Disease-Specific TCR Identification from Bulk TCR Sequencing Data

  • Processed and analyzed multi-disease bulk TCR datasets comprising 465.8M human TCR entries, including 330.3M from 59 NCBI projects and 135.5M from 66 immuneACCESS projects, enabling comprehensive TCR repertoire analysis.
  • Developed a disease-specific recognition framework utilizing unsupervised learning methodologies with the GIANA tool, enhancing TCR classification accuracy.