Development of a Single Molecule Counting Assay to Differentiate Chromophobe Renal Cancer and Oncocytoma in Clinics.

Abstract

Simple SummaryWe previously reported a gene signature, “Chromophobe-Oncocytoma Gene Signature” (COGS), to differentiate chromophobe renal cell carcinoma from oncocytoma. Current clinical workflow with histology and immunohistochemistry can fail to distinguish these two renal cancers. We have evaluated the potential of COGS genes to classify these two renal tumors, on a single-molecule counting platform by measuring the expression of the COGS genes in archival tissue at Augusta University Medical Center. We show the expression level difference of the COGS signature in these tumors is able to classify these cancers accurately using machine learning. The assay has the potential to be instituted in clinically complex cases to differentiate these renal tumors.Malignant chromophobe renal cancer (chRCC) and benign oncocytoma (RO) are two renal tumor types difficult to differentiate using histology and immunohistochemistry-based methods because of their similarity in appearance. We previously developed a transcriptomics-based classification pipeline with “Chromophobe-Oncocytoma Gene Signature” (COGS) on a single-molecule counting platform. Renal cancer patients (n = 32, chRCC = 17, RO = 15) were recruited from Augusta University Medical Center (AUMC). Formalin-fixed paraffin-embedded (FFPE) blocks from their excised tumors were collected. We created a custom single-molecule counting code set for COGS to assay RNA from FFPE blocks. Utilizing hematoxylin-eosin stain, pathologists were able to correctly classify these tumor types (91.8%). Our unsupervised learning with UMAP (Uniform manifold approximation and projection, accuracy = 0.97) and hierarchical clustering (accuracy = 1.0) identified two clusters congruent with their histology. We next developed and compared four supervised models (random forest, support vector machine, generalized linear model with L2 regularization, and supervised UMAP). Supervised UMAP has shown to classify all the cases correctly (sensitivity = 1, specificity = 1, accuracy = 1) followed by random forest models (sensitivity = 0.84, specificity = 1, accuracy = 1). This pipeline can be used as a clinical tool by pathologists to differentiate chRCC from RO.