NanoTS: a deep learning tool for accurate SNP calling in nanopore long-read transcriptome data.

NanoTS achieves F1 scores above 0.980 and 0.966 in SNP detection from nanopore transcriptome data, outperforming existing methods.

• Why it matters: Accurate variant detection in nanopore long-read transcriptome data is challenging, limiting clinical and research applications involving SNPs and pathogenic variants.
• What they did: NanoTS is a deep learning-based tool that analyzes diverse nanopore transcriptome sequencing data, focusing on SNP detection with at least five supporting reads.
• The result: NanoTS enables highly accurate detection and genotype calling of pathogenic variants in Mendelian disorders, suggesting its potential for clinical utility.