Identification of Somatic Gene Signatures in Circulating Cell-Free DNA Associated with Disease Progression in Metastatic Prostate Cancer by a Novel Machine Learning Platform

Applications of Artificial Intelligence in Prostate Cancer Care: A Path to Enhanced Efficiency and Outcomes

The landscape of prostate cancer care has rapidly evolved. We have transitioned from the use of conventional imaging, radical surgeries, and single-agent androgen deprivation therapy to an era of advanced imaging, precision diagnostics, genomics, and targeted treatment options. Concurrently, the emergence of large language models (LLMs) has dramatically transformed the paradigm for artificial intelligence (AI). This convergence of advancements in prostate cancer management and AI provides a compelling rationale to comprehensively review the current state of AI applications in prostate cancer care. Here, we review the advancements in AI-driven applications across the continuum of the journey of a patient with prostate cancer from early interception to survivorship care. We subsequently discuss the role of AI in prostate cancer drug discovery, clinical trials, and clinical practice guidelines. In the localized disease setting, deep learning models demonstrated impressive performance in detecting and grading prostate cancer using imaging and pathology data. For biochemically recurrent diseases, machine learning approaches are being tested for improved risk stratification and treatment decisions. In advanced prostate cancer, deep learning can potentially improve prognostication and assist in clinical decision making. Furthermore, LLMs are poised to revolutionize information summarization and extraction, clinical trial design and operations, drug development, evidence synthesis, and clinical practice guidelines. Synergistic integration of multimodal data integration and human-AI integration are emerging as a key strategy to unlock the full potential of AI in prostate cancer care.

Genomics and Artificial Intelligence: Prostate Cancer

Artificial intelligence (AI) is revolutionizing prostate cancer genomics research. By leveraging machine learning and deep learning algorithms, researchers can rapidly analyze vast genomic datasets to identify patterns and correlations that may be missed by traditional methods. These AI-driven insights can lead to the discovery of novel biomarkers, enhance the accuracy of diagnosis, and predict disease progression and treatment response. As such, AI is becoming an indispensable tool in the pursuit of personalized medicine for prostate cancer.

Assessment of Prostate and Bladder Cancer Genomic Biomarkers Using Artificial Intelligence: a Systematic Review

PURPOSE OF REVIEW

The aim of the systematic review is to assess AI's capabilities in the genetics of prostate cancer (PCa) and bladder cancer (BCa) to evaluate target groups for such analysis as well as to assess its prospects in daily practice.

RECENT FINDINGS

In total, our analysis included 27 articles: 10 articles have reported on PCa and 17 on BCa, respectively. The AI algorithms added clinical value and demonstrated promising results in several fields, including cancer detection, assessment of cancer development risk, risk stratification in terms of survival and relapse, and prediction of response to a specific therapy. Besides clinical applications, genetic analysis aided by the AI shed light on the basic urologic cancer biology. We believe, our results of the AI application to the analysis of PCa, BCa data sets will help to identify new targets for urological cancer therapy. The integration of AI in genomic research for screening and clinical applications will evolve with time to help personalizing chemotherapy, prediction of survival and relapse, aid treatment strategies such as reducing frequency of diagnostic cystoscopies, and clinical decision support, e.g., by predicting immunotherapy response. These factors will ultimately lead to personalized and precision medicine thereby improving patient outcomes.

Niclosamide in prostate cancer: An inhibitor of AR-V7, a mitochondrial uncoupler, or more?

A recent phase Ib study investigating the use of reformulated niclosamide in combination with abiraterone and prednisone in patients with castration-resistant prostate cancer (CRPC) demonstrated encouraging preliminary efficacy with low toxicity. Preclinical studies have reported that niclosamide at clinically relevant concentrations inhibits androgen receptor splice variant 7 (AR-V7), a known tumor driver in CRPC. However, the magnitude of anti-tumor effects of niclosamide either used alone or in combination with abiraterone in these experimental models, far exceeded what could have been explained as a simple AR-V7 inhibition. Niclosamide at clinically relevant concentrations also acts as an oxidative phosphorylation (OxPhos) uncoupler in mitochondria. This raises the question whether the observed effects of niclosamide were partly mediated by OxPhos inhibition. Most OxPhos inhibitors did not demonstrate selectivity towards cancer cells and failed to enter clinical practice due to unacceptable toxicity. However, some mitochondrial uncouplers have greater cytotoxicity against cancerous cells compared to non-cancerous. Hyperpolarization of cancer cell mitochondria, or the more alkaline mitochondrial matrix of cancer cells could be potential reasons for this. Niclosamide can also alter Wnt/β-catenin, mTOR, Notch, NF-kB and STAT3 signaling pathways. Hence, the mechanism of action of reformulated niclosamide in CRPC patients requires further investigation. This will potentially lead to new opportunities to develop and investigate even more selective and effective treatments against prostate cancer.

