Cancer Informatics最新文献

Objectives: This study aims to introduce a prediction model based on a machine learning approach as an efficient solution for prediction purposes to better prognosis and increase CRC survival.

Methods: In the current retrospective study, we used the data of 1062 CRC cases to analyse and establish a prediction model for the 5-year CRC survival. The machine learning algorithms were used to develop prediction models, including random Forest, XG-Boost, bagging, logistic regression, support vector machine, artificial neural network, decision tree, and K-nearest neighbours.

Results: The current study revealed that the XG-Boost with AU-ROC of 0.906 and 0.813 for internal and external conditions gave us better insight into predictability and generalizability than other algorithms.

Conclusion: XG-Boost can be utilised as a knowledge source for implementing intelligent systems as an assistive tool for clinical decision-making in healthcare settings to improve prognosis and increase CRC survival through various clinical solutions that doctors can achieve.

Background: Ovarian cancer has brought serious threats to female health. CCAAT/enhancer binding proteins (C/EBPs) are key transcription factors involved in ovarian cancer. Therefore, comprehensive profiling C/EBPs in ovarian cancer is needed.

Methods: A comprehensive analysis concerning C/EBPs in ovarian cancer was performed. Firstly, detailed expression of C/EBP family members was integrally retrieved and then confirmed using immunohistochemistry. The regulatory effects and transcription regulatory functions of C/EBPs were studied by using regulatory network analysis and enrichment analysis. Using survival analysis, receiver operating characteristic curve analysis, and target-disease association analysis, the predictive prognostic value of C/EBPs on survival and drug responsiveness was systematically evaluated. The effects of C/EBPs on tumor immune infiltration were also assessed.

Results: Ovarian cancer tissues expressed increased CEBPA, CEBPB, and CEBPG but decreased CEBPD when compared with normal control tissues. The overall alteration frequency of C/EBPs in ovarian cancer was approaching 30%. C/EBP family members formed a reciprocal regulatory network involving carcinogenesis and had pivotal transcription regulatory functions. C/EBPs could affect survival of ovarian cancer and correlated with poor survival outcomes (OS: HR = 1.40, P = .0053 and PFS: HR = 1.41, P = .0036). Besides, expression of CEBPA, CEBPB, CEBPD, and CEBPE could predict platinum and taxane responsiveness of ovarian cancer. C/EBPs also affected immune infiltration of ovarian cancer.

Conclusions: C/EBPs were closely involved in ovarian cancer and exerted multiple biological functions. C/EBPs could be exploited as prognostic and predictive biomarkers in ovarian cancer.

Objective: Host immunogenetics (Human Leukocyte Antigen, HLA) play a critical role in the human immune response to melanoma, influencing both melanoma prevalence and immunotherapy outcomes. Beneficial outcomes hinge on the successful binding of epitopes of melanoma antigens to HLA Class I molecules for an effective engagement of cytotoxic CD8+ lymphocytes and subsequent elimination of the cancerous cell. This study evaluated the binding affinity and immunogenicity of HLA Class I to melanoma tumor antigens to identify alleles best suited to facilitate elimination of melanoma antigens.

Methods: In this study, we used freely available software tools to determine in silico the binding affinity and immunogenicity of 2462 reported HLA Class I alleles to all linear nonamer epitopes of 11 known antigens expressed in melanoma tumors (TRP2, S100, Tyrosinase, TRP1, PMEL(17), MAGE1, MAGE4, CTA, BAGE, GAGE/SSX2, Melan).

Results: We identified the following 9 HLA Class I alleles with very high immunogenicity and binding affinity against all 11 melanoma antigens: A*02:14, B*07:10, B*35:10, B*40:10, B*40:12, B*44:10, C*07:11, and C*07:13, and C*07:14.

Conclusion: These 9 HLA alleles possess the potential to aid in the elimination of melanoma both by themselves and by enhancing the beneficial effect of immune checkpoint inhibitors.

Objectives: This research aims to establish a copper homeostasis-related gene signature for predicting the prognosis of epithelial ovarian cancer and to investigate its underlying mechanisms.

Methods: We mainly constructed the copper homeostasis-related gene signature by LASSO regression analysis. Then multiple methods were used to evaluate the independent predictive ability of the model and explored the mechanisms.

