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: Differentiation of NKX3-1, AR, and FOXA1 triple-positive UGS cells. (A) Schematic diagram of the UGS differentiation from hindgut (HG: hindgut cell, UGS: Urogenital sinus cell, Doxy: Doxycycline). (B-C) Western blot results (B) (Full-length blots/gels are presented in Supplementary Fig. 4A) and immunofluorescence images (C) of AR protein in cells treated with DHT, R1881, and without androgen induction as control during UGS differentiation. The molecular weight of the protein was labeled at right. Scale bar, 50 μm (CTRL: control). (D-F) Western blot results (D) (Full-length blots/gels are presented in Supplementary Fig. 4B) and immunofluorescence images (E-F) of AR, FOXA1 and NKX3-1 proteins in cells treated with (E) or without (F) Doxy during UGS differentiation. The molecular weight of the protein was labeled at right. Scale bar, 50 μm. (G) Statistical analysis of the percentages of positive cells for NKX3-1, AR, and FOXA1 with or without Doxy induction during UGS differentiation (n = 3). (H) Relative mRNA expression levels of NKX3-1, AR, and FOXA1 with or without Doxy induction during UGS differentiation (n = 3). (I) Changes in relative mRNA expression levels of markers at various stages throughout the differentiation process from ESCs to UGS (n = 3) (ES: human embryonic stem cell, DE: definitive endoderm cell). (J) Immunofluorescence results of CK5, CK8/18, and P63 in UGS cells. Scale bar, 50 μm. (K-L) Immunofluorescence images (K) and relative mRNA expression level (L) of NKX3-1 after adding Doxy induction for 6 days, for 3 days’ treatment followed by 3 days’ withdrawal, and without Doxy induction for 6 days during UGS differentiation (n = 3). Scale bar, 50 μm. ns, not significant (p > 0.05), *p < 0.05, **p < 0.01, ***p < 0.001