Detecting prognostic biomarkers of breast cancer by regularized Cox proportional hazards models

A transformer model for cause-specific hazard prediction

BACKGROUD

Modelling discrete-time cause-specific hazards in the presence of competing events and non-proportional hazards is a challenging task in many domains. Survival analysis in longitudinal cohorts often requires such models; notably when the data is gathered at discrete points in time and the predicted events display complex dynamics. Current models often rely on strong assumptions of proportional hazards, that is rarely verified in practice; or do not handle sequential data in a meaningful way. This study proposes a Transformer architecture for the prediction of cause-specific hazards in discrete-time competing risks. Contrary to Multilayer perceptrons that were already used for this task (DeepHit), the Transformer architecture is especially suited for handling complex relationships in sequential data, having displayed state-of-the-art performance in numerous tasks with few underlying assumptions on the task at hand.

RESULTS

Using synthetic datasets of 2000-50,000 patients, we showed that our Transformer model surpassed the CoxPH, PyDTS, and DeepHit models for the prediction of cause-specific hazard, especially when the proportional assumption did not hold. The error along simulated time outlined the ability of our model to anticipate the evolution of cause-specific hazards at later time steps where few events are observed. It was also superior to current models for prediction of dementia and other psychiatric conditions in the English longitudinal study of ageing cohort using the integrated brier score and the time-dependent concordance index. We also displayed the explainability of our model's prediction using the integrated gradients method.

CONCLUSIONS

Our model provided state-of-the-art prediction of cause-specific hazards, without adopting prior parametric assumptions on the hazard rates. It outperformed other models in non-proportional hazards settings for both the synthetic dataset and the longitudinal cohort study. We also observed that basic models such as CoxPH were more suited to extremely simple settings than deep learning models. Our model is therefore especially suited for survival analysis on longitudinal cohorts with complex dynamics of the covariate-to-outcome relationship, which are common in clinical practice. The integrated gradients provided the importance scores of input variables, which indicated variables guiding the model in its prediction. This model is ready to be utilized for time-to-event prediction in longitudinal cohorts.

Assessment of the albumin-bilirubin score in breast cancer patients with liver metastasis after surgery

Objective

This study aims to investigate the potential prognostic value of albumin-bilirubin (ALBI) score in breast cancer patients with liver metastasis after surgery.

Methods

This was a retrospective study of 178 breast cancer patients with liver metastasis after surgery. ALBI score was calculated by the following formula: (log10 bilirubin × 0.66) - (albumin × 0.085). The optimal cutoff value of ALBI score was assessed by X-tile. The clinical influence of ALBI score on survival outcomes using Kaplan-Meier method, Log-rank test, Cox proportional hazards regression model. The calibration curves, decision curve analysis and time-dependent ROC curve were used to assess the predictive performance of the nomogram's models.

Results

The classifications of 178 breast cancer patients with liver metastasis after surgery were as follows: low ALBI score group (＜-3.36) vs. high ALBI score group (≥-3.36). The Cox proportional hazards regression model indicated that ALBI score was a potential predictor. Kaplan-Meier survival curve performed that the median disease free survival (p = 0.0029) and overall survival (p＜0.0001) in low ALBI score group were longer than in high ALBI score group. The ALBI-based nomograms had good predictive performance.

Conclusions

The ALBI score has high prognostic ability for survival time in breast cancer with liver metastasis after surgery. These models will be valuable in discriminating patients at high risks of liver metastasis.

Advances in Electrochemical Biosensor Technologies for the Detection of Nucleic Acid Breast Cancer Biomarkers

Breast cancer is the second leading cause of cancer deaths in women worldwide; therefore, there is an increased need for the discovery, development, optimization, and quantification of diagnostic biomarkers that can improve the disease diagnosis, prognosis, and therapeutic outcome. Circulating cell-free nucleic acids biomarkers such as microRNAs (miRNAs) and breast cancer susceptibility gene 1 (BRCA1) allow the characterization of the genetic features and screening breast cancer patients. Electrochemical biosensors offer excellent platforms for the detection of breast cancer biomarkers due to their high sensitivity and selectivity, low cost, use of small analyte volumes, and easy miniaturization. In this context, this article provides an exhaustive review concerning the electrochemical methods of characterization and quantification of different miRNAs and BRCA1 breast cancer biomarkers using electrochemical DNA biosensors based on the detection of hybridization events between a DNA or peptide nucleic acid probe and the target nucleic acid sequence. The fabrication approaches, the biosensors architectures, the signal amplification strategies, the detection techniques, and the key performance parameters, such as the linearity range and the limit of detection, were discussed.

