PREDICTION OF miRNA TARGET GENES IN RENAL CELL CARCINOMA BY USING MACHINE LEARNING ALGORITHMS
Download
Author:
SADDAM HUSSAIN
Citable URI :
https://vspace.vu.edu.pk/detail.aspx?id=274
Publisher :
Virtual University
Date Issued:
1/2/2020 12:00:00 AM
Abstract
Renal cell cancer (RCC) is most prevalent type of renal carcinoma found in adults. The association of miRNAs with cancers is confirmed by identifying crucial role in many physiological processes like development, proliferation and death of cells. miRNAs enable the early cancer diagnosis and prognosis by classifying the miRNAs required for cancer diagnosis. Early stage cancer identification is soothing to deal and miRNAs are potentially incredible markers. Researchers looked at expressed miRNAs in the RCC and Scrabbled to create miRNA profiles to submit early detection and successful intervention. The prediction of miRNAs target genes can better understand personalized medicine and the application of machine learning (ML) methods are used to cope with big problems. So, we used Microsoft Azure ML (Platform as a Service) services to design a predictive experiment model with classification algorithms (Naive Bayes and Support vector machine), predictive models are trained and tested by putative datasets downloaded from miRTar.human and consume as web services and office add-ins in MS Excel. These models retrieved predicted information from 11460 results about 620 different miRNAs targeting 164 transcripts with 1695 different position on 20 genes of 14 Chromosome. The results showed that hsa-miR-1273d transcript ABCC2 and MAPK1 (with BC099905 and NM_002745 transcripts respectively), hsa-miR-744* transcript BRAF and BCL2 (with M14745 and NM_000633 transcripts) and hsa-miR-143* transcript PIK3CA, ALOX5, HIF1A, MAPK and TP53.
URI :
https://vspace.vu.edu.pk/details.aspx?id=274
Citation:
Hussain, S(2019). PREDICTION OF miRNA TARGET GENES IN RENAL CELL CARCINOMA BY USING MACHINE LEARNING ALGORITHMS. Virtual University of Pakistan.(Lahore, Pakistan).
Version :
Final Version
Terms of Use :
Detailed Terms :
Journal :
Files in this item |
Name |
Size |
Format |
Spring 2019_BIF720_MS160400791.pdf |
836kb |
pdf |