Integrating fMRI and SNP data for biomarker identification for schizophrenia with a sparse representation based variable selection method

Background

In recent years, both single-nucleotide polymorphism (SNP) array and functional magnetic resonance imaging (fMRI) have been widely used for the study of schizophrenia (SCZ). In addition, a few studies have been reported integrating both SNPs data and fMRI data for comprehensive analysis.

Methods

In this study, a novel sparse representation based variable selection (SRVS) method has been proposed and tested on a simulation data set to demonstrate its multi-resolution properties. Then the SRVS method was applied to an integrative analysis of two different SCZ data sets, a Single-nucleotide polymorphism (SNP) data set and a functional resonance imaging (fMRI) data set, including 92 cases and 116 controls. Biomarkers for the disease were identified and validated with a multivariate classification approach followed by a leave one out (LOO) cross-validation. Then we compared the results with that of a previously reported sparse representation based feature selection method.

Results

Results showed that biomarkers from our proposed SRVS method gave significantly higher classification accuracy in discriminating SCZ patients from healthy controls than that of the previous reported sparse representation method. Furthermore, using biomarkers from both data sets led to better classification accuracy than using single type of biomarkers, which suggests the advantage of integrative analysis of different types of data.

Conclusions

The proposed SRVS algorithm is effective in identifying significant biomarkers for complicated disease as SCZ. Integrating different types of data (e.g. SNP and fMRI data) may identify complementary biomarkers benefitting the diagnosis accuracy of the disease.

     

基因测序技术的发展以及对个体化用药水平提高的影响

自基因测序技术发明之时起,就已开始运用在生命科学的研究中,对揭示生命本质的研究起到了关键作用。基因测序技术的运用推动了生命科学的发展,并由此引申了更多的科学问题;人们对未知领域的渴求又推动了基因测序技术的进步,发展出更高速、更低价的新技术。随着测序技术的逐步应用,临床个体化用药的水平有了极大的提高。基因测序技术目前已经成功应用于遗传基因多态性标志物的筛选中,使基因导向的合理用药成为可能;还成功应用于疾病组织突变位点标志物的筛查中,使肿瘤靶向用药成为可能;在病原体耐药基因突变检测中的应用,使基于细菌或病毒耐药突变的个体化用药成为可能。随着测序技术向更高通量、更高精度、更低成本的方向发展,基于基因检测的个体化健康时代将会到来。     

An Integrative Framework for Bayesian Variable Selection with Informative Priors for Identifying Genes and Pathways

The discovery of genetic or genomic markers plays a central role in the development of personalized medicine. A notable challenge exists when dealing with the high dimensionality of the data sets, as thousands of genes or millions of genetic variants are collected on a relatively small number of subjects. Traditional gene-wise selection methods using univariate analyses face difficulty to incorporate correlational, structural, or functional structures amongst the molecular measures. For microarray gene expression data, we first summarize solutions in dealing with ‘large p, small n’ problems, and then propose an integrative Bayesian variable selection (iBVS) framework for simultaneously identifying causal or marker genes and regulatory pathways. A novel partial least squares (PLS) g-prior for iBVS is developed to allow the incorporation of prior knowledge on gene-gene interactions or functional relationships. From the point view of systems biology, iBVS enables user to directly target the joint effects of multiple genes and pathways in a hierarchical modeling diagram to predict disease status or phenotype. The estimated posterior selection probabilities offer probabilitic and biological interpretations. Both simulated data and a set of microarray data in predicting stroke status are used in validating the performance of iBVS in a Probit model with binary outcomes. iBVS offers a general framework for effective discovery of various molecular biomarkers by combining data-based statistics and knowledge-based priors. Guidelines on making posterior inferences, determining Bayesian significance levels, and improving computational efficiencies are also discussed.     

An overview of neuroblastoma cell lineage phenotypes and in vitro models

This review was conducted to present the main neuroblastoma (NB) clinical characteristics and the most common genetic alterations present in these pediatric tumors, highlighting their impact in tumor cell aggressiveness behavior, including metastatic development and treatment resistance, and patients’ prognosis. The distinct three NB cell lineage phenotypes, S-type, N-type, and I-type, which are characterized by unique cell surface markers and gene expression patterns, are also reviewed. Finally, an overview of the most used NB cell lines currently available for in vitro studies and their unique cellular and molecular characteristics, which should be taken into account for the selection of the most appropriate model for NB pre-clinical studies, is presented. These valuable models can be complemented by the generation of NB reprogrammed tumor cells or organoids, derived directly from patients’ tumor specimens, in the direction toward personalized medicine.     

