compound.Cox: Univariate feature selection and compound covariate for predicting survival

Construction and validation of a ubiquitination-related prognostic risk score signature in breast cancer

Background

Breast cancer (BC) is a highly common form of cancer that occurs in many parts of the world. However, early -stage BC is curable. Many patients with BC have poor prognostic outcomes owing to ineffective diagnostic and therapeutic tools. The ubiquitination system and associated proteins were found influencing the outcome of individuals with cancer. Therefore, developing a biomarker associated with ubiquitination genes to forecast BC patient outcomes is a feasible strategy.

Objective

The primary goal of this work was to develop a novel risk score signature capable of accurately estimate the future outcome of patients with BC by targeting ubiquitinated genes.

Methods

Univariate Cox regression analysis was conducted utilizing the E1, E2, and E3 ubiquitination-related genes in the GSE20685 dataset. Genes with p < 0.01 were screened again using the Non-negative Matrix Factorization (NMF) algorithm, and the resulting hub genes were composed of a risk score signature. Patients were categorized into two risk groups, and the predictive effect was tested using Kaplan-Meier (KM) and Receiver Operating Characteristic (ROC) curves. This risk score signature was later validated using multiple external datasets, namely TCGA-BRAC, GSE1456, GSE16446, GSE20711, GSE58812 and GSE96058. Immuno-microenvironmental, single-cell, and microbial analyses were also performed.

Results

The selected gene signature comprising six ubiquitination-related genes (ATG5, FBXL20, DTX4, BIRC3, TRIM45, and WDR78) showed good prognostic power in patients with BC. It was validated using multiple externally validated datasets, with KM curves showing significant differences in survival (p < 0.05). The KM curves also demonstrated superior predictive ability compared to traditional clinical indicators. Single-cell analysis revealed that Vd2 gd T cells were less abundantin the low-risk group, whereas patients in the high-risk group lacked myeloid dendritic cells. Tumor microbiological analysis revealed a notable variation in microorganism diversity between the high- and low-risk groups.

Conclusion

This study established an risk score signature consisting of six ubiquitination genes, that can accurately forecast the outcome of patients with BC using multiple datasets. It can provide personalized and targeted assistance to provide the evaluation and therapy of individuals having BC.

Exploring a specialized programmed-cell death patterns to predict the prognosis and sensitivity of immunotherapy in cutaneous melanoma via machine learning

The mortality and therapeutic failure in cutaneous melanoma (CM) are mainly caused by wide metastasis and chemotherapy resistance. Meanwhile, immunotherapy is considered a crucial therapy strategy for CM patients. However, the efficiency of currently available methods and biomarkers in predicting the response of immunotherapy and prognosis of CM is limited. Programmed cell death (PCD) plays a significant role in the occurrence, development, and therapy of various malignant tumors. In this research, we integrated fourteen types of PCD, multi-omics data from TCGA-SKCM and other cohorts in GEO, and clinical CM patients to develop our analysis. Based on significant PCD patterns, two PCD-related CM clusters with different prognosis, tumor microenvironment (TME), and response to immunotherapy were identified. Subsequently, seven PCD-related features, especially CD28, CYP1B1, JAK3, LAMP3, SFN, STAT4, and TRAF1, were utilized to establish the prognostic signature, namely cell death index (CDI). CDI accurately predicted the response to immunotherapy in both CM and other cancers. A nomogram with potential superior predictive ability was constructed, and potential drugs targeting CM patients with specific CDI have also been identified. Given all the above, a novel CDI gene signature was indicated to predict the prognosis and exploit precision therapeutic strategies of CM patients, providing unique opportunities for clinical intelligence and new management methods for the therapy of CM.

Metastasis and basement membrane-related signature enhances hepatocellular carcinoma prognosis and diagnosis by integrating single-cell RNA sequencing analysis and immune microenvironment assessment

BACKGROUND

Hepatocellular carcinoma (HCC) is the most common type of primary liver cancer and second leading cause of cancer-related deaths worldwide. The heightened mortality associated with HCC is largely attributed to its propensity for metastasis, which cannot be achieved without remodeling or loss of the basement membrane (BM). Despite advancements in targeted therapies and immunotherapies, resistance and limited efficacy in late-stage HCC underscore the urgent need for better therapeutic options and early diagnostic biomarkers. Our study aimed to address these gaps by investigating and evaluating potential biomarkers to improve survival outcomes and treatment efficacy in patients with HCC.

METHOD

In this study, we collected the transcriptome sequencing, clinical, and mutation data of 424 patients with HCC from The Cancer Genome Atlas (TCGA) and 240 from the International Cancer Genome Consortium (ICGC) databases. We then constructed and validated a prognostic model based on metastasis and basement membrane-related genes (MBRGs) using univariate and multivariate Cox regression analyses. Five immune-related algorithms (CIBERSORT, QUANTISEQ, MCP counter, ssGSEA, and TIMER) were then utilized to examine the immune landscape and activity across high- and low-risk groups. We also analyzed Tumor Mutation Burden (TMB) values, Tumor Immune Dysfunction and Exclusion (TIDE) scores, mutation frequency, and immune checkpoint gene expression to evaluate immune treatment sensitivity. We analyzed integrin subunit alpha 3 (ITGA3) expression in HCC by performing single-cell RNA sequencing (scRNA-seq) analysis using the TISCH 2.0 database. Lastly, wound healing and transwell assays were conducted to elucidate the role of ITGA3 in tumor metastasis.

RESULTS

Patients with HCC were categorized into high- and low-risk groups based on the median values, with higher risk scores indicating worse overall survival. Five immune-related algorithms revealed that the abundance of immune cells, particularly T cells, was greater in the high-risk group than in the low-risk group. The high-risk group also exhibited a higher TMB value, mutation frequency, and immune checkpoint gene expression and a lower tumor TIDE score, suggesting the potential for better immunotherapy outcomes. Additionally, scRNA-seq analysis revealed higher ITGA3 expression in tumor cells compared with normal hepatocytes. Wound healing scratch and transwell cell migration assays revealed that overexpression of the MBRG ITGA3 enhanced migration of HCC HepG2 cells.

CONCLUSION

This study established a direct molecular correlation between metastasis and BM, encompassing clinical features, tumor microenvironment, and immune response, thereby offering valuable insights for predicting clinical outcomes and immunotherapy responses in HCC.

Combined radiation and chemotherapy versus monotherapy for anaplastic thyroid cancer: A SEER retrospective analysis

Background

The effect of combined radiation and chemotherapy (combination therapy) versus monotherapy on anaplastic thyroid carcinoma (ATC) has not yet been clear.

Methods

We identified 516 ATC patients during 2010-2015 from the Surveillance, Epidemiology and End Results (SEER) database and evaluated their survival outcome using the Kaplan-Meier method, Cox regression analysis and propensity score matching (PSM) technique.

Results

The median overall survival (OS) among the entire cohort was 3 months (95 % confidence interval [CI], 2.58-3.42 months), and the 6- and 12-month OS rates were 29 % (95 % CI, 25.01%-32.88 %) and 13 % (95 % CI, 10.60%-16.58 %), respectively. Multivariable analysis demonstrated that ATC patients not receiving radiotherapy or chemotherapy were unquestionably associated with worse OS (hazard ratio [HR] 3.000, 95 % CI, 2.390-3.764) and cancer-specific survival (CSS) (HR = 3.107, 95 % CI, 2.388-4.043), compared with those receiving combination therapy. However, combination therapy did not predict better prognosis compared with monotherapy (all P > 0.05). After PSM, the median OS and CSS were also not significantly improved in patients undergoing chemoradiotherapy versus chemotherapy alone (OS, P = 0.382; CSS, P = 0.420) or radiotherapy alone (OS, P = 0.065; CSS, P = 0.251).

Conclusion

Combination therapy, compared to monotherapy, does not have the expected improvement in survival beyond the benefits achievable with each single-modality treatment, necessitating further prospective research to tailor its treatment management.

Identification and validation of immunity- and disulfidptosis-related genes signature for predicting prognosis in ovarian cancer

Background

Ovarian cancer (OC) ranks as the fifth most prevalent neoplasm in women and exhibits an unfavorable prognosis. To improve the OC patient's prognosis, a pioneering risk signature was formulated by amalgamating disulfidptosis-related genes.

Methods

A comparative analysis of OC tissues and normal tissues was carried out, and differentially expressed disulfidptosis-related genes (DRGs) were found using the criteria of |log2 (fold change) | > 0.585 and adjusted P-value <0.05. Subsequently, the TCGA training set was utilized to create a prognostic risk signature, which was validated by employing both the TCGA testing set and the GEO dataset. Moreover, the immune cell infiltration, mutational load, response to chemotherapy, and response to immunotherapy were analyzed. To further validate these findings, QRT-PCR analysis was conducted on ovarian tumor cell lines.

