Robust prediction of gene regulation in colorectal cancer tissues from DNA methylation profiles

DNA methylation is recognized as one of several epigenetic regulators of gene expression and as potential driver of carcinogenesis through gene-silencing of tumor suppressors and activation of oncogenes. However, abnormal methylation, even of promoter regions, does not necessarily alter gene expression levels, especially if the gene is already silenced, leaving the exact mechanisms of methylation unanswered. Using a large cohort of matching DNA methylation and gene expression samples of colorectal cancer (CRC; n = 77) and normal adjacent mucosa tissues (n = 108), we investigated the regulatory role of methylation on gene expression. We show that on a subset of genes enriched in common cancer pathways, methylation is significantly associated with gene regulation through gene-specific mechanisms. We built two classification models to infer gene regulation in CRC from methylation differences of tumor and normal tissues, taking into account both gene-silencing and gene-activation effects through hyper- and hypo-methylation of CpGs. The classification models result in high prediction performances in both training and independent CRC testing cohorts (0.92<AUC<0.97) as well as in individual patient data (average AUC = 0.82), suggesting a robust interplay between methylation and gene regulation. Validation analysis in other cancerous tissues resulted in lower prediction performances (0.69<AUC<0.90); however, it identified genes that share robust dependencies across cancerous tissues. In conclusion, we present a robust classification approach that predicts the gene-specific regulation through DNA methylation in CRC tissues with possible transition to different cancer entities. Furthermore, we present HMGA1 as consistently associated with methylation across cancers, suggesting a potential candidate for DNA methylation targeting cancer therapy.     

Breast cancer: integrating the patient with her genome

Increasingly, gene expression data are becoming the currency of the realm in assessing disease prognosis. This has been especially evident in cancer, particularly those malignancies for which tumor samples are fairly accessible and understanding prognostic factors has clear implications for treatment decisions. Recently, Pittman et al. demonstrated substantially increased accuracy of personalized disease outcome prediction in breast cancer by integrating gene-expression profile data with traditional clinical risk factors in a set of 158 breast cancer patients.     

pRRophetic: An R Package for Prediction of Clinical Chemotherapeutic Response from Tumor Gene Expression Levels

We recently described a methodology that reliably predicted chemotherapeutic response in multiple independent clinical trials. The method worked by building statistical models from gene expression and drug sensitivity data in a very large panel of cancer cell lines, then applying these models to gene expression data from primary tumor biopsies. Here, to facilitate the development and adoption of this methodology we have created an R package called pRRophetic. This also extends the previously described pipeline, allowing prediction of clinical drug response for many cancer drugs in a user-friendly R environment. We have developed several other important use cases; as an example, we have shown that prediction of bortezomib sensitivity in multiple myeloma may be improved by training models on a large set of neoplastic hematological cell lines. We have also shown that the package facilitates model development and prediction using several different classes of data.     

Integration of clinical and gene expression data has a synergetic effect on predicting breast cancer outcome

Breast cancer outcome can be predicted using models derived from gene expression data or clinical data. Only a few studies have created a single prediction model using both gene expression and clinical data. These studies often remain inconclusive regarding an obtained improvement in prediction performance. We rigorously compare three different integration strategies (early, intermediate, and late integration) as well as classifiers employing no integration (only one data type) using five classifiers of varying complexity. We perform our analysis on a set of 295 breast cancer samples, for which gene expression data and an extensive set of clinical parameters are available as well as four breast cancer datasets containing 521 samples that we used as independent validation.mOn the 295 samples, a nearest mean classifier employing a logical OR operation (late integration) on clinical and expression classifiers significantly outperforms all other classifiers. Moreover, regardless of the integration strategy, the nearest mean classifier achieves the best performance. All five classifiers achieve their best performance when integrating clinical and expression data. Repeating the experiments using the 521 samples from the four independent validation datasets also indicated a significant performance improvement when integrating clinical and gene expression data. Whether integration also improves performances on other datasets (e.g. other tumor types) has not been investigated, but seems worthwhile pursuing. Our work suggests that future models for predicting breast cancer outcome should exploit both data types by employing a late OR or intermediate integration strategy based on nearest mean classifiers.     

