Clinica chimica acta; international journal of clinical chemistry · 2022
Peritoneal effluent MicroRNA profile for detection of encapsulating peritoneal sclerosis.
СтатьяНазвание и аннотация: Перевод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Wu Kun-Lin, Chou Che-Yi, Chang Hui-Yin, Wu Chih-Hsun, Li An-Lun, Chen Chien-Lung, Tsai Jen-Chieh, Chen Yi-Fan, Chen Chiung-Tong, Tseng Chin-Chung, Chen Jin-Bor, Wang I-Kuan, Hsu Yu-Juei, Lin Shih-Hua, Huang Chiu-Ching, Ma Nianhan
Аннотация
BACKGROUND: Encapsulating peritoneal sclerosis (EPS) is a catastrophic complication of peritoneal dialysis (PD) with high mortality. Our aim is to develop a novel noninvasive microRNA (miRNA) test for EPS.
METHODS: We collected 142 PD effluents (EPS: 62 and non-EPS:80). MiRNA profiles of PD effluents were examined by a high-throughput real-time polymerase chain reaction (PCR) array to first screen. Candidate miRNAs were verified by single real-time PCR. The model for EPS prediction was evaluated by multiple logistic regression and machine learning.
RESULTS: Seven candidate miRNAs were identified from the screening of PCR-array of 377 miRNAs. The top five area under the curve (AUC) values with 5 miRNA-ratios were selected using 127 samples (EPS: 56 vs non-EPS: 71) to produce a receiver operating characteristic curve. After considering clinical characteristics and 5 miRNA-ratios, the accuracies of the machine learning model of Random Forest and multiple logistic regression were boosted to AUC 0.97 and 0.99, respectively. Furthermore, the pathway analysis of miRNA associated targeting genes and miRNA-compound interaction network revealed that these five miRNAs played the roles in TGF-β signaling pathway.
CONCLUSION: The model-based miRNA expressions in PD effluents may help determine the probability of EPS and provide further therapeutic opinion for EPS.
METHODS: We collected 142 PD effluents (EPS: 62 and non-EPS:80). MiRNA profiles of PD effluents were examined by a high-throughput real-time polymerase chain reaction (PCR) array to first screen. Candidate miRNAs were verified by single real-time PCR. The model for EPS prediction was evaluated by multiple logistic regression and machine learning.
RESULTS: Seven candidate miRNAs were identified from the screening of PCR-array of 377 miRNAs. The top five area under the curve (AUC) values with 5 miRNA-ratios were selected using 127 samples (EPS: 56 vs non-EPS: 71) to produce a receiver operating characteristic curve. After considering clinical characteristics and 5 miRNA-ratios, the accuracies of the machine learning model of Random Forest and multiple logistic regression were boosted to AUC 0.97 and 0.99, respectively. Furthermore, the pathway analysis of miRNA associated targeting genes and miRNA-compound interaction network revealed that these five miRNAs played the roles in TGF-β signaling pathway.
CONCLUSION: The model-based miRNA expressions in PD effluents may help determine the probability of EPS and provide further therapeutic opinion for EPS.