Dataset Information

Urinary Proteomic Spectra Analysis Based on Machine Learning for Classification of Kidney Diseases

ABSTRACT: To extract urinary proteome spectral features based on advanced mass spectrometer and machine learning algorithms, it could get more accurate reporting results for disease classification. We tried to establish a novel diagnosis model of kidney diseases by combining machine learning XGBoost algorithm with complete urinary proteomic information.

INSTRUMENT(S): Orbitrap Fusion Lumos

ORGANISM(S): Homo Sapiens (human)

TISSUE(S): Urine

SUBMITTER: Yong Zhang

LAB HEAD: Yong Zhang

PROVIDER: PXD018996 | Pride | 2022-09-13

REPOSITORIES: Pride

ACCESS DATA

Dataset's files

Source:

Items per page:

1 - 5 of 194

Similar Datasets

Project description:Background. Although gene expression arrays have been used to generate molecular predictors of relapse and drug sensitivity in breast cancer, no large study describes genes and exons differentially expressed between breast cancer and benign lesions. Methods. One hundred and sixty-five tumour samples were obtained by fine needle aspiration (FNA). cDNA were hybridized on Splice ArrayTM. A nearest centroid prediction rule was developed to classify lesions as malignant or benign on a training set, and its performance evaluated on an independent validation set. A two-way ANOVA model was used to identify probesets that present a differential expression between cancer and benign lesions while adjusting for scan dates. P-values were adjusted for False Discovery Rate. Findings. Overall 120 breast cancers and 45 benign lesions were included in the study. A 1228-probeset molecular classifier for breast cancer diagnosis was generated from the training set (n=94). This signature accurately classified all samples (100% accuracy, 95% exact CI: 96-100%). In the validation set (n=71), the molecular predictor accurately classified 68 out of 71 tumours (96%, 95% CI: 88-99%). When the 165 samples were taken into account, 37 858 exon-probesets (5.4%) and 3733 genes (20%) were found to be differentially expressed between malignant and benign conditions (adjusted p-value<0.05). Pathway analyses showed that genes involved in spliceosome assembly were significantly enriched in malignant condition (permutation p=0.002). In the same population of 165 samples, 956 exon-probesets presented both a higher intensity and higher splice index in breast cancer, although located on unchanged genes. Interpretation. The present study provides a thorough description of differentially expressed exons between breast cancer and benign lesions, and emphasizes the contribution of spliceosome and alternative transcripts to the molecular portrait of breast malignancy. This allowed the development of a molecular classifier for breast cancer diagnosis using FNA.

Project description:Pseudomonas aeruginosa is one of the most frequent pathogen dominant in complicated urinary tract infections (UTI). To unravel the adaptation strategies of P. aeruginosa to the conditions in the urinary tract and to define the underlying regulatory network an artificial growth system mimicking the conditions in the urinary tract was established. Transcriptome analyses were used to investigate the physiological status of P. aeruginosa under this conditions. We performed comparisons to identify genes induced under artificial urinary tract conditions to unravel the adaptive strategies and the underlying regulatory network used by Pseudomonas aeruginosa during urinary tract infections using Affimetrix GeneChips. Pseudomonas aeruginosa wild type strain PAO1 was grown in an artificial in vitro growth system mimicking the conditions in the urinary tract. Therefore, biofilms were grown on the surface of membrane filters placed on agar plates at 37 Â°C up to the late logarithmic state under aerobic and anaerobic conditions (incubated in an anaerobic beanch). An artificial urine medium (AUM) simulating the averaged urine of an human adult was used as nutrient souce. 10-fold diluted Luria Bertani (LB)-medium was used as reference medium. For growth under oxygen depletion the media were supplemented with 50 mM KNO3 to sustain anaerobic respiration. The biofilms were harveted at this time points and resuspsended in 0.9% (w/v) NaCl. The OD578 of biofilm suspension was 0.8 for all tested conditions. First comparison: Identification of genes induced or repressed under aerobic conditions in the P. aeruginosa wild type PAO1. Here we compared the transcriptome profile of P. aeruginosa PAO1 grown aerobically for 18 h to the late logarithmic phase in biofilms on AUM with the transcriptome profile of the PAO1 strain, which was grown aerobically for 18 h to the late logarithmic phase in biofilms on 10-fold diluted LB. Second comparison: Identification of genes induced or repressed under anaerobic conditions in the P. aeruginosa wild type PAO1. Here we compared the transcriptome profile of P. aeruginosa PAO1 grown anaerobically for 2 days up to the late logarithmic phase in biofilms on AUM supplemented with 50 mM nitrate with the transcriptome profile of the PAO1 strain, which was grown anaerobically for 2 days up to the late logarithmic phase in biofilms on 10-fold diluted LB supplemented with 50 mM nitrate.

			Action	DRS
	DNK_Urine_01.raw	Raw
	DNK_Urine_02.raw	Raw
	DNK_Urine_03.raw	Raw
	DNK_Urine_04.raw	Raw
	DNK_Urine_05.raw	Raw

Dataset Information

Urinary Proteomic Spectra Analysis Based on Machine Learning for Classification of Kidney Diseases

Dataset's files

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets