Monitoring Retinoblastoma by Machine Learning of Aqueous Humor Metabolic Fingerprinting,Small Methods

当前位置： X-MOL 学术 › Small Methods › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

Monitoring Retinoblastoma by Machine Learning of Aqueous Humor Metabolic Fingerprinting
Small Methods ( IF 10.7 ) Pub Date : 2021-12-02 , DOI: 10.1002/smtd.202101220
Wanshan Liu _{1,

2} , Yingxiu Luo _{3,

4} , Jingjing Dai _{3,

4} , Ludi Yang _{3,

4} , Lin Huang _{1,

2} , Ruimin Wang _{1,

2} , Wei Chen _{1,

2} , Yida Huang _{1,

2} , Shiyu Sun _{1,

2} , Jing Cao _{1,

2} , Jiao Wu _{1,

2} , Minglei Han _{3,

4} , Jiayan Fan _{3,

4} , Mengjia He _{3,

4} , Kun Qian _{1,

2} , Xianqun Fan _{3,

4} , Renbing Jia _{3,

4}

Affiliation

The most common intraocular pediatric malignancy, retinoblastoma (RB), accounts for â‰ˆ10% of cancer in children. Efficient monitoring can enhance living quality of patients and 5-year survival ratio of RB up to 95%. However, RB monitoring is still insufficient in regions with limited resources and the mortality may even reach over 70% in such areas. Here, an RB monitoring platform by machine learning of aqueous humor metabolic fingerprinting (AH-MF) is developed, using nanoparticle enhanced laser desorption/ionization mass spectrometry (LDI MS). The direct AH-MF of RB free of sample pre-treatment is recorded, with both high reproducibility (coefficient of variation < 10%) and sensitivity (low to 0.3 pmol) at sample volume down to 40 nL only. Further, early and advanced RB patients with area-under-the-curve over 0.9 and accuracy over 80% are differentiated, through machine learning of AH-MF. Finally, a metabolic biomarker panel of 7 metabolites through accurate MS and tandem MS (MS/MS) with pathway analysis to monitor RB is identified. This work can contribute to advanced metabolic analysis of eye diseases including but not limited to RB and screening of new potential metabolic targets toward therapeutic intervention.

中文翻译：

通过房水代谢指纹的机器学习监测视网膜母细胞瘤

最常见的眼内小儿恶性肿瘤，视网膜母细胞瘤 (RB)，占儿童癌症的 10%。有效的监测可以提高患者的生活质量，RB的5年生存率高达95%。但在资源有限的地区，RB监测仍不充分，死亡率甚至可能达到70%以上。在这里，使用纳米粒子增强激光解吸/电离质谱 (LDI MS) 开发了通过房水代谢指纹 (AH-MF) 机器学习的 RB 监测平台。记录了 RB 的直接 AH-MF，无需样品预处理，仅在样品体积低至 40 nL 时具有高重现性（变异系数 < 10%）和灵敏度（低至 0.3 pmol）。此外，曲线下面积超过 0 的早期和晚期 RB 患者。通过 AH-MF 的机器学习，可以区分 9 和 80% 以上的准确率。最后，通过准确的 MS 和串联 MS (MS/MS) 以及用于监测 RB 的途径分析，确定了 7 种代谢物的代谢生物标志物组。这项工作有助于对眼部疾病进行高级代谢分析，包括但不限于 RB 和筛选新的潜在代谢靶点以进行治疗干预。

更新日期：2022-01-18

点击分享查看原文

点击收藏

阅读更多本刊最新论文