Results

A risk signature was created using fourteen differentially expressed genes (DEGs) associated with disulfidptosis, enabling the classification of ovarian cancer (OC) patients into high-risk group (HRG) and low-risk group (LRG). The HRG exhibited a lower overall survival (OS) compared to the LRG. In addition, the risk score remained an independent predictor even after incorporating clinical factors. Furthermore, the LRG displayed lower stromal, immune, and estimated scores compared to the HRG, suggesting a possible connection between the risk signature, immune cell infiltration, and mutational load. Finally, the QRT-PCR experiments revealed that eight genes were upregulated in the human OC cell line SKOV3 compared with the human normal OC line IOSE80, while six genes were down-regulated.

Conclusions

A fourteen-biomarker signature composed of disulfidptosis-related genes could serve as a valuable risk stratification tool in OC, facilitating the identification of patients who may benefit from individualized treatment and follow-up management.

A novel radiomics approach for predicting TACE outcomes in hepatocellular carcinoma patients using deep learning for multi-organ segmentation

Transarterial chemoembolization (TACE) represent the standard of therapy for non-operative hepatocellular carcinoma (HCC), while prediction of long term treatment outcomes is a complex and multifactorial task. In this study, we present a novel machine learning approach utilizing radiomics features from multiple organ volumes of interest (VOIs) to predict TACE outcomes for 252 HCC patients. Unlike conventional radiomics models requiring laborious manual segmentation limited to tumoral regions, our approach captures information comprehensively across various VOIs using a fully automated, pretrained deep learning model applied to pre-TACE CT images. Evaluation of radiomics random survival forest models against clinical ones using Cox proportional hazard demonstrated comparable performance in predicting overall survival. However, radiomics outperformed clinical models in predicting progression-free survival. Explainable analysis highlighted the significance of non-tumoral VOI features, with their cumulative importance superior to features from the largest liver tumor. The proposed approach overcomes the limitations of manual VOI segmentation, requires no radiologist input and highlight the clinical relevance of features beyond tumor regions. Our findings suggest the potential of this radiomics models in predicting TACE outcomes, with possible implications for other clinical scenarios.

Pan-cancer analysis of the disulfidptosis-related gene RPN1 and its potential biological function and prognostic significance in gliomas

Background

Numerous studies have shown a strong correlation between disulfidptosis and various cancers. However, the expression and function of RPN1, a crucial gene in disulfidptosis, remain unclear in the context of cancer.

Methods

Gene expression and clinical information on lung adenocarcinoma were obtained from The Cancer Genome Atlas (TCGA) and Genotype-Tissue Expression (GTEx) databases. RPN1 expression was analyzed using the Timer2.0 and the Human Protein Atlas (HPA) databases. Prognostic significance was assessed using Cox regression analysis and Kaplan-Meier curves. Genetic mutations and methylation levels were examined using the cBioPortal and UALCAN platforms, respectively. The relationship between RPN1 and tumor mutation burden (TMB) and microsatellite instability (MSI) across different cancer types was analyzed using the Spearman correlation coefficient. The relationship between RPN1 and immune cell infiltration was analyzed using the Timer2.0 database, whereas variations in drug sensitivity were explored using the CellMiner database. Receiver operating characteristic curves validated RPN1's diagnostic potential in glioma, and its correlation with immune checkpoint inhibitors (ICIs) was assessed using Spearman's correlation coefficient. Single-sample gene set enrichment analysis elucidated a link between RPN1 and immune cells and pathways. In addition, a nomogram based on RPN1 was developed to predict patient prognosis. The functional impact of RPN1 on glioma cells was confirmed using scratch and Transwell assays.

Result

RPN1 was aberrantly expressed in various cancers and affected patient prognosis. The main mutation type of RPN1 in the cancer was amplified. RPN1 exhibited a positive correlation with myeloid-derived suppressor cells, neutrophils, and macrophages, and a negative correlation with CD8+ T cells and hematopoietic stem cells. RPN1 expression was associated with TMB and MSI in various cancers. The expression of RPN1 affected drug sensitivity in cancer cells. RPN1 was positively correlated with multiple ICIs in gliomas. RPN1 also affected immune cell infiltration into the tumor microenvironment. RPN1 was an independent prognostic factor for gliomas, and the nomogram demonstrated excellent predictive performance. Interference with RPN1 expression reduces the migratory and invasive ability of glioma cells.

Conclusion

RPN1 exerts multifaceted effects on different stages of cancer, including immune infiltration, prognosis, and treatment outcomes. RPN1 expression affects the prognosis and immune microenvironment infiltration in patients with glioma, making RPN1 a potential target for the treatment of glioma.

Analyzing the involvement of diverse cell death-related genes in diffuse large B-cell lymphoma using bioinformatics techniques

Diffuse large B-cell lymphoma (DLBCL) stands as the most prevalent subtype of non-Hodgkin's lymphoma and exhibits significant heterogeneity. Various forms of programmed cell death (PCD) have been established to have close associations with tumor onset and progression. To this end, this study has compiled 16 PCD-related genes. The investigation delved into genes linked with prognosis, constructing risk models through consecutive application of univariate Cox regression analysis and Lasso-Cox regression analysis. Furthermore, we employed RT-qPCR to validate the mRNA expression levels of certain diagnosis-related genes. Subsequently, the models underwent validation through KM survival curves and ROC curves, respectively. Additionally, nomogram models were formulated employing prognosis-related genes and risk scores. Lastly, disparities in immune cell infiltration abundance and the expression of immune checkpoint-associated genes between high- and low-risk groups, as classified by risk models, were explored. These findings contribute to a more comprehensive understanding of the role played by the 16 PCD-associated genes in DLBCL, shedding light on potential novel therapeutic strategies for the condition.

Nomogram-based prognostic tool for stage IIIB/IV non-small cell lung cancer patients undergoing traditional Chinese medicine treatment

Objective

Given the significant impact of long-term traditional Chinese medicine (TCM) treatment on the prognosis of patients with non-small cell lung cancer (NSCLC), we aimed to develop nomograms, with or without consideration of TCM treatment duration, to accurately predict the overall survival (OS) of patients with stage IIIB/IV NSCLC treated with TCM.

Methods

Nomograms were developed from a training cohort comprised of 292 patients diagnosed with NSCLC, using univariate and multivariate Cox regression analyses to screen for various prognostic factors with and without TCM treatment. The nomograms were evaluated using the concordance index (C-index), calibration curve, and decision curve analysis (DCA), after which they were validated, using the bootstrap self-sampling method for internal validation, and a validation cohort comprised of 175 patients for external validation. Bootstrap validation is a resampling technique that involves randomly selecting and replacing data from the original dataset to make statistical inferences, thereby circumventing the issue of sample reduction that can arise from cross-validation.

Results

We identified seven significant prognostic factors for OS. For nomogram A (excluding TCM treatment time), the C-indexes (95 % confidence interval [CI]) were 0.674 (0.635-0.712) and 0.660 (0.596-0.724) for the training and validation cohorts, respectively. For nomogram B (including TCM treatment time), the C-indices (95 % CI) were 0.846 (0.822-0.870) and 0.783 (0.730-0.894), for the training and validation cohorts, respectively, indicating that nomogram B was superior to nomogram A. Both the calibration curves and DCA results exhibited favorable clinical concordance and usefulness.

Conclusion

The nomogram B yielded precise prognostic predictions for patients with advanced NSCLC treated with TCM.

Pancreatic mucinous adenocarcinoma has different clinical characteristics and better prognosis compared to non-specific PDAC: A retrospective observational study

Background

Pancreatic mucinous adenocarcinoma (PMAC) is a rare malignant tumour, and there is limited understanding of its epidemiology and prognosis. Initially, PMAC was considered a metastatic manifestation of other cancers; however, instances of non-metastatic PMAC have been documented through monitoring, epidemiological studies, and data from the Surveillance, Epidemiology, and End Results (SEER) database. Therefore, it is crucial to investigate the epidemiological characteristics of PMAC and discern the prognostic differences between PMAC and the more prevalent pancreatic ductal adenocarcinoma (PDAC).

Methods

The study used data from the SEER database from 2000 to 2018 to identify patients diagnosed with PMAC or PDAC. To ensure comparable demographic characteristics between PDAC and PMAC, propensity score matching was employed. Kaplan-Meier analysis was used to analyse overall survival (OS) and cancer-specific survival (CSS). Univariate and multivariate Cox regression analyses were used to determine independent risk factors influencing OS and CSS. Additionally, the construction and validation of risk-scoring models for OS and CSS were achieved through the least absolute shrinkage and selection operator-Cox regression technique.

