Renal clear cell carcinoma (ccRCC) comprises over 75% of all renal tumors and arises in the epithelial cells of the proximal convoluted tubule. Molecularly ccRCC is characterized by copy number alterations (CNAs) such as the loss of chromosome 3p and VHL inactivation. Additional driver mutations (SETD2, PBRM1, BAP1, and others) promote genomic instability and tumor cell metastasis through the dysregulation of various metabolic and immune-response pathways. Many researchers identified mutation, gene expression, and proteomic signatures for early diagnosis and prognostics for ccRCC. Despite a tremendous influx of data regarding DNA alterations, gene expression, and protein expression, the incorporation of these analyses for diagnosis and prognosis of RCC into the clinical application has not been implemented yet. In this review, we focused on the molecular changes associated with ccRCC development, along with gene expression and protein signatures, to emphasize the utilization of these molecular profiles in clinical practice. These findings, in the context of machine learning and precision medicine, may help to overcome some of the barriers encountered for implementing molecular profiles of tumors into the diagnosis and treatment of ccRCC.

Publicly available gene expression datasets were analyzed to develop a chromophobe and oncocytoma related gene signature (COGS) to distinguish chRCC from RO. The datasets GSE11151, GSE19982, GSE2109, GSE8271 and GSE11024 were combined into a discovery dataset. The transcriptomic differences were identified with unsupervised learning in the discovery dataset (97.8% accuracy) with density based UMAP (DBU). The top 30 genes were identified by univariate gene expression analysis and ROC analysis, to create a gene signature called COGS. COGS, combined with DBU, was able to differentiate chRCC from RO in the discovery dataset with an accuracy of 97.8%. The classification accuracy of COGS was validated in an independent meta-dataset consisting of TCGA-KICH and GSE12090, where COGS could differentiate chRCC from RO with 100% accuracy. The differentially expressed genes were involved in carbohydrate metabolism, transcriptomic regulation by TP53, beta-catenin-dependent Wnt signaling, and cytokine (IL-4 and IL-13) signaling highly active in cancer cells. Using multiple datasets and machine learning, we constructed and validated COGS as a tool that can differentiate chRCC from RO and complement histology in routine clinical practice to distinguish these two tumors.

Renal clear cell carcinoma (ccRCC) comprises over 75% of all renal tumors and arises in the epithelial cells of the proximal convoluted tubule. Molecularly ccRCC is characterized by copy number alterations (CNAs) such as the loss of chromosome 3p and VHL inactivation. Additional driver mutations (SETD2, PBRM1, BAP1, and others) promote genomic instability and tumor cell metastasis through the dysregulation of various metabolic and immune-response pathways. Many researchers identified mutation, gene expression, and proteomic signatures for early diagnosis and prognostics for ccRCC. Despite a tremendous influx of data regarding DNA alterations, gene expression, and protein expression, the incorporation of these analyses for diagnosis and prognosis of RCC into the clinical application has not been implemented yet. In this review, we focused on the molecular changes associated with ccRCC development, along with gene expression and protein signatures, to emphasize the utilization of these molecular profiles in clinical practice. These findings, in the context of machine learning and precision medicine, may help to overcome some of the barriers encountered for implementing molecular profiles of tumors into the diagnosis and treatment of ccRCC.

Gene expression profiling has been shown to be comparable to other molecular methods for glioma classification. We sought to validate a gene-expression based glioma classification method. Formalin-fixed paraffin embedded tissue and flash frozen tissue collected at the Augusta University (AU) Pathology Department between 2000–2019 were identified and 2 mm cores were taken. The RNA was extracted from these cores after deparaffinization and bead homogenization. One hundred sixty-eight genes were evaluated in the RNA samples on the nCounter instrument. Forty-eight gliomas were classified using a supervised learning algorithm trained by using data from The Cancer Genome Atlas. An ensemble of 1000 linear support vector models classified 30 glioma samples into TP1 with classification confidence of 0.99. Glioma patients in TP1 group have a poorer survival (HR (95% CI) = 4.5 (1.3–15.4), p = 0.005) with median survival time of 12.1 months, compared to non-TP1 groups. Network analysis revealed that cell cycle genes play an important role in distinguishing TP1 from non-TP1 cases and that these genes may play an important role in glioma survival. This could be a good clinical pipeline for molecular classification of gliomas.

Multiple cross-sectional and longitudinal studies have shown that serum levels of the chemokine ligand 2 (CCL-2) are associated with type 1 diabetes (T1D), although the direction of effect differs. We assessed CCL-2 serum levels in a longitudinal cohort to clarify this association, combined with genetic data to elucidate the regulatory role of CCL-2 in T1D pathogenesis.

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.