CORTEXA
← Browse
crossrefAdvanced Science2026-05-14Cited by 0

A Bioinspired Three‐Dimensional High‐Curvature Nano‐Interface Integrated Microfluidic Chip for Small Extracellular Vesicles Enrichment and Machine Learning‐Assisted Prostate Cancer Precision Diagnosis

Le Wang, Yizhong Liang, Manan Sulaiman, Jiaqi Du, Ming Jiang, Zhihua Wang, Xu Yu, Li Xu

ABSTRACT The efficient and unbiased isolation of small extracellular vesicles (sEVs) from complex biological fluids remains a major obstacle for clinical diagnostics. Here, we report a bioinspired microfluidic chip that integrates a three‐dimensional high‐curvature TiO 2 nano‐interface (3D Hic‐TiO 2 ) with a biotin‐modified artificial insertion peptide (BAIP) modification for rapid enrichment of sEV. Bowl‐shaped TiO 2 nanospheres fabricated via electrospray provide topological nanotraps that match the size and curvature of sEVs, enabling efficient size‐selective capture. Coupled with BAIP‐mediated membrane affinity and herringbone‐induced chaotic mixing, the BAIP‐TiO 2 ‐Chip achieved >90% capture efficiency within 5 min. Redox‐responsive BAIP variants enabled mild release of intact sEVs for downstream analysis. When the BAIP‐TiO 2 ‐Chip was applied to plasma samples from clinical prostate cancer (PCa) patients, mass spectrometry‐based proteomic profiling revealed 110 differentially expressed sEV‐associated proteins, including candidates involved in immune regulation and cell adhesion. In parallel, simultaneous quantification of PSA and PSMA mRNAs in sEVs could be achieved. Assisted by machine learning, a boosted decision tree model achieved 80% diagnostic accuracy in distinguishing PCa from benign conditions and healthy donors. This work presents a versatile platform for sEV isolation, enabling both transcriptomic mRNA analysis and proteomic profiling, and provides new molecular insights into PCa for improved early diagnosis.

View free PDFSource page

Related papers

crossrefAdvanced Science2026-06-03

Machine Learning‐Assisted KCl‐CaCl <sub>2</sub> ‐LiCl Electrolyte Design for Low‐Temperature, High‐Performance Calcium‐Based Liquid Metal Batteries

Xinglin Zhou, Lei Huang, Yan Zhou, Xiaohui Ning

ABSTRACT Calcium‐based liquid metal batteries are promising for large‐scale energy storage due to calcium abundance and low cost, yet their practical applications are impeded by high operating temperatures, severe self‐discharge, limited coulombic efficiency, and rapid capacity f…

View free PDFSource page
crossrefAdvanced Science2026-06-26

Machine‐Learning Framework for Designing Stable Interfaces in All‐Solid‐State Lithium‐Ion Batteries

Sehyeok Park, Myeongcho Jang, Hun‐Gi Jung, Kyung Yoon Chung, Seungho Yu

ABSTRACT All‐solid‐state lithium‐ion batteries are promising next‐generation energy‐storage systems, but interfacial instability between cathodes and solid electrolytes remains a major barrier to long‐term durability. Interfacial coatings can mitigate these reactions, yet coating…

View free PDFSource page
crossrefAdvanced Science2026-05-25Cited by 9

Interpretable Machine Learning Framework for Nb─Si Based Alloy Design with Enhanced Fracture Toughness

Dezhi Chen, Chao Xu, Jingyue Yu, Qi Wang, Hongze Fang, Shuo Yin, et al.

ABSTRACT A continuing challenge in aerospace materials is the search for alloys that have desired functional properties to operate at higher temperatures with lower densities. This improves aero‐engine efficiency and reduces CO 2 and other harmful emissions, aligning with aviatio…

View free PDFSource page
crossrefAdvanced Science2026-06-22

Advancing the Design of High‐Efficiency Printable Hole‐Conductor‐Free Mesoscopic Perovskite Solar Cells Through Machine Learning

Hao Meng, Jingzi Zhang, Xu Zhu, Yuelin Wang, Antai Yang, Kailong Hu, et al.

ABSTRACT Breaking through the power conversion efficiency (PCE) limits of printable mesoscopic perovskite solar cells (p‐MPSCs) with machine learning (ML) shows great potential, but has not yet been accomplished. This work establishes a reliable workflow by constructing a high‐qu…

View free PDFSource page
crossrefAdvanced Science2026-06-15

Physics‐Informed Machine Learning for Sustainable Alloy Design: Toward a Recyclable Unified Q&amp;P Steel

Xiaolu Wei, Yong Li, Chenchong Wang, Lingyu Wang, Xiang Song, Keming Mao, et al.

ABSTRACT For sustainable alloy design, unified‐composition approaches offer an effective route to deliver multiple performance levels while reducing chemistry complexity. Quenching and partitioning (Q&amp;P) steels are widely used advanced high‐strength steels, yet their grade de…

View free PDFSource page
crossrefAdvanced Science2026-07-20

Machine Learning–Guided Surface Strain Engineering in Connected Platinum–Nickel Nanoparticle Catalysts for Advanced Oxygen Reduction Performance

Aparna Chitra Sudheer, Gopinathan M. Anilkumar, Hidenori Kuroki, Yuuki Sugawara, Takeo Yamaguchi

ABSTRACT Engineering the surface structure of catalysts is critical for achieving high intrinsic activity in the oxygen reduction reaction (ORR). We report a machine‐learning (ML)‐guided materials design strategy for the synthesis of support‐free, connected nanoparticle catalysts…

View free PDFSource page