Prediction of Patient Drug Response via 3D Bioprinted Gastric Cancer Model Utilized Patient-Derived Tissue Laden Tissue-Specific Bioink

Abstract

Despite significant research progress, tumor heterogeneity remains elusive, and its complexity poses a barrier to anticancer drug discovery and cancer treatment. Response to the same drug varies across patients, and the timing of treatment is an important factor in determining prognosis. Therefore, development of patient-specific preclinical models that can predict a patient's drug response within a short period is imperative. In this study, a printed gastric cancer (pGC) model is developed for preclinical chemotherapy using extrusion-based 3D bioprinting technology and tissue-specific bioinks containing patient-derived tumor chunks. The pGC model retained the original tumor characteristics and enabled rapid drug evaluation within 2 weeks of its isolation from the patient. In fact, it is confirmed that the drug response-related gene profile of pGC tissues co-cultured with human gastric fibroblasts (hGaFibro) is similar to that of patient tissues. This suggested that the application of the pGC model can potentially overcome the challenges associated with accurate drug evaluation in preclinical models (e.g., patient-derived xenografts) owing to the deficiency of stromal cells derived from the patient. Consequently, the pGC model manifested a remarkable similarity with patients in terms of response to chemotherapy and prognostic predictability. Hence, it is considered a promising preclinical tool for personalized and precise treatments.

Keywords: drug efficacy testing; gastric cancer patient‐derived xenograft; gastric tissue‐derived decellularized extracellular matrix; tumor tissue printing.

Figure 1

Tumor tissue printing using patient‐derived tumor‐laden tissue‐specific bioinks and evaluation of characteristics of pGC model. A) Schematic of the fabrication process for a 3D bioprinted model and its application in predicting patient drug responses. B) Production of pGC specimens and C) comparison of pGC sizes under different printing pressures of (i) 25 kPa and (ii) 35 kPa. D) Optical image of pGCs according to tumor tissue content ratio. E) Comparison of pGCs proliferation rate (i) pGC‐intestinal and (ii) pGC‐diffuse by tumor tissue content percentage for 21 days. The error bars represent the S.D. (n=3, ****p< 0.0001). F) Confirmation of culture suitability and the morphology of pGC‐intestinal and pGC‐diffuse tissues according to PDX tissue content using Calcein‐AM staining. Scale bars: 250 µm. G) Hematoxylin & Eosin (H&E) staining images and immunofluorescence staining images of E‐cadherin (green), α‐SMA (red), and DAPI (blue) in original PDX tissue and pGCs tissue at day 7, (i) intestinal type; (ii) diffuse type, Black scale bar: 50 µm; White scale bar: 100 µm. One‐way ANOVAs are used for the statistical analyses in (E).

Figure 2

Assessment of responsiveness to 5‐FU and oxaliplatin‐based chemotherapy using pGC model. A) Evaluation of drug response in pGC tissues treated with various concentrations of 5‐FU. Data represent mean ± S.D. (n=3, ^** p < 0.01, ^**** p < 0.0001, ns; not significant). B) Dose‐response curves after 3 days of treatment with 5‐FU, Docetaxel, and Oxaliplatin under different conditions for pGC‐intestinal and pGC‐diffuse. Representative viability curves were generated from the CCK‐8 assay. The IC₅₀ values for each drug are described in Table 1. C) Assessment of the efficacy of the 5‐FU and Oxaliplatin combination regime in vivo and (D(i)) pGCs model. D(ii)) Two concentration combinations for 5‐FU and Oxaliplatin combination therapy. The error bars represent the S.D. (n=3, ^** p < 0.01, ^*** p < 0.001 ^**** p < 0.0001). E(i)) Immunofluorescence staining images of Annexun V (red) and DAPI (blue) in pGC‐intestinal with or without drug. Scale bar: 50 µm. E(ii)) Quantifications of fluorescence intensity of Annexin V normalized to DAPI. Data represent mean ± S.D. (n=3, ^** p < 0.01, ns; not significant). All measurement data was analysed using the ordinary two‐way ANOVA with Tukey's multiple comparisons test including p‐values.

