We have identified a precursor that differentiates into granulocytes in vitro and in vivo yet belongs to the monocytic lineage. We have termed these cells monocyte-like precursors of granulocytes (MLPGs). Under steady state conditions, MLPGs were absent in the spleen and barely detectable in the bone marrow (BM). In contrast, these cells significantly expanded in tumor-bearing mice and differentiated to polymorphonuclear myeloid-derived suppressor cells (PMN-MDSCs). Selective depletion of monocytic cells had no effect on the number of granulocytes in naive mice but decreased the population of PMN-MDSCs in tumor-bearing mice by 50%. The expansion of MLPGs was found to be controlled by the down-regulation of Rb1, but not IRF8, which is known to regulate the expansion of PMN-MDSCs from classic granulocyte precursors. In cancer patients, putative MLPGs were found within the population of CXCR1+CD15−CD14+HLA-DR−/lo monocytic cells. These findings describe a mechanism of abnormal myelopoiesis in cancer and suggest potential new approaches for selective targeting of MDSCs.

Current screening methods for prostate cancer (PCa) result in a large number of false positives making it difficult for clinicians to assess disease status, thus warranting advancements in screening and early detection methods. The goal of this study was to design a liquid biopsy test that uses flow cytometry–based immunophenotyping and artificial neural network (ANN) analysis to detect PCa. Numerous myeloid and lymphoid cell populations, including myeloid-derived suppressor cells, were measured from 156 patients with PCa, 123 with benign prostatic hyperplasia (BPH), and 99 male healthy donor (HD) controls. Using pattern recognition neural network (PRNN) analysis, a type of ANN, PCa detection compared against HD resulted in 96.6% sensitivity, 87.5% specificity, and an area under the curve (AUC) value of 0.97. Detecting patients with higher risk disease (⩾Gleason 7) against lower risk disease (BPH/Gleason 6) resulted in 92.0% sensitivity, 42.7% specificity, and an AUC of 0.72. This study suggests that analyzing flow cytometry immunophenotyping data with PRNNs may prove to be a useful tool to improve PCa detection and reduce the number of unnecessary prostate biopsies performed each year.

Prostate cancer (PCa) screening and detection relies heavily upon prostate-specific antigen (PSA) testing, but PSA testing has a high rate of false positives, leading to increased risks for overdiagnosis and overtreatment; thus, additional blood-based biomarkers for PCa detection are needed. Flow cytometry-based immunophenotyping of peripheral blood is an accessible and noninvasive technology, but as more parameters are included, new computational methods must be developed for the efficient analysis and utilization of these large datasets for clinical applications. Machine learning algorithms, specifically pattern recognition neural networks (PRNNs), have the potential to assist in these types of analyses, but the flow cytometry data need to be transformed into a usable input format. The goal of this study was to use our newly developed “hypervoxelation of cytometry events” computational technique, or HyperVOX, to transform flow cytometry data into a useable format for input into a series of PRNNs to detect PCa of all Gleason scores (GS) from circulating immune cells. We used standard multiparametric flow cytometry techniques to measure 16 different myeloid and lymphoid cell populations found in the peripheral blood of 156 biopsy-confirmed PCa (GS6 n = 59, GS7 n = 68, GS8 n = 12, GS9 n = 16, and GS10 n = 1; median age = 68 ± 8.7 years) along with 99 male healthy donors (HD) (median age = 53 ± 8.5 years). Flow cytometry data were then transformed using HyperVOX in order to create hypervoxels that can be used as the common feature across all samples. Briefly, each channel was used as an axis in a multidimensional space and divided into four segments, with each event being defined by its location within each segment of each axis. The resulting count of events that fall within each hypervoxel for each sample is then used as the input for the PRNN. With this, a screening-type assay was developed to detect PCa compared against HD. PRNNs were trained using raw flow cytometry data processed using HyperVOX from 97 PCa patients and 67 HD controls. Predictions were evaluated using the performance of the trained PRNNs on 59 PCa patients and 32 HD that were not used for PRNN training (holdout test set). The PRNN classified 28 out of 32 HD and 57 out of 59 PCa samples correctly, resulting in a sensitivity of 96.6% (95% CI, 88.3–99.6), specificity of 87.5% (95% CI, 71.0–96.5), positive predictive value (PPV) of 93.4% (95% CI, 85.1–98.2), negative predictive value (NPV) of 93.3% (95% CI, 78.1–98.2), and an AUC of 0.9656 (95% CI, 0.9202–1). Upon Gleason score stratification, the NN classified 27 out of 28 GS6, 18 out of 19 GS7, and 11 out of 11 >GS7 samples correctly. In a clinical setting, this technology would improve PCa detection and allow clinicians to have a more informed decision when recommending their patients for a prostate biopsy procedure and subsequent medical interventions to help reduce overdiagnosis and overtreatment. Citation Format: George A. Dominguez, John Roop, Alexander Polo, Anthony Campisi, Dmitry I. Gabrilovich, Amit Kumar. Using pattern recognition neural networks to detect prostate cancer: A new method to analyze flow cytometry-based immunophenotyping using machine learning [abstract]. In: Proceedings of the AACR Special Conference on Advances in Liquid Biopsies; Jan 13-16, 2020; Miami, FL. Philadelphia (PA): AACR; Clin Cancer Res 2020;26(11_Suppl):Abstract nr B50.

BAP1 is a ubiquitin hydrolase whose deubiquitinase activity is mediated by polycomb group-like protein ASXL2. Cancer-related mutations/deletions of BAP1 lead to loss-of-function either by directly targeting the catalytic (UCH) or ULD domains of BAP1, the latter disrupts binding to ASXL2, an obligate partner for BAP1 enzymatic activity. However, the biochemical and biophysical properties of the domains involved in forming the enzymatically active complex are unknown. Here we investigate the molecular dynamics, kinetics and stoichiometry of these interactions. We demonstrate that the BAP1 and ASXL2 domain/proteins or protein complexes produced in either bacteria or baculovirus are structurally and functionally active. The interaction between BAP1 and ASXL2 is direct, specific, and stable to in vitro biochemical and biophysical manipulations as detected by isothermal titration calorimetry, GST association, and optical biosensor assays. Association of the ASXL2-AB box greatly stimulates BAP1 deubiquitinase activity. A stable ternary complex can be formed comprised of the BAP1-UCH, BAP1-ULD, and ASXL2-AB domains. Binding of the BAP1-ULD domain to the ASXL2-AB box is rapid, with fast association and slow dissociation rates. Stoichiometric analysis revealed that one molecule of the ULD domain directly interacts with one molecule of the AB Box. Real-time kinetics analysis of ULD/AB protein complex to the UCH domain of BAP1, based on SPR, indicated that formation of the ULD/AB complex with the UCH domain is a single-step event with fast association and slow dissociation rates. These structural and dynamic parameters implicate the possibility for future small-molecule approaches to reactivate latent wild-type UCH activity in BAP-mutant malignancies.

<p>S3. Domain architecture of human BAP1 and ASXL2 and the proteins/domains used in this study</p>