Identification of a 5-gene signature panel for the prediction of prostate cancer progression.

BACKGROUND: Despite nearly 100% 5-year survival for localised prostate cancer, the survival rate for metastatic prostate cancer significantly declines to 32%. Thus, it is crucial to identify molecular indicators that reflect the progression from localised disease to metastatic prostate cancer. METHODS: To search for molecular indicators associated with prostate cancer metastasis, we performed proteomic analysis of rapid autopsy tissue samples from metastatic prostate cancer (N = 8) and localised prostate cancer (N = 2). Then, we utilised multiple independent, publicly available prostate cancer patient datasets to select candidates that also correlate with worse prostate cancer clinical prognosis. RESULTS: We identified 154 proteins with increased expressions in metastases relative to localised prostate cancer through proteomic analysis. From the subset of these candidates that correlate with prostate cancer recurrence (N = 28) and shorter disease-free survival (N = 37), we identified a 5-gene signature panel with improved performance in predicting worse clinical prognosis relative to individual candidates. CONCLUSIONS: Our study presents a new 5-gene signature panel that is associated with worse clinical prognosis and is elevated in prostate cancer metastasis on both protein and mRNA levels. Our 5-gene signature panel represents a potential modality for the prediction of prostate cancer progression towards the onset of metastasis.

Alterations of the chemical profile of cholesterol in cancer tissue as traced with ToF-SIMS.

Cancer has become one of the leading causes of death, with approximately ten million people worldwide dying from cancer each year. In most cases, cancer spreads to remote organs and develops a resistance to therapy. To reduce the deadly impact of cancer, novel targets for markers for early detection are necessary. Given the notable influence of rapid chemical turnover on isotope effects, the heightened turnover rate of cholesterol in cancer offers a promising way for investigation. Time-of-Flight Secondary Ion Mass Spectrometry (ToF-SIMS) offers a valuable tool of tracking cholesterol dynamics. Consequently, we employed ToF-SIMS to assess cholesterol alterations, aiming to uncover potential diagnostic vulnerabilities stemming from heightened cholesterol synthesis. Our study explored the chemical profile of cholesterol influenced by cancer cell metabolism using mammary glands from mice, both with and without cancer. Results revealed a significant increase in the fractional abundance of fragment cholesterol peaks (C27H45+) in cancerous tissues, indicating dysregulated cholesterol metabolism within cancer cells. This suggests potential structural weaknesses or incomplete synthesis. Further investigation into carbon isotope incorporation suggests that the isotopic patterns might be due to the integration of heavier carbon isotopes, although these patterns could be affected by other isotopic influences. Nevertheless, understanding isotope effect of cholesterol profiles have the potential to advance our understanding of cancer biology and improve diagnostic approaches.

Polyploid cancer cells reveal signatures of chemotherapy resistance.

Therapeutic resistance in cancer significantly contributes to mortality, with many patients eventually experiencing recurrence after initial treatment responses. Recent studies have identified therapy-resistant large polyploid cancer cells in patient tissues, particularly in late-stage prostate cancer, linking them to advanced disease and relapse. Here, we analyzed bone marrow aspirates from 44 advanced prostate cancer patients and found the presence of circulating tumor cells with increased genomic content (CTC-IGC) was significantly associated with poorer progression-free survival. Single cell copy number profiling of CTC-IGC displayed clonal origins with typical CTCs, suggesting complete polyploidization. Induced polyploid cancer cells from PC3 and MDA-MB-231 cell lines treated with docetaxel or cisplatin were examined through single cell DNA sequencing, RNA sequencing, and protein immunofluorescence. Novel RNA and protein markers, including HOMER1, TNFRSF9, and LRP1, were identified as linked to chemotherapy resistance. These markers were also present in a subset of patient CTCs and associated with recurrence in public gene expression data. This study highlights the prognostic significance of large polyploid tumor cells, their role in chemotherapy resistance, and their expression of markers tied to cancer relapse, offering new potential avenues for therapeutic development.

Initial Experience with [177Lu]Lu-PSMA-617 After Regulatory Approval for Metastatic Castration-Resistant Prostate Cancer: Efficacy, Safety, and Outcome Prediction.

