GUIdEStaR (G-quadruplex, uORF, IRES, Epigenetics, Small RNA, Repeats), the integrated metadatabase in conjunction with neural network methods

Abstract

Recently, articifial intelligence (AI) based analysis of sequencing data is gaining popularity in the area of bioinformatics. This paper introduces a ready-to-plug-in-to-AI database, GuideStar, integrated with five important nucleotide elements and structure, G-quadruplex, Uorf, IRES, Small RNA, Repeats. We demonstrated the database usage with attribute selection and classification methods using Weka software in identifying the features that are unique to transcription factor genes (TF genes) mediated by small RNAs originated from SARS-CoV-2 in comparison to those from human. G-quadruple (18:15:4, 14:11:3, PU1, 6:3:1), SINE (Short interspersed nuclear element) family, LINE (Long interspersed nuclear element) family, hAT family, and Tc1/mariner family were selected as top ranked attributes. However, statistical confidence was not measured due to small sample size (N: 7 vs 49) because a small number of TF genes have been identified as being mediated by small RNAs with viral origin. GuideStar is freely available at www.guidestar.kr.