Generative Adversarial Networks Accurately Reconstruct Pan-Cancer Histology from Pathologic, Genomic, and Radiographic Latent Features.

Artificial intelligence models have been increasingly used in the analysis of tumor histology to perform tasks ranging from routine classification to identification of novel molecular features. These approaches distill cancer histologic images into high-level features which are used in predictions, but understanding the biologic meaning of such features remains challenging. We present and validate a custom generative adversarial network - HistoXGAN - capable of reconstructing representative histology using feature vectors produced by common feature extractors. We evaluate HistoXGAN across 29 cancer subtypes and demonstrate that reconstructed images retain information regarding tumor grade, histologic subtype, and gene expression patterns. We leverage HistoXGAN to illustrate the underlying histologic features for deep learning models for actionable mutations, identify model reliance on histologic batch effect in predictions, and demonstrate accurate reconstruction of tumor histology from radiographic imaging for a 'virtual biopsy'.

Suppression of tumor cell lactate-generating signaling pathways eradicates murine PTEN/p53-deficient aggressive-variant prostate cancer via macrophage phagocytosis.

Purpose: PTEN loss-of-function/PI3K pathway hyperactivation occurs in ∼50% of metastatic, castrate-resistant prostate cancer patients, resulting in poor therapeutic outcomes and resistance to immune checkpoint inhibitors across multiple malignancies. Our prior studies in prostate-specific PTEN/p53-deleted genetically engineered mice (Pb-Cre;PTEN fl/fl Trp53 fl/fl GEM) with aggressive-variant prostate cancer (AVPC) demonstrated feedback Wnt/ß-catenin signaling activation in 40% mice resistant to androgen deprivation therapy (ADT)/PI3K inhibitor (PI3Ki)/PD-1 antibody (aPD-1) combination, resulting in restoration of lactate cross-talk between tumor-cells and tumor-associated macrophages (TAM), histone lactylation (H3K18lac) and phagocytic suppression within TAM. Here, we targeted immunometabolic mechanism(s) of resistance to ADT/PI3Ki/aPD-1 combination, with the goal of durable tumor control in PTEN/p53-deficient PC. Experimental design: Pb-Cre;PTEN fl/fl Trp53 fl/fl GEM were treated with either ADT (degarelix), PI3Ki (copanlisib), aPD-1, MEK inhibitor (trametinib) or Porcupine inhibitor (LGK 974) as single agents or their combinations. MRI was used to monitor tumor kinetics and immune/proteomic profiling/ ex vivo co-culture mechanistic studies were performed on prostate tumors or established GEM-derived cell lines. Results: We tested whether Wnt/ß-catenin pathway inhibition with LGK 974 addition to degarelix/copanlisib/aPD-1 therapy enhances tumor control in GEM, and observed de novo resistance due to feedback activation of MEK signaling. Based on our observation that degarelix/aPD-1 treatment resulted in partial inhibition of MEK signaling, we substituted trametinib for degarelix/aPD-1 treatment, and observed a durable tumor growth control of PI3Ki/MEKi/PORCNi in 100% mice via H3K18lac suppression and complete TAM activation within TME. Conclusions: Abrogation of lactate-mediated cross-talk between cancer cells and TAM results in durable ADT-independent tumor control in PTEN/p53-deficient AVPC, and warrants further investigation in clinical trials. STATEMENT OF TRANSLATIONAL RELEVANCE: PTEN loss-of-function occurs in ∼50% of mCRPC patients, and associated with poor prognosis, and immune checkpoint inhibitor resistance across multiple malignancies. Our prior studies have demonstrated that ADT/PI3Ki/PD-1 triplet combination therapy controls PTEN/p53-deficient PC in 60% of mice via enhancement of TAM phagocytosis. Here, we discovered that resistance to ADT/PI3K/PD-1 therapy occurred via restoration of lactate production via feedback Wnt/MEK signaling following treatment with PI3Ki, resulting in inhibition of TAM phagocytosis. Critically, co-targeting of PI3K/MEK/Wnt signaling pathways using an intermittent dosing schedule of corresponding targeted agents resulted in complete tumor control and significantly prolonged survival without significant long-term toxicity. Collectively, our findings provide "proof-of-concept" that targeting lactate as a macrophage phagocytic checkpoint controls growth of murine PTEN/p53-deficient PC and warrant further investigation in AVPC clinical trials.

