifuged at 400 g for 10 min at 4 °C. Then supernatant was carefully removed, leaving 2 ml of the sample. The pellet was re-suspended gently in 30 ml of washing buffer (1X PBS + 2% FBS). The solution was centrifuged again at 200 g for 10 min at room temperature (RT). Supernatant was carefully discarded and gently resuspended in 30 ml of media (RPMI-1640 with 10% heat-inactivated FBS-CT with 1 nM DHT, penicillin and streptomycin). Centrifugation was repeated at 200 g for 10 min at RT. Supernatant was carefully removed leaving behind 400 µl of media containing the isolated cells and 50 μl was seeded in each well of a 384-well plate. The samples were then infected with 5×10⁵ ivp of PCA3-Cre-PSEBC-ITSTA adenovirus per well. The plate was kept on a shaker overnight and incubated at 37 °C. Seventy-two hours after infection, Matrigel^TM layer and media were added to wells as described above and the wells were imaged in the presence of D-luciferin. Next, media over the Matrigel^TM layer was replaced with the appropriate treatment media containing 1 nM DHT, 1 nM DHT + 10 μM Bica or 1 nM DHT + 10 μM Enza. Imaging was repeated 48 h post-treatment. Bioluminescence imaging was done 20 min after adding 3.5 mM of D-luciferin.

Dissociation, infection and treatment of primary PCa samples

The biopsy samples were washed three times with HBSS-Ca²⁺-Mg²⁺ (Wisent Bio Products), cut into 1 mm² fragments and incubated overnight at 37 °C (5% CO₂) with shaking in Advanced DMEM/F12 media (ThermoFisher Scientific) complemented with 1X GlutaMAX^TM (ThermoFisher Scientific), 1X Hepes (Sigma-Aldrich) and 1X Primocin (ThermoFisher Scientific) with 100 U/ml of type II Collagenase (ThermoFisher Scientific) and 0.005 MU/ml of DNAse (Milipore, Burlington, MA, USA). The next day, samples were dissociated by vigorous pipetting and incubated at 37 °C (5% CO₂) with shaking for another 2 h. Cell suspensions were washed in a 15 ml tube with 10 ml of 1X PBS and centrifuged at 500 g for 10 min. Supernatants were gently removed, and the cells were resuspended in Accumax^TM solution (Sigma-Aldrich) and incubated for 20 min at 37 °C with frequent agitation. The cells were washed with 10 ml of 1X PBS and resuspended in RPMI-1640 media containing 10% heat-inactivated FBS-CT and 1 nM DHT before seeding in a 384-well plate at a concentration of 2,000 viable cells/well. The cells were then infected with 10⁶ ivp of PCA3-Cre-PSEBC-ITSTA adenovirus per well. The plate was incubated at 37 °C (5% CO₂) for 72 h including rotative agitation for the first 16 h. The Matrigel^TM layer and media were then added to the wells as describe above and the wells were imaged in the presence of D-luciferin. Next, media over the Matrigel^TM layer was replaced with the appropriate treatment media containing 1 nM DHT, 1 nM DHT + 25 μM Bica or 1 nM DHT + 35 μM Enza. Imaging was repeated 72 h post-treatment.

Bioluminescence microscopy imaging

Dynamic bioluminescence microscopy was performed using an LV200 microscope (Olympus, Tokyo, Japan) as previously described ¹⁵. The bioluminescent LV200 microscope is equipped with an EM CCD camera (Andor Ixon 897) and an incubation chamber with temperature control, humidity and gas flow to keep the prostate cells at 37 °C under 5% CO₂. Briefly, each bioluminescence imaging was performed 20 min after adding D-luciferin at 3.5 mM using Olympus UPLSAPO 40X objective (a non-immersive lens with a numerical aperture of 0.95, a working distance of 0.18 mm and a correction collar from 0.11 to 0.23 mm) with exposure times of 20 sec per field of view (FOV) as previously described ¹⁵. The threshold for AR active cells was defined as luminescent signals over background. Because the luminescent signal is the result of an enzymatic reaction that requires ATP for conversion of D-luciferin substrate into oxyluciferin, only live cells expressing the reporter gene would produce light ³⁰. Data analysis and process design for automated image capture were achieved using the CellSens software (Olympus).