Identification of an endoplasmic reticulum stress-related gene signature to predict prognosis and potential drugs of uterine corpus endometrial cancer

Uterine corpus endometrial cancer (UCEC) is the sixth most common female cancer worldwide, with an increasing incidence. Improving the prognosis of patients living with UCEC is a top priority. Endoplasmic reticulum (ER) stress has been reported to be involved in tumor malignant behaviors and therapy resistance, but its prognostic value in UCEC has been rarely investigated. The present study aimed to construct an ER stress-related gene signature for risk stratification and prognosis prediction in UCEC. The clinical and RNA sequencing data of 523 UCEC patients were extracted from TCGA database and were randomly assigned into a test group (n = 260) and training group (n = 263). An ER stress-related gene signature was established by LASSO and multivariate Cox regression in the training group and validated by Kaplan-Meier survival analysis, Receiver Operating Characteristic (ROC) curves and nomograms in the test group. Tumor immune microenvironment was analyzed by CIBERSORT algorithm and single-sample gene set enrichment analysis. R packages and the Connectivity Map database were used to screen the sensitive drugs. Four ERGs (ATP2C2, CIRBP, CRELD2 and DRD2) were selected to build the risk model. The high-risk group had significantly reduced overall survival (OS) (P < 0.05). The risk model had better prognostic accuracy than clinical factors. Tumor-infiltrating immune cells analysis depicted that CD8+ T cells and regulatory T cells were more abundant in the low-risk group, which may be related to better OS, while activated dendritic cells were active in the high-risk group and associated with unfavorable OS. Several kinds of drugs sensitive to the high-risk group were screened out. The present study constructed an ER stress-related gene signature, which has the potential to predict the prognosis of UCEC patients and have implications for UCEC treatment.

Identification and Validation of Two Heterogeneous Molecular Subtypes and a Prognosis Predictive Model for Hepatocellular Carcinoma Based on Pyroptosis

Hepatocellular carcinoma (HCC) is a worldwide malignant cancer with high incidence and mortality. Considering the high heterogeneity of HCC, clarifying molecular characteristics associated with HCC development could help improve patients' outcomes. Pyroptosis is a novel form of cell death and is noted to be implicated in HCC pathogenesis whereas its molecular feature in HCC is unclear. Thus, we intended to clarify the molecular characteristic as well as the clinical significance of pyroptosis for HCC. A systematic bioinformatics analysis was conducted among 40 pyroptosis-related genes based on The Cancer Genome Atlas, the International Cancer Genome Consortium, and the Gene Expression Omnibus databases. A total of 12 HCC-associated pyroptosis-related genes (HPRGs) were identified to be overexpressed in HCC tissues and significantly connected to patients' poor survival. Through consensus clustering based on the HPRGs' expression, we found patients could be stratified into two distinctive pyroptosis subtypes, PyLow and PyHigh. The PyHigh group owned a notable lower survival rate and a higher high-grade proportion compared with the PyLow subtype. Besides, patients' sensitivities to chemotherapeutic drugs also presented distinctive differences between the two subtypes. Indicated by pathway enrichment analysis and immune characteristic difference analysis, the distinctions between the pyroptosis subtypes may be related to tumor immunity. Further, a five-gene risk model composed of BAK1, CHMP4A, CHMP4B, DHX9, and GSDME was established. Subsequent analyses demonstrated that the model could credibly classify patients as low or high risk and was an independent prognostic indicator for HCC. Abnormal expressions of the five genes were validated by biological experiments and new bioinformatics analysis. In conclusion, this study recognized and verified two heterogeneous pyroptosis subtypes and a predictable prognosis model for HCC. Our work may help facilitate the clinical management and treatment of HCC and understand the functions of pyroptosis in oncology.

Kidney Cancer Biomarker Selection Using Regularized Survival Models

Clear cell renal cell carcinoma (ccRCC) is the most common subtype of RCC showing a significant percentage of mortality. One of the priorities of kidney cancer research is to identify RCC-specific biomarkers for early detection and screening of the disease. With the development of high-throughput technology, it is now possible to measure the expression levels of thousands of genes in parallel and assess the molecular profile of individual tumors. Studying the relationship between gene expression and survival outcome has been widely used to find genes associated with cancer survival, providing new information for clinical decision-making. One of the challenges of using transcriptomics data is their high dimensionality which can lead to instability in the selection of gene signatures. Here we identify potential prognostic biomarkers correlated to the survival outcome of ccRCC patients using two network-based regularizers (EN and TCox) applied to Cox models. Some genes always selected by each method were found (COPS7B, DONSON, GTF2E2, HAUS8, PRH2, and ZNF18) with known roles in cancer formation and progression. Afterward, different lists of genes ranked based on distinct metrics (logFC of DEGs or β coefficients of regression) were analyzed using GSEA to try to find over- or under-represented mechanisms and pathways. Some ontologies were found in common between the gene sets tested, such as nuclear division, microtubule and tubulin binding, and plasma membrane and chromosome regions. Additionally, genes that were more involved in these ontologies and genes selected by the regularizers were used to create a new gene set where we applied the Cox regression model. With this smaller gene set, we were able to significantly split patients into high/low risk groups showing the importance of studying these genes as potential prognostic factors to help clinicians better identify and monitor patients with ccRCC.