Methods for the absolute quantification of N-glycan biomarkers

BackgroundMany treatment options especially for cancer show a low efficacy for the majority of patients demanding improved biomarker panels for patient stratification. Changes in glycosylation are a hallmark of many cancers and inflammatory diseases and show great potential as clinical disease markers. The large inter-subject variability in glycosylation due to hereditary and environmental factors can complicate rapid transfer of glycan markers into the clinical practice but also presents an opportunity for personalized medicine.Scope of reviewThis review discusses opportunities of glycan biomarkers in personalized medicine and reviews the methodology for N-glycan analysis with a specific focus on methods for absolute quantification.Major conclusionsThe entry into the clinical practice of glycan markers is delayed in large part due to a lack of adequate methodology for the precise and robust quantification of protein glycosylation. Only absolute glycan quantification can provide a complete picture of the disease related changes and will provide the method robustness required by clinical applications.General significanceGlycan biomarkers have a huge potential as disease markers for personalized medicine. The use of stable isotope labeled glycans as internal standards and heavy-isotope labeling methods will provide the necessary method precision and robustness acceptable for clinical use. This article is part of a Special Issue entitled “Glycans in personalized medicine” Guest Editor: Professor Gordan Lauc.     

Comparison of optimization parametrizations for regional lung compliance estimation using personalized pulmonary poromechanical modeling

Interstitial lung diseases, such as idiopathic pulmonary fibrosis (IPF) or post-COVID-19 pulmonary fibrosis, are progressive and severe diseases characterized by an irreversible scarring of interstitial tissues that affects lung function. Despite many efforts, these diseases remain poorly understood and poorly treated. In this paper, we propose an automated method for the estimation of personalized regional lung compliances based on a poromechanical model of the lung. The model is personalized by integrating routine clinical imaging data – namely computed tomography images taken at two breathing levels in order to reproduce the breathing kinematic—notably through an inverse problem with fully personalized boundary conditions that is solved to estimate patient-specific regional lung compliances. A new parametrization of the inverse problem is introduced in this paper, based on the combined estimation of a personalized breathing pressure in addition to material parameters, improving the robustness and consistency of estimation results. The method is applied to three IPF patients and one post-COVID-19 patient. This personalized model could help better understand the role of mechanics in pulmonary remodeling due to fibrosis; moreover, patient-specific regional lung compliances could be used as an objective and quantitative biomarker for improved diagnosis and treatment follow up for various interstitial lung diseases.

     

Personalized medicine: new genomics,old lessons

Personalized medicine uses traditional, as well as emerging concepts of the genetic and environmental basis of disease to individualize prevention, diagnosis and treatment. Personalized genomics plays a vital, but not exclusive role in this evolving model of personalized medicine. The distinctions between genetic and genomic medicine are more quantitative than qualitative. Personalized genomics builds on principles established by the integration of genetics into medical practice. Principles shared by genetic and genomic aspects of medicine, include the use of variants as markers for diagnosis, prognosis, prevention, as well as targets for treatment, the use of clinically validated variants that may not be functionally characterized, the segregation of these variants in non-Mendelian as well as Mendelian patterns, the role of gene–environment interactions, the dependence on evidence for clinical utility, the critical translational role of behavioral science, and common ethical considerations. During the current period of transition from investigation to practice, consumers should be protected from harms of premature translation of research findings, while encouraging the innovative and cost-effective application of those genomic discoveries that improve personalized medical care.     

A genetic variant in CDKN2A/2B locus was associated with poor prognosis in patients with esophageal squamous cell carcinoma

Esophageal squamous cell carcinoma (ESCC) is among the leading causes of cancer related death. Despite of extensive efforts in identifying valid cancer prognostic biomarkers, only a very small number of markers have been identified. Several genetic variants in the 9p21 region have been identified that are associated with the risk of multiple cancers. Here, we explored the association of two genetic variants in the 9p21 region, CDKN2A/B, rs10811661, and rs1333049 for the first time in 273 subjects with, or without ESCC. We observed that the patients with ESCC had a higher frequency of a TT genotype for rs10811661 than individuals in the control group, and this polymorphism was also associated with tumor size. Moreover, a CC genotype for the rs1333049 polymorphism was associated with a reduced overall survival (OS) of patients with ESCC. In particular, patients with a CC (rs1333049) genotype had a significantly shorter OS (CC genotype: 34.5 ± 8.9 months vs. CG+GG: 47.7 ± 5.9 months; p value = 0.03). We have also shown the association of a novel genetic variant in CDKN2B gene with clinical outcome of patients with ESCC. Further investigations are warranted in a larger population to explore the value of emerging markers as a risk stratification marker in ESCC.     

