Abstract: To elucidate the diagnostic value and clinical relevance of protein kinase D3 (PRKD3) in hepatocellular carcinoma (HCC), we analyzed data retrieved from The Cancer Genome Atlas (TCGA) database, which revealed high expression of PRKD3 in HCC tissues. Subsequently, we collected a total of 392 clinical plasma samples from healthy individuals, patients with cirrhosis or decompensated cirrhosis, and patients with HCC. Plasma PRKD3 levels were then determined across HCC patients and individuals at high risk of developing the disease. The results revealed significantly elevated PRKD3 concentrations in patients with cirrhosis, decompensated cirrhosis, and HCC compared to healthy controls (P<0.01). The areas under the receiver operating characteristic (ROC) curve for these three groups were 0.8107, 0.7899, and 0.7177, respectively. To further evaluate the efficacy of PRKD3 as an adjunctive diagnostic biomarker for HCC, we employed a panel of machine learning algorithms as primary classifiers, including extra trees (ET), gradient boosting (GB), random forest (RF), and support vector machine (SVM). A multi-parameter joint diagnostic model was constructed by combining PRKD3 expression data with a set of clinical parameters, including gender, age, total bilirubin (TBIL), alanine aminotransferase (ALT), aspartate aminotransferase (AST), alkaline phosphatase (ALP), albumin (ALB), alpha-fetoprotein (AFP), and prothrombin induced by vitamin K absence-II (PIVKA-II). This integrated approach exhibited substantially improved diagnostic performance, achieving an accuracy of 0.861, sensitivity of 0.863, specificity of 0.925, and precision of 0.862. Collectively, these findings highlight the potential of PRKD3 as an integral component of a comprehensive diagnostic tool for the early identification of HCC.

基于机器学习的蛋白激酶D3（PRKD3）作为肝细胞癌协同诊断生物标志物的评估研究

[1]BagheriMH, AhlmanMA, LindenbergL, et al., 2017. Advances in medical imaging for the diagnosis and management of common genitourinary cancers. Urol Oncol Semin Orig Invest, 35(7):473-491.

[2]BaiDS, ZhangC, ChenP, et al., 2017. The prognostic correlation of AFP level at diagnosis with pathological grade, progression, and survival of patients with hepatocellular carcinoma. Sci Rep, 7:12870.

[3]BestJ, BechmannLP, SowaJP, et al., 2020. GALAD score detects early hepatocellular carcinoma in an international cohort of patients with nonalcoholic steatohepatitis. Clin Gastroenterol Hepatol, 18(3):728-735.e4.

[4]BiWL, HosnyA, SchabathMB, et al., 2019. Artificial intelligence in cancer imaging: clinical challenges and applications. CA Cancer J Clin, 69(2):127-157.

[5]CalderaroJ, SeraphinTP, LueddeT, et al., 2022. Artificial intelligence for the prevention and clinical management of hepatocellular carcinoma. J Hepatol, 76(6):1348-1361.

[6]ChenJ, DengF, SinghSV, et al., 2008. Protein kinase D3 (PKD3) contributes to prostate cancer cell growth and survival through a PKCε/PKD3 pathway downstream of Akt and ERK1/2. Cancer Res, 68(10):3844-3853.

[7]CuiBM, ChenJ, LuoM, et al., 2021. PKD3 promotes metastasis and growth of oral squamous cell carcinoma through positive feedback regulation with PD-L1 and activation of ERK-STAT1/3-EMT signalling. Int J Oral Sci, 13:8.

[8]DebesJD, RomagnoliPA, PrietoJ, et al., 2021. Serum biomarkers for the prediction of hepatocellular carcinoma. Cancers, 13(7):1681.

[9]DingZX, WangLS, SunJT, et al., 2025. Hepatocellular carcinoma: pathogenesis, molecular mechanisms, and treatment advances. Front Oncol, 15:1526206.

[10]DurandN, BorgesS, StorzP, 2016. Protein kinase D enzymes as regulators of EMT and cancer cell invasion. J Clin Med, 5(2):20.

[11]El-SeragHB, JinQC, TayobN, et al., 2025. HES V2.0 outperforms GALAD for detection of HCC: a phase 3 biomarker study in the United States. Hepatology, 81(2):465-475.

[12]EvansIM, ZacharyIC, 2011. Protein kinase D in vascular biology and angiogenesis. IUBMB Life, 63(4):258-263.

