Fig 2: Transfer learning from TMAs to WSIs of prostate cancer tissue.Additional examples to the ones presented in Fig. 4. Example of H&E (left image), virtual IHC (middle image), and real IHC (right image) staining for NKX3.1 (top) and AR (bottom) of prostate cancer tissue WSIs. Blue-framed zoomed-in regions display accurate staining pattern. Red-framed zoomed-in regions display examples of virtual staining mispredictions.

Fig 3: Visual quality assessment of virtually stained IHC images of the EMPaCT prostate cancer TMA.(A) Example virtual TMA cores across all six markers (left column) and selected zoomed in regions (middle column) that highlight accurate staining patterns. Real reference IHC images for each marker are given on the right column. We observed that AR+ and NKX3.1+ cells exhibited correct distribution in the luminal epithelial compartment of the prostatic glands and nuclear localization. Furthermore, a few NKX3.1+ cells in stromal regions (possibly stroma-invading tumor cells) were correctly predicted. Similarities in specific, matched areas between virtual and real IHC images were mainly assessed for staining pattern and overall intensity levels: we observed that the expression of markers indicative of tumor-specific molecular profile, such as loss of TP53 and ERG overexpression, did not largely deviate between virtual and real images at a TMA core level, which would be crucial for diagnostic applicability.(B) Same as (A) but highlighting regions with inaccurate or inconclusive staining. We observed non-specific signal in extra-cellular-matrix/stroma regions (NKX3.1, p53, ERG), occasional false nuclear expression (CD44), and systematic lack of recognition of CD146+ vascular structures.

Fig 4: Generation of AR and FOXA1 double-positive UGS cells. (A) The immunofluorescence results of AR after differentiation with different conditions. Scale bar = 50 μm (CTRL: control). (B) Statistical results of AR-positive cells in (A) (n = 3). (C) The immunofluorescence results of FOXA1 after differentiation with different conditions. Scale bar = 50 μm. (D) Statistical results of FOXA1-positive cells in (C) (n = 3). (E) Changes in the mRNA levels of the prostatic markers SOX9, P63 (TP63), and CK5 (KRT5) after differentiation with different conditions (n = 4). (F-G) The immunofluorescence results (F) and mRNA levels (G, n = 4) of NKX3-1 after differentiation. Scale bar = 50 μm. ns, not significant (p > 0.05), *p < 0.05, **p < 0.01, ***p < 0.001

Fig 5: The formation of structural prostate organoids through 3D culture of ESC-derived UGS cells. (A) Illustration of the generation of prostatic organoids from human ESCs. (B) Brightfield images of organoids at week 1, 2, 3, and 5. Scale bar, 50 μm. (C) Diameter statistical graph of organoids after 3D cultivation for the first 20 days. (D) DAPI immunofluorescence results of organoids on week 3 and 5. Scale bar, 50 μm. (E) Immunofluorescence results of NKX3-1, KI67, FOXA1, and AR on week 3 of organoids cultivation. Scale bar, 50 μm. (F-I) H&E staining images (F), immunofluorescence results of E-Cadherin (G), P63 and CK18 (H), and CK5 and CK18 (I) of organoids at week 4. Scale bar, 50 μm. (J) Flow cytometry results of CK18 of organoids. 3D cultured organoids for 9 days were used (ISO: isotype control)