Results

The SEER database included 84,857 patients with PDAC and 3345 patients with PMAC. Notably, significant distinctions were observed in the distribution of tumour sites, diagnosis time, use of radiotherapy and chemotherapy, tumour size, grading, and staging between the two groups. The prognosis exhibited notable improvement among married individuals, those receiving acceptable chemotherapy, and those with focal PMAC (p < 0.05). Conversely, patients with elevated log odds of positive lymph node scores or higher pathological grades in the pancreatic tail exhibited a more unfavourable prognosis (p < 0.05). The risk-scoring models for OS or CSS based on prognostic factors indicated a significantly lower prognosis for high-risk patients compared to their low-risk counterparts (area under the curve OS: 0.81-0.82, CSS: 0.80-0.82).

Conclusion

PMAC exhibits distinct clinical characteristics compared to non-specific PDAC. Leveraging these features and pathological classifications allows for accurate prognostication of PMAC or PDAC.

AttBiLFNet: A novel hybrid network for accurate and efficient arrhythmia detection in imbalanced ECG signals

Within the domain of cardiovascular diseases, arrhythmia is one of the leading anomalies causing sudden deaths. These anomalies, including arrhythmia, are detectable through the electrocardiogram, a pivotal component in the analysis of heart diseases. However, conventional methods like electrocardiography encounter challenges such as subjective analysis and limited monitoring duration. In this work, a novel hybrid model, AttBiLFNet, was proposed for precise arrhythmia detection in ECG signals, including imbalanced class distributions. AttBiLFNet integrates a Bidirectional Long Short-Term Memory (BiLSTM) network with a convolutional neural network (CNN) and incorporates an attention mechanism using the focal loss function. This architecture is capable of autonomously extracting features by harnessing BiLSTM's bidirectional information flow, which proves advantageous in capturing long-range dependencies. The attention mechanism enhances the model's focus on pertinent segments of the input sequence, which is particularly beneficial in class imbalance classification scenarios where minority class samples tend to be overshadowed. The focal loss function effectively addresses the impact of class imbalance, thereby improving overall classification performance. The proposed AttBiLFNet model achieved 99.55% accuracy and 98.52% precision. Moreover, performance metrics such as MF1, K score, and sensitivity were calculated, and the model was compared with various methods in the literature. Empirical evidence showed that AttBiLFNet outperformed other methods in terms of both accuracy and computational efficiency. The introduced model serves as a reliable tool for the timely identification of arrhythmias.

Identification of exosome-related gene signature as a promising diagnostic and therapeutic tool for breast cancer

Background

Exosomes are promising tools for the development of new diagnostic and therapeutic approaches. Exosomes possess the ability to activate signaling pathways that contribute to the remodeling of the tumor microenvironment, angiogenesis, and the regulation of immune responses. We aimed to develop a prognostic score based on exosomes derived from breast cancer.

Materials and methods

Training was conducted on the TCGA-BRCA dataset, while validation was conducted on GSE20685, GSE5764, GSE7904, and GSE29431. A total of 121 genes related to exosomes were retrieved from the ExoBCD database. The Cox proportional hazards model is used to develop risk score model. The GSVA package was utilized to analyze single-sample gene sets and identify exosome signatures, while the WGCNA package was utilized to identify gene modules associated with clinical outcomes. The clusterProfiler and GSVA R packages facilitated gene set enrichment and variation analyses. Furthermore, CIBERSORT quantified immune infiltration, and a correlation between gene expression and drug sensitivity was assessed using the TIDE algorithm.

Results

An exosome-related prognostic score was established using the following selected genes: ABCC9, PIGR, CXCL13, DOK7, CD24, and IVL. Various immune cells that promote cancer immune evasion were associated with a high-risk prognostic score, which was an independent predictor of outcome. High-risk and low-risk groups exhibited significantly different infiltration abundances (p < 0.05). By conducting a sensitivity comparison, we found that patients with high-risk scores exhibited more favorable responses to immunotherapy than those with low-risk scores.

Conclusion

The exosome-related gene signature exhibits outstanding performance in predicting the prognosis and cancer status of patients with breast cancer and guiding immunotherapy.

A novel tumor mutation-related long non-coding RNA signature for predicting overall survival and immunotherapy response in lung adenocarcinoma

Background

Immunotherapy has changed the treatment landscape for lung cancer. This study aims to construct a tumor mutation-related model that combines long non-coding RNA (lncRNA) expression levels and tumor mutation levels in tumor genomes to detect the possibilities of the lncRNA signature as an indicator for predicting the prognosis and response to immunotherapy in lung adenocarcinoma (LUAD).

Methods

We downloaded the tumor mutation profiles and RNA-seq expression database of LUAD from The Cancer Genome Atlas (TCGA). Differentially expressed lncRNAs were extracted based on the cumulative number of mutations. Cox regression analyses were used to identify the prognostic lncRNA signature, and the prognostic value of the five selected lncRNAs was validated by using survival analysis and the receiver operating characteristic (ROC) curve. We used qPCR to validate the expression of five selected lncRNAs between human lung epithelial and human lung adenocarcinoma cell lines. The ImmuCellAI, immunophenoscore (IPS) scores and Tumor Immune Dysfunction and Exclusion (TIDE) analyses were used to predict the response to immunotherapy for this mutation related lncRNA signature.

Results

A total of 162 lncRNAs were detected among the differentially expressed lncRNAs between the Tumor mutational burden (TMB)-high group and the TMB-low group. Then, five lncRNAs (PLAC4, LINC01116, LINC02163, MIR223HG, FAM83A-AS1) were identified as tumor mutation-related candidates for constructing the prognostic prediction model. Kaplan‒Meier curves showed that the overall survival of the low-risk group was significantly better than that of the high-risk group, and the results of the GSE50081 set were consistent. The expression levels of PD1, PD-L1 and CTLA4 in the low-risk group were higher than those in the high-risk group. The IPS scores and TIDE scores of patients in the low-risk group were significantly higher than those in the high-risk group.

Conclusion

Our findings demonstrated that the five lncRNAs (PLAC4, LINC01116, LINC02163, MIR223HG, FAM83A-AS1) were identified as candidates for constructing the tumor mutation-related model which may serve as an indicator of tumor mutation levels and have important implications for predicting the response to immunotherapy in LUAD.

Identifying the tumor-associated macrophage of lung adenocarcinoma reveals immune landscape through omics data integration

The tumor-associated macrophages (TAM) play a crucial role in lung adenocarcinoma (LUAD), which can cause the proliferation, migration and invasion of tumor cells. In particular, TAMs mainly regulate changes in the tumor microenvironment thereby contributing to tumorigenesis and progression. Recently, an increasing number of studies are using single-cell RNA (Sc-RNA) sequencing to investigate changes in the composition and transcriptomics of the tumor microenvironment. We obtained Sc-RNA sequencing data of LUAD from GEO database and transcriptome data with clinical information of LUAD patients from TCGA database. A group of important genes in the state transition of TAMs was identified by analyzing TAMs at the single-cell level, while 5 TAM-related prognostic genes were obtained by omics data integration, and a prognostic model was constructed. GOBP analysis revealed that TAM-related genes were mainly enriched in tumor-promoting and immunosuppression-related pathways. After ROC analysis, it was found that the AUC of the prognosis model reached 0.751, with well predictive effectiveness. The 5 unique genes, HLA-DMB, HMGN3, ID3, PEBP1, and TUBA1B, was finally identified through synthesized analysis. The transcriptional characteristics of 5 genes were determined through GEPIA2 database and RT-qPCR. The increased expression of TUBA1B in advanced LUAD may serve as a prognostic indicator, while low expression of PEBP1 in LUAD may have the potential to become a therapeutic target.

Lactylation-related gene signature for prognostic prediction and immune infiltration analysis in breast cancer

Background

Lactylation is implicated in various aspects of tumor biology, but its relation to breast cancer remains poorly understood. This study aimed to explore the roles of the lactylation-related genes in breast cancer and its association with the tumor microenvironment.

Methods

The expression and mutation patterns of lactylation-related genes were analyzed using the breast cancer data from The Cancer Genome Atlas (TCGA) database and GSE20685 datasets. Unsupervised clustering was used to identify two lactylation clusters. A lactylation-related gene signature was developed and validated using the training and validation cohorts. Immune cell infiltration and drug response were assessed.

Results

We analyzed the mRNA expression, copy number variations, somatic mutations, and correlation networks of 22 lactylation-related genes in breast cancer tissues. We identified two distinct lactylation clusters with different survival outcomes and immune microenvironments. We further classified the patients into two gene subtypes based on lactylation clusters and identified a 7-gene signature for breast cancer survival prognosis. The prognostic score based on this signature demonstrated prognostic value and predicted the therapeutic response.

Conclusion

Lactylation-related genes play a critical role in breast cancer by influencing tumor growth, immune microenvironment, and drug response. This lactylation-related gene signature may serve as a prognostic marker and a potential therapeutic target for breast cancer.

