Magnetic nanoparticle (MNP)-based immunochromatographic tests (ICTs) display long-term stability and an enhanced capability for multiplex biomarker detection, surpassing conventional gold nanoparticles (AuNPs) and fluorescence-based ICTs. In this study, we innovatively developed zwitterionic silica-coated MNPs (MNP@Si-Zwit/COOH) with outstanding antifouling capabilities and effectively utilised them for the simultaneous identification of the nucleocapsid protein (N protein) of the severe acute respiratory syndrome coronavirus (SARS-CoV-2) and influenza A/B. The carboxyl-functionalised MNPs with 10% zwitterionic ligands (MNP@Si-Zwit 10/COOH) exhibited a wide linear dynamic detection range and the most pronounced signal-to-noise ratio when used as probes in the ICT. The relative limit of detection (LOD) values were achieved in 12 min by using a magnetic assay reader (MAR), with values of 0.0062 ng/mL for SARS-CoV-2 and 0.0051 and 0.0147 ng/mL, respectively, for the N protein of influenza A and influenza B. By integrating computer vision and deep learning to enhance the image processing of immunoassay results for multiplex detection, a classification accuracy in the range of 0.9672–0.9936 was achieved for evaluating the three proteins at concentrations of 0, 0.1, 1, and 10 ng/mL. The proposed MNP-based ICT for the multiplex diagnosis of biomarkers holds substantial promise for applications in both medical institutions and self-administered diagnostic settings.

中文翻译：

---

深度学习辅助两性离子磁性免疫色谱分析用于生物标志物的多重诊断

基于磁性纳米颗粒 (MNP) 的免疫层析测试 (ICT) 表现出长期稳定性和增强的多重生物标志物检测能力，超越了传统的金纳米颗粒 (AuNP) 和基于荧光的 ICT。在本研究中，我们创新性地开发了具有出色防污能力的两性离子二氧化硅包被的MNP（MNP@Si-Zwit/COOH），并有效地将其用于同步识别严重急性呼吸综合征冠状病毒（SARS）的核衣壳蛋白（N蛋白） -CoV-2）和甲型/乙型流感。具有 10% 两性离子配体的羧基功能化 MNP (MNP@Si-Zwit 10/COOH) 在用作 ICT 探针时表现出较宽的线性动态检测范围和最显着的信噪比。使用磁力分析仪 (MAR) 在 12 分钟内即可达到相对检测限 (LOD) 值，SARS-CoV-2 的相对检测限 (LOD) 值分别为 0.0062 ng/mL，N 的相对检测限 (LOD) 值分别为 0.0051 和 0.0147 ng/mL。甲型流感和乙型流感的蛋白质。通过集成计算机视觉和深度学习来增强免疫分析结果的图像处理以进行多重检测，在评估浓度为 0、0.1 的三种蛋白质时，分类精度达到了 0.9672–0.9936 范围。 、1 和 10 纳克/毫升。所提出的基于 MNP 的 ICT 用于生物标志物的多重诊断对于医疗机构和自我管理诊断环境的应用具有巨大的前景。