RSF1 and Not Cyclin D1 Gene Amplification May Predict Lack of Benefit from Adjuvant Tamoxifen in High-Risk Pre-Menopausal Women in the MA.12 Randomized Clinical Trial

Most women with estrogen receptor expressing breast cancers receiving anti-estrogens such as tamoxifen may not need or benefit from them. Besides the estrogen receptor, there are no predictive biomarkers to help select breast cancer patients for tamoxifen treatment. CCND1 (cyclin D1) gene amplification is a putative candidate tamoxifen predictive biomarker. The RSF1 (remodeling and spacing factor 1) gene is frequently co-amplified with CCND1 on chromosome 11q. We validated the predictive value of these biomarkers in the MA.12 randomized study of adjuvant tamoxifen vs. placebo in high-risk premenopausal early breast cancer. Premenopausal women with node-positive/high-risk node-negative early breast cancer received standard adjuvant chemotherapy and then were randomized to tamoxifen (20 mg/day) or placebo for 5 yrs. Overall survival (OS) and relapse-free survival (RFS) were evaluated. Fluorescent in-situ hybridization was performed on a tissue microarray of 495 breast tumors (74% of patients) to measure CCND1 and RSF1 copy number. A multivariate Cox model to obtain hazard ratios (HR) adjusting for clinico-pathologic factors was used to assess the effect of these biomarkers on Os and RFS. 672 women were followed for a median of 8.4 years. We were able to measure the DNA copy number of CCND1 in 442 patients and RSF1 in 413 patients. CCND1 gene amplification was observed in 8.7% and RSF1 in 6.8% of these patients, preferentially in estrogen receptor-positive breast cancers. No statistically significant interaction with treatment was observed for either CCND1 or RSF1 amplification, although patients with high RSF1 copy number did not show benefit from adjuvant tamoxifen (HR = 1.11, interaction p = 0.09). Unlike CCND1 amplification, RSF1 amplification may predict for outcome in high-risk premenopausal breast cancer patients treated with adjuvant tamoxifen.     

Combining gene signatures improves prediction of breast cancer survival

Background

Several gene sets for prediction of breast cancer survival have been derived from whole-genome mRNA expression profiles. Here, we develop a statistical framework to explore whether combination of the information from such sets may improve prediction of recurrence and breast cancer specific death in early-stage breast cancers. Microarray data from two clinically similar cohorts of breast cancer patients are used as training (n = 123) and test set (n = 81), respectively. Gene sets from eleven previously published gene signatures are included in the study.

Principal Findings

To investigate the relationship between breast cancer survival and gene expression on a particular gene set, a Cox proportional hazards model is applied using partial likelihood regression with an L2 penalty to avoid overfitting and using cross-validation to determine the penalty weight. The fitted models are applied to an independent test set to obtain a predicted risk for each individual and each gene set. Hierarchical clustering of the test individuals on the basis of the vector of predicted risks results in two clusters with distinct clinical characteristics in terms of the distribution of molecular subtypes, ER, PR status, TP53 mutation status and histological grade category, and associated with significantly different survival probabilities (recurrence: p = 0.005; breast cancer death: p = 0.014). Finally, principal components analysis of the gene signatures is used to derive combined predictors used to fit a new Cox model. This model classifies test individuals into two risk groups with distinct survival characteristics (recurrence: p = 0.003; breast cancer death: p = 0.001). The latter classifier outperforms all the individual gene signatures, as well as Cox models based on traditional clinical parameters and the Adjuvant! Online for survival prediction.

Conclusion

Combining the predictive strength of multiple gene signatures improves prediction of breast cancer survival. The presented methodology is broadly applicable to breast cancer risk assessment using any new identified gene set.     