[177Lu]Lu-PSMA-617 was approved by the U.S. Food and Drug Administration for patients with prostate-specific membrane antigen (PSMA)-positive metastatic castration-resistant prostate cancer (mCRPC). Since the time of regulatory approval, however, real-world data have been lacking. This study investigated the efficacy, safety, and outcome predictors of [177Lu]Lu-PSMA-617 at a major U.S. academic center. Methods: Patients with mCRPC who received [177Lu]Lu-PSMA-617 at the Johns Hopkins Hospital outside clinical trials were screened for inclusion. Patients who underwent [177Lu]Lu-PSMA-617 and had available outcome data were included in this study. Outcome data included prostate-specific antigen (PSA) response (≥50% decline), PSA progression-free survival (PFS), and overall survival (OS). Toxicity data were evaluated according to the Common Terminology Criteria for Adverse Events version 5.03. The study tested the association of baseline circulating tumor DNA mutational status in homologous recombination repair, PI3K alteration pathway, and aggressive-variant prostate cancer-associated genes with treatment outcome. Baseline PSMA PET/CT images were analyzed using SelectPSMA, an artificial intelligence algorithm, to predict treatment outcome. Associations with the observed treatment outcome were evaluated. Results: All 76 patients with PSMA-positive mCRPC who received [177Lu]Lu-PSMA-617 met the inclusion criteria. A PSA response was achieved in 30 of 74 (41%) patients. The median PSA PFS was 4.1 mo (95% CI, 2.0-6.2 mo), and the median OS was 13.7 mo (95% CI, 11.3-16.1 mo). Anemia of grade 3 or greater, thrombocytopenia, and neutropenia were observed in 9 (12%), 3 (4%), and 1 (1%), respectively, of 76 patients. Transient xerostomia was observed in 23 (28%) patients. The presence of aggressive-variant prostate cancer-associated genes was associated with a shorter PSA PFS (median, 1.3 vs. 6.3 mo; P = 0.040). No other associations were observed between circulating tumor DNA mutational status and treatment outcomes. Eighteen of 71 (25%) patients classified by SelectPSMA as nonresponders had significantly lower rates of PSA response than patients classified as likely responders (6% vs. 51%; P < 0.001), a shorter PSA PFS (median, 1.3 vs. 6.3 mo; P < 0.001), and a shorter OS (median, 6.3 vs. 14.5 mo; P = 0.046). Conclusion: [177Lu]Lu-PSMA-617 offered in a real-world setting after regulatory approval in the United States demonstrated antitumor activity and a favorable toxicity profile. Artificial-intelligence-based analysis of baseline PSMA PET/CT images may improve patient selection. Validation of these findings on larger cohorts is warranted.

Cells in the Polyaneuploid Cancer Cell State are Pro-Metastatic.

There remains a large need for a greater understanding of the metastatic process within the prostate cancer field. Our research aims to understand the adaptive - ergo potentially metastatic - responses of cancer to changing microenvironments. Emerging evidence has implicated a role of the Polyaneuploid Cancer Cell (PACC) state in metastasis, positing the PACC state as capable of conferring metastatic competency. Mounting in vitro evidence supports increased metastatic potential of cells in the PACC state. Additionally, our recent retrospective study of prostate cancer patients revealed that PACC presence in the prostate at the time of radical prostatectomy was predictive of future metastatic progression. To test for a causative relationship between PACC state biology and metastasis, we leveraged a novel method designed for flow-cytometric detection of circulating tumor cells (CTCs) and disseminated tumor cells (DTCs) in subcutaneous, caudal artery, and intracardiac mouse models of metastasis. This approach provides both quantitative and qualitative information about the number and PACC-status of recovered CTCs and DTCs. Collating data from all models, we found that 74% of recovered CTCs and DTCs were in the PACC state. In vivo colonization assays proved PACC populations can regain proliferative capacity at metastatic sites following dormancy. Additional direct and indirect mechanistic in vitro analyses revealed a PACC-specific partial Epithelial-to-Mesenchymal-Transition phenotype and a pro-metastatic secretory profile, together providing preliminary evidence that PACCs are mechanistically linked to metastasis.

Urinary extracellular vesicle-derived miR-126-3p predicts lymph node invasion in patients with high-risk prostate cancer.