A nonparametric method for classification trees using grouped covariates

A group of variables are commonly seen in diagnostic medicine when multiple prognostic factors are aggregated into a composite score to represent the risk profile. A model selection method considers these covariates as all-in or all-out types. Model selection procedures for grouped covariates and their applications have thrived in recent years, in part because of the development of genetic research in which gene–gene or gene–environment interactions and regulatory network pathways are considered groups of individual variables. However, little has been discussed on how to utilize grouped covariates to grow a classification tree. In this paper, we propose a nonparametric method to address the selection of split variables for grouped covariates and their following selection of split points. Comprehensive simulations were implemented to show the superiority of our procedures compared to a commonly used recursive partition algorithm. The practical use of our method is demonstrated through a real data analysis that uses a group of prognostic factors to classify the successful mobilization of peripheral blood stem cells.     

MD-Miner: a network-based approach for personalized drug repositioning

Background

Due to advances in next generation sequencing technologies and corresponding reductions in cost, it is now attainable to investigate genome-wide gene expression and variants at a patient-level, so as to better understand and anticipate heterogeneous responses to therapy. Consequently, it is feasible to inform personalized drug treatment decisions using personal genomics data. However, these efforts are limited due to a lack of reliable computational approaches for predicting effective drugs for individual patients. The reverse gene set enrichment analysis (i.e., connectivity mapping) approach and its variants have been widely and successfully used for drug prediction. However, the performance of these methods is limited by undefined mechanism of action (MoA) of drugs and reliance on cohorts of patients rather than personalized predictions for individual patients.

Results

In this study, we have developed and evaluated a computational approach, known as Mechanism and Drug Miner (MD-Miner), using a network-based computational approach to predict effective drugs and reveal potential drug mechanisms of action at the level of signaling pathways. Specifically, the patient-specific signaling network is constructed by integrating known disease associated genes with patient-derived gene expression profiles. In parallel, a drug mechanism of action network is constructed by integrating drug targets and z-score profiles of drug-induced gene expression (pre vs. post-drug treatment). Potentially effective candidate drugs are prioritized according to the number of common genes between the patient-specific dysfunctional signaling network and drug MoA network. We evaluated the MD-Miner method on the PC-3 prostate cancer cell line, and showed that it significantly improved the success rate of discovering effective drugs compared with the random selection, and could provide insight into potential mechanisms of action.

Conclusions

This work provides a signaling network-based drug repositioning approach. Compared with the reverse gene signature based drug repositioning approaches, the proposed method can provide clues of mechanism of action in terms of signaling transduction networks.

     

Feature Selection and Classification of MAQC-II Breast Cancer and Multiple Myeloma Microarray Gene Expression Data

Microarray data has a high dimension of variables but available datasets usually have only a small number of samples, thereby making the study of such datasets interesting and challenging. In the task of analyzing microarray data for the purpose of, e.g., predicting gene-disease association, feature selection is very important because it provides a way to handle the high dimensionality by exploiting information redundancy induced by associations among genetic markers. Judicious feature selection in microarray data analysis can result in significant reduction of cost while maintaining or improving the classification or prediction accuracy of learning machines that are employed to sort out the datasets. In this paper, we propose a gene selection method called Recursive Feature Addition (RFA), which combines supervised learning and statistical similarity measures. We compare our method with the following gene selection methods:

• Support Vector Machine Recursive Feature Elimination (SVMRFE)
• Leave-One-Out Calculation Sequential Forward Selection (LOOCSFS)
• Gradient based Leave-one-out Gene Selection (GLGS)

To evaluate the performance of these gene selection methods, we employ several popular learning classifiers on the MicroArray Quality Control phase II on predictive modeling (MAQC-II) breast cancer dataset and the MAQC-II multiple myeloma dataset. Experimental results show that gene selection is strictly paired with learning classifier. Overall, our approach outperforms other compared methods. The biological functional analysis based on the MAQC-II breast cancer dataset convinced us to apply our method for phenotype prediction. Additionally, learning classifiers also play important roles in the classification of microarray data and our experimental results indicate that the Nearest Mean Scale Classifier (NMSC) is a good choice due to its prediction reliability and its stability across the three performance measurements: Testing accuracy, MCC values, and AUC errors.     