A Novel Model to Combine Clinical and Pathway-Based Transcriptomic Information for the Prognosis Prediction of Breast Cancer

Breast cancer is the most common malignancy in women worldwide. With the increasing awareness of heterogeneity in breast cancers, better prediction of breast cancer prognosis is much needed for more personalized treatment and disease management. Towards this goal, we have developed a novel computational model for breast cancer prognosis by combining the Pathway Deregulation Score (PDS) based pathifier algorithm, Cox regression and L1-LASSO penalization method. We trained the model on a set of 236 patients with gene expression data and clinical information, and validated the performance on three diversified testing data sets of 606 patients. To evaluate the performance of the model, we conducted survival analysis of the dichotomized groups, and compared the areas under the curve based on the binary classification. The resulting prognosis genomic model is composed of fifteen pathways (e.g. P53 pathway) that had previously reported cancer relevance, and it successfully differentiated relapse in the training set (log rank p-value = 6.25e-12) and three testing data sets (log rank p-value<0.0005). Moreover, the pathway-based genomic models consistently performed better than gene-based models on all four data sets. We also find strong evidence that combining genomic information with clinical information improved the p-values of prognosis prediction by at least three orders of magnitude in comparison to using either genomic or clinical information alone. In summary, we propose a novel prognosis model that harnesses the pathway-based dysregulation as well as valuable clinical information. The selected pathways in our prognosis model are promising targets for therapeutic intervention.     

A Hybrid Deep Learning Model for Predicting Molecular Subtypes of Human Breast Cancer Using Multimodal Data

BackgroundThe prediction of breast cancer subtypes plays a key role in the diagnosis and prognosis of breast cancer. In recent years, deep learning (DL) has shown good performance in the intelligent prediction of breast cancer subtypes. However, most of the traditional DL models use single modality data, which can just extract a few features, so it cannot establish a stable relationship between patient characteristics and breast cancer subtypes.DatasetWe used the TCGA-BRCA dataset as a sample set for molecular subtype prediction of breast cancer. It is a public dataset that can be obtained through the following link: https://portal.gdc.cancer.gov/projects/TCGA-BRCAMethodsIn this paper, a Hybrid DL model based on the multimodal data is proposed. We combine the patient's gene modality data with image modality data to construct a multimodal fusion framework. According to the different forms and states, we set up feature extraction networks respectively, and then we fuse the output of the two feature networks based on the idea of weighted linear aggregation. Finally, the fused features are used to predict breast cancer subtypes. In particular, we use the principal component analysis to reduce the dimensionality of high-dimensional data of gene modality and filter the data of image modality. Besides, we also improve the traditional feature extraction network to make it show better performance.ResultsThe results show that compared with the traditional DL model, the Hybrid DL model proposed in this paper is more accurate and efficient in predicting breast cancer subtypes. Our model achieved a prediction accuracy of 88.07% in 10 times of 10-fold cross-validation. We did a separate AUC test for each subtype, and the average AUC value obtained was 0.9427. In terms of subtype prediction accuracy, our model is about 7.45% higher than the previous average.     

Group additive regression models for genomic data analysis

One important problem in genomic research is to identify genomic features such as gene expression data or DNA single nucleotide polymorphisms (SNPs) that are related to clinical phenotypes. Often these genomic data can be naturally divided into biologically meaningful groups such as genes belonging to the same pathways or SNPs within genes. In this paper, we propose group additive regression models and a group gradient descent boosting procedure for identifying groups of genomic features that are related to clinical phenotypes. Our simulation results show that by dividing the variables into appropriate groups, we can obtain better identification of the group features that are related to the phenotypes. In addition, the prediction mean square errors are also smaller than the component-wise boosting procedure. We demonstrate the application of the methods to pathway-based analysis of microarray gene expression data of breast cancer. Results from analysis of a breast cancer microarray gene expression data set indicate that the pathways of metalloendopeptidases (MMPs) and MMP inhibitors, as well as cell proliferation, cell growth, and maintenance are important to breast cancer-specific survival.     

