Identification of Mutations in Long Non-Coding RNA Sequence of Covid-19 using Machine Learning Approach

Main Article Content

Revathi Annem, Jyothi Singaraju


The transcripts which do not produce proteins and longer than 200 nucleotides are known to be long non- coding RNAs (lncRNAs). Mutations associated with disease is often studied to know about disease and its prevention. The mutations also help to diagnosis the diseases and develop new drug for the treatment of the diseases. Various computational methods have been developed to study about the lncRNAs functions and mutations associated with diseases but still, it is an unknown task. Machine Learning is one of the methods, which used to study about errors in the RNA sequence. As a lncRNA is novel class of RNAs the mutations of it are not yet studied. The mutations in lncRNA sequence play an important role in the disease development, so which can also be used as a strong biomarker of the diseases. Previous studies identified the mutations using high throughput DNA sequencing technologies. This proposed method focused on the mutation identification in Covid-19 long non-coding RNA sequence using Machine Learning Approach. The proposed system is a novel Machine Learning method for identifying the possible point mutations in the long non-coding RNA sequence. The results shown that this novel method has high accuracy in identifying point mutations.

Article Details