Bayesian personalized treatment selection strategies that integrate predictive with prognostic determinants

The evolution of “informatics” technologies has the potential to generate massive databases, but the extent to which personalized medicine may be effectuated depends on the extent to which these rich databases may be utilized to advance understanding of the disease molecular profiles and ultimately integrated for treatment selection, necessitating robust methodology for dimension reduction. Yet, statistical methods proposed to address challenges arising with the high‐dimensionality of omics‐type data predominately rely on linear models and emphasize associations deriving from prognostic biomarkers. Existing methods are often limited for discovering predictive biomarkers that interact with treatment and fail to elucidate the predictive power of their resultant selection rules. In this article, we present a Bayesian predictive method for personalized treatment selection that is devised to integrate both the treatment predictive and disease prognostic characteristics of a particular patient's disease. The method appropriately characterizes the structural constraints inherent to prognostic and predictive biomarkers, and hence properly utilizes these complementary sources of information for treatment selection. The methodology is illustrated through a case study of lower grade glioma. Theoretical considerations are explored to demonstrate the manner in which treatment selection is impacted by prognostic features. Additionally, simulations based on an actual leukemia study are provided to ascertain the method's performance with respect to selection rules derived from competing methods.     

Robust Prediction of Anti-Cancer Drug Sensitivity and Sensitivity-Specific Biomarker

The personal genomics era has attracted a large amount of attention for anti-cancer therapy by patient-specific analysis. Patient-specific analysis enables discovery of individual genomic characteristics for each patient, and thus we can effectively predict individual genetic risk of disease and perform personalized anti-cancer therapy. Although the existing methods for patient-specific analysis have successfully uncovered crucial biomarkers, their performance takes a sudden turn for the worst in the presence of outliers, since the methods are based on non-robust manners. In practice, clinical and genomic alterations datasets usually contain outliers from various sources (e.g., experiment error, coding error, etc.) and the outliers may significantly affect the result of patient-specific analysis. We propose a robust methodology for patient-specific analysis in line with the NetwrokProfiler. In the proposed method, outliers in high dimensional gene expression levels and drug response datasets are simultaneously controlled by robust Mahalanobis distance in robust principal component space. Thus, we can effectively perform for predicting anti-cancer drug sensitivity and identifying sensitivity-specific biomarkers for individual patients. We observe through Monte Carlo simulations that the proposed robust method produces outstanding performances for predicting response variable in the presence of outliers. We also apply the proposed methodology to the Sanger dataset in order to uncover cancer biomarkers and predict anti-cancer drug sensitivity, and show the effectiveness of our method.     

Entropy-based gene ranking without selection bias for the predictive classification of microarray data

Background

We describe the E-RFE method for gene ranking, which is useful for the identification of markers in the predictive classification of array data. The method supports a practical modeling scheme designed to avoid the construction of classification rules based on the selection of too small gene subsets (an effect known as the selection bias, in which the estimated predictive errors are too optimistic due to testing on samples already considered in the feature selection process).

Results

With E-RFE, we speed up the recursive feature elimination (RFE) with SVM classifiers by eliminating chunks of uninteresting genes using an entropy measure of the SVM weights distribution. An optimal subset of genes is selected according to a two-strata model evaluation procedure: modeling is replicated by an external stratified-partition resampling scheme, and, within each run, an internal K-fold cross-validation is used for E-RFE ranking. Also, the optimal number of genes can be estimated according to the saturation of Zipf's law profiles.

Conclusions

Without a decrease of classification accuracy, E-RFE allows a speed-up factor of 100 with respect to standard RFE, while improving on alternative parametric RFE reduction strategies. Thus, a process for gene selection and error estimation is made practical, ensuring control of the selection bias, and providing additional diagnostic indicators of gene importance.

     

Precision Medicine with Imprecise Therapy: Computational Modeling for Chemotherapy in Breast Cancer

Medical oncology is in need of a mathematical modeling toolkit that can leverage clinically-available measurements to optimize treatment selection and schedules for patients. Just as the therapeutic choice has been optimized to match tumor genetics, the delivery of those therapeutics should be optimized based on patient-specific pharmacokinetic/pharmacodynamic properties. Under the current approach to treatment response planning and assessment, there does not exist an efficient method to consolidate biomarker changes into a holistic understanding of treatment response. While the majority of research on chemotherapies focus on cellular and genetic mechanisms of resistance, there are numerous patient-specific and tumor-specific measures that contribute to treatment response. New approaches that consolidate multimodal information into actionable data are needed. Mathematical modeling offers a solution to this problem. In this perspective, we first focus on the particular case of breast cancer to highlight how mathematical models have shaped the current approaches to treatment. Then we compare chemotherapy to radiation therapy. Finally, we identify opportunities to improve chemotherapy treatments using the model of radiation therapy. We posit that mathematical models can improve the application of anticancer therapeutics in the era of precision medicine. By highlighting a number of historical examples of the contributions of mathematical models to cancer therapy, we hope that this contribution serves to engage investigators who may not have previously considered how mathematical modeling can provide real insights into breast cancer therapy.     

