Unravelling cancer subtype-specific driver genes in single-cell transcriptomics data with CSDGI

Abstract

AbstractCancer is known as a heterogeneous disease.Cancerdrivergenes (CDGs) need to be inferred for understanding tumor heterogeneity in cancer. However, the existing computational methods have identified many common CDGs. A key challenge exploring cancer progression is to infer cancer subtype-specific driver genes (CSDGs), which provides guidane for the diagnosis, treatment and prognosis of cancer. The significant advancements in single-cell RNA-sequencing (scRNA-seq) technologies have opened up new possibilities for studying human cancers at the individual cell level. In this study, we develop a novel unsupervised method,CSDGI(CancerSubtype-specificDriverGeneInference), which applies Encoder-Decoder-Framework consisting of low-rank residual neural networks to inferring driver genes corresponding to potential cancer subtypes at single-cell level. To infer CSDGs, we applyCSDGIto the tumor single-cell transcriptomics data. To filter the redundant genes before driver gene inference, we perform the differential expression genes (DEGs). The experimental results demonstrateCSDGIis effective to infer driver genes that are cancer subtype-specific. Functional and disease enrichment analysis shows these inferred CSDGs indicate the key biological processes and disease pathways.CSDGIis the first method to explore cancer driver genes at the cancer subtype level. We believe that it can be a useful method to understand the mechanisms of cell transformation driving tumours.Author summaryCancer is recognized as a complex disease with diverse characteristics. In order to comprehend the diversity within tumors, it is essential to infer cancer subtype-specific driver genes (CSDGs), which offer valuable insights for investigating cancer progression and treatment. The remarkable progress made in single-cell RNA-sequencing (scRNA-seq) technologies has ushered in new prospects for studying human cancers at the cellular level. Cancer Subtype-specific Driver Gene Inference (CSDGI) is a novel unsupervised method proposed. In our study, we use Encoder-Decoder-Framework to infer driver genes specific to cancer subtypes in the CSDGI. We apply CSDGI to three tumor single-cell transcriptomics data. The experimental results have shown the effectiveness of CSDGI. Furthermore, functional and disease enrichment analyses illustrate that these inferred CSDGs shed light on crucial biological processes and disease pathways. Our collection of driver genes will serve as a valuable resource in unraveling the mechanisms driving cell transformation in tumors.