Single-cell and spatial profiling identify three response trajectories to pembrolizumab and radiation therapy in triple negative breast cancer.

Strategies are needed to better identify patients that will benefit from immunotherapy alone or who may require additional therapies like chemotherapy or radiotherapy to overcome resistance. Here we employ single-cell transcriptomics and spatial proteomics to profile triple negative breast cancer biopsies taken at baseline, after one cycle of pembrolizumab, and after a second cycle of pembrolizumab given with radiotherapy. Non-responders lack immune infiltrate before and after therapy and exhibit minimal therapy-induced immune changes. Responding tumors form two groups that are distinguishable by a classifier prior to therapy, with one showing high major histocompatibility complex expression, evidence of tertiary lymphoid structures, and displaying anti-tumor immunity before treatment. The other responder group resembles non-responders at baseline and mounts a maximal immune response, characterized by cytotoxic T cell and antigen presenting myeloid cell interactions, only after combination therapy, which is mirrored in a murine model of triple negative breast cancer.

The molecular consequences of androgen activity in the human breast.

Estrogen and progesterone have been extensively studied in the mammary gland, but the molecular effects of androgen remain largely unexplored. Transgender men are recorded as female at birth but identify as male and may undergo gender-affirming androgen therapy to align their physical characteristics and gender identity. Here we perform single-cell-resolution transcriptome, chromatin, and spatial profiling of breast tissues from transgender men following androgen therapy. We find canonical androgen receptor gene targets are upregulated in cells expressing the androgen receptor and that paracrine signaling likely drives sex-relevant androgenic effects in other cell types. We also observe involution of the epithelium and a spatial reconfiguration of immune, fibroblast, and vascular cells, and identify a gene regulatory network associated with androgen-induced fat loss. This work elucidates the molecular consequences of androgen activity in the human breast at single-cell resolution.

Trends and Determinants of Self-reported Aspirin Use Among Patients With Diabetes Stratified by Presence and Risk of Cardiovascular Diseases: A Repeated Pan-Canadian Cross-sectional Study.

OBJECTIVES: Our aim in this study was to quantify the prevalence over time and identify determinants of acetylsalicylic acid (ASA) use in patients with diabetes with and without cardiovascular disease (CVD) in a representative Canadian sample from 2005 to 2014, and to determine whether the use of ASA among patients with diabetes changed after the Diabetes Canada clinical practice guidelines updates. METHODS: Data from the Canadian Community Health Survey were used. Respondents who were at least 35 years of age and diagnosed with diabetes---not during pregnancy---were included and categorized into secondary prevention (previous heart disease or stroke) or primary prevention (high or low CVD risk) groups. A stratified and weighted multivariable logistic regression model was used to quantify ASA use and identify determinants of use. RESULTS: Our sample consisted of 15,100 respondents with diabetes (weighted sample of ∼2,429,900). Approximately 70% and 50% of Canadians with diabetes used ASA for secondary and primary prevention, respectively. Overall, the trend of ASA use was stable over the study period in both the secondary and the primary prevention groups. This trend did not change after the clinical practice guidelines update in 2008. Having a regular doctor and older age were associated with increased use of ASA. Other significant determinants independently associated with ASA use included income, body mass index, smoking, immigration status, gender and chronic diseases. CONCLUSIONS: Among patients with diabetes in Canada, ASA appears to be underutilized in secondary prevention and high-risk primary prevention populations. Future research should address whether regular use of ASA is associated with clinical outcomes among patients with diabetes.

An N-Cadherin 2 expressing epithelial cell subpopulation predicts response to surgery, chemotherapy and immunotherapy in bladder cancer.

Neoadjuvant chemotherapy (NAC) prior to surgery and immune checkpoint therapy (ICT) have revolutionized bladder cancer management. However, stratification of patients that would benefit most from these modalities remains a major clinical challenge. Here, we combine single nuclei RNA sequencing with spatial transcriptomics and single-cell resolution spatial proteomic analysis of human bladder cancer to identify an epithelial subpopulation with therapeutic response prediction ability. These cells express Cadherin 12 (CDH12, N-Cadherin 2), catenins, and other epithelial markers. CDH12-enriched tumors define patients with poor outcome following surgery with or without NAC. In contrast, CDH12-enriched tumors exhibit superior response to ICT. In all settings, patient stratification by tumor CDH12 enrichment offers better prediction of outcome than currently established bladder cancer subtypes. Molecularly, the CDH12 population resembles an undifferentiated state with inherently aggressive biology including chemoresistance, likely mediated through progenitor-like gene expression and fibroblast activation. CDH12-enriched cells express PD-L1 and PD-L2 and co-localize with exhausted T-cells, possibly mediated through CD49a (ITGA1), providing one explanation for ICT efficacy in these tumors. Altogether, this study describes a cancer cell population with an intriguing diametric response to major bladder cancer therapeutics. Importantly, it also provides a compelling framework for designing biomarker-guided clinical trials.