Figure 3

Identification of 5‐FU response‐related features in pGC with hGaFibro model. A) Schematic of the manufacturing process of pGC co‐culture with hGaFibro model for drug evaluation. B) Immunofluorescence staining images of E‐cadherin (green), Vimentin (red), and DAPI (blue) in pGC‐intestinal cultured in g‐dECM with or without hGaFibro. Scale bar: 100 µm. C) Dose‐response curves after 3 days of treatment with 5‐FU under various conditions of the presence and absence of hGaFibro in g‐dECM. Data represent mean ± S.D. (n=3, ^**** p < 0.0001). D) Volcano plots represent the fold change and P value of up‐regulated (red) and down‐regulated (blue) differentially expressed genes (DEGs) on day 7 after pGC co‐culture with hGaFirbro models versus PDX models. x‐axis: Log₂fold change (FC), Cutoff for Log₂FC is 2. E) Gene set enrichment analysis (GSEA) of transcriptional profiles in pGC with hGaFibro models versus PDX models. E(i)) Enrichment plots of genes in hallmark FOCAL_ADHESION; E(ii)) hallmark_GLYCOLYSIS. (NES; normalized enrichment score, false discovery rate (FDR) q‐value <0.05). F) Heatmap showing the EMT‐related genes (PT; patient tissues). G(i)) Immunofluorescence staining images of E‐cadherin (green), Vimentin (red), and DAPI (blue) in pGC‐intestinal cultured in g‐dECM with or without hGaFibro. Scale bar: 50 µm. G(ii)) Quantifications of fluorescence intensity of E‐cadherin and Vimentin to normalized of DAPI. Data represent mean ± S.D. (n=3, ^* p < 0.05, ns; not significant). All measurement data was analyzed using the ordinary two‐way ANOVA with Tukey's multiple comparisons test including p‐values.

Figure 4

Comprehensive gene expression profiles associated with responsiveness to chemotherapy in pGC with hGaFibro models. A) Heatmap showing 20 drug resistance‐related genes (PT; patient tissues). B) Bar plots showing the most enriched KEGG pathways in the (i) down‐regulated genes in PDX tumor comparing to patient tumor and (ii) up‐regulated genes in pGC with hGaFibro comparing to PDX tumor. C) GSEA of the pGC with hGaFibro models versus PDX models. The pGC with hGaFibro models show Notch, Wnt, EMT, and Rho GTPase signaling pathways were enriched (NES; normalized enrichment score). D) Identification of significantly altered gene ontology (biological processes, cellular component, and molecular function) by GSEA (q‐value < 0.05) in the pGC with hGaFirbro models. E) Protein‐protein interaction (PPI) enrichment analysis utilizing the STRING network for the 469 DEGs exhibiting upregulation in the pGC with hGaFribro model. Enrichment P‐value are corrected for multiple testing using the method of Benjamini and Hochberg.

Figure 5

Investigation of responsiveness to 5‐FU and oxaliplatin‐based chemotherapy in a pGC‐biopsy tissue model. A) Hematoxylin & Eosin (H&E) staining of patient‐derived gastric tumor tissue. Scale bar: 50 µm B) Analysis of viability, culture suitability, and the morphology of pGC‐biopsy tissues in g‐dECM and Matrigel using live/dead staining. Scale bars: 200 µm. C) Immunofluorescence staining images of EpCAM (green), α‐SMA (red), and DAPI (blue) at day 7. Scale bars: 50 µm. D) Comparison of pGC‐biopsy tissue proliferation rates according to material type for 14 days. The error bars represent the S.D. (n=3, ^**** p < 0.0001). E) Evaluation of drug response in pGC‐biopy tissue encapsulated in g‐dECM and Matrigel treated with various concentrations of (i) 5‐FU and (ii) oxaliplatin, respectively. Data represent mean ± S.D. (n=3, ^*** p < 0.001, ^**** p < 0.0001, ns; not significant). F) Summary of a model for rapid drug efficacy evaluation within 2 weeks using patient‐derived tumor tissue. All measurement data was analyzed using the ordinary two‐way ANOVA with Tukey's multiple comparisons test including p‐values.