Novel artificial intelligence machine learning approaches to precisely predict survival and site-specific recurrence in cervical cancer: A multi-institutional study

BackgroundMachine learning (ML) has been gradually integrated into oncologic research but seldom applied to predict cervical cancer (CC), and no model has been reported to predict survival and site-specific recurrence simultaneously. Thus, we aimed to develop ML models to predict survival and site-specific recurrence in CC and to guide individual surveillance.MethodsWe retrospectively collected data on CC patients from 2006 to 2017 in four hospitals. The survival or recurrence predictive value of the variables was analyzed using multivariate Cox, principal component, and K-means clustering analyses. The predictive performances of eight ML models were compared with logistic or Cox models. A novel web-based predictive calculator was developed based on the ML algorithms.ResultsThis study included 5112 women for analysis (268 deaths, 343 recurrences): (1) For site-specific recurrence, larger tumor size was associated with local recurrence, while positive lymph nodes were associated with distant recurrence. (2) The ML models exhibited better prognostic predictive performance than traditional models. (3) The ML models were superior to traditional models when multiple variables were used. (4) A novel predictive web-based calculator was developed and externally validated to predict survival and site-specific recurrence.ConclusionML models might be a better analytic approach in CC prognostic prediction than traditional models as they can predict survival and site-specific recurrence simultaneously, especially when using multiple variables. Moreover, our novel web-based calculator may provide clinicians with useful information and help them make individual postoperative follow-up plans and further treatment strategies.     

Toward the precision breast cancer survival prediction utilizing combined whole genome-wide expression and somatic mutation analysis

Background

Breast cancer is the most common type of invasive cancer in woman. It accounts for approximately 18% of all cancer deaths worldwide. It is well known that somatic mutation plays an essential role in cancer development. Hence, we propose that a prognostic prediction model that integrates somatic mutations with gene expression can improve survival prediction for cancer patients and also be able to reveal the genetic mutations associated with survival.

Method

Differential expression analysis was used to identify breast cancer related genes. Genetic algorithm (GA) and univariate Cox regression analysis were applied to filter out survival related genes. DAVID was used for enrichment analysis on somatic mutated gene set. The performance of survival predictors were assessed by Cox regression model and concordance index(C-index).

Results

We investigated the genome-wide gene expression profile and somatic mutations of 1091 breast invasive carcinoma cases from The Cancer Genome Atlas (TCGA). We identified 118 genes with high hazard ratios as breast cancer survival risk gene candidates (log rank p?<? 0.0001 and c-index?=?0.636). Multiple breast cancer survival related genes were found in this gene set, including FOXR2, FOXD1, MTNR1B and SDC1. Further genetic algorithm (GA) revealed an optimal gene set consisted of 88 genes with higher c-index (log rank p?<? 0.0001 and c-index?=?0.656). We validated this gene set on an independent breast cancer data set and achieved a similar performance (log rank p?<? 0.0001 and c-index?=?0.614). Moreover, we revealed 25 functional annotations, 15 gene ontology terms and 14 pathways that were significantly enriched in the genes that showed distinct mutation patterns in the different survival risk groups. These functional gene sets were used as new features for the survival prediction model. In particular, our results suggested that the Fanconi anemia pathway had an important role in breast cancer prognosis.

Conclusions

Our study indicated that the expression levels of the gene signatures remain the effective indicators for breast cancer survival prediction. Combining the gene expression information with other types of features derived from somatic mutations can further improve the performance of survival prediction. The pathways that were associated with survival risk suggested by our study can be further investigated for improving cancer patient survival.

     

Identification of DNA methylation changes associated with human gastric cancer

Background

Multiple breast cancer gene expression profiles have been developed that appear to provide similar abilities to predict outcome and may outperform clinical-pathologic criteria; however, the extent to which seemingly disparate profiles provide additive prognostic information is not known, nor do we know whether prognostic profiles perform equally across clinically defined breast cancer subtypes. We evaluated whether combining the prognostic powers of standard breast cancer clinical variables with a large set of gene expression signatures could improve on our ability to predict patient outcomes.

