KDDC: a new framework that integrates kmers, dataset filtering, dimension reduction and classification algorithms to achieve immune cell heterogeneity classification.

Introduction: Integrating immune repertoire sequencing data with single cell sequencing data offers profound insights into the diversity of immune cells and their dynamic changes across various disease states. Methods: Here, we propose a novel KDDC framework that integrates kmers, dataset selection, dimensionality reduction and classification algorithms to facilitate the heterogeneous classification of immune cells. Results and Discussion: By comparing various kmer length combinations across seven different classification algorithms, we found that B cell receptor-based cellsubset classification outperforms T cell receptor-based classification, achievingan average AUC of over 96%. This finding offers a new perspective on the classification of immune cells. We also observed that 11 distinct cell subpopulations exhibited differences in cell proportions, inflammatory factorexpression, cell communication, and metabolic pathways, with notable activity in metabolic pathways. These variations may reflect the adaptive changes of cellsubpopulations in response to different disease states. This study aims to uncoverthe potential biological significance of immune prediction, target antigens, andeffective evaluation by analyzing the immune characteristics of specific cellsubsets at the cellular level. These findings will not only enhance ourunderstanding of immune system functions but also offer new directions for the development and optimization of immunotherapy.