Suppression of Tumor Cell Lactate-generating Signaling Pathways Eradicates Murine PTEN/p53-deficient Aggressive-variant Prostate Cancer via Macrophage Phagocytosis.

PURPOSE: Phosphatase and tensin homolog (PTEN) loss-of-function/PI3K pathway hyperactivation is associated with poor therapeutic outcomes and immune checkpoint inhibitor resistance across multiple malignancies. Our prior studies in Pb-Cre;PTENfl/flTrp53fl/fl genetically engineered mice (GEM) with aggressive-variant prostate cancer (AVPC) demonstrated tumor growth control in 60% mice following androgen deprivation therapy/PI3K inhibitor (PI3Ki)/programmed cell death protein 1 (PD-1) antibody combination, via abrogating lactate cross-talk between cancer cells and tumor-associated macrophages (TAM), and suppression of histone lactylation (H3K18lac)/phagocytic activation within TAM. Here, we targeted immunometabolic mechanism(s) of PI3Ki resistance, with the goal of durable tumor control in AVPC. EXPERIMENTAL DESIGN: Pb-Cre;PTENfl/flTrp53fl/fl GEM were treated with PI3Ki (copanlisib), MEK inhibitor (trametinib) or Porcupine inhibitor (LGK'974) singly or their combinations. MRI was used to monitor tumor kinetics and immune/proteomic profiling/ex vivo coculture mechanistic studies were performed on GEM tumors or corresponding tumor-derived cell lines. RESULTS: Given our proteomic profiling showing persistent MEK signaling within tumors of PI3Ki-resistant GEM, we tested whether addition of trametinib to copanlisib enhances tumor control in GEM, and we observed 80% overall response rate via additive suppression of lactate within TME and H3K18lac within TAM, relative to copanlisib (37.5%) monotherapy. The 20% resistant mice demonstrated feedback Wnt/ß-catenin activation, resulting in restoration of lactate secretion by tumor cells and H3K18lac within TAM. Cotargeting Wnt/ß-catenin signaling with LGK'974 in combination with PI3Ki/MEKi, demonstrated durable tumor control in 100% mice via H3K18lac suppression and complete TAM activation. CONCLUSIONS: Abrogation of lactate-mediated cross-talk between cancer cells and TAM results in durable ADT-independent tumor control in PTEN/p53-deficient AVPC, and warrants further investigation in clinical trials.

Reversal of Lactate and PD-1-mediated Macrophage Immunosuppression Controls Growth of PTEN/p53-deficient Prostate Cancer.

PURPOSE: Phosphatase and tensin homolog (PTEN) loss of function occurs in approximately 50% of patients with metastatic castrate-resistant prostate cancer (mCRPC), and is associated with poor prognosis and responsiveness to standard-of-care therapies and immune checkpoint inhibitors. While PTEN loss of function hyperactivates PI3K signaling, combinatorial PI3K/AKT pathway and androgen deprivation therapy (ADT) has demonstrated limited anticancer efficacy in clinical trials. Here, we aimed to elucidate mechanism(s) of resistance to ADT/PI3K-AKT axis blockade, and to develop rational combinatorial strategies to effectively treat this molecular subset of mCRPC. EXPERIMENTAL DESIGN: Prostate-specific PTEN/p53-deficient genetically engineered mice (GEM) with established 150-200 mm3 tumors, as assessed by ultrasound, were treated with either ADT (degarelix), PI3K inhibitor (copanlisib), or anti-PD-1 antibody (aPD-1), as single agents or their combinations, and tumors were monitored by MRI and harvested for immune, transcriptomic, and proteomic profiling, or ex vivo co-culture studies. Single-cell RNA sequencing on human mCRPC samples was performed using 10X Genomics platform. RESULTS: Coclinical trials in PTEN/p53-deficient GEM revealed that recruitment of PD-1-expressing tumor-associated macrophages (TAM) thwarts ADT/PI3Ki combination-induced tumor control. The addition of aPD-1 to ADT/PI3Ki combination led to TAM-dependent approximately 3-fold increase in anticancer responses. Mechanistically, decreased lactate production from PI3Ki-treated tumor cells suppressed histone lactylation within TAM, resulting in their anticancer phagocytic activation, which was augmented by ADT/aPD-1 treatment and abrogated by feedback activation of Wnt/ß-catenin pathway. Single-cell RNA-sequencing analysis in mCRPC patient biopsy samples revealed a direct correlation between high glycolytic activity and TAM phagocytosis suppression. CONCLUSIONS: Immunometabolic strategies that reverse lactate and PD-1-mediated TAM immunosuppression, in combination with ADT, warrant further investigation in patients with PTEN-deficient mCRPC.