Methods

Using clinical-pathological variables and a collection of 323 gene expression "modules", including 115 previously published signatures, we build multivariate Cox proportional hazards models using a dataset of 550 node-negative systemically untreated breast cancer patients. Models predictive of pathological complete response (pCR) to neoadjuvant chemotherapy were also built using this approach.

Results

We identified statistically significant prognostic models for relapse-free survival (RFS) at 7 years for the entire population, and for the subgroups of patients with ER-positive, or Luminal tumors. Furthermore, we found that combined models that included both clinical and genomic parameters improved prognostication compared with models with either clinical or genomic variables alone. Finally, we were able to build statistically significant combined models for pathological complete response (pCR) predictions for the entire population.

Conclusions

Integration of gene expression signatures and clinical-pathological factors is an improved method over either variable type alone. Highly prognostic models could be created when using all patients, and for the subset of patients with lymph node-negative and ER-positive breast cancers. Other variables beyond gene expression and clinical-pathological variables, like gene mutation status or DNA copy number changes, will be needed to build robust prognostic models for ER-negative breast cancer patients. This combined clinical and genomics model approach can also be used to build predictors of therapy responsiveness, and could ultimately be applied to other tumor types.     

Individual risk prediction: Comparing random forests with Cox proportional-hazards model by a simulation study

With big data becoming widely available in healthcare, machine learning algorithms such as random forest (RF) that ignores time-to-event information and random survival forest (RSF) that handles right-censored data are used for individual risk prediction alternatively to the Cox proportional hazards (Cox-PH) model. We aimed to systematically compare RF and RSF with Cox-PH. RSF with three split criteria [log-rank (RSF-LR), log-rank score (RSF-LRS), maximally selected rank statistics (RSF-MSR)]; RF, Cox-PH, and Cox-PH with splines (Cox-S) were evaluated through a simulation study based on real data. One hundred eighty scenarios were investigated assuming different associations between the predictors and the outcome (linear/linear and interactions/nonlinear/nonlinear and interactions), training sample sizes (500/1000/5000), censoring rates (50%/75%/93%), hazard functions (increasing/decreasing/constant), and number of predictors (seven, 15 including noise variables). Methods' performance was evaluated with time-dependent area under curve and integrated Brier score. In all scenarios, RF had the worst performance. In scenarios with a low number of events (⩽70), Cox-PH was at least noninferior to RSF, whereas under linearity assumption it outperformed RSF. Under the presence of interactions, RSF performed better than Cox-PH as the number of events increased whereas Cox-S reached at least similar performance with RSF under nonlinear effects. RSF-LRS performed slightly worse than RSF-LR and RSF-MSR when including noise variables and interaction effects. When applied to real data, models incorporating survival time performed better. Although RSF algorithms are a promising alternative to conventional Cox-PH as data complexity increases, they require a higher number of events for training. In time-to-event analysis, algorithms that consider survival time should be used.     

More evidence for prediction model of radiosensitivity

With the development of precision medicine, searching for potential biomarkers plays a major role in personalized medicine. Therefore, how to predict radiosensitivity to improve radiotherapy is a burning question. The definition of radiosensitivity is complex. Radiosensitive gene/biomarker can be useful for predicting which patients would benefit from radiotherapy. The discovery of radiosensitivity biomarkers require multiple pieces of evidence. A prediction model of breast cancer radiosensitivity based on six genes was established. We had put forward some supplements on the basis of the present study. We found that there were no differences between high- and low-risk scores in the non-radiotherapy group. Patients who received radiotherapy had a significantly better overall survival than non-radiotherapy patients in the predicted low-risk score patients. Furthermore, there was no difference between radiotherapy group and non-radiotherapy group in the high-risk score group. Those results firmly supported the prediction model of radiosensitivity. In addition, building a radiosensitivity prediction model was systematically discussed. Genes of model could be screened by different methods, such as Cox regression analysis, Lasso Cox regression method, random forest algorithm and other methods. In the future, precision radiotherapy might depend on the combination of multi-omics data and high dimensional image data.     