[13]FodaZH, AnnapragadaAV, BoyapatiK, et al., 2023. Detecting liver cancer using cell-free DNA fragmentomes. Cancer Discov, 13(3):616-631.

[14]FujiwaraN, LopezC, MarshTL, et al., 2025. Phase 3 validation of PAaM for hepatocellular carcinoma risk stratification in cirrhosis. Gastroenterology, 168(3):556-567.e7.

[15]GhoshS, ZhaoX, AlimM, et al., 2025. Artificial intelligence applied to ‘omics data in liver disease: towards a personalised approach for diagnosis, prognosis and treatment. Gut, 74(2):295-311.

[16]GoldenbergSL, NirG, SalcudeanSE, 2019. A new era: artificial intelligence and machine learning in prostate cancer. Nat Rev Urol, 16(7):391-403.

[17]HaCH, WangWY, JhunBS, et al., 2008. Protein kinase D-dependent phosphorylation and nuclear export of histone deacetylase 5 mediates vascular endothelial growth factor-induced gene expression and angiogenesis. J Biol Chem, 283(21):14590-14599.

[18]HanBF, ZhengRS, ZengHM, et al., 2024. Cancer incidence and mortality in China, 2022. J Natl Cancer Cent, 4(1):47-53.

[19]HiraokaA, KudoM, TadaT, et al., 2025. The current status of tumor markers as biomarkers in the era of immunotherapy for hepatocellular carcinoma: alpha-fetoprotein alone is not sufficient. Oncology, 104(1):79-91.

[20]HouJL, BergT, VogelA, et al., 2025. Comparative evaluation of multimarker algorithms for early-stage HCC detection in multicenter prospective studies. JHEP Rep, 7(2):101263.

[21]HuangHR, WuFF, YuY, et al., 2024. Multi-transcriptomics analysis of microvascular invasion-related malignant cells and development of a machine learning-based prognostic model in hepatocellular carcinoma. Front Immunol, 15:1436131.

[22]HuckB, DussS, HausserA, et al., 2014. Elevated protein kinase D3 (PKD3) expression supports proliferation of triple-negative breast cancer cells and contributes to mTORC1-S6K1 pathway activation. J Biol Chem, 289(6):3138-3147.

[23]KuwanoA, TanakaM, SuzukiH, et al., 2021. Upregulated expression of hypoxia reactive genes in peripheral blood mononuclear cells from chronic liver disease patients. Biochem Biophys Rep, 27:101068.

[24]LaiQ, ItoT, IesariS, et al., 2024. Role of protein induced by vitamin-K absence-II in transplanted patients with HCC not producing alpha-fetoprotein. Liver Transpl, 30(5):472-483.

[25]LeeJ, HongEM, KimJH, et al., 2022. Ursodeoxycholic acid inhibits epithelial-mesenchymal transition, suppressing invasiveness of bile duct cancer cells: an in vitro study. Oncol Lett, 24(6):448.

[26]LiHQ, ZhangJY, ShiY, et al., 2025. Identification of matrix stiffness-related molecular subtypes in HCC via integrating multi-omics analysis and machine learning algorithms. J Transl Med, 23:716.

[27]LiL, HuaL, FanHH, et al., 2019. Interplay of PKD3 with SREBP1 promotes cell growth via upregulating lipogenesis in prostate cancer cells. J Cancer, 10(25):6395-6404.

[28]LiuY, SongH, YuSY, et al., 2020. Protein kinase D3 promotes the cell proliferation by activating the ERK1/c-MYC axis in breast cancer. J Cell Mol Med, 24(3):2135-2144.

[29]LiuYC, WangXH, YangYZ, 2020. Hepatic Hippo signaling inhibits development of hepatocellular carcinoma. Clin Mol Hepatol, 26(4):742-750.

[30]LiuZK, WuYC, KhanAA, et al., 2024. Deep learning-based radiomics allows for a more accurate assessment of sarcopenia as a prognostic factor in hepatocellular carcinoma. J Zhejiang Univ-Sci B (Biomed & Biotechnol), 25(1):83-90.

[31]MaemuraK, NatsugoeS, TakaoS, 2014. Molecular mechanism of cholangiocarcinoma carcinogenesis. J Hepato-Biliary Pancreat Sci, 21(10):754-760.

[32]MoldogazievaNT, MokhosoevIM, ZavadskiySP, et al., 2021. Proteomic profiling and artificial intelligence for hepatocellular carcinoma translational medicine. Biomedicines, 9(2):159.

