Key therapeutic targets implicated at the early stage of hepatocellular carcinoma identified through machine-learning approaches

Overexpression and clinicopathological significance of zinc finger protein 71 in hepatocellular carcinoma

BACKGROUND

Hepatocellular carcinoma (HCC) is one of the most prevalent and aggressive forms of liver cancer, with high morbidity and poor prognosis due to late diagnosis and limited treatment options. Despite advances in understanding its molecular mechanisms, effective biomarkers for early detection and targeted therapy remain scarce. Zinc finger protein 71 (ZNF71), a zinc-finger protein, has been implicated in various cancers, yet its role in HCC remains largely unexplored. This gap in knowledge underscores the need for further investigation into the ZNF71 of potential as a diagnostic or therapeutic target in HCC.

AIM

To explore the expression levels, clinical relevance, and molecular mechanisms of ZNF71 in the progression of HCC.

METHODS

The study evaluated ZNF71 expression in 235 HCC specimens and 13 noncancerous liver tissue samples using immunohistochemistry. High-throughput datasets were employed to assess the differential expression of ZNF71 in HCC and its association with clinical and pathological features. The impact of ZNF71 on HCC cell line growth was examined through clustered regularly interspaced short palindromic repeat knockout screens. Co-expressed genes were identified and analyzed for enrichment using LinkedOmics and Sangerbox 3.0, focusing on significant correlations (P < 0.01, correlation coefficient ≥ 0.3). Furthermore, the relationship between ZNF71 expression and immune cell infiltration was quantified using TIMER2.0.

RESULTS

ZNF71 showed higher expression in HCC tissues vs non-tumorous tissues, with a significant statistical difference (P < 0.05). Data from the UALCAN platform indicated increased ZNF71 levels across early to mid-stage HCC, correlating with disease severity (P < 0.05). High-throughput analysis presented a standardized mean difference in ZNF71 expression of 0.55 (95% confidence interval [CI]: 0.34-0.75). The efficiency of ZNF71 mRNA was evaluated, yielding an area under the curve of 0.78 (95%CI: 0.75-0.82), a sensitivity of 0.63 (95%CI: 0.53-0.72), and a specificity of 0.82 (95%CI: 0.73-0.89). Diagnostic likelihood ratios were positive at 3.61 (95%CI: 2.41-5.41) and negative at 0.45 (95%CI: 0.36-0.56). LinkedOmics analysis identified strong positive correlations of ZNF71 with genes such as ZNF470, ZNF256, and ZNF285. Pathway enrichment analyses highlighted associations with herpes simplex virus type 1 infection, the cell cycle, and DNA replication. Negative correlations involved metabolic pathways, peroxisomes, and fatty acid degradation. TIMER2.0 analysis demonstrated positive correlations of high ZNF71 expression with various immune cell types, including CD4+ T cells, B cells, regulatory T cells, monocytes, macrophages, and myeloid dendritic cells.

CONCLUSION

ZNF71 is significantly upregulated in HCC, correlating with the disease's clinical and pathological stages. It appears to promote HCC progression through mechanisms involving the cell cycle and metabolism and is associated with immune cell infiltration. These findings suggest that ZNF71 could be a novel target for diagnosing and treating HCC.

Circulating miRNA's biomarkers for early detection of hepatocellular carcinoma in Egyptian patients based on machine learning algorithms