Identification of a novel glycolysis-related gene signature that can predict the survival of patients with lung adenocarcinoma

Lung cancer is one of the most malignant cancers worldwide, and lung adenocarcinoma (LUAD) is the most common histologic subtype. Thousands of biomarkers related to the survival and prognosis of patients with this cancer type have been investigated through database mining; however, the prediction effect of a single gene biomarker is not satisfactorily specific or sensitive. Thus, the present study aimed to develop a novel gene signature of prognostic values for patients with LUAD. Using a data-mining method, we performed expression profiling of 1145 mRNAs in large cohorts with LUAD (n = 511) from The Cancer Genome Atlas database. Using the Gene Set Enrichment Analysis, we selected 198 genes related to GLYCOLYSIS, which is the most important enrichment gene set. Moreover, these genes were identified using Cox proportional regression modeling. We established a risk score staging system to predict the outcome of patients with LUAD and subsequently identified four genes (AGRN, AKR1A1, DDIT4, and HMMR) that were closely related to the prognosis of patients with LUAD. The identified genes allowed us to classify patients into the high-risk group (with poor outcome) and low-risk group (with better outcome). Compared with other clinical factors, the risk score has a better performance in predicting the outcome of patients with LUAD, particularly in the early stage of LUAD. In conclusion, we developed a four-gene signature related to glycolysis by utilizing the Cox regression model and a risk staging model for LUAD, which might prove valuable for the clinical management of patients with LUAD.     

Penalized Cox regression analysis in the high-dimensional and low-sample size settings, with applications to microarray gene expression data

MOTIVATION: An important application of microarray technology is to relate gene expression profiles to various clinical phenotypes of patients. Success has been demonstrated in molecular classification of cancer in which the gene expression data serve as predictors and different types of cancer serve as a categorical outcome variable. However, there has been less research in linking gene expression profiles to the censored survival data such as patients' overall survival time or time to cancer relapse. It would be desirable to have models with good prediction accuracy and parsimony property. RESULTS: We propose to use the L(1) penalized estimation for the Cox model to select genes that are relevant to patients' survival and to build a predictive model for future prediction. The computational difficulty associated with the estimation in the high-dimensional and low-sample size settings can be efficiently solved by using the recently developed least-angle regression (LARS) method. Our simulation studies and application to real datasets on predicting survival after chemotherapy for patients with diffuse large B-cell lymphoma demonstrate that the proposed procedure, which we call the LARS-Cox procedure, can be used for identifying important genes that are related to time to death due to cancer and for building a parsimonious model for predicting the survival of future patients. The LARS-Cox regression gives better predictive performance than the L(2) penalized regression and a few other dimension-reduction based methods. CONCLUSIONS: We conclude that the proposed LARS-Cox procedure can be very useful in identifying genes relevant to survival phenotypes and in building a parsimonious predictive model that can be used for classifying future patients into clinically relevant high- and low-risk groups based on the gene expression profile and survival times of previous patients.     

A prognostic 11 long noncoding RNA expression signature for breast invasive carcinoma

Breast cancer, the most common cancer in women worldwide, is associated with high mortality. The long non-coding RNAs (lncRNAs) with a little capacity of coding proteins is playing an increasingly important role in the cancer paradigm. Accumulating evidences demonstrate that lncRNAs have crucial connections with breast cancer prognosis while the studies of lncRNAs in breast cancer are still in its primary stage. In this study, we collected 1052 clinical patient samples, a comparatively large sample size, including 13 159 lncRNA expression profiles of breast invasive carcinoma (BRCA) from The Cancer Genome Atlas database to identify prognosis-related lncRNAs. We randomly separated all of these clinical patient samples into training and testing sets. In the training set, we performed univariable Cox regression analysis for primary screening and played the model for Robust likelihood-based survival for 1000 times. Then 11 lncRNAs with a frequency more than 600 were selected for prediction of the prognosis of BRCA. Using the analysis of multivariate Cox regression, we established a signature risk-score formula for 11 lncRNA to identify the relationship between lncRNA signatures and overall survival. The 11 lncRNA signature was validated both in the testing and the complete set and could effectively classify the high-/low-risk group with different OS. We also verified our results in different stages. Moreover, we analyzed the connection between the 11 lncRNAs and the genes of ESR1, PGR, and Her2, of which protein products (ESR, PGR, and HER2) were used to classify the breast cancer subtypes widely. The results indicated correlations between 11 lncRNAs and the gene of PGR and ESR1. Thus, a prognostic model for 11 lncRNA expression was developed to classify the BRAC clinical patient samples, providing new avenues in understanding the potential therapeutic methods of breast cancer.     

