Person:

Huang, Xudong

Background: Appilication of MR imaging to diagnose Adhesive Capsulitis (AC) has previously been described. However, there is insufficient information available for the MRI analysis of AC. This study is to describe and evaluate the pathomorphology of the shoulder in Asian patients with AC compared to healthy volunteers. Methodology/Principal Findings: 60 Asian patients with clinically diagnosed AC and 60 healthy volunteers without frozen shoulder underwent MRI of the shoulder joint. All subjects who were age- and sex-matched control ones underwent routine MRI scans of the affected shoulder, including axial, oblique coronal, oblique sagittal T1WI SE and coronal oblique T2WI FSE sequences. Significant abnormal findings were observed on MRI, especially at the rotator cuff interval. The coracohumeral ligament (CHL), articular capsule thickness in the rotator cuff interval as well as the fat space under coracoid process were evaluated. MRI showed that patients with adhesive capsulitis had a significantly thickened coracohumeral ligament and articular capsule in the rotator cuff interval compared to the control subjects (4.2 vs. 2.4 mm, 7.2 vs. 4.4 mm; p<0.05). Partial or complete obliteration of the subcoracoid fat triangle was significantly more frequent in patients with adhesive capsulitis compared with control subjects (73% vs. 13%, 26% vs. 1.6%; p<0.001). Synovitis-like abnormality around the long biceps tendon was significantly more common in patients with adhesive capsulitis than in control subjects. With regards to the inter-observer variability, two MR radiologists had an excellent kappa value of 0.86. Conclusions/Significance: MRI can be used to show characteristic findings in diagnosing AC. Thickening of the CHL and the capsule at the rotator cuff interval and complete obliteration of the fat triangle under the coracoid process have been shown to be the most characteristic MR findings seen with AC.

Background: Comprehensive evaluation of common genetic variations through association of single nucleotide polymorphisms (SNPs) with complex human diseases on the genome-wide scale is an active area in human genome research. One of the fundamental questions in a SNP-disease association study is to find an optimal subset of SNPs with predicting power for disease status. To find that subset while reducing study burden in terms of time and costs, one can potentially reconcile information redundancy from associations between SNP markers. Results: We have developed a feature selection method named Supervised Recursive Feature Addition (SRFA). This method combines supervised learning and statistical measures for the chosen candidate features/SNPs to reconcile the redundancy information and, in doing so, improve the classification performance in association studies. Additionally, we have proposed a Support Vector based Recursive Feature Addition (SVRFA) scheme in SNP-disease association analysis. Conclusions: We have proposed using SRFA with different statistical learning classifiers and SVRFA for both SNP selection and disease classification and then applying them to two complex disease data sets. In general, our approaches outperform the well-known feature selection method of Support Vector Machine Recursive Feature Elimination and logic regression-based SNP selection for disease classification in genetic association studies. Our study further indicates that both genetic and environmental variables should be taken into account when doing disease predictions and classifications for the most complex human diseases that have gene-environment interactions.

Background: An important subfamily of membrane proteins are the transmembrane α-helical proteins, in which the membrane-spanning regions are made up of α-helices. Given the obvious biological and medical significance of these proteins, it is of tremendous practical importance to identify the location of transmembrane segments. The difficulty of inferring the secondary or tertiary structure of transmembrane proteins using experimental techniques has led to a surge of interest in applying techniques from machine learning and bioinformatics to infer secondary structure from primary structure in these proteins. We are therefore interested in determining which physicochemical properties are most useful for discriminating transmembrane segments from non-transmembrane segments in transmembrane proteins, and for discriminating intrinsically unstructured segments from intrinsically structured segments in transmembrane proteins, and in using the results of these investigations to develop classifiers to identify transmembrane segments in transmembrane proteins. Results: We determined that the most useful properties for discriminating transmembrane segments from non-transmembrane segments and for discriminating intrinsically unstructured segments from intrinsically structured segments in transmembrane proteins were hydropathy, polarity, and flexibility, and used the results of this analysis to construct classifiers to discriminate transmembrane segments from non-transmembrane segments using four classification techniques: two variants of the Self-Organizing Global Ranking algorithm, a decision tree algorithm, and a support vector machine algorithm. All four techniques exhibited good performance, with out-of-sample accuracies of approximately 75%. Conclusions: Several interesting observations emerged from our study: intrinsically unstructured segments and transmembrane segments tend to have opposite properties; transmembrane proteins appear to be much richer in intrinsically unstructured segments than other proteins; and, in approximately 70% of transmembrane proteins that contain intrinsically unstructured segments, the intrinsically unstructured segments are close to transmembrane segments.