Differential gene expression detection and sample classification using penalized linear regression models

Differential gene expression detection and sample classification using microarray data have received much research interest recently. Owing to the large number of genes p and small number of samples n (p > n), microarray data analysis poses big challenges for statistical analysis. An obvious problem owing to the 'large p small n' is over-fitting. Just by chance, we are likely to find some non-differentially expressed genes that can classify the samples very well. The idea of shrinkage is to regularize the model parameters to reduce the effects of noise and produce reliable inferences. Shrinkage has been successfully applied in the microarray data analysis. The SAM statistics proposed by Tusher et al. and the 'nearest shrunken centroid' proposed by Tibshirani et al. are ad hoc shrinkage methods. Both methods are simple, intuitive and prove to be useful in empirical studies. Recently Wu proposed the penalized t/F-statistics with shrinkage by formally using the (1) penalized linear regression models for two-class microarray data, showing good performance. In this paper we systematically discussed the use of penalized regression models for analyzing microarray data. We generalize the two-class penalized t/F-statistics proposed by Wu to multi-class microarray data. We formally derive the ad hoc shrunken centroid used by Tibshirani et al. using the (1) penalized regression models. And we show that the penalized linear regression models provide a rigorous and unified statistical framework for sample classification and differential gene expression detection.     

Classification of multiple cancer types by multicategory support vector machines using gene expression data

MOTIVATION: High-density DNA microarray measures the activities of several thousand genes simultaneously and the gene expression profiles have been used for the cancer classification recently. This new approach promises to give better therapeutic measurements to cancer patients by diagnosing cancer types with improved accuracy. The Support Vector Machine (SVM) is one of the classification methods successfully applied to the cancer diagnosis problems. However, its optimal extension to more than two classes was not obvious, which might impose limitations in its application to multiple tumor types. We briefly introduce the Multicategory SVM, which is a recently proposed extension of the binary SVM, and apply it to multiclass cancer diagnosis problems. RESULTS: Its applicability is demonstrated on the leukemia data (Golub et al., 1999) and the small round blue cell tumors of childhood data (Khan et al., 2001). Comparable classification accuracy shown in the applications and its flexibility render the MSVM a viable alternative to other classification methods. SUPPLEMENTARY INFORMATION: http://www.stat.ohio-state.edu/~yklee/msvm.htm     

Linear regression and two-class classification with gene expression data

MOTIVATION: Using gene expression data to classify (or predict) tumor types has received much research attention recently. Due to some special features of gene expression data, several new methods have been proposed, including the weighted voting scheme of Golub et al., the compound covariate method of Hedenfalk et al. (originally proposed by Tukey), and the shrunken centroids method of Tibshirani et al. These methods look different and are more or less ad hoc. RESULTS: We point out a close connection of the three methods with a linear regression model. Casting the classification problem in the general framework of linear regression naturally leads to new alternatives, such as partial least squares (PLS) methods and penalized PLS (PPLS) methods. Using two real data sets, we show the competitive performance of our new methods when compared with the other three methods.     

Clinical drug response can be predicted using baseline gene expression levels and in vitro drug sensitivity in cell lines

We demonstrate a method for the prediction of chemotherapeutic response in patients using only before-treatment baseline tumor gene expression data. First, we fitted models for whole-genome gene expression against drug sensitivity in a large panel of cell lines, using a method that allows every gene to influence the prediction. Following data homogenization and filtering, these models were applied to baseline expression levels from primary tumor biopsies, yielding an in vivo drug sensitivity prediction. We validated this approach in three independent clinical trial datasets, and obtained predictions equally good, or better than, gene signatures derived directly from clinical data.     

基于生物信息学的胃癌早期诊断预测模型研究

利用The Cancer Genome Atlas和Genotype-Tissue Expression公共数据检索收集胃癌(Gastric cancer, GC)基因表达数据集,筛选与早期胃癌密切相关的基因并构建胃癌早期诊断预测模型。运用Deseq2软件包筛选早期胃癌差异基因,并对差异基因进行GO和KEGG富集分析。通过STRING数据库建立其蛋白质相互作用网络并利用Cytoscape软件提取关键子网得到候选关键基因,进一步利用MedCalc软件确认胃癌早期诊断关键基因。根据筛选得到的10个关键基因构建基于支持向量机、随机森林、朴素贝叶斯、K-近邻、极限梯度提升和自适应提升等六种算法的胃癌早期诊断预测模型,依据ROC曲线和准确率等评价指标对各个分类器模型进行评估,通过独立测试集验证得到极致梯度提升诊断预测模型为最优模型。本研究成果为提高结胃癌早期诊断的研究提供了新的思路和方法。     