A novel microRNA-based signature predicts prognosis among nasopharyngeal cancer patients

Nasopharyngeal cancer is one of the most common malignant tumors in the head and neck. Identification of promising miRNA biomarkers might benefit a lot to the detection of nasopharyngeal carcinoma. miRNA expression profile and clinical information were obtained from two microarray profiling data sets from the Gene Expression Omnibus (GEO) database. miRNA signature model was constructed via univariate Cox survival analysis, multivariate Cox survival analysis, and least absolute shrinkage and selection operator Cox regression analysis. Kaplan–Meier curve, area under the curve (AUC), decision curve analysis, Box plot, and nomogram were used to evaluate the prognosis of the model to patients. 67 up-regulated and 93 down-regulated miRNAs were identified from GEO microarray data sets (P < 0.05). A three-miRNA signature (has-miR-142-3p, has-miR-29c, and has-miR-30e) was obviously associated with the overall survival of nasopharyngeal carcinoma patients (P  < 0.001). The AUCs for the signature were 0.74, 0.7 for the training set and external validation set. The AUC of disease free survival and distant metastasis-free survival were also high. The model has better clinical independence and has better clinical prediction effect when combined with clinical characteristics (P < 0.0001). Compared with the published models, our model had a higher AUC. Our results revealed that a three-miRNA signature was a potential novel prognostic biomarker for nasopharyngeal carcinoma.Impact statementNasopharyngeal cancer is one of the most common malignant tumors in the head and neck. Identification of promising miRNA biomarkers might benefit a lot to the detection of nasopharyngeal carcinoma. A three-miRNA signature (has-miR-142-3p, has-miR-29c, and has-miR-30e) was obviously associated with the overall survival of nasopharyngeal carcinoma patients. The model has better clinical independence and has better clinical prediction effect when combined with clinical characteristics. Our results revealed that a three-miRNA signature was a potential novel prognostic biomarker for nasopharyngeal carcinoma.     

A high-quality model for predicting the prognosis of breast neuroendocrine carcinoma to help clinicians decide on appropriate treatment methods: A population-based analysis

BackgroundBreast neuroendocrine carcinoma (NEC) is a rare malignancy with unclear treatment options and prognoses. This study aimed to construct a high-quality model to predict overall survival (OS) and breast cancer-specific survival (BCSS) and help clinicians choose appropriate breast NEC treatments.Patients and methodsA total of 378 patients with breast NEC and 349,736 patients with breast invasive ductal carcinoma (IDC) were enrolled in the Surveillance, Epidemiology, and End Results (SEER) database between 2010 and 2018. Propensity score matching (PSM) was performed to balance the clinical baseline. Prognostic factors determined by multivariate Cox analysis were included in the nomogram. C-index and calibration curves were used to verify the performance of the nomogram.ResultsNomograms were constructed for the breast NEC and breast IDC groups after PSM. The C–index of the nomograms ranged from 0.834 to 0.880 in the internal validation and 0.818–0.876 in the external validation, indicating that the nomogram had good discrimination. The risk stratification system showed that patients with breast NEC had worse prognoses than those with breast IDC in the low-risk and intermediate-risk groups but had a similar prognosis that those in the high-risk group. Moreover, patients with breast NEC may have a better prognosis when undergoing surgery plus chemotherapy than when undergoing surgery alone or chemotherapy alone.ConclusionsWe established nomograms with a risk stratification system to predict OS and BCSS in patients with breast NEC. This model could help clinicians evaluate prognosis and provide individualized treatment recommendations for patients with breast NEC.     

