Abstract
As the most common pathological type of nephrotic syndrome,membranous nephropathy(MN)presents diversity in progression trends,facing severe complications.The precise discrimination of MN from healthy people,other types of nephrotic syndrome or those with therapeutic remission has always been huge challenge in clinics,not to mention comprehensive individualized monitoring relied on minimally invasive molecular detection means.Herein,we construct a functionalized pore architecture to couple with machine learning to aid all-round peptidome enrichment and data profiling from hundreds of hu-man serum samples,and finally establish a set of defined peptide panel consisting of 12 specific feature signals.In addition to the realization of above-mentioned precise discrimination with more than 97％of sensitivity,88％of accuracy and f1 score,the simultaneously comprehensive individualized monitoring for MN can also be achieved,including conventionally screening diagnosis,congeneric distinction and prog-nostic evaluation.This work greatly advances the development of peptidome data-driven individualized monitoring means for complex diseases and undoubtedly inspire more devotion into molecular detection field.
基金项目
国家重点研发计划(2018YFA0507501)
国家自然科学基金(22074019)
国家自然科学基金(21425518)
国家自然科学基金(22004017)
Shanghai Sailing Program(20YF1405300)
维普
万方数据