基于AR模型的基因芯片数据识别

将自回归模型(AR)模型引入基因芯片数据识别领域,提出了基于自回归模型的时间序列特征提取方法．利用动态时轴弯曲(DTW)作为分类器,在标准的肿瘤基因芯片数据的识别结果表明,本方法能够达到100％的识别率,可以应用于基因芯片数据的识别、分类和基因疾病推断。     

Multi-class cancer subtype classification based on gene expression signatures with reliability analysis

Differential diagnosis among a group of histologically similar cancers poses a challenging problem in clinical medicine. Constructing a classifier based on gene expression signatures comprising multiple discriminatory molecular markers derived from microarray data analysis is an emerging trend for cancer diagnosis. To identify the best genes for classification using a small number of samples relative to the genome size remains the bottleneck of this approach, despite its promise. We have devised a new method of gene selection with reliability analysis, and demonstrated that this method can identify a more compact set of genes than other methods for constructing a classifier with optimum predictive performance for both small round blue cell tumors and leukemia. High consensus between our result and the results produced by methods based on artificial neural networks and statistical techniques confers additional evidence of the validity of our method. This study suggests a way for implementing a reliable molecular cancer classifier based on gene expression signatures.     

An Integrative Analysis to Identify Driver Genes in Esophageal Squamous Cell Carcinoma

BackgroundFew driver genes have been well established in esophageal squamous cell carcinoma (ESCC). Identification of the genomic aberrations that contribute to changes in gene expression profiles can be used to predict driver genes.MethodsWe searched for driver genes in ESCC by integrative analysis of gene expression microarray profiles and copy number data. To narrow down candidate genes, we performed survival analysis on expression data and tested the genetic vulnerability of each genes using public RNAi screening data. We confirmed the results by performing RNAi experiments and evaluating the clinical relevance of candidate genes in an independent ESCC cohort.ResultsWe found 10 significantly recurrent copy number alterations accompanying gene expression changes, including loci 11q13.2, 7p11.2, 3q26.33, and 17q12, which harbored CCND1, EGFR, SOX2, and ERBB2, respectively. Analysis of survival data and RNAi screening data suggested that GRB7, located on 17q12, was a driver gene in ESCC. In ESCC cell lines harboring 17q12 amplification, knockdown of GRB7 reduced the proliferation, migration, and invasion capacities of cells. Moreover, siRNA targeting GRB7 had a synergistic inhibitory effect when combined with trastuzumab, an anti-ERBB2 antibody. Survival analysis of the independent cohort also showed that high GRB7 expression was associated with poor prognosis in ESCC.ConclusionOur integrative analysis provided important insights into ESCC pathogenesis. We identified GRB7 as a novel ESCC driver gene and potential new therapeutic target.     

A framework for personalized medicine: prediction of drug sensitivity in cancer by proteomic profiling

Background

The goal of personalized medicine is to provide patients optimal drug screening and treatment based on individual genomic or proteomic profiles. Reverse-Phase Protein Array (RPPA) technology offers proteomic information of cancer patients which may be directly related to drug sensitivity. For cancer patients with different drug sensitivity, the proteomic profiling reveals important pathophysiologic information which can be used to predict chemotherapy responses.

Results

The goal of this paper is to present a framework for personalized medicine using both RPPA and drug sensitivity (drug resistance or intolerance). In the proposed personalized medicine system, the prediction of drug sensitivity is obtained by a proposed augmented naive Bayesian classifier (ANBC) whose edges between attributes are augmented in the network structure of naive Bayesian classifier. For discriminative structure learning of ANBC, local classification rate (LCR) is used to score augmented edges, and greedy search algorithm is used to find the discriminative structure that maximizes classification rate (CR). Once a classifier is trained by RPPA and drug sensitivity using cancer patient samples, the classifier is able to predict the drug sensitivity given RPPA information from a patient.

Conclusion

In this paper we proposed a framework for personalized medicine where a patient is profiled by RPPA and drug sensitivity is predicted by ANBC and LCR. Experimental results with lung cancer data demonstrate that RPPA can be used to profile patients for drug sensitivity prediction by Bayesian network classifier, and the proposed ANBC for personalized cancer medicine achieves better prediction accuracy than naive Bayes classifier in small sample size data on average and outperforms other the state-of-the-art classifier methods in terms of classification accuracy.