1st International and 10th National Iranian Conference on Bioinformatics
Home Accepted Papers
Prediction of Plants lncRNAs with machine Learning based approaches
Paper ID : 1473-ICB10
Authors:
Maryam Azizi1, Ehsan Mohseni Fard2, Kaveh Kavousi3, Mohammad Reza Ghaffari *4
1Zanjan
2Department of Plant Production and Genetics, Faculty of Agriculture, University of Zanjan, Zanjan, Iran
3University of Tehran
4Systems and Synthetic Biology, Agricultural Biotechnology Research Institute of Iran, Agricultural Research, Education and Extention Organization (AREEO), Karaj, Iran
Abstract:
Long noncoding RNAs(lncRNAs) play a significant role in molecular mechanisms, including transcription, post-transcription, and epigenetic regulation. Coding and non-coding sequences can be detected using available high-throughput sequencing technologies and prediction tools. Since lncRNA sequences are less conserved than mRNA sequences, homology cannot identify lncRNA transcripts by itself. Thus, detecting lncRNAs is typically done by identifying known genes based on several manual curation and removal steps of coding RNAs, but these predictions may be incorrect due to incomplete information. The presence of ORFs in lncRNA, which encode a small peptide and play an important regulatory role, adds to the detection's complexity. Machine learning is used in many of the lncRNA prediction software programs currently available to researchers. Some of these software's are used to predict protein-coding potential and are not specific to lncRNAs, and some of them were developed for particular species. Machine learning can help automate lncRNA detection of big data more accurately and quickly. A general overview of the studies on lncRNAs prediction and validation and their advantages are presented in detail in the current review.
Keywords:
lncRNAs; Machine learning; Prediction
Status : Paper Accepted (Poster Presentation)