A novel feature extraction method based on highly expressed SNPs for tissue-specific gene prediction

Abstract Background Gene expression provides a means for an organism to produce gene products necessary the live. Variation in significant levels can distinguish and tissue which is expressed. Tissue-specific expression, often determined by single nucleotide polymorphisms (SNPs), potential molecular markers or therapeutic targets disease progression. Therefore, SNPs are good candidates identifying The current bioinformatics literature uses network modeling summarize complex interactions between transcription factors, genes, products. Here, our focus on SNPs’ impact tissue-specific levels. To best of knowledge, we not aware any studies that genes using SNP Method We propose novel feature extraction method based highly expressed k-mers as features. also optimal k-mer sizes used approach. Determining still open research question it depends dataset purpose analysis. evaluate algorithm’s performance range multinomial naive Bayes (MNB) classifier 49 human tissues from Genotype-Tissue Expression (GTEx) portal. Conclusions Our approach achieves practical results with size 3. Based analysis number under study, [7, 8, 9] [8, 9, 10] typically machine learning model.