Semiparametric estimation for joint modeling of colorectal cancer risk and functional biomarkers measured with errors

This research is motivated by a pilot colorectal adenoma study, where the outcome of interest is the presence of colorectal adenoma representing risk for colorectal cancer, and the predictors of interest are protein biomarkers that are repeatedly measured with errors along the length of a microscopic structure in the human colon, the colon crypt. Biomarkers of this type are referred to as functional biomarkers. The investigators are interested in identifying features of functional biomarkers that are associated with risk for colorectal cancer. In this paper, we investigate a joint modeling approach, where the binary clinical outcome is modeled using a logistic regression model with the unobserved true functional biomarkers as the predictors. Most existing methods are developed either for linear models or for functional biomarkers measured without errors and cannot be directly applied to our data. The applicable methods include a two-step method and a maximum likelihood method, which have some limitations. We propose a robust semiparametric method to overcome the limitations of the existing methods. We study the properties of the proposed method, and show in simulations that it compares favorably with other methods and also offers significant savings in CPU time. We analyze the pilot colorectal adenoma data and show that expression levels of AFC, a tumor suppressor gene, in the transitional area from the proliferation zone to the differentiation zone of colon crypts are likely to be associated with risk for colorectal cancer. Given the relatively small sample size in the pilot study, our results need to be validated in the future full-scale studies.     

Yin Yang Gene Expression Ratio Signature for Lung Cancer Prognosis

Many studies have established gene expression-based prognostic signatures for lung cancer. All of these signatures were built from training data sets by learning the correlation of gene expression with the patients'' survival time. They require all new sample data to be normalized to the training data, ultimately resulting in common problems of low reproducibility and impracticality. To overcome these problems, we propose a new signature model which does not involve data training. We hypothesize that the imbalance of two opposing effects in lung cancer cells, represented by Yin and Yang genes, determines a patient’s prognosis. We selected the Yin and Yang genes by comparing expression data from normal lung and lung cancer tissue samples using both unsupervised clustering and pathways analyses. We calculated the Yin and Yang gene expression mean ratio (YMR) as patient risk scores. Thirty-one Yin and thirty-two Yang genes were identified and selected for the signature development. In normal lung tissues, the YMR is less than 1.0; in lung cancer cases, the YMR is greater than 1.0. The YMR was tested for lung cancer prognosis prediction in four independent data sets and it significantly stratified patients into high- and low-risk survival groups (p = 0.02, HR = 2.72; p = 0.01, HR = 2.70; p = 0.007, HR = 2.73; p = 0.005, HR = 2.63). It also showed prediction of the chemotherapy outcomes for stage II & III. In multivariate analysis, the YMR risk factor was more successful at predicting clinical outcomes than other commonly used clinical factors, with the exception of tumor stage. The YMR can be measured in an individual patient in the clinic independent of gene expression platform. This study provided a novel insight into the biology of lung cancer and shed light on the clinical applicability.     

Molecular classification of multiple tumor types

Using gene expression data to classify tumor types is a very promising tool in cancer diagnosis. Previous works show several pairs of tumor types can be successfully distinguished by their gene expression patterns (Golub et al. 1999, Ben-Dor et al. 2000, Alizadeh et al. 2000). However, the simultaneous classification across a heterogeneous set of tumor types has not been well studied yet. We obtained 190 samples from 14 tumor classes and generated a combined expression dataset containing 16063 genes for each of those samples. We performed multi-class classification by combining the outputs of binary classifiers. Three binary classifiers (k-nearest neighbors, weighted voting, and support vector machines) were applied in conjunction with three combination scenarios (one-vs-all, all-pairs, hierarchical partitioning). We achieved the best cross validation error rate of 18.75% and the best test error rate of 21.74% by using the one-vs-all support vector machine algorithm. The results demonstrate the feasibility of performing clinically useful classification from samples of multiple tumor types.     

