Accurate detection of benign and malignant renal tumor subtypes with MethylBoostER: An epigenetic marker-driven learning framework

Evidence of DNA methylation heterogeneity and epipolymorphism in kidney cancer tissue samples

Clear cell renal cell carcinoma (ccRCC) is characterised by significant genetic heterogeneity, which has diagnostic and prognostic implications. Very limited evidence is available regarding DNA methylation heterogeneity. We therefore generate sequence level DNA methylation data on 136 multi-region tumour and normal kidney tissue from 18 ccRCC patients, along with matched whole exome sequencing (85 samples) and gene expression (47 samples) data on a subset of samples. We perform a comprehensive systematic analysis of heterogeneity between patients, within a patient and within a sample. We demonstrate that bulk methylation data may be deconvoluted into cell-type-specific latent methylation components (LMCs), and that LMC1, which is likely to represent T cells, is associated with prognostic parameters. Differential epipolymorphism was noted between ccRCC and normal tissue in the promoter region of genes which are known to be associated with kidney cancer. This was externally validated in an independent cohort of 71 ccRCC and normal kidney tissues. Differential epipolymorphism in the gene promoter was a predictor of gene expression, after adjusting for average methylation. This represents the first evaluation of epipolymorphism in ccRCC and suggests that gains and losses in methylation disorder may have a functional relevance, gleaning important information on tumourigenesis.

Application of machine learning for high-throughput tumor marker screening

High-throughput sequencing and multiomics technologies have allowed increasing numbers of biomarkers to be mined and used for disease diagnosis, risk stratification, efficacy assessment, and prognosis prediction. However, the large number and complexity of tumor markers make screening them a substantial challenge. Machine learning (ML) offers new and effective ways to solve the screening problem. ML goes beyond mere data processing and is instrumental in recognizing intricate patterns within data. ML also has a crucial role in modeling dynamic changes associated with diseases. Used together, ML techniques have been included in automatic pipelines for tumor marker screening, thereby enhancing the efficiency and accuracy of the screening process. In this review, we discuss the general processes and common ML algorithms, and highlight recent applications of ML in tumor marker screening of genomic, transcriptomic, proteomic, and metabolomic data of patients with various types of cancers. Finally, the challenges and future prospects of the application of ML in tumor therapy are discussed.

Early detection and diagnosis of cancer with interpretable machine learning to uncover cancer-specific DNA methylation patterns

Cancer, a collection of more than two hundred different diseases, remains a leading cause of morbidity and mortality worldwide. Usually detected at the advanced stages of disease, metastatic cancer accounts for 90% of cancer-associated deaths. Therefore, the early detection of cancer, combined with current therapies, would have a significant impact on survival and treatment of various cancer types. Epigenetic changes such as DNA methylation are some of the early events underlying carcinogenesis. Here, we report on an interpretable machine learning model that can classify 13 cancer types as well as non-cancer tissue samples using only DNA methylome data, with 98.2% accuracy. We utilize the features identified by this model to develop EMethylNET, a robust model consisting of an XGBoost model that provides information to a deep neural network that can generalize to independent data sets. We also demonstrate that the methylation-associated genomic loci detected by the classifier are associated with genes, pathways and networks involved in cancer, providing insights into the epigenomic regulation of carcinogenesis.

Indocyanine Green-Loaded Nanobubbles Targeting Carbonic Anhydrase IX for Multimodal Imaging of Renal Cell Carcinoma

Background and Purpose

The early diagnosis and differential diagnosis of renal cell carcinoma (RCC) has always been a clinical difficulty and a research focus. Carbonic anhydrase IX (CA IX) is highly expressed on the cell membrane of RCC but is not expressed in normal renal tissues. In this study, nanobubbles (NBs) targeting CA IX with ultrasound and photoacoustic multimodal imaging capabilities were prepared to explore a new method for the diagnosis and differential diagnosis of RCC.

Methods

Indocyanine green (ICG)-loaded lipid NBs (ICG-NBs) were prepared by using the filming rehydration method, and anti-CA IX polypeptides (ACPs) were attached to their surfaces to prepare CA IX-targeted NBs (ACP/ICG-NBs). The particle size, zeta potential and ICG encapsulation efficiency of these nanobubbles were measured, and their specific targeting and binding abilities to RCC cells were determined. The in vitro and in vivo ultrasound, photoacoustic and fluorescence imaging characteristics of these nanobubbles were also assessed.

Results

The particle size of the ACP/ICG-NBs was 475.9 nm in diameter, and their zeta potential was -2.65 mV. Laser confocal microscopy and flow cytometry both confirmed that ACP/ICG-NBs had specific binding activity and ideal affinity to CA IX-positive RCC cells (786-O) but not to CA IX-negative RCC cells (ACHN). The intensities of the in vitro ultrasound, photoacoustic and fluorescence imaging were positively correlated with the concentrations of ACP/ICG-NBs. In in vivo ultrasound and photoacoustic imaging experiments, ACP/ICG-NBs exhibited specific enhanced ultrasound and photoacoustic imaging effects in 786-O xenograft tumors.

Conclusion

The ICG- and ACP-loaded targeted nanobubbles that we prepared had the capability of ultrasound, photoacoustic and fluorescence multimodal imaging and could specifically enhance the ultrasound and photoacoustic imaging of RCC xenograft tumors. This outcome has potential clinical application value for the diagnosis of RCC at the early stage and the differential diagnosis of benign and malignant kidney tumors.