Results: The 15-copper homeostasis-related gene (15-CHRG) signature was successfully established. Utilizing an optimal cut-off value of 0.35, we divided the training dataset into high-risk and low-risk subgroups. Kaplan-Meier analysis revealed that survival times for the high-risk subgroup were significantly shorter than those in the low-risk group (P < .05). Additionally, the Area Under the Curve (AUC) of the 15-CHRG signature achieved 0.822 at 1 year, 0.762 at 3 years, and 0.696 at 5 years in the training set. COX regression analysis confirmed the 15-CHRG signature as both accurate and independent. Gene set enrichment (GSEA), Kyoto Encyclopedia of Gene and Genome (KEGG) and Gene Ontology (GO) analysis showed that there were significant differences in apoptosis, p53 pathway, protein synthesis, hydrolase and transport-related pathways between high-risk group and low-risk group. In tumor immune cell (TIC) analysis, the increased expression of resting mast cells was positively correlated with the risk score.

Conclusion: Consequently, the 15-CHRG signature shows significant potential as a method for accurately predicting clinical outcomes and treatment responses in patients with epithelial ovarian cancer.

Objectives: Adrenocortical carcinoma (ACC), a rare and aggressive adrenal cortex cancer, poses significant challenges due to high mortality, poor prognosis, and early post-surgery recurrence. Variability in survival across ACC stages emphasizes the need to uncover its molecular underpinnings. Adrenocortical adenoma, a benign tumor, adds to diagnostic challenges, highlighting the necessity for molecular insights. The Non-SMC Associated Condensin Complex (NCAP) gene family, recognized for roles in chromosomal structure and cell cycle control. This study focuses on evaluating NCAP gene functions and importance in ACC through gene expression profiling to identify diagnostic and therapeutic targets.

Methods: Microarray datasets from ACC patients, obtained from the Gene Expression Omnibus database, were normalized to eliminate batch effects. Differential expression analysis of NCAP family genes, facilitated by the GEPIA2 database, included survival and pathological stage evaluations. A Protein-Protein Interaction network was constructed using GeneMANIA, and additional insights were gained through Gene Ontology enrichment analysis, correlation analysis, and ROC curve analysis.

Results: ACC samples exhibited elevated levels of NCAPG, NCAPG2, and NCAPH compared to normal and adenoma samples. Increased expression of these genes correlated with poor overall survival, particularly in advanced disease stages. The Protein-Protein Interaction network highlighted interactions with related proteins, and Gene Ontology enrichment analysis demonstrated their involvement in chromosomal structure and control. Differentially expressed NCAP genes showed positive associations, and ROC curve analysis indicated their high discriminatory power in identifying ACC from adenoma and normal samples.

Conclusion: The study emphasizes the potential importance of NCAPG, NCAPG2, and NCAPH in ACC, suggesting roles in tumor aggressiveness and diagnostic relevance. These genes could serve as therapeutic targets and markers for ACC, but further exploration into their molecular activities and validation studies is imperative to fully harness their diagnostic and therapeutic potential, advancing precision medicine approaches against this rare but lethal malignancy.

Objective: Network analysis techniques often require tuning hyperparameters for optimal performance. For instance, the independent cascade model necessitates determining the probability of diffusion. Despite its importance, a consensus on effective parameter adjustment remains elusive.

Methods: In this study, we propose a novel approach utilizing experimental design methodologies, specifically 2-Factorial Analysis for Screening, and Response Surface Methodology (RSM) for parameter adjustment. We apply this methodology to the task of detecting cancer driver genes in colorectal cancer.

Result: Through experimental validation of colorectal cancer data, we demonstrate the effectiveness of our proposed methodology. Compared with existing methods, our approach offers several advantages, including reduced computational overhead, systematic parameter selection grounded in statistical theory, and improved performance in detecting cancer driver genes.

Conclusion: This study presents a significant advancement in the field of network analysis by providing a practical and systematic approach to hyperparameter tuning. By optimizing parameter settings, our methodology offers promising implications for critical biomedical applications such as cancer driver gene detection.

Background: Alternative polyadenylation (APA) plays a vital regulatory role in various diseases. It is widely accepted that APA is regulated by APA regulatory factors.

Objective: Whether APA regulatory factors affect the prognosis of renal cell carcinoma remains unclear, and this is the main topic of this study.

Methods: We downloaded the transcriptome and clinical data from The Cancer Genome Atlas (TCGA) database. We used the Lasso regression system to construct an APA model for analyzing the relationship between common APA regulatory factors and renal cell carcinoma. We also validated our APA model using independent GEO datasets (GSE29609, GSE76207).

Results: It was found that the expression levels of 5 APA regulatory factors (CPSF1, CPSF2, CSTF2, PABPC1, and PABPC4) were significantly associated with tumor gene mutation burden (TMB) score in renal clear cell carcinoma, and the risk score constructed using the expression level of 5 key APA regulatory factors could be used to predict the outcome of renal clear cell carcinoma. The TMB score is associated with the remodeling of the immune microenvironment.