Consistent estimation of the expected Brier score in general survival models with right-censored event times

In survival analysis with censored data the mean squared error of prediction can be estimated by weighted averages of time-dependent residuals. Graf et al. (1999) suggested a robust weighting scheme based on the assumption that the censoring mechanism is independent of the covariates. We show consistency of the estimator. Furthermore, we show that a modified version of this estimator is consistent even when censoring and event times are only conditionally independent given the covariates. The modified estimators are derived on the basis of regression models for the censoring distribution. A simulation study and a real data example illustrate the results.     

Peripheral immune cell gene expression predicts survival of patients with non-small cell lung cancer

Prediction of cancer recurrence in patients with non-small cell lung cancer (NSCLC) currently relies on the assessment of clinical characteristics including age, tumor stage, and smoking history. A better prediction of early stage cancer patients with poorer survival and late stage patients with better survival is needed to design patient-tailored treatment protocols. We analyzed gene expression in RNA from peripheral blood mononuclear cells (PBMC) of NSCLC patients to identify signatures predictive of overall patient survival. We find that PBMC gene expression patterns from NSCLC patients, like patterns from tumors, have information predictive of patient outcomes. We identify and validate a 26 gene prognostic panel that is independent of clinical stage. Many additional prognostic genes are specific to myeloid cells and are more highly expressed in patients with shorter survival. We also observe that significant numbers of prognostic genes change expression levels in PBMC collected after tumor resection. These post-surgery gene expression profiles may provide a means to re-evaluate prognosis over time. These studies further suggest that patient outcomes are not solely determined by tumor gene expression profiles but can also be influenced by the immune response as reflected in peripheral immune cells.     

Logistic regression for disease classification using microarray data: model selection in a large p and small n case

MOTIVATION: Logistic regression is a standard method for building prediction models for a binary outcome and has been extended for disease classification with microarray data by many authors. A feature (gene) selection step, however, must be added to penalized logistic modeling due to a large number of genes and a small number of subjects. Model selection for this two-step approach requires new statistical tools because prediction error estimation ignoring the feature selection step can be severely downward biased. Generic methods such as cross-validation and non-parametric bootstrap can be very ineffective due to the big variability in the prediction error estimate. RESULTS: We propose a parametric bootstrap model for more accurate estimation of the prediction error that is tailored to the microarray data by borrowing from the extensive research in identifying differentially expressed genes, especially the local false discovery rate. The proposed method provides guidance on the two critical issues in model selection: the number of genes to include in the model and the optimal shrinkage for the penalized logistic regression. We show that selecting more than 20 genes usually helps little in further reducing the prediction error. Application to Golub's leukemia data and our own cervical cancer data leads to highly accurate prediction models. AVAILABILITY: R library GeneLogit at http://geocities.com/jg_liao     

Tissue classification with gene expression profiles.

Constantly improving gene expression profiling technologies are expected to provide understanding and insight into cancer-related cellular processes. Gene expression data is also expected to significantly aid in the development of efficient cancer diagnosis and classification platforms. In this work we examine three sets of gene expression data measured across sets of tumor(s) and normal clinical samples: The first set consists of 2,000 genes, measured in 62 epithelial colon samples (Alon et al., 1999). The second consists of approximately equal to 100,000 clones, measured in 32 ovarian samples (unpublished extension of data set described in Schummer et al. (1999)). The third set consists of approximately equal to 7,100 genes, measured in 72 bone marrow and peripheral blood samples (Golub et al, 1999). We examine the use of scoring methods, measuring separation of tissue type (e.g., tumors from normals) using individual gene expression levels. These are then coupled with high-dimensional classification methods to assess the classification power of complete expression profiles. We present results of performing leave-one-out cross validation (LOOCV) experiments on the three data sets, employing nearest neighbor classifier, SVM (Cortes and Vapnik, 1995), AdaBoost (Freund and Schapire, 1997) and a novel clustering-based classification technique. As tumor samples can differ from normal samples in their cell-type composition, we also perform LOOCV experiments using appropriately modified sets of genes, attempting to eliminate the resulting bias. We demonstrate success rate of at least 90% in tumor versus normal classification, using sets of selected genes, with, as well as without, cellular-contamination-related members. These results are insensitive to the exact selection mechanism, over a certain range.     