Novel ensemble feature selection techniques applied to high-grade gastroenteropancreatic neuroendocrine neoplasms for the prediction of survival

BACKGROUND AND OBJECTIVE

Determining the most informative features for predicting the overall survival of patients diagnosed with high-grade gastroenteropancreatic neuroendocrine neoplasms is crucial to improve individual treatment plans for patients, as well as the biological understanding of the disease. The main objective of this study is to evaluate the use of modern ensemble feature selection techniques for this purpose with respect to (a) quantitative performance measures such as predictive performance, (b) clinical interpretability, and (c) the effect of integrating prior expert knowledge.

METHODS

The Repeated Elastic Net Technique for Feature Selection (RENT) and the User-Guided Bayesian Framework for Feature Selection (UBayFS) are recently developed ensemble feature selectors investigated in this work. Both allow the user to identify informative features in datasets with low sample sizes and focus on model interpretability. While RENT is purely data-driven, UBayFS can integrate expert knowledge a priori in the feature selection process. In this work, we compare both feature selectors on a dataset comprising 63 patients and 110 features from multiple sources, including baseline patient characteristics, baseline blood values, tumor histology, imaging, and treatment information.

RESULTS

Our experiments involve data-driven and expert-driven setups, as well as combinations of both. In a five-fold cross-validated experiment without expert knowledge, our results demonstrate that both feature selectors allow accurate predictions: A reduction from 110 to approximately 20 features (around 82%) delivers near-optimal predictive performances with minor variations according to the choice of the feature selector, the predictive model, and the fold. Thereafter, we use findings from clinical literature as a source of expert knowledge. In addition, expert knowledge has a stabilizing effect on the feature set (an increase in stability of approximately 40%), while the impact on predictive performance is limited.

CONCLUSIONS

The features WHO Performance Status, Albumin, Platelets, Ki-67, Tumor Morphology, Total MTV, Total TLG, and SUVmax are the most stable and predictive features in our study. Overall, this study demonstrated the practical value of feature selection in medical applications not only to improve quantitative performance but also to deliver potentially new insights to experts.

Factorial survival analysis for treatment effects under dependent censoring

Factorial analyses offer a powerful nonparametric means to detect main or interaction effects among multiple treatments. For survival outcomes, for example, from clinical trials, such techniques can be adopted for comparing reasonable quantifications of treatment effects. The key difficulty to solve in survival analysis concerns the proper handling of censoring. So far, all existing factorial analyses for survival data have been developed under the independent censoring assumption, which is too strong for many applications. As a solution, the central aim of this article is to develop new methods for factorial survival analyses under quite general dependent censoring regimes. This will be accomplished by combining existing nonparametric methods for factorial survival analyses with techniques developed for survival copula models. As a result, we will present an appealing F-test that exhibits sound performance in our simulation study. The new methods are illustrated in a real data analysis. We implement the proposed method in an R function surv.factorial(.) in the R package compound.Cox.

Survival nomogram for medulloblastoma and multi-center external validation cohort

Background: Medulloblastoma (MB) is a highly malignant neuroepithelial tumor occurring in the central nervous system. The objective of this study was to establish an effective prognostic nomogram to predict the overall survival (OS) of MB patients. Materials and methods: The nomogram was developed using data from a retrospective cohort of 280 medulloblastoma patients (aged 3-18 years) identified from Beijing Tiantan Hospital between 2016 and 2021 as the training cohort. To validate the performance of the nomogram, collaborations were formed with eight leading pediatric oncology centers across different regions of China. A total of 162 medulloblastoma patients meeting the inclusion criteria were enrolled from these collaborating centers. Cox regression analysis, best subsets regression, and Lasso regression were employed to select independent prognostic factors. The nomogram's prognostic effectiveness for overall survival was assessed using the concordance index, receiver operating characteristic curve, and calibration curve. Results: In the training cohort, the selected variables through COX regression, best subsets regression, and Lasso regression, along with their clinical significance, included age, molecular subtype, histological type, radiotherapy, chemotherapy, metastasis, and hydrocephalus. The internally and externally validated C-indexes were 0.907 and 0.793, respectively. Calibration curves demonstrated the precise prediction of 1-, 3-, and 5-year OS for MB patients using the nomogram. Conclusion: This study developed a nomogram that incorporates clinical and molecular factors to predict OS prognosis in medulloblastoma patients. The nomogram exhibited improved predictive accuracy compared to previous studies and demonstrated good performance in the external validation cohort. By considering multiple factors, clinicians can utilize this nomogram as a valuable tool for individualized prognosis prediction and treatment decision-making in medulloblastoma patients.

TMSB4X: A novel prognostic marker for non-small cell lung cancer

Non-small cell lung cancer (NSCLC), as the main type of lung cancer, has a long history of high incidence and mortality. Despite the continuous updates to the American Joint Committee on Cancer (AJCC) staging system, which adapt to evolving treatment modalities and diagnostic advancements, it is evident that patients at the same stage exhibit varying prognoses. The heterogeneity of tumors underscores the need for molecular diagnostics to assume a pivotal role in tumor staging and patient stratification. In our investigation, we meticulously analyzed the data of the Cancer Genome Atlas (TCGA) and Gene Expression Omnibus (GEO) database, incorporating clinical patients and scrutinizing pathological specimens. Through this comprehensive approach, we established a correlation between the expression of the Thymosin beta 4 X-linked (TMSB4X) gene and poorer disease-free survival (DFS) and overall survival (OS) post-surgery. Compared to the TMSB4X positive expression group, patients in the negative expression group had a better prognosis, with longer DFS (median disease-free survival (median DFS): 16.2 months vs. 11.3 months, P = 0.032) and OS (median overall survival (mOS): 29.8 months vs. 18.5 months, P = 0.033). Furthermore, our findings suggest that TMSB4X may facilitate immune evasion in non-small cell lung cancer cells by influencing the activation of infiltrating dendritic cells (DCs) in tumor infiltrating immune cells (TIICs) (R = 0.27, P = 4.8E+08). In summary, TMSB4X emerges as an unfavorable prognostic factor for NSCLC, potentially modulating the tumor immune microenvironment through its regulatory impact on dendritic cell function, thus facilitating tumor immune escape.

Diagnosis of lung cancer following emergency admission: Examining care pathways, clinical outcomes, and advanced NSCLC treatment in an Italian cancer Center

Background

Lung cancer patients diagnosed following emergency admission often present with advanced disease and poor performance status, leading to suboptimal treatment options and outcomes. This study aimed to investigate the clinical and molecular characteristics, treatment initiation, and survival outcomes of these patients.

Methods

We retrospectively analyzed data from 124 patients diagnosed with lung cancer following emergency admission at a single institution. Clinical characteristics, results of molecular analyses for therapeutic purpose, systemic treatment initiation, and survival outcomes were assessed. Correlations between patients' characteristics and treatment initiation were analyzed.

Results

Median age at admission was 73 years, and 79.0 % had at least one comorbidity. Most patients (87.1 %) were admitted due to cancer-related symptoms. Molecular analyses were performed in 89.5 % of advanced non-small cell lung cancer (NSCLC) cases. In this subgroup, two-thirds (66.2 %) received first-line therapy. Median overall survival (OS) was 3.9 months for the entire cohort, and 2.9 months for patients with metastatic lung cancer. Among patients with advanced NSCLC, OS was significantly longer for those with actionable oncogenic drivers and those who received first-line therapy. Improvement of performance status during hospitalization resulted in increased probability of receiving first-line systemic therapy.

Discussion

Patients diagnosed with lung cancer following emergency admission demonstrated poor survival outcomes. Treatment initiation, particularly for patients with actionable oncogenic drivers, was associated with longer OS. These findings highlight the need for proactive medical approaches, including improving access to molecular diagnostics and targeted treatments, to optimize outcomes in this patient population.

Prediction of Rapid Early Progression and Survival Risk with Pre-Radiation MRI in WHO Grade 4 Glioma Patients

Recent clinical research describes a subset of glioblastoma patients that exhibit REP prior to the start of radiation therapy. Current literature has thus far described this population using clinicopathologic features. To our knowledge, this study is the first to investigate the potential of conventional radiomics, sophisticated multi-resolution fractal texture features, and different molecular features (MGMT, IDH mutations) as a diagnostic and prognostic tool for prediction of REP from non-REP cases using computational and statistical modeling methods. The radiation-planning T1 post-contrast (T1C) MRI sequences of 70 patients are analyzed. An ensemble method with 5-fold cross-validation over 1000 iterations offers an AUC of 0.793 ± 0.082 for REP versus non-REP classification. In addition, copula-based modeling under dependent censoring (where a subset of the patients may not be followed up with until death) identifies significant features (p-value < 0.05) for survival probability and prognostic grouping of patient cases. The prediction of survival for the patients' cohort produces a precision of 0.881 ± 0.056. The prognostic index (PI) calculated using the fused features shows that 84.62% of REP cases fall under the bad prognostic group, suggesting the potential of fused features for predicting a higher percentage of REP cases. The experimental results further show that multi-resolution fractal texture features perform better than conventional radiomics features for prediction of REP and survival outcomes.