Liver cancer, which ranks sixth globally and third in cancer-related deaths, is caused by chronic liver disorders and a variety of risk factors. Despite therapeutic improvements, the prognosis for Hepatocellular Carcinoma (HCC) remains poor, with a 5-year survival rate for advanced cases of less than 12%. Although there is a noticeable decrease in the frequency of cases, liver cancer remains a significant worldwide health concern, with estimates surpassing one million cases by 2025. The prevalence of HCC has increased in Egypt, and it includes several neoplasms with distinctive messenger RNA (mRNA) and microRNA (miRNA) expression profiles. In HCC patients, certain miRNAs, such as miRNA-483-5P and miRNA-21, are upregulated, whereas miRNA-155 is elevated in HCV-infected people, encouraging hepatocyte proliferation. Short noncoding RNAs called miRNAs in circulation have the potential as HCC diagnostic and prognostic markers. This paper proposed a model for examining circulating miRNAs as diagnostic and predictive markers for HCC in Egyptian patients and their clinical and pathological characteristics. The proposed HCC detection model consists of three main phases: data preprocessing phase, feature selection based on the proposed Binary African Vulture Optimization Algorithm (BAVO) phase, and finally, classification as well as cross-validation phase. The first phase namely the data preprocessing phase tackle the main problems associated with the adopted datasets. In the feature selection based on the proposed BAVO algorithm phase, a new binary version of the BAVO swarm-based algorithm is introduced to select the relevant markers for HCC. Finally, in the last phase, namely the classification and cross-validation phase, the support vector machine and k-folds cross-validation method are utilized. The proposed model is evaluated on three studies on Egyptians who had HCC. A comparison between the proposed model and traditional statistical studies is reported to demonstrate the superiority of using the machine learning model for evaluating circulating miRNAs as diagnostic markers of HCC. The specificity and sensitivity for differentiation of HCC cases in comparison with the statistical-based method for the first study were 98% against 88% and 99% versus 92%, respectively. The second study revealed the sensitivity and specificity were 97.78% against 90% and 98.89% versus 92.5%, respectively. The third study reported 83.2% against 88.8% and 95.80% versus 92.4%, respectively. Additionally, the results show that circulating miRNA-483-5p, 21, and 155 may be potential new prognostic and early diagnostic biomarkers for HCC.

Decoding the Possible Molecular Mechanisms in Pediatric Wilms Tumor and Rhabdoid Tumor of the Kidney through Machine Learning Approaches

Objective: Wilms tumor (WT) and Rhabdoid tumor (RT) are pediatric renal tumors and their differentiation is based on histopathological and molecular analysis. The present study aimed to introduce the panels of mRNAs and microRNAs involved in the pathogenesis of these cancers using deep learning algorithms. Methods: Filter, graph, and association rule mining algorithms were applied to the mRNAs/microRNAs data. Results: Candidate miRNAs and mRNAs with high accuracy (AUC: 97%/93% and 94%/97%, respectively) could differentiate the WT and RT classes in training and test data. Let-7a-2 and C19orf24 were identified in the WT, while miR-199b and RP1-3E10.2 were detected in the RT by analysis of Association Rule Mining. Conclusion: The application of the machine learning methods could identify mRNA/miRNA patterns to discriminate WT from RT. The identified miRNAs/mRNAs panels could offer novel insights into the underlying molecular mechanisms that are responsible for the initiation and development of these cancers. They may provide further insight into the pathogenesis, prognosis, diagnosis, and molecular-targeted therapy in pediatric renal tumors.

Uncovering key molecular mechanisms in the early and late-stage of papillary thyroid carcinoma using association rule mining algorithm

OBJECTIVE

Thyroid Cancer (TC) is the most frequent endocrine malignancy neoplasm. It is the sixth cause of cancer in women worldwide. The treatment process could be expedited by identifying the controlling molecular mechanisms at the early and late stages, which can contribute to the acceleration of treatment schemes and the improvement of patient survival outcomes. In this work, we study the significant mRNAs through Machine Learning Algorithms in both the early and late stages of Papillary Thyroid Cancer (PTC).

METHOD

During the course of our study, we investigated various methods and techniques to obtain suitable results. The sequence of procedures we followed included organizing data, using nested cross-validation, data cleaning, and normalization at the initial stage. Next, to apply feature selection, a t-test and binary Non-Dominated Sorting Genetic Algorithm II (NSGAII) were chosen to be employed. Later on, during the analysis stage, the discriminative power of the selected features was evaluated using machine learning and deep learning algorithms. Finally, we considered the selected features and utilized Association Rule Mining algorithm to identify the most important ones for improving the decoding of dominant molecular mechanisms in PTC through its early and late stages.

RESULT

The SVM classifier was able to distinguish between early and late-stage categories with an accuracy of 83.5% and an AUC of 0.78 based on the identified mRNAs. The most significant genes associated with the early and late stages of PTC were identified as (e.g., ZNF518B, DTD2, CCAR1) and (e.g., lnc-DNAJB6-7:7, RP11-484D2.3, MSL3P1), respectively.

CONCLUSION

Current study reveals a clear picture of the potential candidate genes that could play a major role not only in the early stage, but also throughout the late one. Hence, the findings could be of help to identify therapeutic targets for more effective PTC drug developments.