[33]PiratvisuthT, HouJL, TanwandeeT, et al., 2023. Development and clinical validation of a novel algorithmic score (GAAD) for detecting HCC in prospective cohort studies. Hepatol Commun, 7(11):e0317.

[34]RazaghiA, BjörnstedtM, 2024. Exploring selenoprotein P in liver cancer: advanced statistical analysis and machine learning approaches. Cancers, 16(13):2382.

[35]SungH, FerlayJ, SiegelRL, et al., 2021. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin, 71(3):209-249.

[36]SwansonK, WuE, ZhangA, et al., 2023. From patterns to patients: advances in clinical machine learning for cancer diagnosis, prognosis, and treatment. Cell, 186(8):1772-1791.

[37]TianS, ChenYY, ZhangYM, et al., 2023. Clinical value of serum AFP and PIVKA-II for diagnosis, treatment and prognosis of hepatocellular carcinoma. J Clin Lab Anal, 37(1):e24823.

[38]TianY, XieB, WangSY, et al., 2024. PRKD3 promotes proliferation of liver cancer cells: a downstream proteomics profiling study. Am J Transl Res, 16(11):6384-6398.

[39]VargheseRS, ZhangXR, GiridharanS, et al., 2025. Multi-omics feature selection to identify biomarkers for hepatocellular carcinoma. Metabolites, 15(9):575.

[40]WangK, DongLB, LuQ, et al., 2023. Incorporation of protein induced by vitamin K absence or antagonist-II into transplant criteria expands beneficiaries of liver transplantation for hepatocellular carcinoma: a multicenter retrospective cohort study in China. Int J Surg, 109(12):4135-4144.

[41]WangSY, XieB, DengHH, et al., 2025. Effect of PRKD3 on cell cycle in gastric cancer progression and downstream regulatory networks. Med Oncol, 42(5):135.

[42]XuSJ, DingN, ZhengS, et al., 2022. RNA binding protein-based risk score model for prognosis prediction of patients with hepatocellular carcinoma. Chin Med J, 135(23):2890-2892.

[43]XuZQ, LuoSQ, WuZJ, et al., 2025. Current status and perspectives of molecular mechanisms of gender difference in hepatocellular carcinoma: the tip of the iceberg? BioSci Trends, 19(3):266-280.

[44]YanJ, XieB, TianY, et al., 2022. iTRAQ-based proteome profiling of differentially expressed proteins in insulin-resistant human hepatocellular carcinoma. Front Cell Dev Biol, 10:836041.

[45]YangHY, XuM, ChiXF, et al., 2017. Higher PKD3 expression in hepatocellular carcinoma (HCC) tissues predicts poorer prognosis for HCC patients. Clin Res Hepatol Gastroenterol, 41(5):554-563.

[46]YangT, XingH, WangGQ, et al., 2019. A novel online calculator based on serum biomarkers to detect hepatocellular carcinoma among patients with hepatitis B. Clin Chem, 65(12):1543-1553.

[47]YeamanC, AyalaMI, WrightJR, et al., 2004. Protein kinase D regulates basolateral membrane protein exit from trans-Golgi network. Nat Cell Biol, 6(2):106-112.

[48]ZhangJW, ZhangYJ, WangJQ, et al., 2019. Protein kinase D3 promotes gastric cancer development through p65/6-phosphofructo-2-kinase/fructose-2,6-biphosphatase 3 activation of glycolysis. Exp Cell Res, 380(2):188-197.

[49]ZhangSY, LiuH, YinMM, et al., 2020. Deletion of protein kinase D3 promotes liver fibrosis in mice. Hepatology, 72(5):1717-1734.

[50]ZhouJ, YuL, GaoX, et al., 2011. Plasma microRNA panel to diagnose hepatitis B virus–related hepatocellular carcinoma. J Clin Oncol, 29(36):4781-4788.

[51]ZhouJ, SunH, WangZ, et al., 2025. China Liver Cancer Guidelines for the Diagnosis and Treatment of Hepatocellular Carcinoma (2024 Edition). Liver Cancer, 14(6):779-835.

[52]ZhuLP, LvB, GaoYF, et al., 2025. Lactucin alleviates liver fibrosis by regulating the TLR4-MyD88-MAPK/NF-κB signaling pathway through intestinal flora. Arch Biochem Biophys, 12:110341.

Similar articles