Gene co-expression network construction and analysis for identification of genetic biomarkers associated with glioblastoma multiforme using topological findings

BACKGROUND

Glioblastoma multiforme (GBM) is one of the most malignant types of central nervous system tumors. GBM patients usually have a poor prognosis. Identification of genes associated with the progression of the disease is essential to explain the mechanisms or improve the prognosis of GBM by catering to targeted therapy. It is crucial to develop a methodology for constructing a biological network and analyze it to identify potential biomarkers associated with disease progression.

METHODS

Gene expression datasets are obtained from TCGA data repository to carry out this study. A survival analysis is performed to identify survival associated genes of GBM patient. A gene co-expression network is constructed based on Pearson correlation between the gene's expressions. Various topological measures along with set operations from graph theory are applied to identify most influential genes linked with the progression of the GBM.

RESULTS

Ten key genes are identified as a potential biomarkers associated with GBM based on centrality measures applied to the disease network. These genes are SEMA3B, APS, SLC44A2, MARK2, PITPNM2, SFRP1, PRLH, DIP2C, CTSZ, and KRTAP4.2. Higher expression values of two genes, SLC44A2 and KRTAP4.2 are found to be associated with progression and lower expression values of seven gens SEMA3B, APS, MARK2, PITPNM2, SFRP1, PRLH, DIP2C, and CTSZ are linked with the progression of the GBM.

CONCLUSIONS

The proposed methodology employing a network topological approach to identify genetic biomarkers associated with cancer.

Prognostic prediction and immunotherapy response analysis of the fatty acid metabolism-related genes in clear cell renal cell carcinoma

Background

Clear cell renal cell carcinoma (ccRCC) is a common urinary cancer. Although diagnostic and therapeutic approaches for ccRCC have been improved, the survival outcomes of patients with advanced ccRCC remain unsatisfactory. Fatty acid metabolism (FAM) has been increasingly recognized as a critical modulator of cancer development. However, the significance of the FAM in ccRCC remains unclear. Herein, we explored the function of a FAM-related risk score in the stratification and prediction of treatment responses in patients with ccRCC.

Methods

First, we applied an unsupervised clustering method to categorize patients from The Cancer Genome Atlas (TCGA) and International Cancer Genome Consortium (ICGC) datasets into subtypes and retrieved FAM-related genes from the MSigDB database. We discern differentially expressed genes (DEGs) among different subtypes. Then, we applied univariate Cox regression analysis followed by least absolute shrinkage and selection operator (LASSO) linear regression based on DEGs expression to establish a FAM-related risk score for ccRCC.

Results

We stratified the three ccRCC subtypes based on FAM-related genes with distinct overall survival (OS), clinical features, immune infiltration patterns, and treatment sensitivities. We screened nine genes from the FAM-related DEGs in the three subtypes to establish a risk prediction model for ccRCC. Nine FAM-related genes were differentially expressed in the ccRCC cell line ACHN compared to the normal kidney cell line HK2. High-risk patients had worse OS, higher genomic heterogeneity, a more complex tumor microenvironment (TME), and elevated expression of immune checkpoints. This phenomenon was validated in the ICGC cohort.

Conclusion

We constructed a FAM-related risk score that predicts the prognosis and therapeutic response of ccRCC. The close association between FAM and ccRCC progression lays a foundation for further exploring FAM-related functions in ccRCC.

Construction and validation of a prognostic prediction model for gastric cancer using a series of genes related to lactate metabolism

Background

Gastric cancer (GC) is one of the most common clinical malignant tumors worldwide, with high morbidity and mortality. The commonly used tumor-node-metastasis (TNM) staging and some common biomarkers have a certain value in predicting the prognosis of GC patients, but they gradually fail to meet the clinical demands. Therefore, we aim to construct a prognostic prediction model for GC patients.

Methods

A total of 350 cases were included in the STAD (Stomach adenocarcinoma) entire cohort of TCGA (The Cancer Genome Atlas), including the STAD training cohort of TCGA (n = 176) and the STAD testing cohort of TCGA (n = 174). GSE15459 (n = 191), and GSE62254 (n = 300) were for external validation.

Results

Through differential expression analysis and univariate Cox regression analysis in the STAD training cohort of TCGA, we screened out five genes among 600 genes related to lactate metabolism for the construction of our prognostic prediction model. The internal and external validations showed the same result, that is, patients with higher risk score were associated with poor prognosis (all p < 0.05), and our model works well without regard of patients' age, gender, tumor grade, clinical stage or TNM stage, which supports the availability, validity and stability of our model. Gene function analysis, tumor-infiltrating immune cells analysis, tumor microenvironment analysis and clinical treatment exploration were performed to improve the practicability of the model, and hope to provide a new basis for more in-depth study of the molecular mechanism for GC and for clinicians to formulate more reasonable and individualized treatment plans.

Conclusions

We screened out and used five genes related to lactate metabolism to develop a prognostic prediction model for GC patients. The prediction performance of the model is confirmed by a series of bioinformatics and statistical analysis.

Circadian Genes MBOAT2/CDA/LPCAT2/B4GALT5 in the Metabolic Pathway Serve as New Biomarkers of PACA Prognosis and Immune Infiltration

Pancreatic cancer (PACA) is a highly malignant tumor with a poor prognosis. Recent studies have discovered substantial differences in the expression levels of several circadian genes in PACA samples compared to normal samples. The goal of this research was to find differentially expressed rhythm genes (DERGs) in PACA samples and determine their role in the development of PACA. A total of 299 DERGs were identified in PACA, including 134 downregulated genes and 165 upregulated genes. DERGs were significantly abundant in the metabolic pathway and immune response pathways, according to GO and KEGG analyses. Survival analyses showed that PACA patients who had higher expression levels of MBOAT2/CDA/LPCAT2/B4GALT5 had shorter overall survival times. Using cell assay verification, the mRNA levels of MBOAT2/CDA/LPCAT2/B4GALT5 in Patu-8988 and PNAC-1 cells were found to be significantly higher than those in HPDE6-C7 cells, which was in line with previous studies on PACA patient data. Through conducting univariate Cox analysis, it was determined that MBOAT2/CDA/LPCAT2/B4GALT5 expression, age and grade were all high-risk factors. The MBOAT2/CDA/LPCAT2/B4GALT5 genes were independently correlated with overall survival, according to the multivariate Cox analysis. The proportion of immune cells in PACA and normal samples significantly changed, according to the immune infiltration analysis. Furthermore, MBOAT2/CDA/LPCAT2/B4GALT5 expression levels were significantly related to the level of immune cell infiltration. The protein-protein interaction network of the MBOAT2/CDA/LPCAT2/B4GALT5 genes included 54 biological nodes and 368 interacting genes. In conclusion, the finding of these DERGs adds to the investigation of the molecular processes underlying the onset and progression of PACA. In the future, DERGs may serve as prognostic and diagnostic biomarkers as well as drug targets for chronotherapy in PACA patients.

Apoptosis related genes mediated molecular subtypes depict the hallmarks of the tumor microenvironment and guide immunotherapy in bladder cancer

Apoptosis has been discovered as a mechanism of cell death. The purpose of this study is to identify the diagnostic signature factors related to bladder cancer (BLCA) through apoptosis related genes (ARGs). Clinicopathological parameters and transcriptomics data of 1,440 BLCA patients were obtained from 7 datasets (GSE13507, GSE31684, GSE32548, GSE32894, GSE48075, TCGA-BLCA, and IMvigor210). We first identified prognosis-related ARGs in BLCA and used them to construct two ARGs molecular subtypes by using consensus clustering algorithm. By using principal component analysis algorithms, a ARGscore was constructed to quantify the index of individualized patient. High ARGscore correlated with progressive malignancy and poor outcomes in BLCA patients. High ARGscore was associated with higher immune cell, higher estimate scores, higher stromal scores, higher immune scores, higher immune checkpoint, and lower tumor purity, which was consistent with the "immunity tidal model theory". Preclinically, BLCA immunotherapy cohorts confirmed patients with low ARGscore demonstrated significant therapeutic advantages and clinical benefits. These findings contribute to our understanding of ARGs and immunotherapy in BLCA. The ARGscore is a potentially useful tool to predict the prognosis and immunotherapy in BLCA.