Immunofluorescence

Patient cell samples were fixed after the second bioluminescence imaging, while cell lines were fixed 24 h after seeding. Cells were fixed using 4% paraformaldehyde, then permeabilized with 0.5% triton-X 100 in PBS for 10 min. The cells were washed in PBS, blocked with 5% bovine serum albumin (BSA), and then incubated for 1 h at RT with primary antibodies against: alpha-Methylacyl-CoA racemase (AMACR, 1:50) (ab93045, Abcam, Toronto, ON, Canada), Nucleolin (1:200) (ab136649, Abcam,) or NKX3.1 (1:100) (AES0314, ^MJSBioLynx Inc., Brockville, ON, Canada). Primary antibodies were diluted in PBS-2% BSA. After washing cells three times with PBS containing 0.025% Tween 20, cells were subsequently treated with secondary Anti-mouse IgG Alexa Fluor 488, 1:500 (4408S, New England Biolabs) and Anti-Rabbit IgG Alexa Fluor 594, 1:200 (A11012, Thermofisher Scientific) diluted in PBS-2% BSA for 1 h at RT. After washing cells three times with PBS containing 0.025% Tween 20, nuclei were co-stained for 5 min with DAPI, washed again, and cells were retained for fluorescent imaging.

Statistical analysis

Linear discriminate analyses (LDA) were performed using Microsoft Excel 16.0 and XLSTAT Addinsoft version 2020.1.3.65325 (Addinsoft Inc., New York, U.S.). LDA factor scores and ROC curves were obtained from these analyses. Comparison of areas under the ROC curve (AUC) was done with the DeLong method ³¹. Statistical analyses were performed using GraphPad Prism (La Jolla, CA, USA). Bar graphs were expressed as mean ± standard deviation (SD). Data were compared by one sample t-test, paired and unpaired Student's t-test, one-way or two-way analysis of variance (ANOVA). Post hoc Bonferroni, Tukey or Dunnett tests were performed where significant interactions were observed in ANOVAs. Significance was established as p ≤ 0.05 (*), 0.01 (**), 0.001 (***), and 0.0001 (****).

Integration of PCA3 and PSEBC promoter specificities as a single output to image PCa cell antiandrogen response

To allow identification of PCa cells sensitive to ARAT, we needed to design a system that was both PCa-specific and that enabled imaging of AR transcriptional activity. When the PCA3 promoter driving a strong three-step amplification system (3STA) was tested in PCa and non-PCa cell lines, it was highly active in PCa cells but not in breast or bladder cancer cell lines (Figure 1A); it was also not regulated by androgens ²³. Contrary to the PCA3 promoter, the PSA chimeric promoter, PSEBC, was highly androgen responsive in AR-expressing PCa cell lines and it was also active in AR-expressing breast cancer cells such as CAMA-1 and ZR-75-1 (Figure 1B).

To exploit the combined potential of PCA3 and PSEBC promoters as a single output (PCa specificity and AR activity monitoring), we developed the multi-promoter integrated two-step transcriptional amplification system (MP-ITSTA) (Figure 2A). MP-ITSTA utilizes the site-specific recombination ability of Cre recombinase to specifically remove the DNA fragment between two LoxP sites. The system consists of 4 major steps: 1) the activation of the first promoter leads to the production of Cre recombinase; 2) the Cre recombinase then identifies the LoxP sites and cleaves the DNA fragment between them (which contains a stop cassette); 3) a second promoter is activated and the GAL4VP16 protein is produced; 4) the GAL4VP16 fusion protein binds to GAL4RE upstream of the reporter gene and amplifies promoter-driven expression. Therefore, this system is designed to combine the specificity of two promoters in order to drive the expression of a single reporter gene after TSTA transcriptional amplification (Figure 2A).

As a first step for the development of the MP-ITSTA system, we inserted a sequence that would completely inhibit the Luc expression in the absence of Cre recombinase between the LoxP sites, namely the stop cassette. It has been shown that recombination efficiency between two LoxP sites on the same DNA molecule is dependent on the distance between them. The minimum distance required between two sites to allow recombination is 82 base pairs long ³². Therefore, we tested the ability of the bovine growth hormone (BGH) or Simian Virus 40 (SV40) polyadenylation (poly-A) sequences inserted between the LoxP sites (as a stop cassette) to inhibit the ubiquitous SV40 promoter (Figure 2B). As shown, both sequences could block the SV40 promoter-driven firefly luciferase gene in the absence of Cre. Upon co-transfection with the plasmid expressing Cre recombinase under ubiquitous CMV promoters, the BGH poly-A stop led to a better reactivation of the system giving 4.04-times higher Luc signal compared to the SV40 poly-A stop (Figure 2B). Following this result, we used the BGH poly-A stop sequence for our next experiments.