Survival of Patients with Metastatic Prostate Cancer After Disease Progression on an Androgen Receptor Axis-Targeted Therapy Given in the Metastatic Castration-Sensitive Versus Metastatic Castration-Resistant Prostate Cancer Setting

Androgen receptor axis-targeted therapies (ARATs; androgen receptor or androgen synthesis inhibitors) have been approved for the treatment of patients with metastatic castration-sensitive and castration-resistant prostate cancer (mCSPC and mCRPC) on the basis of improved overall survival (OS) in randomized clinical trials. However, it is not clear whether the OS for patients after progression on first-line ARAT differs if the first ARAT was administered in the mCSPC versus mCRPC setting and what its estimates are. We assessed the OS after disease progression on ARAT given as first-line therapy in mCSPC versus mCRPC. Patient-level data were collected retrospectively, and only those treated with first-line ARAT for mCSPC or mCRPC were included. For patients receiving ARAT in the mCRPC setting, no prior ARAT was allowed in the mCSPC setting. The median OS and hazard ratio (HR) were determined via Kaplan-Meier analysis from the time of progression on ARAT. Of 382 patients treated with first-line ARAT, 172 (44 mCSPC and 128 mCRPC) had experienced disease progression and were included in the analysis. Median OS was similar in the mCSPC (23 mo) and mCRPC (17 mo) settings (HR 0.99, 95% confidence interval 0.62-1.56; p = 0.95). A total of 138 patients received subsequent systemic therapy after progression. Our results suggest that median OS is similar after progression on one ARAT, whether given in the first-line mCSPC or first-line mCRPC setting, and is estimated to be <2 yr. These data have implications for patient prognostication and the design of clinical trials in the post-ARAT setting for further drug development. PATIENT SUMMARY: We investigated whether the survival benefit differs between metastatic castration-sensitive and castration-resistant prostate cancer for patients who have already experienced cancer progression after first-line treatment with one drug targeting the androgen receptor pathway  (called ARAT). We found that the median survival benefit was less than 2 years and was similar for the two groups.

Detection of BRCA1, and BRCA2 Alterations in Matched Tumor Tissue and Circulating Cell-Free DNA in Patients with Prostate Cancer in a Real-World Setting

BACKGROUND

Poly (ADP-ribose) polymerase (PARP) inhibitors are approved for patients with metastatic castration-resistant prostate cancer harboring deleterious or suspected deleterious BRCA1 and/or 2 mutations. Identifying patients with prostate cancer harboring these mutations may be challenging. Circulating cell-free DNA (cfDNA) provides an avenue for an easier detection of these mutations. Herein, we aimed to evaluate the concordance of BRCA mutations in the tumor tissue and cfDNA in patients with metastatic prostate cancer in the real-world setting.

METHODS

Somatic genomic profiling results were obtained from a clinical cohort of patients at our institution who had at least two samples tested. One of the samples needed to be from either primary or metastatic tissue. Concordance was adjusted to not include mutation types that the cfDNA platforms were not designed to detect.

RESULTS

The presence or absence of mutations in the BRCA gene was assessed in a total of 589 samples, including 327 cfDNA samples, from 260 patients with metastatic prostate cancer. The median time between the first test and any subsequent test was 22.8 (0.0-232) months. BRCA mutation was present in the patient's original prostate tissue in 23 samples (3.9%) of patients. The adjusted concordance between prostate tumor tissue and cfDNA was 97.9% [95% CI, 95.3-99.1%]. The adjusted concordance between metastatic samples and cfDNA was 93.5% [95% CI, 86.4-97.3%]. Of the patients who had a BRCA mutation detected in their prostate tissue, there was a 70% probability of detecting a BRCA mutation in the patient's cfDNA as well. For patients who did not have a detectable BRCA mutation in their primary prostate tissue, the probability of detecting a subsequent one later in the disease course was less than 0.9%.