Conclusions: By identifying key APA regulatory factors in renal cell carcinoma and constructing risk scores for key APA regulatory factors, we showed that key APA regulators affect prognosis of renal clear cell carcinoma patients. In addition, the risk score level is associated with TMB, indicating that APA may affect the efficacy of immunotherapy through immune microenvironment-related genes. This helps us better understand the mRNA processing mechanism of renal clear cell carcinoma.

Lung cancer imposes a burden on the health care system worldwide affecting 2 million people and causing 1.8 million deaths in 2021.More than 85% of all lung cancer cases are reported under Non-small-cell lung cancer (NSCLC). It is critical to discover gene alterations to treat non-small cell lung cancer successfully. The CAP/IASLC/AMP recommendations supported use of polymerase chain reaction (PCR) and fluorescent in situ hybridization (FISH) EGFR (epidermal growth factor receptor) mutations and ALK (Anaplastic lymphoma kinase) rearrangements, respectively. A study presented in the annual meeting of the American Society of Clinical Oncology (ASCO) in Chicago emphasized the need for comprehensive genomic profiling (CGP) before single gene tests (SGTs) since it demonstrated that SGT can result in the depletion of precious biopsy samples. As a result, the efficacy of thorough genetic Profiling (CGP) is reduced, preventing patients from receiving valuable genetic information about their tumors.

Large-scale, multi-site collaboration is becoming indispensable for a wide range of research and clinical activities in oncology. To facilitate the next generation of advances in cancer biology, precision oncology and the population sciences it will be necessary to develop and implement data management and analytic tools that empower investigators to reliably and objectively detect, characterize and chronicle the phenotypic and genomic changes that occur during the transformation from the benign to cancerous state and throughout the course of disease progression. To facilitate these efforts it is incumbent upon the informatics community to establish the workflows and architectures that automate the aggregation and organization of a growing range and number of clinical data types and modalities ranging from new molecular and laboratory tests to sophisticated diagnostic imaging studies. In an attempt to meet those challenges, leading health care centers across the country are making steep investments to establish enterprise-wide, data warehouses. A significant limitation of many data warehouses, however, is that they are designed to support only alphanumeric information. In contrast to those traditional designs, the system that we have developed supports automated collection and mining of multimodal data including genomics, digital pathology and radiology images. In this paper, our team describes the design, development and implementation of a multi-modal, Clinical & Research Data Warehouse (CRDW) that is tightly integrated with a suite of computational and machine-learning tools to provide actionable insight into the underlying characteristics of the tumor environment that would not be revealed using standard methods and tools. The System features a flexible Extract, Transform and Load (ETL) interface that enables it to adapt to aggregate data originating from different clinical and research sources depending on the specific EHR and other data sources utilized at a given deployment site.

Breast cancer is one of the leading causes of cancer mortality. Breast cancer patients in developing countries, especially sub-Saharan Africa, South Asia, and South America, suffer from the highest mortality rate in the world. One crucial factor contributing to the global disparity in mortality rate is long delay of diagnosis due to a severe shortage of trained pathologists, which consequently has led to a large proportion of late-stage presentation at diagnosis. To tackle this critical healthcare disparity, we have developed a deep learning-based diagnosis system for metastatic breast cancer that can achieve high diagnostic accuracy as well as computational efficiency and mobile readiness suitable for an under-resourced environment. We evaluated 4 Convolutional Neural Network (CNN) architectures: MobileNetV2, VGG16, ResNet50 and ResNet101. The MobileNetV2-based diagnostic model outperformed the more complex VGG16, ResNet50 and ResNet101 models in diagnostic accuracy, model generalization, and model training efficiency. The ROC AUC of MobilenetV2 (0.933, 95% CI: 0.930, 0.936) was higher than VGG16 (0.911, 95% CI: 0.908, 0.915), ResNet50 (0.869, 95% CI: 0.866, 0.873), and ResNet101 (0.873, 95% CI: 0.869, 0.876). The time per inference step for the MobileNetV2 model (15 ms/step) was substantially lower than that of VGG16 (48 ms/step), ResNet50 (37 ms/step), and ResNet110 (56 ms/step). The visual comparisons between the model prediction and ground truth have demonstrated that the MobileNetV2 diagnostic models can identify very small cancerous nodes embedded in a large area of normal cells which is challenging for manual image analysis. Equally Important, the light weight MobleNetV2 models were computationally efficient and ready for mobile devices or devices of low computational power. These advances empower the development of a resource-efficient and high performing AI-based metastatic breast cancer diagnostic system that can adapt to under-resourced healthcare facilities in developing countries.