To investigate extracellular vesicles (EVs), biomarkers for predicting lymph node invasion (LNI) in patients with high-risk prostate cancer (HRPCa), plasma, and/or urine samples were prospectively collected from 45 patients with prostate cancer (PCa) and five with benign prostatic hyperplasia (BPH). Small RNA sequencing was performed to identify miRNAs in the EVs. All patients with PCa underwent radical prostatectomy and extended pelvic lymph node dissection. Differentially expressed miRNAs were identified in patients with and without pathologically-verified LNI. The candidate miRNAs were validated in low-risk prostate cancer (LRPCa) and BPH. Four miRNA species (e.g., miR-126-3p) and three miRNA species (e.g., miR-27a-3p) were more abundant in urinary and plasma EVs, respectively, of patients with PCa. None of these miRNA species were shared between urinary and plasma EVs. miR-126-3p was significantly more abundant in patients with HR PCa with LNI than in those without (P = 0.018). miR-126-3p was significantly more abundant in the urinary EVs of patients with HRPCa than in those with LRPCa (P = 0.017) and BPH (P = 0.011). In conclusion, urinary EVs-derived miR-126-3p may serve as a good biomarker for predicting LNI in patients with HRPCa.

Genomic Determinants Associated with Modes of Progression and Patterns of Failure in Metachronous Oligometastatic Castration-sensitive Prostate Cancer.

BACKGROUND AND OBJECTIVE: Oligometastatic castration-sensitive prostate cancer (omCSPC) represents an early state in the progression of metastatic disease for which patients experience better outcomes in comparison to those with higher disease burden. Despite the generally more indolent nature, there is still much heterogeneity, with some patients experiencing a more aggressive clinical course unexplained by clinical features alone. Our aim was to investigate correlation of tumor genomics with the mode of progression (MOP) and pattern of failure (POF) following first treatment (metastasis-directed and/or systemic therapy) for omCSPC. METHODS: We performed an international multi-institutional retrospective study of men treated for metachronous omCSPC who underwent tumor next-generation sequencing with at least 1 yr of follow-up after their first treatment. Descriptive MOP and POF results are reported with respect to the presence of genomic alterations in pathways of interest. MOP was defined as class I, long-term control (LTC; no radiographic progression at last follow-up), class II, oligoprogression (1-3 lesions), or class III, polyprogression (≥4 lesions). POF included the location of lesions at first failure. Genomic pathways of interest included TP53, ATM, RB1, BRCA1/2, SPOP, and WNT (APC, CTNNB1, RNF43). Genomic associations with MOP/POF were compared using χ2 tests. Exploratory analyses revealed that the COSMIC mutational signature and differential gene expression were also correlated with MOP/POF. Overall survival (OS) was calculated via the Kaplan-Meier method from the time of first failure. KEY FINDINGS AND CLINICAL IMPLICATIONS: We included 267 patients in our analysis; the majority had either one (47%) or two (30%) metastatic lesions at oligometastasis. The 3-yr OS rate was significantly associated with MOP (71% for polyprogression vs 91% for oligoprogression; p = 0.005). TP53 mutation was associated with a significantly lower LTC rate (27.6% vs 42.3%; p = 0.04) and RB1 mutation was associated with a high rate of polyprogression (50% vs 19.9%; p = 0.022). Regarding POF, bone failure was significantly more common with tumors harboring TP53 mutations (44.8% vs25.9%; p = 0.005) and less common with SPOP mutations (7.1% vs 31.4%; p = 0.007). Visceral failure was more common with tumors harboring either WNT pathway mutations (17.2% vs 6.8%, p = 0.05) or SPOP mutations (17.9% vs 6.3%; p = 0.04). Finally, visceral and bone failures were associated with distinct gene-expression profiles. CONCLUSIONS AND CLINICAL IMPLICATIONS: Tumor genomics provides novel insight into MOP and POF following treatment for metachronous omCSPC. Patients with TP53 and RB1 mutations have a higher likelihood of progression, and TP53, SPOP, and WNT pathway mutations may have a role in metastatic organotropism. PATIENT SUMMARY: We evaluated cancer progression after a first treatment for metastatic prostate cancer with up to five metastases. We found that mutations in certain genes were associated with the location and extent of further metastasis in these patients.

Multiparameter flow cytometric detection and analysis of rare cells in in vivo models of cancer metastasis.

