Next-generation sequencing (NGS) genomic data offer valuable high-throughput genomic information for computational applications in medicine. Using genomic data to identify disease-associated genes to estimate cancer mortality risk remains challenging regarding to computational efficiency and risk integration. For determining mortality-related genes, we propose an information fusion system based on a fuzzy system to fuse the numerous deep-learning-based risk scores, consider the significance of features related to time-varying effects and risk stratifications, and interpret the directional relationship and interaction between outcome and predictors. Fuzzy rules were implemented to integrate the considerations mentioned above by merging all the risk score models to achieve advanced risk estimation. The genomic data of head and neck squamous cell carcinoma (HNSCC) were used to evaluate the performance of the proposed computational approach. The results indicated that the proposed computational approach exhibited optimal ability to identify mortality risk-related genes in HNSCC patients. The results also suggest that HNSCC mortality is associated with cancer inflammatory response, the interleukin-17A signaling pathway, stellate cell activation, and the extracellular-regulated protein kinase five signaling pathway, which might offer new therapeutic targets HNSCC through immunologic or antiangiogenic mechanisms. The proposed information fusion system can promote the determination of high-risk genes related to cancer mortality. This study contributes a valid cancer mortality risk estimate that can identify mortality-related genes.

There is substantial evidence that common genes based on single nucleotide polymorphisms (SNPs) are associated with cancer risk. Identifying disease-causing SNPs has, therefore, become an essential area of research. In this study, we used an arithmetic optimization algorithm (AOA) to select the significant genes using interactions between SNPs in breast cancer. We simultaneously analyzed several independent SNPs of genes for different combinations of interactions and their associated genotypes and calculated the variance between the case and control groups. The optimal combination of interactions was identified by determining the most significant difference in co-occurrence between the case and control groups. We also used the odds ratio (OR) to assess the effect of each combination of SNPs. Our research used a simulated breast cancer SNP dataset, which included 19 SNPs in 372 control participants and 398 breast cancer cases. The estimated OR of the best predicted SNP combination for breast cancer varied from 1.77 to 4.97 (confidence interval (CI): 1.22-13.47; p < 0.05) for specific combinations of two to six SNPs compared with their non-SNP combinations. Our AOA method accurately predicted high-risk SNP-SNP interactions for breast cancer. The proposed algorithm can potentially be adapted to study SNP-SNP interactions in various diseases and cancers.

Breast cancer (BRCA) and head and neck cancer (HNSC) represent significant global health challenges, underscoring the critical need for accurate prognosis in these patient populations. Tumor suppressor genes (TSGs) and oncogenes (OCGs) play pivotal roles in cancer progression, yet exhibit low mutation rates in affected individuals. Consequently, distinct omics patterns are necessary for estimating prognosis risk in patients harboring wild-type OCGs and TSGs. This study investigates mRNA expression of driver genes across TSG/OCG mutant subgroups and employs hierarchical clustering to identify mRNA expression patterns associated with higher prognosis risk. Data from both cancer cohorts were analyzed using agglomerative hierarchical clustering, revealing survival discrepancies between clusters in OCG/TSG-Wild subgroups. Our results emphasize the potential utilizing driver gene expression for prognostic risk estimation in BRCA and HNSC patients with wild-type OCGs and TSGs.

Identifying and characterizing the interaction between risk factors for multiple outcomes (multi-outcome interaction) has been one of the greatest challenges faced by complex multifactorial diseases. However, the existing approaches have several limitations in identifying the multi-outcome interaction. To address this issue, we proposed a multi-outcome interaction identification approach called MOAI. MOAI was motivated by the limitations of estimating the interaction simultaneously occurring in multi-outcomes and by the success of Pareto set filter operator for identifying multi-outcome interaction. MOAI permits the identification for the interaction of multiple outcomes and is applicable in population-based study designs. Our experimental results exhibited that the existing approaches are not effectively used to identify the multi-outcome interaction, whereas MOAI obviously exhibited superior performance in identifying multi-outcome interaction. We applied MOAI to identify the interaction between risk factors for colorectal cancer (CRC) in both metastases and mortality prognostic outcomes. An interaction between vaspin and carcinoembryonic antigen (CEA) was found, and the interaction indicated that patients with CRC characterized by higher vaspin (≥30%) and CEA (≥5) levels could simultaneously increase both metastases and mortality risk. The immunostaining evidence revealed that determined multi-outcome interaction could effectively identify the difference between non-metastases/survived and metastases/deceased patients, which offers multi-prognostic outcome risk estimation for CRC. To our knowledge, this is the first report of a multi-outcome interaction associated with a complex multifactorial disease. MOAI is freely available at https://sites.google.com/view/moaitool/home.

