Multiscale Element-Doped Nanowire Array-Coupled Machine Learning Reveals Metabolic Fingerprints of Nonreversible Liver Diseases

Abstract

Timely detection of nonreversible liver diseases contributes greatly to reasonable therapy and quality of life. Given the current situation, minimally invasive high-specificity molecular diagnosis based on body fluid can be a good choice. Herein, a mesoporous superstructure is designed using silicon atom-doped nanowire arrays to uniformly load Pt nanoparticles on the surface to produce a desirable ionization effect. We apply the multiscale element-doped nanowire arrays to efficiently assist extraction of high-quality metabolic fingerprints from only 35 nL of serum within seconds. Using different machine learning algorithms, we establish specific biomarker panels to distinguish different liver diseases from the healthy control, with more than 90% accuracy, sensitivity, and specificity. Moreover, from established biomarker panels, we further determine key metabolites of significant difference (p < 0.01) via group comparison to realize the discrimination of different liver diseases with 100% sensitivity. Our work confirms the design protocol of an advanced diagnosis tool and lays a robust foundation for metabolic molecular diagnosis in large-scale clinical application.

Designed Nanomaterials‐Assisted Proteomics and Metabolomics Analysis for In Vitro Diagnosis

“…Silica with superior heat carrier properties and high porosity has also been widely applied for omics analysis. [57] For example, Qu et al Reproduced with permission. [74] Copyright 2023, Elsevier.…”

“…Reproduced with permission. [ 57 ] Copyright 2022, American Chemical Society. D) The dendrimer‐modified silica nanoparticles.…”

“…C) The multiscale element-doped nanowire array. Reproduced with permission [57]. Copyright 2022, American Chemical Society.…”

Hollow Core–Shell Metal Oxide Heterojunctions for the Urinary Metabolic Fingerprint-Based Noninvasive Diagnostic Strategy

“…22−24 Various inorganic materials, especially hybrid metal oxides, show unique attraction in LDI analysis, namely avoiding background interference in the low mass range (<1000 Da) compared with traditional organic matrices. 12,25−27 The heat dissipation and charge transfer properties of hybrid metal oxide matrices are considered the great forces behind thermally driven desorption and photoionization during LDI-MS. 22,23,28 However, the deficient design of the structure and composition may have an insufficiently positive affection on the selective ionization of small metabolites, leading the results to not be ideal enough for precise disease screening. Our group has confirmed that p−n metal oxide heterojunctions (MOHs) can greatly improve the transfer of holes from n-type to p-type one, thereby enhancing the separation efficiency of electron−hole pairs at the heterojunction under laser irradiation 23 and facilitating charge transfer of analytes to improve ionization.…”

“…Mass spectrometry (MS), surface-enhanced Raman spectroscopy, and nuclear magnetic resonance are the most versatile analytical avenues for complex biological samples in metabolic research. In particular, MS-based techniques have high sensitivity and low sample consumption, which is especially meaningful for clinically valuable samples. , Recently, laser desorption/ionization MS (LDI-MS) has attracted much attention in metabolic analysis due to its high throughput, fast detection speed, and simple sample preparation. − Various inorganic materials, especially hybrid metal oxides, show unique attraction in LDI analysis, namely avoiding background interference in the low mass range (<1000 Da) compared with traditional organic matrices. ,− The heat dissipation and charge transfer properties of hybrid metal oxide matrices are considered the great forces behind thermally driven desorption and photoionization during LDI-MS. ,, However, the deficient design of the structure and composition may have an insufficiently positive affection on the selective ionization of small metabolites, leading the results to not be ideal enough for precise disease screening. Our group has confirmed that p–n metal oxide heterojunctions (MOHs) can greatly improve the transfer of holes from n-type to p-type one, thereby enhancing the separation efficiency of electron–hole pairs at the heterojunction under laser irradiation and facilitating charge transfer of analytes to improve ionization .…”