Rapid and reliable circulating tumor cell (CTC) and disseminated tumor cell (DTC) detection are critical for rigorous evaluation of in vivo metastasis models. Clinical data show that each step of the metastatic cascade presents increasing barriers to success, limiting the number of successful metastatic cells to fewer than 1 in 1,500,000,000. As such, it is critical for scientists to employ approaches that allow for the evaluation of metastatic competency at each step of the cascade. Here, we present a flow cytometry-based method that enables swift and simultaneous comparison of both CTCs and DTCs from single animals, enabling evaluation of multiple metastatic steps within a single model system. We present the necessary gating strategy and optimized sample preparation conditions necessary to capture CTCs and DTCs using this approach. We also provide proof-of-concept experiments emphasizing the appropriate limits of detection of these conditions. Most importantly, we successfully recover CTCs and DTCs from murine blood and bone marrow. In Supplemental materials, we expand the applicability of our method to lung tissue and exemplify a potential multi-plexing strategy to further characterize recovered CTCs and DTCs. This approach to multiparameter flow cytometric detection and analysis of rare cells in in vivo models of metastasis is reproducible, high throughput, broadly applicable, and highly adaptable to a wide range of scientific inquiries. Most notably, it simplifies the recovery and analysis of CTCs and DTCs from the same animal, allowing for a rapid first look at the comparative metastatic competency of various model systems throughout multiple steps of the metastatic cascade.

Lung adenocarcinomas without driver genes converge to common adaptive strategies through diverse genetic, epigenetic, and niche construction evolutionary pathways.

Somatic evolution selects cancer cell phenotypes that maximize survival and proliferation in dynamic environments. Although cancer cells are molecularly heterogeneous, we hypothesized convergent adaptive strategies to common host selection forces can be inferred from patterns of epigenetic and genetic evolutionary selection in similar tumors. We systematically investigated gene mutations and expression changes in lung adenocarcinomas with no common driver genes (n = 313). Although 13,461 genes were mutated in at least one sample, only 376 non-synonymous mutations evidenced positive evolutionary selection with conservation of 224 genes, while 1736 and 2430 genes exhibited ≥ two-fold increased and ≥ 50% decreased expression, respectively. Mutations under positive selection are more frequent in genes with significantly altered expression suggesting they often "hardwire" pre-existing epigenetically driven adaptations. Conserved genes averaged 16-fold higher expression in normal lung tissue compared to those with selected mutations demonstrating pathways necessary for both normal cell function and optimal cancer cell fitness. The convergent LUAD phenotype exhibits loss of differentiated functions and cell-cell interactions governing tissue organization. Conservation with increased expression is found in genes associated with cell cycle, DNA repair, p53 pathway, epigenetic modifiers, and glucose metabolism. No canonical driver gene pathways exhibit strong positive selection, but extensive down-regulation of membrane ion channels suggests decreased transmembrane potential may generate persistent proliferative signals. NCD LUADs perform niche construction generating a stiff, immunosuppressive microenvironment through selection of specific collagens and proteases. NCD LUADs evolve to a convergent phenotype through a network of interconnected genetic, epigenetic, and ecological pathways.

Urinary extracellular vesicle-derived miR-126-3p predicts lymph node invasion in patients with high-risk prostate cancer.

To investigate extracellular vesicles (EVs) biomarkers for predicting lymph node invasion (LNI) in patients with high-risk prostate cancer (HRPCa), plasma and/or urine samples were prospectively collected from 45 patients with prostate cancer (PCa) and five with benign prostatic hyperplasia (BPH). Small RNA sequencing was performed to identify miRNAs in the EVs. All patients with PCa underwent radical prostatectomy and extended pelvic lymph node dissection. Differentially-expressed miRNAs were identified in patients with and without pathologically-verified LNI. The candidate miRNAs were validated in low-risk prostate cancer (LRPCa) and BPH. Four miRNA species (e.g. miR-126-3p) and three miRNA species (e.g. miR-27a-3p) were more abundant in urinary and plasma EVs, respectively, of patients with PCa. None of these miRNA species were shared between urinary and plasma EVs. miR-126-3p was significantly more abundant in patients with HR PCa with LNI than in those without (P = 0.018). miR-126-3p was significantly more abundant in the urinary EVs of patients with HRPCa than in those with LRPCa (P = 0.017) and BPH (P = 0.011). In conclusion, urinary EVs-derived miR-126-3p may serve as a good biomarker for predicting LNI in patients with HRPCa.