Adenovirus containing both the Cre recombinase and the LoxP in a single backbone were generated. In concordance with earlier studies ²⁷, it was not possible to amplify adenoviral backbone plasmids containing both the wild-type Cre recombinase and the LoxP sites. This was secondary to the leaky expression of wild-type Cre recombinase causing non-specific cleavage of LoxP sites in prokaryotic bacterial systems. To inhibit bacterial expression of Cre, an intron was inserted 465 nucleotides downstream of the Cre recombinase start site; the absence of post-transcriptional splicing machinery in E. coli would prevent the expression of functional Cre and allow adenoviral DNA amplification. We tested three intron sequences inserted in the Cre cDNA: 1) a human BGH-Ig chimeric intron (5′-donor site from the first intron of the human β-globin and the branch and 3′-acceptor site from the intron located between the leader and body of an immunoglobulin gene heavy chain variable region ²⁷), 2) the mice protamine 2 gene (Prm2) intron ³³ and 3) the modified Prm2 containing eukaryotic splice site (AG). As shown in Figure 2C, all three intron sequences, when inserted in the Cre cDNA, did not affect the expression of Luc when compared to wild-type Cre after plasmid transfection. However, only the Cre recombinase containing chimeric human intron allowed amplification of adenoviral backbones in bacteria. Therefore, the BGH-Ig chimeric human intron was used in all our MP-ITSTA constructs.

Additionally, the biosensor that we describe in this manuscript consists of three promoters: PCA3, PSEBC and GAL4RE minimal-TK promoter, expressing different genes. It is known that having two promoters very close to one another causes steric hindrance and also competition in binding of transcription factors, thereby reducing gene output ^34-36. To account for these factors, we had to find the optimal relative orientation of each component of the MP-ITSTA (promoters, amplifier, reporter). We compared Luc activities when the activator and amplifier cassette were in several orientations. For these experiments, the SV40 promoter was driving TSTA and the PCA3 promoter was driving Cre expression (Figure 3A). After testing the system in 22Rv1, LAPC4, DU-145 (PCa), CAMA-1 (breast cancer) and SW780 (bladder cancer) cell lines, we observed that orientation A provided the highest reporter gene signal while also being specific to PCa cells due to PCA3-driven Cre expression (Figure 3B).

As a final step, we determined if the Cre recombinase levels produced by PCA3 weak promoter was sufficient to recombine all the LoxP sites. Quantitative PCR using primer sets within the stop cassette or firefly luciferase gene as an internal control showed that PCA3-driven Cre recombinase could remove more than 98% of the stop cassette after only 48 h. As a control, a TSTA virus expressing green fluorescent protein (GFP) instead of Cre recombinase did not show any cleavage of the stop cassette and DNA copy number of viruses remained stable over time (Figure 3C).

PCA3-Cre-PSEBC-ITSTA system is specific to PCa cells and can measure the transcriptional activity of the androgen receptor

The PCA3 promoter was shown to be PCa-specific, while the PSEBC promoter was not, but it can monitor response to androgen deprivation therapy (Figure 1). Thus, incorporation of these two promoters together in the multi-promoter integrated system could theoretically monitor androgen deprivation therapy response in PCa cells harvested from patients. We first tested the ability of PCA3-Cre-PSEBC-ITSTA to signal specifically in PCa cells. PCA3-Cre-PSEBC-ITSTA generated Luc activity was more than 1500-times higher in 22Rv1 PCa cells when compared to non-prostatic CAMA-1 or ZR-75-1 cells. By contrast, this ratio was only 24-times higher when the PSEBC-TSTA system was used (Figure 4A). In fact, PCA3-Cre-PSEBC-ITSTA not only restricted the expression of Luc to PCa cells but it also kept the sensitivity of the system to the AR agonist (DHT) to levels comparable to that obtained when using the PSEBC promoter alone (Figure 4B).

Dynamic bioluminescence imaging of single cells allows characterization of heterogeneous androgenic response in AR-active PCa cell lines

Before undertaking bioluminescence microscopy studies, we have tried to dynamically monitor our biosensor luminescence signal variation after ARAT treatment using a standard bioluminescent plate reader. Unfortunately, this technique could not detect a significant signal variation after ARAT treatment nor different response patterns between ARAT sensitive and insensitive cell lines (Figure S1). Consequently, we have tested bioluminescence microscopy technology to monitor single-cell response to ARAT therapy ¹⁵. Bioluminescence microscopy allows same-cell reporter activity quantification and tracking before and after treatment. This same-cell normalization is needed to compensate for cell-to-cell differences in viral transduction, viability in culture or transcriptional activity.