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.

Background: The prognosis for many cancers could be improved dramatically if they could be detected while still at the microscopic disease stage. It follows from a comprehensive statistical analysis that a number of antigens such as hTERT, PCNA and Ki-67 can be considered as cancer markers, while another set of antigens such as P27KIP1 and FHIT are possible markers for normal tissue. Because more than one marker must be considered to obtain a classification of cancer or no cancer, and if cancer, to classify it as malignant, borderline, or benign, we must develop an intelligent decision system that can fullfill such an unmet medical need. Results: We have developed an intelligent decision system using machine learning techniques and markers to characterize tissue as cancerous, non-cancerous or borderline. The system incorporates learning techniques such as variants of support vector machines, neural networks, decision trees, self-organizing feature maps (SOFM) and recursive maximum contrast trees (RMCT). These variants and algorithms we have developed, tend to detect microscopic pathological changes based on features derived from gene expression levels and metabolic profiles. We have also used immunohistochemistry techniques to measure the gene expression profiles from a number of antigens such as cyclin E, P27KIP1, FHIT, Ki-67, PCNA, Bax, Bcl-2, P53, Fas, FasL and hTERT in several particular types of neuroendocrine tumors such as pheochromocytomas, paragangliomas, and the adrenocortical carcinomas (ACC), adenomas (ACA), and hyperplasia (ACH) involved with Cushing's syndrome. We provided statistical evidence that higher expression levels of hTERT, PCNA and Ki-67 etc. are associated with a higher risk that the tumors are malignant or borderline as opposed to benign. We also investigated whether higher expression levels of P27KIP1 and FHIT, etc., are associated with a decreased risk of adrenomedullary tumors. While no significant difference was found between cell-arrest antigens such as P27KIP1 for malignant, borderline, and benign tumors, there was a significant difference between expression levels of such antigens in normal adrenal medulla samples and in adrenomedullary tumors. Conclusions: Our frame work focused on not only different classification schemes and feature selection algorithms, but also ensemble methods such as boosting and bagging in an effort to improve upon the accuracy of the individual classifiers. It is evident that when all sorts of machine learning and statistically learning techniques are combined appropriately into one integrated intelligent medical decision system, the prediction power can be enhanced significantly. This research has many potential applications; it might provide an alternative diagnostic tool and a better understanding of the mechanisms involved in malignant transformation as well as information that is useful for treatment planning and cancer prevention.

Background: DNA methylation profiles differ among disease types and, therefore, can be used in disease diagnosis. In addition, large-scale whole genome DNA methylation data offer tremendous potential in understanding the role of DNA methylation in normal development and function. However, due to the unique feature of the methylation data, powerful and robust statistical methods are very limited in this area. Results: In this paper, we proposed and examined a new statistical method to detect differentially methylated loci for case control designs that is fully nonparametric and does not depend on any assumption for the underlying distribution of the data. Moreover, the proposed method adjusts for the age effect that has been shown to be highly correlated with DNA methylation profiles. Using simulation studies and a real data application, we have demonstrated the advantages of our method over existing commonly used methods. Conclusions: Compared to existing methods, our method improved the detection power for differentially methylated loci for case control designs and controlled the type I error well. Its applications are not limited to methylation data; it can be extended to many other case–control studies.

Background: Microarray data have a high dimension of variables and a small sample size. In microarray data analyses, two important issues are how to choose genes, which provide reliable and good prediction for disease status, and how to determine the final gene set that is best for classification. Associations among genetic markers mean one can exploit information redundancy to potentially reduce classification cost in terms of time and money. Results: To deal with redundant information and improve classification, we propose a gene selection method, Recursive Feature Addition, which combines supervised learning and statistical similarity measures. To determine the final optimal gene set for prediction and classification, we propose an algorithm, Lagging Prediction Peephole Optimization. By using six benchmark microarray gene expression data sets, we compared Recursive Feature Addition with recently developed gene selection methods: Support Vector Machine Recursive Feature Elimination, Leave-One-Out Calculation Sequential Forward Selection and several others. Conclusions: On average, with the use of popular learning machines including Nearest Mean Scaled Classifier, Support Vector Machine, Naive Bayes Classifier and Random Forest, Recursive Feature Addition outperformed other methods. Our studies also showed that Lagging Prediction Peephole Optimization is superior to random strategy; Recursive Feature Addition with Lagging Prediction Peephole Optimization obtained better testing accuracies than the gene selection method varSelRF.