Disrupting prostate cancer research: Challenge accepted; report from the 2023 Coffey-Holden Prostate Cancer Academy Meeting.

INTRODUCTION: The 2023 Coffey-Holden Prostate Cancer Academy (CHPCA) Meeting, themed "Disrupting Prostate Cancer Research: Challenge Accepted," was convened at the University of California, Los Angeles, Luskin Conference Center, in Los Angeles, CA, from June 22 to 25, 2023. METHODS: The 2023 marked the 10th Annual CHPCA Meeting, a discussion-oriented scientific think-tank conference convened annually by the Prostate Cancer Foundation, which centers on innovative and emerging research topics deemed pivotal for advancing critical unmet needs in prostate cancer research and clinical care. The 2023 CHPCA Meeting was attended by 81 academic investigators and included 40 talks across 8 sessions. RESULTS: The central topic areas covered at the meeting included: targeting transcription factor neo-enhancesomes in cancer, AR as a pro-differentiation and oncogenic transcription factor, why few are cured with androgen deprivation therapy and how to change dogma to cure metastatic prostate cancer without castration, reducing prostate cancer morbidity and mortality with genetics, opportunities for radiation to enhance therapeutic benefit in oligometastatic prostate cancer, novel immunotherapeutic approaches, and the new era of artificial intelligence-driven precision medicine. DISCUSSION: This article provides an overview of the scientific presentations delivered at the 2023 CHPCA Meeting, such that this knowledge can help in facilitating the advancement of prostate cancer research worldwide.

Punctuational evolution is pervasive in distal site metastatic colonization.

The evolution of metastasis represents a lethal stage of cancer progression. Yet, the evolutionary kinetics of metastatic disease remain unresolved. Here, using single cell CRISPR-Cas9 lineage tracing data, we show that in metastatic disease, gradual molecular evolution is punctuated by episodes of rapid evolutionary change associated with lineage divergence. By measuring punctuational effects across the metastatic cascade, we show that punctuational effects contribute more to the molecular diversity at distal site metastases compared to the paired primary tumor, suggesting qualitatively different modes of evolution may drive primary and metastatic tumor progression. This is the first empirical evidence for distinct patterns of molecular evolution at early and late stages of metastasis and demonstrates the complex interplay of cell intrinsic and extrinsic factors that shape lethal cancer.

Exploration of drug resistance mechanisms in triple negative breast cancer cells using a microfluidic device and patient tissues.

Chemoresistance is a major cause of treatment failure in many cancers. However, the life cycle of cancer cells as they respond to and survive environmental and therapeutic stress is understudied. In this study, we utilized a microfluidic device to induce the development of doxorubicin-resistant (DOXR) cells from triple negative breast cancer (TNBC) cells within 11 days by generating gradients of DOX and medium. In vivo chemoresistant xenograft models, an unbiased genome-wide transcriptome analysis, and a patient data/tissue analysis all showed that chemoresistance arose from failed epigenetic control of the nuclear protein-1 (NUPR1)/histone deacetylase 11 (HDAC11) axis, and high NUPR1 expression correlated with poor clinical outcomes. These results suggest that the chip can rapidly induce resistant cells that increase tumor heterogeneity and chemoresistance, highlighting the need for further studies on the epigenetic control of the NUPR1/HDAC11 axis in TNBC.

Drug-resilient Cancer Cell Phenotype Is Acquired via Polyploidization Associated with Early Stress Response Coupled to HIF2α Transcriptional Regulation.

Therapeutic resistance and recurrence remain core challenges in cancer therapy. How therapy resistance arises is currently not fully understood with tumors surviving via multiple alternative routes. Here, we demonstrate that a subset of cancer cells survives therapeutic stress by entering a transient state characterized by whole-genome doubling. At the onset of the polyploidization program, we identified an upregulation of key transcriptional regulators, including the early stress-response protein AP-1 and normoxic stabilization of HIF2α. We found altered chromatin accessibility, ablated expression of retinoblastoma protein (RB1), and enrichment of AP-1 motif accessibility. We demonstrate that AP-1 and HIF2α regulate a therapy resilient and survivor phenotype in cancer cells. Consistent with this, genetic or pharmacologic targeting of AP-1 and HIF2α reduced the number of surviving cells following chemotherapy treatment. The role of AP-1 and HIF2α in stress response by polyploidy suggests a novel avenue for tackling chemotherapy-induced resistance in cancer. SIGNIFICANCE: In response to cisplatin treatment, some surviving cancer cells undergo whole-genome duplications without mitosis, which represents a mechanism of drug resistance. This study presents mechanistic data to implicate AP-1 and HIF2α signaling in the formation of this surviving cell phenotype. The results open a new avenue for targeting drug-resistant cells.

