Connecting Histopathology Imaging and Proteomics in Kidney Cancer through Machine Learning

Abstract

Proteomics data encode molecular features of diagnostic value and accurately reflect key underlying biological mechanisms in cancers. Histopathology imaging is a well-established clinical approach to cancer diagnosis. The predictive relationship between large-scale proteomics and H&E-stained histopathology images remains largely uncharacterized. Here we investigate such associations through the application of machine learning, including deep neural networks, to proteomics and histology imaging datasets generated by the Clinical Proteomic Tumor Analysis Consortium (CPTAC) from clear cell renal cell carcinoma patients. We report robust correlations between a set of diagnostic proteins and predictions generated by an imaging-based classification model. Proteins significantly correlated with the histology-based predictions are significantly implicated in immune responses, extracellular matrix reorganization, and metabolism. Moreover, we showed that the genes encoding these proteins also reliably recapitulate the biological associations with imaging-derived predictions based on strong gene–protein expression correlations. Our findings offer novel insights into the integrative modeling of histology and omics data through machine learning, as well as the methodological basis for new research opportunities in this and other cancer types.

Radiomics Applications in Renal Tumor Assessment: A Comprehensive Review of the Literature

“…Furthermore, complementary RNA (cRNA) expression and gene expression also strongly correlated with image-based data (r = 0.76). Despite no radiological TA being performed in these studies, the relevant information obtained can be applied to further develop prediction scores comprising quantitative image data [57].…”

Promises of Big Data and Artificial Intelligence in Nephrology and Transplantation

“…Those needs that are classified as unmet require provision of some ample spaces for the purpose of imagination in relation to leveraging the strength associated with big data, as well as relevant artificial intelligence (AI) to improve the overall status of patients with kidney diseases [25]. In this article, we discuss the big data concepts in nephrology, describe the potential use of AI in nephrology and transplantation, and also encourage researchers and clinicians to submit their invaluable research, including original clinical research studies [26][27][28][29][30], database studies from registries [31][32][33], meta-analyses [34][35][36][37][38][39][40][41][42][43][44], and artificial intelligence research [25,[45][46][47][48] in nephrology and transplantation. Table 1 demonstrates known and commonly used databases that have provided big data in nephrology and transplantation [49][50][51].…”

Application of Proteomics in Cancer: Recent Trends and Approaches for Biomarkers Discovery

“…Although it is yet to be confirmed whether this mutation can be used for clinical prediction, this study supports that ML can discriminate the gene mutation profile in hepatocellular carcinoma. Another example is connecting microscopy images and proteomics through ML ( 131 ). This study adopted a convolutional neural network algorithm to analyze histology from the Cancer Imaging Archive and proteomics datasets from CPTAC.…”