Associations between gene expressions in breast cancer and patient survival

We analyzed associations between gene expression in breast cancer and patient survival for 8024 genes from a previously published microarray data set. Analysis of survival, by using the logrank test, was performed automatically for each gene. After correcting for multiple testing, we identified 95 genes whose expression was significantly associated with patient survival. The independent prognostic value of the genes ranking the highest in univariate analysis, together with clinical parameters, was assessed by Cox multivariate regression analysis. The P-values from these logrank tests were also mapped to chromosomal positions and compared with previously reported amplicon regions. We used PubGene web tools to identify groups of genes that had co-occurred in the literature and whose expression patterns were associated with survival. Our analyses demonstrate the comprehensiveness of the microarray technology with respect to measuring gene expression and indicate that the technology may be used to screen for potential clinical markers.     

Identification of prognostic genes for recurrent risk prediction in triple negative breast cancer patients in Taiwan

Discrepancies in the prognosis of triple negative breast cancer exist between Caucasian and Asian populations. Yet, the gene signature of triple negative breast cancer specifically for Asians has not become available. Therefore, the purpose of this study is to construct a prediction model for recurrence of triple negative breast cancer in Taiwanese patients. Whole genome expression profiling of breast cancers from 185 patients in Taiwan from 1995 to 2008 was performed, and the results were compared to the previously published literature to detect differences between Asian and Western patients. Pathway analysis and Cox proportional hazard models were applied to construct a prediction model for the recurrence of triple negative breast cancer. Hierarchical cluster analysis showed that triple negative breast cancers from different races were in separate sub-clusters but grouped in a bigger cluster. Two pathways, cAMP-mediated signaling and ephrin receptor signaling, were significantly associated with the recurrence of triple negative breast cancer. After using stepwise model selection from the combination of the initial filtered genes, we developed a prediction model based on the genes SLC22A23, PRKAG3, DPEP3, MORC2, GRB7, and FAM43A. The model had 91.7% accuracy, 81.8% sensitivity, and 94.6% specificity under leave-one-out support vector regression. In this study, we identified pathways related to triple negative breast cancer and developed a model to predict its recurrence. These results could be used for assisting with clinical prognosis and warrant further investigation into the possibility of targeted therapy of triple negative breast cancer in Taiwanese patients.     

CASPAR: a hierarchical bayesian approach to predict survival times in cancer from gene expression data

MOTIVATION: DNA microarrays allow the simultaneous measurement of thousands of gene expression levels in any given patient sample. Gene expression data have been shown to correlate with survival in several cancers, however, analysis of the data is difficult, since typically at most a few hundred patients are available, resulting in severely underdetermined regression or classification models. Several approaches exist to classify patients in different risk classes, however, relatively little has been done with respect to the prediction of actual survival times. We introduce CASPAR, a novel method to predict true survival times for the individual patient based on microarray measurements. CASPAR is based on a multivariate Cox regression model that is embedded in a Bayesian framework. A hierarchical prior distribution on the regression parameters is specifically designed to deal with high dimensionality (large number of genes) and low sample size settings, that are typical for microarray measurements. This enables CASPAR to automatically select small, most informative subsets of genes for prediction. RESULTS: Validity of the method is demonstrated on two publicly available datasets on diffuse large B-cell lymphoma (DLBCL) and on adenocarcinoma of the lung. The method successfully identifies long and short survivors, with high sensitivity and specificity. We compare our method with two alternative methods from the literature, demonstrating superior results of our approach. In addition, we show that CASPAR can further refine predictions made using clinical scoring systems such as the International Prognostic Index (IPI) for DLBCL and clinical staging for lung cancer, thus providing an additional tool for the clinician. An analysis of the genes identified confirms previously published results, and furthermore, new candidate genes correlated with survival are identified.