Cancer cells employ lipid droplets to survive toxic stress.

BACKGROUND: Lipid reprogramming is a known mechanism to increase the energetic demands of proliferating cancer cells to drive and support tumorigenesis and progression. Elevated lipid droplets (LDs) are a well-known alteration of lipid reprogramming in many cancers, including prostate cancer (PCa), and are associated with high tumor aggressiveness as well as therapy resistance. The mechanism of LD accumulation and specific LD functions are still not well understood; however, it has been shown that LDs can form as a protective mechanism against lipotoxicity and lipid peroxidation in the cell. METHODS: This study investigated the significance of LDs in PCa. This was done by staining, imaging, image quantification, and flow cytometry analysis of LDs in PCa cells. Additionally, lipidomics and metabolomics experiments were performed to assess the difference of metabolites and lipids in control and treatment surviving cancer cells. Lastly, to assess clinical significance, multiple publicly available datasets were mined for LD-related data. RESULTS: Our study demonstrated that prostate and breast cancer cells that survive 72 h of chemotherapy treatment have elevated LDs. These LDs formed in tandem with elevated reactive oxygen species levels to sequester damaged and excess lipids created by oxidative stress, which promoted cell survival. Additionally, by inhibiting diacylglycerol O-acyltransferase 1 (DGAT1) (which catalyzes triglyceride synthesis into LDs) and treating with chemotherapy simultaneously, we were able to decrease the overall amount of LDs and increase cancer cell death compared to treating with chemotherapy alone. CONCLUSIONS: Overall, our study proposes a potential combination therapy of DGAT1 inhibitors and chemotherapy to increase cancer cell death.

Tumour tissue-derived small extracellular vesicles reflect molecular subtypes of bladder cancer.

mRNA-based molecular subtypes have implications for bladder cancer prognosis and clinical benefit from certain therapies. Whether small extracellular vesicles (sEVs) can reflect bladder cancer molecular subtypes is unknown. We performed whole transcriptome RNA sequencing for formalin fixed paraffin embedded (FFPE) tumour tissues and sEVs separated from matched tissue explants, urine and plasma in patients with bladder cancer. sEVs were separated using size-exclusion chromatography, and characterized by transmission electron microscopy, nano flow cytometry and western blots, respectively. High yield of sEVs were obtained using approximately 1 g of tissue, incubated with media for 30 min. FFPE tumour tissue and tumour tissue-derived sEVs demonstrated good concordance in molecular subtype classification. All urinary sEVs were classified as luminal subtype, while all plasma sEVs were classified as Ba/Sq subtype, regardless of the molecular subtypes indicated by their matched FFPE tumour tissue. The comparison within urine sEVs, which may exclude the sample type specific background, could pick up the different biology between NMIBC and MIBC, as well as the signature genes related to molecular subtypes. Four candidate sEV-related bladder cancer-specific mRNA biomarkers, FAM71E2, OR4K5, FAM138F and KRTAP26-1, were identified by analysing matched urine sEVs, tumour tissue derived sEVs, and adjacent normal tissue derived sEVs. Compared to sEVs separated from biofluids, tissue-derived sEVs may reflect more tissue- or disease-specific biological features. Urine sEVs are promising biomarkers to be used for liquid biopsy-based molecular subtype classification, but the current algorithm needs to be modified/adjusted. Future work is needed to validate the four new bladder cancer-specific biomarkers in large cohorts.

AlphaML: A clear, legible, explainable, transparent, and elucidative binary classification platform for tabular data.

