Integrated differential transcript usage and transcript abundance analyses reveal isoform-level remodeling in clear cell renal cell carcinoma

Clear cell renal cell carcinoma (ccRCC) is characterized by transcriptional reprogramming driven by hypoxia signaling, metabolic rewiring, and immune modulation. While gene-level analyses have defined key features of ccRCC biology, they do not capture isoform-level variation arising from alternative splicing. Differential transcript usage (DTU) represents an additional regulatory layer that may influence protein function, pathway activity, and clinical outcomes, yet its role in ccRCC biology and prognosis remains incompletely understood. We assessed differential expression in 127 ccRCC tumors and 33 normal-adjacent tissues from the Dartmouth Cancer Center cohort, with external validation in 94 CPTAC tumors, adjusting for cell-type proportions. Formal DTU was first tested using DRIMSeq/stageR, which evaluates shifts in relative isoform proportions within genes. StageR-significant transcripts were then evaluated in a separate covariate-adjusted limma-voom transcript-abundance analysis incorporating clinical and tumor microenvironment covariates. Consensus clustering of transcript-level expression defined tumor subgroups, and Cox proportional hazards modeling integrated transcript-level features with clinical variables. In tumor versus normal comparisons, 1,170 transcripts passed both the formal DTU screen and the covariate-adjusted transcript-abundance criteria, mapping to canonical ccRCC pathways with distinct patterns across functional and non-functional transcript classes. Consensus clustering based on transcript-level expression identified two subgroups with distinct angiogenic profiles and significant survival differences. Cluster-level analysis revealed DTU-supported transcript-abundance changes in genes involved in cytoskeletal organization ( ACTB ), immune processes ( B2M ), extracellular matrix organization ( FN1 , APLP2 ), and iron metabolism ( FTH1 ), with protein domain alterations including the loss of actin-associated domains in ACTB and immunoglobulin-like domains in B2M . Prognostic modeling identified twelve candidate transcripts passing an exploratory selection threshold across repeated train-test splits and provided preliminary evidence of additional prognostic information when combined with clinical variables. External validation was limited to two overlapping candidates, FGFR1 and NUCB1 . Isoform-level features may serve as biomarkers and therapeutic targets in ccRCC.