Sensitivity Analysis for Survival Prognostic Prediction with Gene Selection: A Copula Method for Dependent Censoring

Prognostic analysis for patient survival often employs gene expressions obtained from high-throughput screening for tumor tissues from patients. When dealing with survival data, a dependent censoring phenomenon arises, and thus the traditional Cox model may not correctly identify the effect of each gene. A copula-based gene selection model can effectively adjust for dependent censoring, yielding a multi-gene predictor for survival prognosis. However, methods to assess the impact of various types of dependent censoring on the multi-gene predictor have not been developed. In this article, we propose a sensitivity analysis method using the copula-graphic estimator under dependent censoring, and implement relevant methods in the R package "compound.Cox". The purpose of the proposed method is to investigate the sensitivity of the multi-gene predictor to a variety of dependent censoring mechanisms. In order to make the proposed sensitivity analysis practical, we develop a web application. We apply the proposed method and the web application to a lung cancer dataset. We provide a template file so that developers can modify the template to establish their own web applications.

Construction of a prognostic prediction model for renal clear cell carcinoma combining clinical traits

Kidney renal clear cell carcinoma (KIRC) is one of the common malignant tumors of the urinary system. Patients with different risk levels are other in terms of disease progression patterns and disease regression. The poorer prognosis for high-risk patients compared to low-risk patients. Therefore, it is essential to accurately high-risk screen patients and gives accurate and timely treatment. Differential gene analysis, weighted correlation network analysis, Protein-protein interaction network, and univariate Cox analysis were performed sequentially on the train set. Next, the KIRC prognostic model was constructed using the least absolute shrinkage and selection operator (LASSO), and the Cancer Genome Atlas (TCGA) test set and the Gene Expression Omnibus dataset verified the model's validity. Finally, the constructed models were analyzed; including gene set enrichment analysis (GSEA) and immune analysis. The differences in pathways and immune functions between the high-risk and low-risk groups were observed to provide a reference for clinical treatment and diagnosis. A four-step key gene screen resulted in 17 key factors associated with disease prognosis, including 14 genes and 3 clinical features. The LASSO regression algorithm selected the seven most critical key factors to construct the model: age, grade, stage, GDF3, CASR, CLDN10, and COL9A2. In the training set, the accuracy of the model in predicting 1-, 2- and 3-year survival rates was 0.883, 0.819, and 0.830, respectively. The accuracy of the TCGA dataset was 0.831, 0.801, and 0.791, and the accuracy of the GSE29609 dataset was 0.812, 0.809, and 0.851 in the test set. Model scoring divided the sample into a high-risk group and a low-risk group. There were significant differences in disease progression and risk scores between the two groups. GSEA analysis revealed that the enriched pathways in the high-risk group mainly included proteasome and primary immunodeficiency. Immunological analysis showed that CD8 (+) T cells, M1 macrophages, PDCD1, and CTLA4 were upregulated in the high-risk group. In contrast, antigen-presenting cell stimulation and T-cell co-suppression were more active in the high-risk group. This study added clinical characteristics to constructing the KIRC prognostic model to improve prediction accuracy. It provides help to assess the risk of patients more accurately. The differences in pathways and immunity between high and low-risk groups were also analyzed to provide ideas for treating KIRC patients.

Cross-trial prediction of depression remission using problem-solving therapy: A machine learning approach

BACKGROUND

Psychotherapy is a standard depression treatment; however, determining a patient's prognosis with therapy relies on clinical judgment that is subject to trial-and-error and provider variability.

PURPOSE

To develop machine learning (ML) algorithms to predict depression remission for patients undergoing 6 months of problem-solving therapy (PST).

METHOD

Using data from the treatment arm of 2 randomized trials, ML models were trained and validated on ENGAGE-2 (ClinicalTrials.gov, #NCT03841682) and tested on RAINBOW (ClinicalTrials.gov, #NCT02246413) for predictions at baseline and at 2-months. Primary outcome was depression remission using the Depression Symptom Checklist (SCL-20) score < 0.5 at 6 months. Predictor variables included baseline characteristics (sociodemographic, behavioral, clinical, psychosocial) and intervention engagement through 2-months.

RESULTS

Of the 26 candidate variables, 8 for baseline and 11 for 2-months were predictive of depression remission, and used to train the models. The best-performing model predicted remission with an accuracy significantly greater than chance in internal validation using the ENGAGE-2 cohort, at baseline [72.6% (SD = 3.6%), p < 0.0001] and at 2-months [72.3% (5.1%), p < 0.0001], and in external validation with the RAINBOW cohort at baseline [58.3% (0%), p < 0.0001] and at 2-months [62.3% (0%), p < 0.0001]. Model-agnostic explanations highlighted key predictors of depression remission at the cohort and patient levels, including female sex, lower self-reported sleep disturbance, lower sleep-related impairment, and lower negative problem orientation.

CONCLUSIONS

ML models using clinical and patient-reported data can predict depression remission for patients undergoing PST, affording opportunities for prospective identification of likely responders, and for developing personalized early treatment optimization along the patient care trajectory.

The Landscape of Using Glycosyltransferase Gene Signatures for Overall Survival Prediction in Hepatocellular Carcinoma

Hepatocellular carcinoma (HCC) is a heterogeneous disease that occurs in the setting of chronic liver diseases. The role of glycosyltransferase (GT) genes has recently been the focus of research associated with tumor development. However, the prognostic value of GT genes in HCC remains unclear. Therefore, this study aimed to identify GT genes related to HCC prognosis through bioinformatics analysis. We firstly constructed a prognostic signature based on four GT genes using univariate and least absolute shrinkage and selection operator (LASSO) Cox regression analyses in The Cancer Genome Atlas (TCGA) dataset. Next, the risk score of each patient was calculated, and HCC patients were divided into high- and low-risk groups. Kaplan–Meier analysis showed that the survival rate of high-risk patients was significantly lower than that of low-risk patients. Receiver operating characteristic (ROC) curves assessed that risk scores calculated with a four-gene signature could predict 3- and 5-year overall survival (OS) of HCC patients, revealing the prognostic ability of this gene signature. Moreover, univariate and multivariate Cox regression analyses demonstrated that the risk score was an independent prognostic factor of HCC. Finally, functional analysis revealed that immune-related pathways were enriched and the immune status was different between the two risk groups in HCC. In summary, the novel GT gene signature could be used for prognostic prediction of HCC. Thus, targeting the GT genes may serve as an alternative treatment strategy for HCC.

Dynamic Risk Prediction via a Joint Frailty-Copula Model and IPD Meta-Analysis: Building Web Applications

Clinical risk prediction formulas for cancer patients can be improved by dynamically updating the formulas by intermediate events, such as tumor progression. The increased accessibility of individual patient data (IPD) from multiple studies has motivated the development of dynamic prediction formulas accounting for between-study heterogeneity. A joint frailty-copula model for overall survival and time to tumor progression has the potential to develop a dynamic prediction formula of death from heterogenous studies. However, the process of developing, validating, and publishing the prediction formula is complex, which has not been sufficiently described in the literature. In this article, we provide a tutorial in order to build a web-based application for dynamic risk prediction for cancer patients on the basis of the R packages joint.Cox and Shiny. We demonstrate the proposed methods using a dataset of breast cancer patients from multiple clinical studies. Following this tutorial, we demonstrate how one can publish web applications available online, which can be manipulated by any user through a smartphone or personal computer. After learning this tutorial, developers acquire the ability to build an online web application using their own datasets.

Survival Risk Prediction of Esophageal Cancer Based on the Kohonen Network Clustering Algorithm and Kernel Extreme Learning Machine

Accurate prediction of the survival risk level of patients with esophageal cancer is significant for the selection of appropriate treatment methods. It contributes to improving the living quality and survival chance of patients. However, considering that the characteristics of blood index vary with individuals on the basis of their ages, personal habits and living environment etc., a unified artificial intelligence prediction model is not precisely adequate. In order to enhance the precision of the model on the prediction of esophageal cancer survival risk, this study proposes a different model based on the Kohonen network clustering algorithm and the kernel extreme learning machine (KELM), aiming to classifying the tested population into five catergories and provide better efficiency with the use of machine learning. Firstly, the Kohonen network clustering method was used to cluster the patient samples and five types of samples were obtained. Secondly, patients were divided into two risk levels based on 5-year net survival. Then, the Taylor formula was used to expand the theory to analyze the influence of different activation functions on the KELM modeling effect, and conduct experimental verification. RBF was selected as the activation function of the KELM. Finally, the adaptive mutation sparrow search algorithm (AMSSA) was used to optimize the model parameters. The experimental results were compared with the methods of the artificial bee colony optimized support vector machine (ABC-SVM), the three layers of random forest (TLRF), the gray relational analysis–particle swarm optimization support vector machine (GP-SVM) and the mixed-effects Cox model (Cox-LMM). The results showed that the prediction model proposed in this study had certain advantages in terms of prediction accuracy and running time, and could provide support for medical personnel to choose the treatment mode of esophageal cancer patients.

