Tumor DNA Methylation Profiles Enable Diagnosis, Prognosis Prediction, and Screening for Cervical Cancer

Methods in DNA methylation array dataset analysis: A review

Understanding the intricate relationships between gene expression levels and epigenetic modifications in a genome is crucial to comprehending the pathogenic mechanisms of many diseases. With the advancement of DNA Methylome Profiling techniques, the emphasis on identifying Differentially Methylated Regions (DMRs/DMGs) has become crucial for biomarker discovery, offering new insights into the etiology of illnesses. This review surveys the current state of computational tools/algorithms for the analysis of microarray-based DNA methylation profiling datasets, focusing on key concepts underlying the diagnostic/prognostic CpG site extraction. It addresses methodological frameworks, algorithms, and pipelines employed by various authors, serving as a roadmap to address challenges and understand changing trends in the methodologies for analyzing array-based DNA methylation profiling datasets derived from diseased genomes. Additionally, it highlights the importance of integrating gene expression and methylation datasets for accurate biomarker identification, explores prognostic prediction models, and discusses molecular subtyping for disease classification. The review also emphasizes the contributions of machine learning, neural networks, and data mining to enhance diagnostic workflow development, thereby improving accuracy, precision, and robustness.

Emerging biomarkers and molecular targets for precision medicine in cervical cancer

Cervical cancer remains a significant global health burden, necessitating innovative approaches for improved diagnostics and personalized treatment strategies. Precision medicine has emerged as a promising paradigm, leveraging biomarkers and molecular targets to tailor therapy to individual patients. This review explores the landscape of emerging biomarkers and molecular targets in cervical cancer, highlighting their potential implications for precision medicine. By integrating these biomarkers into comprehensive diagnostic algorithms, clinicians can identify high-risk patients at an earlier stage, enabling timely intervention and improved patient outcomes. Furthermore, the identification of specific molecular targets has paved the way for the development of targeted therapies aimed at disrupting key pathways implicated in cervical carcinogenesis. In conclusion, the evolving landscape of biomarkers and molecular targets presents exciting opportunities for advancing precision medicine in cervical cancer. By harnessing these insights, clinicians can optimize treatment selection, enhance patient outcomes, and ultimately transform the management of this devastating disease.

Focusing on the Abnormal Events of NPC1, NPC2, and NPC1L1 in Pan-Cancer and Further Constructing LUAD and KICH Prediction Models

Cancer's high incidence and death rate jeopardize human health and life, and it has become a global public health issue. Some members of NPCs have been studied in a few cancers, but comprehensive and prognostic analysis is lacking in most cancers. In this study, we used the Cancer Genome Atlas (TCGA) data genomics and transcriptome technology to examine the differential expression and prognosis of NPCs in 33 cancer samples, as well as to investigate NPCs mutations and their effect on patient prognosis and to evaluate the methylation level of NPCs in cancer. The linked mechanisms and medication resistance were subsequently investigated in order to investigate prospective tumor therapy approaches. The relationships between NPCs and immune infiltration, immune cells, immunological regulatory substances, and immune pathways were also investigated. Finally, the LUAD and KICH prognostic prediction models were built using univariate and multivariate COX regression analysis. Additionally, the mRNA and protein levels of NPCs were also identified.

PAX1 and SEPT9 methylation analyses in cervical exfoliated cells are highly efficient for detecting cervical (pre)cancer in hrHPV-positive women