Thus, with the use of a LV200 bioluminescent microscope, the impact of a treatment can be visualized and measured by determining the initial and final luminescence status of a single cell (Figure 5A-B). Indeed, change in luminescence over time can be determined by calculating the slope between luminescence measurements from the same cell (Figure 5C). Thus, single cells can be represented in a two-dimensional array with change in luminescence over time and the final luminescence activity as two distinct parameters (Figure 5D). Androgen activation, as measured by luminescence activity, follows a log-normal curvature ³⁷. Data were therefore log-transformed. This representation shows the single-cell AR activity with heterogeneous response to DHT in LAPC4 cells expressing a wild-type AR (Figure 5D). Interestingly, despite being treated with DHT, some cells had a decrease in luminescence activity over time; this demonstrated the complexity of heterogeneous analysis to discriminate non-responsive over responsive cell populations. For that purpose, we decided to use a linear discriminate approach described below to distinguish responsive from non-responsive cell populations.

PCA3-Cre-PSEBC-ITSTA and dynamic bioluminescence microscopy can assess cell line response to antiandrogen therapy

The ability of the PCA3-Cre-PSEBC-ITSTA system to assess the sensitivity of LNCaP (sensitive), LAPC4 (moderately resistant) and 22Rv1 (resistant) PCa cell lines to two ARATs, Enza and Bica ^{38, 39}, was evaluated using a linear discriminate approach. First, change in bioluminescent activity, calculated from each individual cell, was plotted according to bioluminescent activity for each cell after treatment per treatment condition. As seen in Figure 6, treatment of LNCaP or LAPC4 cells with DHT, in combination with Enza or Bica, for 48 h significantly decreased change in bioluminescent activity both over time and after treatment compared to the DHT alone (control condition; Figure 6A-B). In contrast, when the same conditions were applied to ARAT-resistant 22Rv1 cells, no differences were observed in luminescence activity over time or after treatment, demonstrating that resistant cells maintain normal AR signaling when subjected to inefficacious ARAT (Figure 6C). Furthermore, we performed a linear discriminant analysis (LDA) for each combination of treatment (Enza or Bica) and control (DHT) data sets. LDA projects the two-dimensional change in bioluminescent activity over time versus bioluminescent activity after treatment into a single axis that best separates two populations (Figure 6D) and gives an LDA score for each cell. To quantify the difference of the two single-cell populations, we modeled the ROC curves based on the LDA score of each cell per combination of treatment (Enza or Bica) and control (DHT) data sets to calculate the area under the curve (AUC), which here is a synthetic index of the ARAT sensitivity of a single-cell population ¹³. For example, an AUC of 0.5 reflects an ARAT resistant population because no discrimination could be observed in the AR activity between ARAT-treated and untreated cells.

As expected with the ARAT sensitive LNCaP cell line, the AUC of the ROC curves are close to 1 for both Bica (AUC= 0.9452) and Enza (AUC= 0.9588) -treated cells, meaning the AR activity of single cells differed markedly between LNCaP cells treated with ARAT and control. In contrast, AUCs for the Bica and Enza conditions tested on 22Rv1 cells are 0.5650 and 0.5760, respectively, indicating no distinguishable AR activity between ARAT-treated and untreated 22Rv1 cells, consistent with the ARAT resistant status of 22Rv1 cell line. The AUC for LAPC4 was intermediate for Bica (AUC= 0. 7820) and Enza (AUC= 0. 8351) -treated cells. For all cell lines tested, no significant differences between Enza and Bica ROC curves were observed. However, the AUC of each cell line was different from each other, regardless of the condition tested in compliance with the ARAT status of each cell line (Figure 6E).

To ensure that the data generated was reliable, we tested three independent experiments for LAPC4 cells and observed negligible variation in AUC results (Figure 6F). Moreover, as an internal control, LDA and subsequent ROC curves were generated for combinations of two DHT control data sets. As expected, AUC for these combination conditions were not significantly different from 0.5, consistent with DHT populations behaving like other DHT controls (Figure 6F). This data demonstrates that the PCA3-Cre-PSEBC-ITSTA system could identify the ARAT sensitivity of single PCa cell populations.