Identification of a Four Cancer Stem Cell-Related Gene Signature and Establishment of a Prognostic Nomogram Predicting Overall Survival of Pancreatic Adenocarcinoma

BACKGROUND

Cancer stem cells (CSCs) are now being considered as the initial component in the development of pancreatic adenocarcinoma (PAAD). Our aim was to develop a CSCrelated signature to assess the prognosis of PAAD patients for the optimization of treatment.

METHODS

Differentially expressed genes (DEGs) between pancreatic tumor and normal tissue in the Cancer Genome Atlas (TCGA) were screened out, and the weighted gene correlation network analysis (WGCNA) was employed to identify the CSC-related gene sets. Then, univariate, Lasso Cox regression analyses and multivariate Cox regression were applied to construct a prognostic signature using the CSC-related genes. Its prognostic performance was validated in TCGA and ICGC cohorts. Furthermore, Univariate and multivariate Cox regression analyses were used to identify independent prognostic factors in PAAD, and a prognostic nomogram was established.

RESULTS

The Kaplan-Meier analysis, ROC curve and C-index indicated the good performance of the CSC-related signature at predicting overall survival (OS). Univariate Cox regression and multivariate Cox regression revealed that the CSC-related signature was an independent prognostic factor in PAAD. The nomogram was superior to the risk model and AJCC stage in predicting OS. In terms of mutation and tumor immunity, patients in the high-risk group had higher tumor mutation burden (TMB) scores than patients in the low-risk group, and the immune score and the ESTIMATE score were significantly lower in the high-risk group. Moreover, according to the results of principal component analysis (PCA) and Gene Set Enrichment Analysis (GSEA), the low-risk and high-risk groups displayed different stemness statuses based on the risk model.

CONCLUSION

Our study identified four CSC-related gene signatures and established a prognostic nomogram that reliably predicts OS in PAAD. The findings may support new ideas for screening therapeutic targets to inhibit stem characteristics and the development of PAAD.

Network Intrusion Detection: An Analytical Assessment Using Deep Learning and State-of-the-Art Machine Learning Models

The internet connected devices are prone to cyber threats. Most of the companies are developing devices with built-in cyber threat protection mechanism or recommending prevention measure. But cyber threat is becoming harder to trace due to the availability of various tools and techniques to bypass the normal prevention measures. A data mining-based intrusion detection system can play a key role to handle such cyberattacks. This paper proposes a threefold approach to analyzing intrusion detection system. In the first phase, experiments have been conducted by applying SVM, Decision Tree, and KNN. In the second phase, Random Forest, and XGBoost are applied as lately they have been showing significant improved performance in supervised learning. Finally, deep learning techniques, namely, Feed Forward, LSTM, and Gated Recurrent Unit neural network are applied to conduct the experiment. Kyoto Honeypot Dataset is used for experimental purpose. The results show a significant improvement in IDS outperforming the state of the arts on this dataset. Such improvement strengthens the applicability proposed model in IDS.

A survival tree based on stabilized score tests for high-dimensional covariates

A survival tree can classify subjects into different survival prognostic groups. However, when data contains high-dimensional covariates, the two popular classification trees exhibit fatal drawbacks. The logrank tree is unstable and tends to have false nodes; the conditional inference tree is difficult to interpret the adjusted P-value for high-dimensional tests. Motivated by these problems, we propose a new survival tree based on the stabilized score tests. We propose a novel matrix-based algorithm in order to tests a number of nodes simultaneously via stabilized score tests. We propose a recursive partitioning algorithm to construct a survival tree and develop our original R package uni.survival.tree (https://cran.r-project.org/package=uni.survival.tree) for implementation. Simulations are performed to demonstrate the superiority of the proposed method over the existing methods. The lung cancer data analysis demonstrates the usefulness of the proposed method.

Comprehensive analysis of an immune-related ceRNA network in identifying a novel lncRNA signature as a prognostic biomarker for hepatocellular carcinoma

The function of competitive endogenous RNA (ceRNA) network in the immune regulation of hepatocellular carcinoma (HCC) is unclear. Our study aimed to construct an immune-related ceRNA network and develop an immune-related long noncoding RNA (lncRNA) signature to assess the prognosis of HCC patients and to optimize the treatment methods. We firstly constructed a ceRNA regulatory network for HCC using differentially expressed lncRNAs, mRNAs and microRNAs (miRNAs) from the Cancer Genome Atlas. A signature was constructed by 11 immune-related prognostic lncRNAs from the ceRNA network. The survival analysis and receiver operating characteristic analysis validated the reliability of the signature. Multivariate Cox regression analysis revealed that the signature could act an independent prognostic indicator. This signature also showed high association with immune cell infiltration and immune check blockades. LINC00491 was identified as the hub lncRNA in the signature. In vitro and in vivo evidence demonstrated that silencing of LINC00491 significantly inhibited HCC growth. Finally, 59 lncRNAs, 21 miRNAs, and 26 mRNAs were obtained to build the immune-related ceRNA network for HCC. In conclusion, our novel immune-related lncRNA prognostic signature and the immune-related ceRNA network might provide in-depth insights into tumor-immune interaction of HCC and promote better individual treatment strategies in HCC patients.

A Prospectively Validated Prognostic Model for Patients with Locally Advanced Squamous Cell Carcinoma of the Head and Neck Based on Radiomics of Computed Tomography Images

BACKGROUND

Locoregionally advanced head and neck squamous cell carcinoma (HNSCC) patients have high relapse and mortality rates. Imaging-based decision support may improve outcomes by optimising personalised treatment, and support patient risk stratification. We propose a multifactorial prognostic model including radiomics features to improve risk stratification for advanced HNSCC, compared to TNM eighth edition, the gold standard.

PATIENT AND METHODS

Data of 666 retrospective- and 143 prospective-stage III-IVA/B HNSCC patients were collected. A multivariable Cox proportional-hazards model was trained to predict overall survival (OS) using diagnostic CT-based radiomics features extracted from the primary tumour. Separate analyses were performed using TNM8, tumour volume, clinical and biological variables, and combinations thereof with radiomics features. Patient risk stratification in three groups was assessed through Kaplan-Meier (KM) curves. A log-rank test was performed for significance (p-value < 0.05). The prognostic accuracy was reported through the concordance index (CI).

RESULTS

A model combining an 11-feature radiomics signature, clinical and biological variables, TNM8, and volume could significantly stratify the validation cohort into three risk groups (p < 0∙01, CI of 0.79 as validation).

CONCLUSION

A combination of radiomics features with other predictors can predict OS very accurately for advanced HNSCC patients and improves on the current gold standard of TNM8.

Variable selection for censored data using Modified Correlation Adjusted coRrelation (MCAR) scores

Dealing with high-dimensional censored data is very challenging because of the complexities in data structure. This article focuses on developing a variable selection procedure for censored high-dimensional data with the AFT models using the Modified Correlation Adjusted coRrelation (MCAR) scores method. The latter is developed based on CAR scores method that provides a canonical ordering that encourages grouping of correlated predictors and down-weights antagonistic variables. The proposed MCAR scores method is developed as an extension of the CAR scores method using NOVEL integration of the sample and threshold estimator of the correlation matrix as suggested by Huang and Frylewicz. The proposed MCAR exhibits computationally more efficient estimates under model sparsity and can provide a canonical ordering among the predictors. The MCAR method is a greedy method that is also easy to understand and can perform estimation and variable selection simultaneously. Performances of variable selection by the MCAR method have been compared with other existing regularized techniques in literature-such as the lasso, elastic net and with a machine learning technique called boosting and with the censored CAR by a number of simulation studies and a real microarray data set called diffuse large-B-cell lymphoma. Results indicate that when correlation exists among the covariates, the MCAR method outperforms all five techniques while for uncorrelated data, the MCAR performs quite similar to the CAR method but clearly outperforms the other three methods. The empirical study further reveals that the MCAR method exhibits the best predictive performance among the methods.

Identification and Validation of a Potential Prognostic 7-lncRNA Signature for Predicting Survival in Patients with Multiple Myeloma

BACKGROUND

An increasing number of studies have indicated that the abnormal expression of certain long noncoding RNAs (lncRNAs) is linked to the overall survival (OS) of patients with myeloma.

METHODS

Gene expression data of myeloma patients were downloaded from the Gene Expression Omnibus (GEO) database (GSE4581 and GSE57317). Cox regression analysis, Kaplan-Meier, and receiver operating characteristic (ROC) analysis were performed to construct and validate the prediction model. Single sample gene set enrichment (ssGSEA) and Kyoto Encyclopedia of Genes and Genomes (KEGG) analysis were used to predict the function of a specified lncRNA.