Convolutional neural networks can accurately distinguish four histologic growth patterns of lung adenocarcinoma in digital slides.

During the diagnostic workup of lung adenocarcinomas (LAC), pathologists evaluate distinct histological tumor growth patterns. The percentage of each pattern on multiple slides bears prognostic significance. To assist with the quantification of growth patterns, we constructed a pipeline equipped with a convolutional neural network (CNN) and soft-voting as the decision function to recognize solid, micropapillary, acinar, and cribriform growth patterns, and non-tumor areas. Slides of primary LAC were obtained from Cedars-Sinai Medical Center (CSMC), the Military Institute of Medicine in Warsaw and the TCGA portal. Several CNN models trained with 19,924 image tiles extracted from 78 slides (MIMW and CSMC) were evaluated on 128 test slides from the three sites by F1-score and accuracy using manual tumor annotations by pathologist. The best CNN yielded F1-scores of 0.91 (solid), 0.76 (micropapillary), 0.74 (acinar), 0.6 (cribriform), and 0.96 (non-tumor) respectively. The overall accuracy of distinguishing the five tissue classes was 89.24%. Slide-based accuracy in the CSMC set (88.5%) was significantly better (p < 2.3E-4) than the accuracy in the MIMW (84.2%) and TCGA (84%) sets due to superior slide quality. Our model can work side-by-side with a pathologist to accurately quantify the percentages of growth patterns in tumors with mixed LAC patterns.

A novel machine learning approach reveals latent vascular phenotypes predictive of renal cancer outcome.

Gene expression signatures are commonly used as predictive biomarkers, but do not capture structural features within the tissue architecture. Here we apply a 2-step machine learning framework for quantitative imaging of tumor vasculature to derive a spatially informed, prognostic gene signature. The trained algorithms classify endothelial cells and generate a vascular area mask (VAM) in H&E micrographs of clear cell renal cell carcinoma (ccRCC) cases from The Cancer Genome Atlas (TCGA). Quantification of VAMs led to the discovery of 9 vascular features (9VF) that predicted disease-free-survival in a discovery cohort (n = 64, HR = 2.3). Correlation analysis and information gain identified a 14 gene expression signature related to the 9VF's. Two generalized linear models with elastic net regularization (14VF and 14GT), based on the 14 genes, separated independent cohorts of up to 301 cases into good and poor disease-free survival groups (14VF HR = 2.4, 14GT HR = 3.33). For the first time, we successfully applied digital image analysis and targeted machine learning to develop prognostic, morphology-based, gene expression signatures from the vascular architecture. This novel morphogenomic approach has the potential to improve previous methods for biomarker development.

Machine learning approaches to analyze histological images of tissues from radical prostatectomies.

Computerized evaluation of histological preparations of prostate tissues involves identification of tissue components such as stroma (ST), benign/normal epithelium (BN) and prostate cancer (PCa). Image classification approaches have been developed to identify and classify glandular regions in digital images of prostate tissues; however their success has been limited by difficulties in cellular segmentation and tissue heterogeneity. We hypothesized that utilizing image pixels to generate intensity histograms of hematoxylin (H) and eosin (E) stains deconvoluted from H&E images numerically captures the architectural difference between glands and stroma. In addition, we postulated that joint histograms of local binary patterns and local variance (LBPxVAR) can be used as sensitive textural features to differentiate benign/normal tissue from cancer. Here we utilized a machine learning approach comprising of a support vector machine (SVM) followed by a random forest (RF) classifier to digitally stratify prostate tissue into ST, BN and PCa areas. Two pathologists manually annotated 210 images of low- and high-grade tumors from slides that were selected from 20 radical prostatectomies and digitized at high-resolution. The 210 images were split into the training (n=19) and test (n=191) sets. Local intensity histograms of H and E were used to train a SVM classifier to separate ST from epithelium (BN+PCa). The performance of SVM prediction was evaluated by measuring the accuracy of delineating epithelial areas. The Jaccard J=59.5 ± 14.6 and Rand Ri=62.0 ± 7.5 indices reported a significantly better prediction when compared to a reference method (Chen et al., Clinical Proteomics 2013, 10:18) based on the averaged values from the test set. To distinguish BN from PCa we trained a RF classifier with LBPxVAR and local intensity histograms and obtained separate performance values for BN and PCa: JBN=35.2 ± 24.9, OBN=49.6 ± 32, JPCa=49.5 ± 18.5, OPCa=72.7 ± 14.8 and Ri=60.6 ± 7.6 in the test set. Our pixel-based classification does not rely on the detection of lumens, which is prone to errors and has limitations in high-grade cancers and has the potential to aid in clinical studies in which the quantification of tumor content is necessary to prognosticate the course of the disease. The image data set with ground truth annotation is available for public use to stimulate further research in this area.