PCA3-Cre-PSEBC-ITSTA allows dynamic imaging of primary PCa cells from naive PCa patient samples and can evaluate their ARAT sensitivity

To investigate the translational potential of the methods, we tested the PCA3-Cre-PSEBC-ITSTA system on primary cells harvested from prostate specimens of six treatment-naive PCa patients with a Gleason score of 7 or less. Before ARAT, AR active PCa cells were detected in every freshly dissociated sample. Single-cell analysis for each ARAT condition was compared to control DHT to obtain AUC data after LDA, as described above. Average AUC for the Bica and Enza conditions tested on primary cells were significantly different from 0.5, with a mean of 0.6561 and 0.6429, respectively, which correlate with the ARAT naive status of PCa patients. For all samples tested, no significant difference between the Enza and Bica ROC curves were observed (Figure 7). These two observations confirm the ability of the PCA3-Cre-PSEBC-ITSTA system to identify PCa cells and assess their ARAT sensitivity.

ARAT therapeutic sensitivity of single PCa cell population from mCRPC patients determined by PCA3-Cre-PSEBC-ITSTA system correlates with clinical patient response

As another step towards clinical translation, we tested the ability of the PCA3-Cre-PSEBC-ITSTA to identify ARAT-resistance status from primary PCa cells, shedding from the prostate into urine of mCRPC patients with established therapeutic ARAT sensitivity. First, to ensure that luminescent cells detected by PCA3-Cre-PSEBC-ITSTA system were PCa cells, as opposed to inflammatory, urothelial or benign prostate cells, we stained positive cells with a panel of markers known to distinguish PCa from non-PCa cells ²⁴. Triple PCa marker immunofluorescence (nucleolin, AMACR and NKX3.1) and DAPI staining after cell imaging and fixation showed co-localization of the three signals with that of Luc expressing cells. Several established PCa and bladder cancer cell lines showing that our panel of markers was specific for PCa cells were used as controls (Figure S2).

Metastatic CRPC Patient 7 had progressed after several lines of therapy including Bica, docetaxel and abiraterone acetate before urine sampling. He had previously been treated with enzalutamide for a short duration (less than one month), which was discontinued due to intolerance. Therefore, the patient was not considered enzalutamide-resistant (Figure 8A). Cells collected from urine were isolated and infected with PCA3-Cre-PSEBC-ITSTA for 72 h. At baseline, 141 positive cells were detected and then treated with either DHT, DHT + Bica, or DHT + Enza for 48 h before reimaging. Change in luminescence activity over time and luminescence activity after treatment was evaluated to generate ROC curves after LDA analysis, as described above (Figure 8B-D). As expected for Bica, an AUC of 0.5119 was obtained, indicating a non-responsive PCa cell population for this treatment. Furthermore, the AUC of 0.7240 for Enza suggested a better clinical efficiency of Enza as an ARAT treatment for this patient (Figure 8D).

Metastatic CRPC Patient 8 initially presented with a high-risk PCa (stage 4 Gleason score 9) and started bicalutamide upon PSA progression under castration. Despite this treatment, the patient's PSA level increased over time, suggesting that the cancer was resistant to bicalutamide. After a switch to enzalutamide, there was a strong PSA drop which showed sensitivity to enzalutamide (Figure 8E). Cells collected from the patient's urine were sampled twice and infected with PCA3-Cre-PSEBC-ITSTA in the presence of DHT. Baseline bioluminescence imaging was performed 72 h after infection, detecting 281 and 275 cells for the first and second sampling, respectively. After the baseline imaging, cells were then treated with either DHT alone or in combination with Bica or Enza for the first and second sampling, respectively. Single-cell bioluminescence was measured again 48 h post-treatment. The change in luminescence activity over time and luminescence activity after treatment was measured. As seen in Figure 8F-left, we observed an overlap of Bica and DHT treated cell populations when analyzed with these two parameters. In comparison, Enza treated cells showed an apparent reduction in luminescence activity parameters compared to DHT control (Figure 8F-right). Moreover, after LDA analysis, centroids were further apart between Enza and DHT conditions than between Bica and DHT conditions (Figure 8G). The corresponding ROC curves generated after LDA analysis demonstrated that the ability to discriminate single cells between untreated and treated groups was significantly better with Enza than Bica (Figure 8H). The AUC obtained for Bica and Enza were 0.6644 and 0.8645 respectively and in concordance with the observed Bica clinical response (Figure 8E and H). Overall, these results demonstrated that single-cell bioluminescence microscopy extracted data could serve as predictive response biomarkers to ARAT.