RESULTS

In this study, a seven-lncRNA signature was identified and used to construct a risk score system for myeloma prognosis. This system was used to stratify patients with different survival rates in the training set into high-risk and low-risk groups. Test set, the entire test set, the external validation set, and the myeloma subtype achieved the authentication of the results. In addition, functional enrichment analysis indicated that 7 prognostic lncRNAs may be involved in the tumorigenesis of myeloma through cancer-related pathways and biological processes. The results of the immune score showed that IF_I was negatively correlated with the risk score. Compared with the published gene signature, the 7-lncRNA model has a higher C-index (above 0.8).

CONCLUSION

In summary, our data provide evidence that seven lncRNAs could be used as independent biomarkers to predict the prognosis of myeloma, which also indicated that these 7 lncRNAs may be involved in the progression of myeloma.

Establishment and validation of a prognostic nomogram based on a novel five-DNA methylation signature for survival in endometrial cancer patients

Background

This study aimed to explore the prognostic role of DNA methylation pattern in endometrial cancer (EC) patients.

Methods

Differentially methylated genes (DMGs) of EC patients with distinct survival from The Cancer Genome Atlas (TCGA) database were analyzed to identify methylated genes as biomarkers for EC prognosis. The Least Absolute Shrinkage and Selection Operator (LASSO) analysis was used to construct a risk score model. A nomogram was built based on analysis combining the risk score model with clinicopathological signatures together, and then verified in the validation cohort and patients in our own center.

Results

In total, 157 DMGs were identified between different prognostic groups. Based on the LASSO analysis, five genes (GBP4, OR8K3, GABRA2, RIPPLY2, and TRBV5‐7) were screened for the establishment of risk score model. The model outperformed in prognostic accuracy at varying follow‐up times (AUC for 3 years: 0.824, 5 years: 0.926, and 7 years: 0.853). Multivariate analysis identified four independent risk factors including menopausal status (HR = 3.006, 95%CI: 1.062–8.511, p = 0.038), recurrence (HR = 2.116, 95%CI: 1.061–4.379, p = 0.046), lymph node metastasis (LNM, HR = 3.465, 95%CI: 1.225–9.807, p = 0.019), and five‐DNA methylation risk model (HR = 3.654, 95%CI: 1.458–9.161, p = 0.006) in training cohort. The performance of the nomogram was good in the training (AUC = 0.828), validation (AUC = 0.866) and the whole cohorts (AUC = 0.843). Furthermore, we verified the nomogram with 24 patients in our center and the Kaplan–Meier survival curve also proved to be significantly different (p < 0.01). The subgroup analysis in different stratifications indicated that the accuracy was high in different subgroups for age, histological type, tumor grade, and clinical stage (all p < 0.01).

Conclusions

Briefly, our work established and verified a five‐DNA methylation risk model, and a nomogram merging the model with clinicopathological characteristics to facilitate individual prediction of EC patients for clinicians.

Wheat Kernel Variety Identification Based on a Large Near-Infrared Spectral Dataset and a Novel Deep Learning-Based Feature Selection Method

Near-infrared (NIR) hyperspectroscopy becomes an emerging nondestructive sensing technology for inspection of crop seeds. A large spectral dataset of more than 140,000 wheat kernels in 30 varieties was prepared for classification. Feature selection is a critical segment in large spectral data analysis. A novel convolutional neural network-based feature selector (CNN-FS) was proposed to screen out deeply target-related spectral channels. A convolutional neural network with attention (CNN-ATT) framework was designed for one-dimension data classification. Popular machine learning models including support vector machine (SVM) and partial least square discrimination analysis were used as the benchmark classifiers. Features selected by conventional feature selection algorithms were considered for comparison. Results showed that the designed CNN-ATT produced a higher performance than the compared classifier. The proposed CNN-FS found a subset of features, which made a better representation of raw dataset than conventional selectors did. The CNN-ATT achieved an accuracy of 93.01% using the full spectra and keep its high precision (90.20%) by training on the 60-channel features obtained via the CNN-FS method. The proposed methods have great potential for handling the analyzing tasks on other large spectral datasets. The proposed feature selection structure can be extended to design other new model-based selectors. The combination of NIR hyperspectroscopic technology and the proposed models has great potential for automatic nondestructive classification of single wheat kernels.

Weighted correlation gene network analysis reveals a new stemness index-related survival model for prognostic prediction in hepatocellular carcinoma

In this study, we constructed a new survival model using mRNA expression-based stemness index (mRNAsi) for prognostic prediction in hepatocellular carcinoma (HCC). Weighted correlation network analysis (WGCNA) of HCC transcriptome data (374 HCC and 50 normal liver tissue samples) from the TCGA database revealed 7498 differentially expressed genes (DEGs) that clustered into seven gene modules. LASSO regression analysis of the top two gene modules identified ANGPT2, EMCN, GLDN, USHBP1 and ZNF532 as the top five mRNAsi-related genes. We constructed our survival model with these five genes and tested its performance using 243 HCC and 202 normal liver samples from the ICGC database. Kaplan-Meier survival curve and receive operating characteristic curve analyses showed that the survival model accurately predicted the prognosis and survival of high- and low-risk HCC patients with high sensitivity and specificity. The expression of these five genes was significantly higher in the HCC tissues from the TCGA, ICGC, and GEO datasets (GSE25097 and GSE14520) than in normal liver tissues. These findings demonstrate that a new survival model derived from five strongly correlating mRNAsi-related genes provides highly accurate prognoses for HCC patients.

A practical perspective on the concordance index for the evaluation and selection of prognostic time-to-event models

Developing a prognostic model for biomedical applications typically requires mapping an individual's set of covariates to a measure of the risk that he or she may experience the event to be predicted. Many scenarios, however, especially those involving adverse pathological outcomes, are better described by explicitly accounting for the timing of these events, as well as their probability. As a result, in these cases, traditional classification or ranking metrics may be inadequate to inform model evaluation or selection. To address this limitation, it is common practice to reframe the problem in the context of survival analysis, and resort, instead, to the concordance index (C-index), which summarises how well a predicted risk score describes an observed sequence of events. A practically meaningful interpretation of the C-index, however, may present several difficulties and pitfalls. Specifically, we identify two main issues: i) the C-index remains implicitly, and subtly, dependent on time, and ii) its relationship with the number of subjects whose risk was incorrectly predicted is not straightforward. Failure to consider these two aspects may introduce undesirable and unwanted biases in the evaluation process, and even result in the selection of a suboptimal model. Hence, here, we discuss ways to obtain a meaningful interpretation in spite of these difficulties. Aiming to assist experimenters regardless of their familiarity with the C-index, we start from an introductory-level presentation of its most popular estimator, highlighting the latter's temporal dependency, and suggesting how it might be correctly used to inform model selection. We also address the nonlinearity of the C-index with respect to the number of correct risk predictions, elaborating a simplified framework that may enable an easier interpretation and quantification of C-index improvements or deteriorations.

A risk prediction model of DNA methylation improves prognosis evaluation and indicates gene targets in prostate cancer

Aim: Prostate cancer (PCa) is the most common malignancy found in males worldwide. Although it is mostly indolent, PCa still poses a serious threat to long-term health. Materials & methods: The Cancer Genome Atlas data were randomly divided into training and validation groups. Least absolute shrinkage and selection operator regression on DNA methylation data in the training group was conducted to build the model, which was validated in the validation group. Weighted correlation network analysis was conducted on RNA-seq data to identify the therapy target. Functional validation (western blot, quantitative real-time PCR, cell transfection, Cell Counting Kit-8 assay, colony formation assay, wound healing assay and transwell invasion assay) for the target was conducted. Results: The model is an independent predictor of prognosis. The knockdown of FOXD1 inhibits cell proliferation, migration and invasion of PCa. Conclusion: The risk of patients could be evaluated by the model, which revealed that FOXD1 might promote poor prognosis.

Comparison of the marginal hazard model and the sub-distribution hazard model for competing risks under an assumed copula

For the analysis of competing risks data, three different types of hazard functions have been considered in the literature, namely the cause-specific hazard, the sub-distribution hazard, and the marginal hazard function. Accordingly, medical researchers can fit three different types of the Cox model to estimate the effect of covariates on each of the hazard function. While the relationship between the cause-specific hazard and the sub-distribution hazard has been extensively studied, the relationship to the marginal hazard function has not yet been analyzed due to the difficulties related to non-identifiability. In this paper, we adopt an assumed copula model to deal with the model identifiability issue, making it possible to establish a relationship between the sub-distribution hazard and the marginal hazard function. We then compare the two methods of fitting the Cox model to competing risks data. We also extend our comparative analysis to clustered competing risks data that are frequently used in medical studies. To facilitate the numerical comparison, we implement the computing algorithm for marginal Cox regression with clustered competing risks data in the R joint.Cox package and check its performance via simulations. For illustration, we analyze two survival datasets from lung cancer and bladder cancer patients.