Prediction of ncRNA from RNA-Seq data using machine learning techniques
by Faroza Shamsheem; Tunga Arundhathi; Khaleda Afroaz
International Journal of Bioinformatics Research and Applications (IJBRA), Vol. 19, No. 2, 2023

Abstract: Non-coding RNAs (ncRNAs) are currently receiving more attention in bioinformatics and biology as a result of the rapidly increasing significance of biological research. In biological processes like transcription and translation, they are crucial. We must classify ncRNAs in order to better understand the causes of illness and develop effective treatments. It is preferable to classify non-coding RNA transcripts into several groups in addition to differentiating between coding and non-coding transcripts. There are several approaches available for this task, but their classification performance is still a major problem. In this study, we initially developed machine learning techniques to separate coding transcripts from non-coding transcripts, and then we classified ncRNAs into corresponding classifications. On the human dataset, we have assessed the effectiveness of four machine learning methods, namely: logistic regression, random forest, XGBoost, and decision tree. Among these four algorithms, the maximum accuracy level is gained by random forest, with nearly 83%.

Online publication date: Mon, 31-Jul-2023

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Bioinformatics Research and Applications (IJBRA):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com