Studies have investigated PAX1 and SEPT methylation were closely associated with cervical cancer. For this study, we verified the expressions of PAX1 and SEPT9 methylation in 236 hrHPV women cervical exfoliated cells by using quantitative methylation-specific PCR and we further explored their diagnostic value in cervical (pre)cancer detection. Our results identified that the methylation rates and levels of PAX1 and SEPT9 increased with cervical lesion severity. For a diagnosis of cervical (pre)cancer, the area under the curve (AUC) of PAX1 methylation was 0.77 (95% CI 0.71-0.83) and the AUC of SEPT9 methylation was 0.86 (95% CI 0.81∼0.90). Analyses of the PAX1 and SEPT9 methylation statuses alone or combined with commonly used tests can efficiently identify cervical (pre)cancer. In particular, SEPT9 methylation might serve as an effective and powerful biomarker for the diagnosis of cervical (pre)cancer and as an alternative triage test in HPV-based cervical (pre)cancer screening programs.Impact StatementWhat is already known on this subject? This subject showed that PAX1 and SEPT9 methylation were closely associated with cervical cancer. The methylation rates and levels of PAX1 and SEPT9 increased with cervical lesion severity and reached a peak in cervical cancer exfoliated cells. We further assessed the diagnostic performances of PAX1 and SEPT9 methylation in cervical cancer screening. In detecting cervical (pre)cancer, the sensitivity values of PAX1 and SEPT9 methylation were up to 61.18% and 82.35%, respectively, and the specificity values of PAX1 and SEPT9 methylation were up to 95.36% and 86.75%, respectively. Moreover, the ROC curve analysis showed AUC values of 0.77 for PAX1 methylation and 0.86 for SEPT9 methylation tests, which were significantly superior to other commonly used tests. These findings suggest that PAX1 and SEPT9 methylation detection may have great clinical potential in cervical cancer screening.What the results of this study add? The rates and levels of PAX1 and SEPT9 methylation increased with the severity of the cervical lesions. For a diagnosis of cervical (pre)cancer, the area under the curve (AUC) of PAX1 methylation was 0.77 (95% CI 0.71-0.83), and the sensitivity and specificity values were 61.18% and 95.36%, respectively. The AUC value of the SEPT9 methylation was 0.86 (95% CI 0.81 ∼ 0.90), and the sensitivity and specificity values were 82.35% and 86.75%, respectively. Compared with the various tests we conducted, the PAX1 methylation showed the highest specificity (95.36%), and the SEPT9 methylation demonstrated the highest accuracy(86.00%).What the implications are of these findings for clinical practice and/or further research? The methylation levels of PAX1 and SEPT9 had a certain predictive effect on the severity of cervical lesions in hrHPV-positive women. In addition, SEPT9 methylation analysis performs better than PAX1 methylation analysis and commonly used tests in cervical exfoliated cells for detecting cervical (pre)cancer in hrHPV-positive women. SEPT9 methylation analysis merits consideration as an effective and objective, alternative triage test in HPV-based cervical (pre)cancer screening programs.

Assessing the capacity of methylated DNA markers of cervical squamous cell carcinoma to discriminate oropharyngeal squamous cell carcinoma in human papillomavirus mediated disease

OBJECTIVE

Early identification of human papillomavirus associated oropharyngeal squamous cell carcinoma (HPV(+)OPSCC) is challenging and novel biomarkers are needed. We hypothesized that a panel of methylated DNA markers (MDMs) found in HPV(+) cervical squamous cell carcinoma (CSCC) will have similar discrimination in HPV(+)OPSCC tissues.

MATERIALS AND METHODS

Formalin-fixed, paraffin-embedded tissues were obtained from patients with primary HPV(+)OPSCC or HPV(+)CSCC; control tissues included normal oropharynx palatine tonsil (NOP) and cervix (NCS). Using a methylation-specific polymerase chain reaction, 21 previously validated cervical MDMs were evaluated on tissue-extracted DNA. Discrimination between case and control cervical and oropharynx tissue was assessed using area under the curve (AUC).

RESULTS

34 HPV(+)OPSCC, 36 HPV(+)CSCC, 26 NOP, and 24 NCS patients met inclusion criteria. Within HPV(+)CSCC, 18/21 (86%) of MDMs achieved an AUC ≥ 0.9 and all MDMs exhibited better than chance classifications relative to control cervical tissue (all p < 0.001). In contrast, within HPV(+)OPSCC only 5/21 (24%) MDMs achieved an AUC ≥ 0.90 but 19/21 (90%) exhibited better than chance classifications relative to control tonsil tissue (all p < 0.001). Overall, 13/21 MDMs had statistically significant lower AUCs in the oropharyngeal cohort compared to the cervical cohort, and only 1 MDM exhibited a statistically significant increase in AUC.