A Systems Biology-Based Gene Expression Classifier of Glioblastoma Predicts Survival with Solid Tumors

Accurate prediction of survival of cancer patients is still a key open problem in clinical research. Recently, many large-scale gene expression clusterings have identified sets of genes reportedly predictive of prognosis; however, those gene sets shared few genes in common and were poorly validated using independent data. We have developed a systems biology-based approach by using either combined gene sets and the protein interaction network (Method A) or the protein network alone (Method B) to identify common prognostic genes based on microarray gene expression data of glioblastoma multiforme and compared with differential gene expression clustering (Method C). Validations of prediction performance show that the 23-prognostic gene classifier identified by Method A outperforms other gene classifiers identified by Methods B and C or previously reported for gliomas on 17 of 20 independent sample cohorts across five tumor types. We also find that among the 23 genes are 21 related to cellular proliferation and two related to response to stress/immune response. We further find that the increased expression of the 21 genes and the decreased expression of the other two genes are associated with poorer survival, which is supportive with the notion that cellular proliferation and immune response contribute to a significant portion of predictive power of prognostic classifiers. Our results demonstrate that the systems biology-based approach enables to identify common survival-associated genes.     

Immediate transfection of patient-derived leukemia: a novel source for generating cell-based vaccines

Background

The production of cell-based cancer vaccines by gene vectors encoding proteins that stimulate the immune system has advanced rapidly in model systems. We sought to develop non-viral transfection methods that could transform patient tumor cells into cancer vaccines, paving the way for rapid production of autologous cell-based vaccines.

Methods

As the extended culture and expansion of most patient tumor cells is not possible, we sought to first evaluate a new technology that combines electroporation and chemical transfection in order to determine if plasmid-based gene vectors could be instantaneously delivered to the nucleus, and to determine if gene expression was possible in a cell-cycle independent manner. We tested cultured cell lines, a primary murine tumor, and primary human leukemia cells from diagnostic work-up for transgene expression, using both RFP and CD137L expression vectors.

Results

Combined electroporation-transfection directly delivered plasmid DNA to the nucleus of transfected cells, as demonstrated by confocal microscopy and real-time PCR analysis of isolated nuclei. Expression of protein from plasmid vectors could be detected as early as two hours post transfection. However, the kinetics of gene expression from plasmid-based vectors in tumor cell lines indicated that optimal gene expression was still dependent on cell division. We then tested to see if pediatric acute lymphocytic leukemia (ALL) would also display the rapid gene expression kinetics of tumor cells lines, determining gene expression 24 hours after transfection. Six of 12 specimens showed greater than 17% transgene expression, and all samples showed at least some transgene expression.

Conclusion

Given that transgene expression could be detected in a majority of primary tumor samples analyzed within hours, direct electroporation-based transfection of primary leukemia holds the potential to generate patient-specific cancer vaccines. Plasmid-based gene therapy represents a simple means to generate cell-based cancer vaccines and does not require the extensive infrastructure of a virus-based vector system.     

Regularized estimation for the accelerated failure time model

Summary .  In the presence of high-dimensional predictors, it is challenging to develop reliable regression models that can be used to accurately predict future outcomes. Further complications arise when the outcome of interest is an event time, which is often not fully observed due to censoring. In this article, we develop robust prediction models for event time outcomes by regularizing the Gehan's estimator for the accelerated failure time (AFT) model ( Tsiatis, 1996 , Annals of Statistics 18, 305–328) with least absolute shrinkage and selection operator (LASSO) penalty. Unlike existing methods based on the inverse probability weighting and the Buckley and James estimator ( Buckley and James, 1979 , Biometrika 66, 429–436), the proposed approach does not require additional assumptions about the censoring and always yields a solution that is convergent. Furthermore, the proposed estimator leads to a stable regression model for prediction even if the AFT model fails to hold. To facilitate the adaptive selection of the tuning parameter, we detail an efficient numerical algorithm for obtaining the entire regularization path. The proposed procedures are applied to a breast cancer dataset to derive a reliable regression model for predicting patient survival based on a set of clinical prognostic factors and gene signatures. Finite sample performances of the procedures are evaluated through a simulation study.