-
公开(公告)号：US20240347136A1
公开(公告)日：2024-10-17
申请号：US18036947
申请日：2022-08-17
发明人： Xiaoliang CHENG , Lei ZHANG , Yue ZHOU , Wei ZHANG , Kejia ZHENG
摘要： Disclosed are a feature screening method and apparatus, a storage medium, and an electronic device. The method includes: determining feature validation subsets based on data features in sample data; partitioning the sample data into individual sample groups corresponding to different individuals based on an individual to which the sample data belongs, and performing cross-validation partitioning based on the individual sample groups, to determine a training dataset and a validation dataset obtained through partitioning; training a machine learning model of a processing target based on the training and validation datasets corresponding to each feature validation subset; and determining a target data feature group corresponding to the processing target based on training process data of each model. Thereout, cross-validation partitioning makes sample data of one individual not being partitioned into training and validation datasets meanwhile, avoiding impact of individual sample data on performance of the model and improving accuracy of feature screening.
-
公开(公告)号：US20230258648A1
公开(公告)日：2023-08-17
申请号：US18301249
申请日：2023-04-16
发明人： Xiaoliang CHENG , Meijuan LI , Yue ZHOU , Wei ZHANG , Kejia ZHENG
CPC分类号： G01N33/6815 , G16H50/30 , G01N2800/042 , G01N2800/50
摘要： The present disclosure provides a marker and use thereof in predicting a possibility of a subject with diabetes. The marker described may include at least one of α-hydroxybutyric acid (α-HB), 1,5-anhydroglucitol (1,5-AG), asymmetric dimethylarginine (ADMA), cystine, ethanolamine, taurine, L-leucine, L-tryptophan, hydroxylysine, and L-aspartate. The possibility of the subject with diabetes may be predicted using a prediction model (e.g., prediction models 2-5) related to the marker based on a concentration of the marker. The prediction model 2 is related to α-HB. The prediction model 3 is related to 1,5-AG and ADMA. The prediction model 4 is related to cystine, ethanolamine, taurine, L-leucine, L-tryptophan and hydroxylysine. The prediction model 5 is related to α-HB, 1,5-AG, cystine, ethanolamine, taurine and L-aspartate.
-
3.发明公开公开(公告)号：US20230393042A1
公开(公告)日：2023-12-07
申请号：US18036646
申请日：2022-08-17
发明人： Xiaoliang CHENG , Jing YU , Yue ZHOU , Wei ZHANG , Kejia ZHENG
CPC分类号： G01N1/42 , G01N1/34 , G01N30/72 , G01N30/34 , G01N2001/4088 , C12N9/0032 , C12Y304/21004 , C12Y105/03004 , C12N9/6427
摘要： The invention discloses a pretreatment method, a preservation method, an automatic treatment system and a detection method for a urine sample, and directs to the technical field of biological detection. The pretreatment method comprises subjecting a urine sample after protein lysis to a reductive alkylation treatment, followed by protein enrichment and enzymolysis. The protein enrichment is performed on the sample after the reductive alkylation treatment using a PVDF filter plate for protein enrichment; The invention also provides an automatic treatment system and an automatic sample treatment method. The treatment system greatly reduces the labor intensity of people, is beneficial to facilitate the treatment efficiency of urine sample treatment, meets the requirements of high-flux and automated pretreatment of the proteomics, and accommodates the reproducibility and flux of current clinical needs.
-
公开(公告)号：US20230358754A1
公开(公告)日：2023-11-09
申请号：US18356209
申请日：2023-07-20
发明人： Xiaoliang CHENG , Meijuan LI , Yue ZHOU , Wei ZHANG , Kejia ZHENG
CPC分类号： G01N33/6815 , G16H50/30 , G01N2800/042 , G01N2800/50
摘要： The present disclosure provides a marker and use thereof in predicting a possibility of a subject with diabetes. The marker described may include at least one of α-hydroxybutyric acid (α-HB), 1,5-anhydroglucitol (1,5-AG), asymmetric dimethylarginine (ADMA), cystine, ethanolamine, taurine, L-leucine, L-tryptophan, hydroxylysine, and L-aspartate. The possibility of the subject with diabetes may be predicted using a prediction model (e.g., prediction models 2-5) related to the marker based on a concentration of the marker. The prediction model 2 is related to α-HB. The prediction model 3 is related to 1,5-AG and ADMA. The prediction model 4 is related to cystine, ethanolamine, taurine, L-leucine, L-tryptophan and hydroxylysine. The prediction model 5 is related to α-HB, 1,5-AG, cystine, ethanolamine, taurine and L-aspartate.
-
公开(公告)号：US20230258654A1
公开(公告)日：2023-08-17
申请号：US18301279
申请日：2023-04-17
发明人： Xiaoliang CHENG , Yue ZHOU , Wei ZHANG , Kejia ZHENG
IPC分类号： G01N33/68
CPC分类号： G01N33/6848 , G01N2570/00
摘要： The embodiments of the present disclosure provide a method for analyzing a body fluid proteome. The method comprises: obtaining a sample to be tested I enriched with low-abundance proteins by removing high-abundance proteins in an initial sample A using an affinity technique; obtaining a sample to be tested II enriched with low-abundance proteins by removing high-abundance proteins in an initial sample B using chemical precipitation, wherein the initial sample A and the initial sample B are obtained from a same body fluid sample of a same subject; obtaining a proteome data set I by performing proteomic analysis on the sample to be tested I; obtaining a proteome data set II by performing proteomic analysis on the sample to be tested II; and determining a final quantified proteome data set of the body fluid sample based on the proteome data set I and the proteome data set II.
-
-
-
-
搜索结果
5 条记录 (耗时 0.02 秒)
