"Scientists in the laboratory of Rendong Yang, PhD, associate professor of Urology, have developed a new large language model that can interpret transcriptomic data in cancer cell lines more accurately than conventional approaches, as detailed in a recent study published in Nature Communications. Long-read RNA sequencing technologies have transformed transcriptomics research by detecting complex RNA splicing and gene fusion events that have often been missed by conventional short-read RNA-sequencing methods."
"To address this challenge, Yang's team developed a new genomic large language model, called DeepChopper, to facilitate the detection and removal of chimera artifacts in dRNAseq data. "Leveraging recent advances in large language model that can interpret complex genetic patterns, DeepChopper processes long genomic contexts with single-nucleotide resolution. This capability enables precise identification of adapter sequences within base-called long reads, facilitating the detection and removal of chimera artifacts in dRNAseq data," the authors wrote."
Long-read RNA sequencing, including nanopore direct RNA sequencing (dRNA-seq), enables full-length RNA molecule sequencing and reveals complex splicing and gene fusions often missed by short-read methods. dRNA-seq can produce chimeric artifacts that join multiple RNA sequences into a single incorrect read, compromising isoform detection and gene fusion quantification. DeepChopper is a genomic large language model designed to detect and remove these chimera artifacts by processing long genomic contexts with single-nucleotide resolution and identifying adapter sequences within base-called long reads. Application to a prostate cancer cell line transcriptome validated the tool's utility for improving transcriptomic accuracy in cancer cell lines.
Read at News Center
Unable to calculate read time
Collection
[
|
...
]