With millions of cases of bladder cancer (BC) worldwide, the need for tools to ensure early diagnosis of this condition is of concern. Scientists recently used mitochondria-related genes (MRGs), known to be involved in disease progression, to create a new diagnostic model using machine learning (ML).
The results were published in Scientific Reportsindicating the potential of this model pending further validation.
Study: Machine learning prediction of a new diagnostic model using mitochondria-related genes for bladder cancer patients. Image credit: mi_viri/Shutterstock.com
Bladder cancer
Bladder cancer is three to four times more common in men than in women, making it the sixth leading cause of cancer in men. It is mainly caused by smoking and exposure to certain industrial chemicals and usually affects middle-aged and elderly men.
Although bladder cancer is more prevalent in developed populations, its prognosis remains relatively poor despite medical advances. This has led to the development of better diagnostic tools, prognostic models and therapeutic approaches.
Mitochondria, the subcellular organelles responsible for energy production, control cell metabolism and regulate key cellular processes such as programmed cell death, signaling, and calcium ion levels.
Cancer cells, which require a lot of energy, primarily use glycolysis—a less efficient anaerobic pathway—as opposed to normal cells that rely on oxidative phosphorylation, a more efficient aerobic pathway that can produce up to 15 times more energy.
This difference in energy production is part of the ‘Warburg effect’, where abnormal mitochondrial function leads to altered metabolism in cancer cells. For example, malfunctioning mitochondria can prevent cancer cells from undergoing programmed death, allowing them to survive and spread.
In addition, mitochondrial abnormalities can cause oxidative stress to cellular components such as DNA and proteins, increasing the risk of cancer, conferring resistance to cancer therapies, and promoting tumor growth.
“Given the important roles of MRGs in BC progression, it is important to consider new MRG-based biomarkers for BC patients.”
ML is part of the artificial intelligence (AI) arsenal, which identifies patterns and insights from raw data without providing detailed instructions.
This allows the system to predict, categorize and identify trends that could include tumor-related transcript patterns. In the current study, researchers attempted to exploit the power of ML on transcriptomes to create a new diagnostic model for BC based on MRGs.
What did the study show?
Researchers analyzed 165 bladder cancer (BC) samples and 67 controls to study the differential expression of mitochondria-related genes (MRGs). They identified 752 differentially expressed MRGs, with 440 showing increased expression and the rest down-regulated.
These genes were significantly involved in cellular pathways related to organ formation in embryos, cell fate, transcriptional regulation, neurodegenerative diseases, and muscle tissue disorders.
The analysis identified nearly 50 features associated with B.C. and narrowed down to 13 critical genes. Among them, TRAF3 interacting protein 3 (TRAF3IP3), oxidative stress-induced growth inhibitor mitochondrial inhibitor (OXSM), N-myristoyltransferase 1 (NMT1) and Glutaroxin 2 (GLRX2) were found to be key targets. GLRX2, in particular, is important for maintaining the redox balance in the mitochondria, which helps normal cellular processes continue without oxidative damage.
The expression patterns of GLRX2, NMT1, OXSM and TRAF3IP3 showed clear differences between BC samples and controls, achieving 90% differentiation efficiency. GLRX2, NMT1, and OXSM were highly upregulated in BC, while TRAF3IP3 was significantly downregulated.
These findings were consistent in two additional datasets, demonstrating that this model more effectively differentiates BC from control samples than individual gene biomarkers.
In addition, the study investigated where these genes are predominantly expressed, finding that different pathways and immune cells in the tumor microenvironment respond differently to changes in gene regulation. For example, higher levels of activated natural killer (NK) and plasma cells were associated with increased GLRX2 expression.
NMT1 expression, which was significantly increased in several BC cell lines, encodes a protein crucial for protein modification and signaling, potentially enhancing cancer cell interactions with the extracellular matrix—a key process in cancer spread. Significantly, suppression of NMT1 led to restricted growth of BC cells, indicating its role in BC promotion.
conclusions
The emergence of transcriptomics and ML in diagnostic tumor models has given impetus to the search for accurate and timely diagnosis of BC without the need for invasive and painful biopsies. This ML approach can help formulate personalized diagnostic and therapeutic plans based on biomarker selection.
It can also speed up decisions with increased efficiency. Finally, it can aid in understanding the process of tumor development through the insights it provides into the underlying tumor biology.
The current study identified four genes (GLRX2, NMT1, OXSM and TRAF3IP3) for BC diagnosis. These were incorporated into a diagnostic model. It was also found that they played an important role in the development of BC. Further research is necessary to confirm these findings in a more diverse sample.
“Our findings could potentially lead to increased accuracy and reliability in the diagnosis of BC, contributing to more personalized and effective medical interventions for patients in the future.”