Leveraging the potential of machine learning and recognizing the broad applications of binary classification, it becomes essential to develop platforms that are not only powerful but also transparent, interpretable, and user friendly. We introduce alphaML, a user-friendly platform that provides clear, legible, explainable, transparent, and elucidative (CLETE) binary classification models with comprehensive customization options. AlphaML offers feature selection, hyperparameter search, sampling, and normalization methods, along with 15 machine learning algorithms with global and local interpretation. We have integrated a custom metric for hyperparameter search that considers both training and validation scores, safeguarding against under- or overfitting. Additionally, we employ the NegLog2RMSL scoring method, which uses both training and test scores for a thorough model evaluation. The platform has been tested using datasets from multiple domains and offers a graphical interface, removing the need for programming expertise. Consequently, alphaML exhibits versatility, demonstrating promising applicability across a broad spectrum of tabular data configurations.

Diagnostic liquid biopsy biomarkers in renal cell cancer.

The clinical presentation of renal cell cancer (RCC) is shifting towards incidental and early detection, creating new challenges in RCC diagnosis. Overtreatment might be reduced with the development of new diagnostic biomarkers to distinguish benign from malignant small renal masses (SRMs). Differently from tissue biopsies, liquid biopsies are obtained from a patient's blood or urine and, therefore, are minimally invasive and suitable for longitudinal monitoring. The most promising types of liquid biopsy biomarkers for RCC diagnosis are circulating tumour cells, extracellular vesicles (EVs) and cell-free DNA. Circulating tumour cell assays have the highest specificity, with low processing time and costs. However, the biological characteristics and low sensitivity limit the use of these markers in SRM diagnostics. Cell-free DNA might complement the diagnosis of high-volume RCC, but the potential for clinical application in SRMs is limited. EVs have the highest biological abundance and the highest sensitivity in identifying low-volume disease; moreover, the molecular characteristics of these markers make EVs suitable for multiple analytical applications. Thus, currently, EV assays have the greatest potential for diagnostic application in RCC (including identification of SRMs). All these liquid biomarkers have potential in clinical practice, pending validation studies. Biomarker implementation will be needed to also improve characterization of RCC subtypes. Last, diagnostic biomarkers might be extended to prognostic or predictive applications.

Comparison of Multiple Segmentation Methods for Volumetric Delineation of Primary Prostate Cancer with Prostate-Specific Membrane Antigen-Targeted 18F-DCFPyL PET/CT.

This study aimed to assess the accuracy of intraprostatic tumor volume measurements on prostate-specific membrane antigen-targeted 18F-DCFPyL PET/CT made with various segmentation methods. An accurate understanding of tumor volumes versus segmentation techniques is critical for therapy planning, such as radiation dose volume determination and response assessment. Methods: Twenty-five men with clinically localized, high-risk prostate cancer were imaged with 18F-DCFPyL PET/CT before radical prostatectomy. The tumor volumes and tumor-to-prostate ratios (TPRs) of dominant intraprostatic foci of uptake were determined using semiautomatic segmentation (applying SUVmax percentage [SUV%] thresholds of SUV30%-SUV70%), adaptive segmentation (using adaptive segmentation percentage [A%] thresholds of A30%-A70%), and manual contouring. The histopathologic tumor volume (TV-Histo) served as the reference standard. The significance of differences between TV-Histo and PET-based tumor volume were assessed using the paired-sample Wilcoxon signed-rank test. The Spearman correlation coefficient was used to establish the strength of the association between TV-Histo and PET-derived tumor volume. Results: Median TV-Histo was 2.03 cm3 (interquartile ratio [IQR], 1.16-3.36 cm3), and median TPR was 10.16%. The adaptive method with an A40% threshold most closely determined the tumor volume, with a median difference of +0.19 (IQR, -0.71 to +2.01) and a median relative difference of +7.6%. The paired-sample Wilcoxon test showed no significant difference in PET-derived tumor volume and TV-Histo using A40%, A50%, SUV40%, and SUV50% threshold segmentation algorithms (P > 0.05). For both threshold-based segmentation methods, use of higher thresholds (e.g., SUV60% or SUV70% and A50%-A70%) resulted in underestimation of tumor volumes, and use of lower thresholds (e.g., SUV30% or SUV40% and A30%) resulted in overestimation of tumor volumes relative to TV-Histo and TPR. Manual segmentation overestimated the tumor volume, with a median difference of +2.49 (IQR, 0.42-4.11) and a median relative difference of +130%. Conclusion: Segmentation of intraprostatic tumor volume and TPR with an adaptive segmentation approach most closely approximates TV-Histo. This information might be used to guide the primary treatment of men with clinically localized, high-risk prostate cancer.