Deep learning generates synthetic cancer histology for explainability and education.

Artificial intelligence methods including deep neural networks (DNN) can provide rapid molecular classification of tumors from routine histology with accuracy that matches or exceeds human pathologists. Discerning how neural networks make their predictions remains a significant challenge, but explainability tools help provide insights into what models have learned when corresponding histologic features are poorly defined. Here, we present a method for improving explainability of DNN models using synthetic histology generated by a conditional generative adversarial network (cGAN). We show that cGANs generate high-quality synthetic histology images that can be leveraged for explaining DNN models trained to classify molecularly-subtyped tumors, exposing histologic features associated with molecular state. Fine-tuning synthetic histology through class and layer blending illustrates nuanced morphologic differences between tumor subtypes. Finally, we demonstrate the use of synthetic histology for augmenting pathologist-in-training education, showing that these intuitive visualizations can reinforce and improve understanding of histologic manifestations of tumor biology.

Cabozantinib Unlocks Efficient In Vivo Targeted Delivery of Neutrophil-Loaded Nanoparticles into Murine Prostate Tumors.

A major barrier to the successful application of nanotechnology for cancer treatment is the suboptimal delivery of therapeutic payloads to metastatic tumor deposits. We previously discovered that cabozantinib, a tyrosine kinase inhibitor, triggers neutrophil-mediated anticancer innate immunity, resulting in tumor regression in an aggressive PTEN/p53-deficient genetically engineered murine model of advanced prostate cancer. Here, we specifically investigated the potential of cabozantinib-induced neutrophil activation and recruitment to enhance delivery of BSA-coated polymeric nanoparticles (BSA-NPs) into murine PTEN/p53-deficient prostate tumors. On the basis of the observation that BSA coating of NPs enhanced association and internalization by activated neutrophils by approximately 6-fold in vitro, relative to uncoated NPs, we systemically injected BSA-coated, dye-loaded NPs into prostate-specific PTEN/p53-deficient mice that were pretreated with cabozantinib. Flow cytometric analysis revealed an approximately 4-fold increase of neutrophil-associated BSA-NPs and an approximately 32-fold increase in mean fluorescent dye uptake following 3 days of cabozantinib/BSA-NP administration, relative to BSA-NP alone. Strikingly, neutrophil depletion with Ly6G antibody abolished dye-loaded BSA-NP accumulation within tumors to baseline levels, demonstrating targeted neutrophil-mediated intratumoral NP delivery. Furthermore, we observed an approximately 13-fold decrease in accumulation of BSA-NPs in the liver, relative to uncoated NPs, post-cabozantinib treatment, suggesting that BSA coating of NPs can significantly enhance cabozantinib-induced, neutrophil-mediated targeted intratumoral drug delivery, while mitigating off-target toxicity. Collectively, we demonstrate a novel targeted nano-immunotherapeutic strategy for enhanced intratumoral delivery of BSA-NPs, with translational potential to significantly augment therapeutic indices of cancer medicines, thereby overcoming current pharmacologic barriers commonly encountered in preclinical/early-phase drug development.