CONCLUSIONS

Previously validated MDMs exhibited robust performance in independent HPV(+)CSCC patients. However, most of these MDMs exhibited higher discrimination for HPV(+)CSCC than for HPV(+)OPSCC. This suggests that each SCC subtype requires a unique set of MDMs for optimal discrimination. Future studies are necessary to establish an MDM panel for HPV(+)OPSCC.

Deep Learning-Based Recognition of Cervical Squamous Interepithelial Lesions

Cervical squamous intraepithelial lesions (SILs) are precursor lesions of cervical cancer, and their accurate diagnosis enables patients to be treated before malignancy manifests. However, the identification of SILs is usually laborious and has low diagnostic consistency due to the high similarity of pathological SIL images. Although artificial intelligence (AI), especially deep learning algorithms, has drawn a lot of attention for its good performance in cervical cytology tasks, the use of AI for cervical histology is still in its early stages. The feature extraction, representation capabilities, and use of p16 immunohistochemistry (IHC) among existing models are inadequate. Therefore, in this study, we first designed a squamous epithelium segmentation algorithm and assigned the corresponding labels. Second, p16-positive area of IHC slides were extracted with Whole Image Net (WI-Net), followed by mapping the p16-positive area back to the H&E slides and generating a p16-positive mask for training. Finally, the p16-positive areas were inputted into Swin-B and ResNet-50 to classify the SILs. The dataset comprised 6171 patches from 111 patients; patches from 80% of the 90 patients were used for the training set. The accuracy of the Swin-B method for high-grade squamous intraepithelial lesion (HSIL) that we propose was 0.914 [0.889-0.928]. The ResNet-50 model for HSIL achieved an area under the receiver operating characteristic curve (AUC) of 0.935 [0.921-0.946] at the patch level, and the accuracy, sensitivity, and specificity were 0.845, 0.922, and 0.829, respectively. Therefore, our model can accurately identify HSIL, assisting the pathologist in solving actual diagnostic issues and even directing the follow-up treatment of patients.

Gynecological cancer prognosis using machine learning techniques: A systematic review of last three decades (1990–2022)

OBJECTIVE

Many Computer Aided Prognostic (CAP) systems based on machine learning techniques have been proposed in the field of oncology. The objective of this systematic review was to assess and critically appraise the methodologies and approaches used in predicting the prognosis of gynecological cancers using CAPs.

METHODS

Electronic databases were used to systematically search for studies utilizing machine learning methods in gynecological cancers. Study risk of bias (ROB) and applicability were assessed using the PROBAST tool. 139 studies met the inclusion criteria, of which 71 predicted outcomes for ovarian cancer patients, 41 predicted outcomes for cervical cancer patients, 28 predicted outcomes for uterine cancer patients, and 2 predicted outcomes for gynecological malignancies broadly.

RESULTS

Random forest (22.30 %) and support vector machine (21.58 %) classifiers were used most commonly. Use of clinicopathological, genomic and radiomic data as predictors was observed in 48.20 %, 51.08 % and 17.27 % of studies, respectively, with some studies using multiple modalities. 21.58 % of studies were externally validated. Twenty-three individual studies compared ML and non-ML methods. Study quality was highly variable and methodologies, statistical reporting and outcome measures were inconsistent, preventing generalized commentary or meta-analysis of performance outcomes.

CONCLUSION

There is significant variability in model development when prognosticating gynecological malignancies with respect to variable selection, machine learning (ML) methods and endpoint selection. This heterogeneity prevents meta-analysis and conclusions regarding the superiority of ML methods. Furthermore, PROBAST-mediated ROB and applicability analysis demonstrates concern for the translatability of existing models. This review identifies ways that this can be improved upon in future works to develop robust, clinically translatable models within this promising field.