In the era of advanced precision medicine, next-generation genomic data are crucial to achieve breakthroughs in cancer medicine. Effective cancer mortality risk estimation for genomic data associated with cancer remains a vital challenge. The combination of machine learning algorithms and conventional survival analysis can advance the detection of high-risk missense mutation variants and candidate genes associated with cancer mortality in next-generation genomic data. In this article, a fuzzy logic system combined with machine learning algorithms and conventional survival analysis named FuzzyDeepCoxPH was proposed to identify high-risk missense mutation variants and candidate genes highly associated with cancer mortality. DL-derived abstracted weights and Cox proportional hazards (CoxPH) ratios were used to develop four model-based risk scores to consider the factor importance associated with risk stratification, time-varying effects, and individual and interaction effects among features. Fuzzy rules based on a fuzzy logic system were designed to integrate these considerations by merging four model-based risk scores to develop advanced risk estimation. The clinical features and next-generation sequencing of deoxyribonucleic acid and ribonucleic acid genomic data were used to evaluate FuzzyDeepCoxPH performance. The results indicated that FuzzyDeepCoxPH can effectively distinguish high-risk variants and candidate genes related to cancer mortality. In FuzzyDeepCoxPH, the fuzzy logic system was applied to combine DL-based and CoxPH-based models to provide a comprehensive cancer mortality risk estimation for cancer medicine.

Kidney clear cell carcinoma is commonly characterized by poor prognosis, which is associated with the function and differential expression of specific genes. The combination of a typical statistical survival model and nonparametric random forest algorithm provides a more precise estimation for the association between gene mutations and all-cause mortality risk. This study identifies mortality risk-associated gene mutations in kidney clear cell carcinoma by using a random survival forest algorithm. Of 22 candidate genes, VHL (variable importance [VIMP] = 0.097), EDIL3 (VIMP = 0.037), PBRM1 (VIMP = 0.027), PTEN (VIMP = 0.012), BAP1 (VIMP = 0.010), and HMGN5 (VIMP = 0.002) were selected and used to develop a dichotomous risk model for all-cause mortality by using the estimated risk threshold. The high-risk group exhibited a relatively poor survival rate than did the low-risk group (95.5% vs. 93.0%). In conclusion, this study provides a simple dichotomous model for mutation risk, according to the gene mutation risk threshold, by using a random survival forest model. For the gene mutation risk model, VHL, EDIL3, PBRM1, PTEN, BAP1, and HMGN5 were selected to effectively determine the effects of gene mutation on all-cause mortality from kidney clear cell carcinoma.

Studies have proven that single nucleotide polymorphism (SNP)-SNP interaction detection is helpful for understanding the susceptibility of an individual to genetic diseases. Although multifactor dimensionality reduction (MDR) is an effective SNP-SNP interaction detection algorithm, the mechanism of SNP-SNP interaction detection based on MDR contingency tables has not been widely studied. In this study, we propose a multi-objective MDR to detect SNP-SNP interactions. In the proposed multi-objective MDR, multiple measures can be simultaneously considered for detecting epistatic interactions. Then, set theory is used to select the best epistatic interactions in k-fold cross-validation to achieve high identification accuracy for SNP-SNP interactions. Two MDR parameters, namely the correct classification rate (CCR) and predictive summary index (PSI), were used for evaluating the algorithms. The results revealed that the detection success rates of multi-objective MDR were higher than those of other MDR-based algorithms in identifying epistatic interactions. Based on the CCR and PSI, our study demonstrated that the proposed multi-objective MDR can effectively detect SNP-SNP interactions.