CONCLUSION

There is a high level of concordance between tissue and blood for BRCA mutations. Testing cfDNA can provide reliable information on BRCA mutational status and is a viable alternative to solid tissue sequencing when unavailable. The development of a new BRCA mutation later in the disease course is a rare event.

Genomic landscape of advanced prostate cancer patients with BRCA1 versus BRCA2 mutations as detected by comprehensive genomic profiling of cell-free DNA

BRCA1-mutated prostate cancer has been shown to be less responsive to poly (ADP-ribose) polymerase (PARP) inhibitors as compared to BRCA2-mutated prostate cancer. The reason for this differential response is not clear. We hypothesized this differential sensitivity to PARP inhibitors may be explained by distinct genomic landscapes of BRCA1 versus BRCA2 co-segregating genes. In a large dataset of 7,707 men with advanced prostate cancer undergoing comprehensive genomic profiling (CGP) of cell-free DNA (cfDNA), 614 men harbored BRCA1 and/or BRCA2 alterations. Differences in the genomic landscape of co-segregating genes was investigated by Fisher's exact test and probabilistic graphical models (PGMs). Results demonstrated that BRCA1 was significantly associated with six other genes, while BRCA2 was not significantly associated with any gene. These findings suggest BRCA2 may be the main driver mutation, while BRCA1 mutations tend to co-segregate with mutations in other molecular pathways contributing to prostate cancer progression. These hypothesis-generating data may explain the differential response to PARP inhibition and guide towards the development of combinatorial drug regimens in those with BRCA1 mutation.

Comprehensive Genomic Profiling of Cell-Free DNA in Men With Advanced Prostate Cancer: Differences in Genomic Landscape Based on Race

Advanced prostate cancer (aPC) in Black men was reported to present with aggressive features and to be associated with poor prognosis. Herein, we compared the cell-free DNA (cfDNA) genomic landscape of aPC in Black vs White men. Patients (pts) with aPC from 6 academic institutions and available cfDNA comprehensive genomic profiling (CGP) were included. Association between mutated genes and race was evaluated using Barnard’s test and a Probabilistic Graphical Model (PGM) machine learning approach. Analysis included 743 aPC pts (217 Black, 526 White) with available cfDNA CGP. The frequency of alterations in the androgen receptor gene was significantly higher in Black vs White men (55.3% vs 35% respectively, P < .001). Additionally, alterations in EGFR, MYC, FGFR1, and CTNNB1 were present at higher frequencies in Black men. PGM analysis and Barnard’s test were concordant. Findings from the largest cohort of Black men with aPC undergoing cfDNA CGP may guide further drug development in these men.

Application of Circulating Tumor Cells and Circulating Free DNA from Peripheral Blood in the Prognosis of Advanced Gastric Cancer

Objective

To explore the application value of circulating tumor cells (CTCs) and circulating free DNA (cfDNA) from peripheral blood in the prognosis of advanced gastric cancer (AGC). Here, we measured CTCs and cfDNA quantity for predicting the outcome of patients. Patients and Methods. Forty-five patients with advanced gastric cancer who underwent neoadjuvant chemotherapy and surgical treatment were enrolled in this study. All patients received neoadjuvant chemotherapy with paclitaxel + S-1 + oxaliplatin (PSOX) regimen, and CTCs and cfDNA of the peripheral blood were detected before and after neoadjuvant therapy. Relationships between the number/type of CTC or cfDNA and the efficacy of neoadjuvant chemotherapy were analyzed.

Results

Among 45 patients, 43 (95.6%) were positive, and the positive rate of mesenchymal CTC was increased with the increase in the T stage. The proportion of mesenchymal CTC was positively correlated with the N stage (P < 0.05), and the larger N stage will have the higher proportion of mesenchymal CTC. Patients with a small number of mesenchymal CTC before neoadjuvant chemotherapy were more likely to achieve partial response (PR) with neoadjuvant therapy. Patients with positive CA-199 were more likely to achieve PR with neoadjuvant therapy (P < 0.05). Patients in the PR group were more likely to have decreased/unchanged cfDNA concentration after neoadjuvant therapy (P=0.119). After neoadjuvant therapy (before surgery), the cfDNA concentration was higher and the efficacy of neoadjuvant therapy (SD or PD) was lower (P=0.045).

Conclusions

Peripheral blood CTC, especially interstitial CTC and cfDNA, has a certain value in predicting the efficacy and prognosis of neoadjuvant chemotherapy in advanced gastric cancer.