Faculté de Médecine du Kremlin Bicêtre, Université Paris-Sud, Université Paris-Saclay, 94270 Le Kremlin-Bicêtre, France.
Energy & Memory, Brain Plasticity Unit, CNRS, ESPCI Paris, PSL Research University, 75006 Paris, France.
Biomolecules. 2024 Oct 31;14(11):1394. doi: 10.3390/biom14111394.
Hepatoblastoma is the most common primary liver cancer in children. Poor outcomes are primarily associated with patients who have distant metastases. Using the Mammalian Metabolic Enzyme Database, we investigated the overexpression of metabolic enzymes in hepatoblastoma tumors compared to noncancerous liver tissue in the GSE131329 transcriptome dataset. For the overexpressed enzymes, we applied ElasticNet machine learning to assess their predictive value for metastasis. A metabolic expression score was then computed from the significant enzymes and integrated into a clinical-biological logistic regression model. Forty-one overexpressed enzymes distinguished hepatoblastoma tumors from noncancerous liver tissues. Eighteen of these enzymes predicted metastasis status with an AUC of 0.90, demonstrating 85.7% sensitivity and 92.3% specificity. ElasticNet machine learning identified and as key predictors of metastasis. Univariate analyses confirmed the significance of these enzymes, with respective -values of 0.0058 and 0.0091. A metabolic score based on and expression discriminated metastasis status and high-risk CHIC scores (-value = 0.005). The metabolic score was more sensitive than the C1/C2 classifier in predicting metastasis (accuracy: 0.72 vs. 0.55). In a regression model integrating the metabolic score with epidemiological parameters (gender, age at diagnosis, histological type, and clinical PRETEXT stage), the metabolic score was confirmed as an independent adverse predictor of metastasis (-value = 0.003, odds ratio: 2.12). This study identified the dual overexpression of and in hepatoblastoma patients at risk of metastasis (high-risk CHIC classification). The combined tumor expression of and was used to compute a metabolic score, which was validated as an independent predictor of metastatic status in hepatoblastoma.
肝母细胞瘤是儿童中最常见的原发性肝癌。不良预后主要与发生远处转移的患者有关。利用哺乳动物代谢酶数据库，我们研究了在 GSE131329 转录组数据集的肝癌肿瘤与非癌性肝组织中代谢酶的过度表达。对于过度表达的酶，我们应用弹性网络机器学习来评估它们对转移的预测价值。然后，从有意义的酶中计算出代谢表达评分，并将其整合到临床生物学逻辑回归模型中。41 种过度表达的酶将肝母细胞瘤肿瘤与非癌性肝组织区分开来。其中 18 种酶以 AUC 为 0.90 预测转移状态，显示出 85.7%的敏感性和 92.3%的特异性。弹性网络机器学习鉴定出 和 是转移的关键预测因子。单变量分析证实了这些酶的重要性，相应的 P 值分别为 0.0058 和 0.0091。基于 和 表达的代谢评分可区分转移状态和高危 CHIC 评分（P 值=0.005）。代谢评分在预测转移方面比 C1/C2 分类器更敏感（准确性：0.72 对 0.55）。在整合代谢评分与流行病学参数（性别、诊断时年龄、组织学类型和临床 PRETEXT 分期）的回归模型中，代谢评分被确认为转移的独立不良预测因子（P 值=0.003，优势比：2.12）。本研究鉴定出肝母细胞瘤患者转移风险高（高危 CHIC 分类）的 和 双重过度表达。肿瘤中 和 的联合表达用于计算代谢评分，该评分被验证为肝母细胞瘤转移状态的独立预测因子。