Background: In microarray experiments with small sample sizes, it is a challenge to estimate p-values accurately and decide cutoff p-values for gene selection appropriately. Although permutation-based methods have proved to have greater sensitivity and specificity than the regular t-test, their p-values are highly discrete due to the limited number of permutations available in very small sample sizes. Furthermore, estimated permutation-based p-values for true nulls are highly correlated and not uniformly distributed between zero and one, making it difficult to use current false discovery rate (FDR)-controlling methods. Results: We propose a model-based information sharing method (MBIS) that, after an appropriate data transformation, utilizes information shared among genes. We use a normal distribution to model the mean differences of true nulls across two experimental conditions. The parameters of the model are then estimated using all data in hand. Based on this model, p-values, which are uniformly distributed from true nulls, are calculated. Then, since FDR-controlling methods are generally not well suited to microarray data with very small sample sizes, we select genes for a given cutoff p-value and then estimate the false discovery rate. Conclusion: Simulation studies and analysis using real microarray data show that the proposed method, MBIS, is more powerful and reliable than current methods. It has wide application to a variety of situations.

Introduction: In the classification of Mass Spectrometry (MS) proteomics data, peak detection, feature selection, and learning classifiers are critical to classification accuracy. To better understand which methods are more accurate when classifying data, some publicly available peak detection algorithms for Matrix assisted Laser Desorption Ionization Mass Spectrometry (MALDI-MS) data were recently compared; however, the issue of different feature selection methods and different classification models as they relate to classification performance has not been addressed. With the application of intelligent computing, much progress has been made in the development of feature selection methods and learning classifiers for the analysis of high-throughput biological data. The main objective of this paper is to compare the methods of feature selection and different learning classifiers when applied to MALDI-MS data and to provide a subsequent reference for the analysis of MS proteomics data. Results: We compared a well-known method of feature selection, Support Vector Machine Recursive Feature Elimination (SVMRFE), and a recently developed method, Gradient based Leave-one-out Gene Selection (GLGS) that effectively performs microarray data analysis. We also compared several learning classifiers including K-Nearest Neighbor Classifier (KNNC), Naïve Bayes Classifier (NBC), Nearest Mean Scaled Classifier (NMSC), uncorrelated normal based quadratic Bayes Classifier recorded as UDC, Support Vector Machines, and a distance metric learning for Large Margin Nearest Neighbor classifier (LMNN) based on Mahanalobis distance. To compare, we conducted a comprehensive experimental study using three types of MALDI-MS data. Conclusion: Regarding feature selection, SVMRFE outperformed GLGS in classification. As for the learning classifiers, when classification models derived from the best training were compared, SVMs performed the best with respect to the expected testing accuracy. However, the distance metric learning LMNN outperformed SVMs and other classifiers on evaluating the best testing. In such cases, the optimum classification model based on LMNN is worth investigating for future study.

We reported that iron influx drives the translational expression of the neuronal amyloid precursor protein (APP), which has a role in iron efflux. This is via a classic release of repressor interaction of APP mRNA with iron-regulatory protein-1 (IRP1) whereas IRP2 controls the mRNAs encoding the L- and H-subunits of the iron storage protein, ferritin. Here, we identified thirteen potent APP translation blockers that acted selectively towards the uniquely configured iron-responsive element (IRE) RNA stem loop in the 5′ untranslated region (UTR) of APP mRNA. These agents were 10-fold less inhibitory of 5′UTR sequences of the related prion protein (PrP) mRNA. Western blotting confirmed that the ‘ninth’ small molecule in the series selectively reduced neural APP production in SH-SY5Y cells at picomolar concentrations without affecting viability or the expression of α-synuclein and ferritin. APP blocker-9 (JTR-009), a benzimidazole, reduced the production of toxic Aβ in SH-SY5Y neuronal cells to a greater extent than other well tolerated APP 5′UTR-directed translation blockers, including posiphen, that were shown to limit amyloid burden in mouse models of Alzheimer's disease (AD). RNA binding assays demonstrated that JTR-009 operated by preventing IRP1 from binding to the IRE in APP mRNA, while maintaining IRP1 interaction with the H-ferritin IRE RNA stem loop. Thus, JTR-009 constitutively repressed translation driven by APP 5′UTR sequences. Calcein staining showed that JTR-009 did not indirectly change iron uptake in neuronal cells suggesting a direct interaction with the APP 5′UTR. These studies provide key data to develop small molecules that selectively reduce neural APP and Aβ production at 10-fold lower concentrations than related previously characterized translation blockers. Our data evidenced a novel therapeutic strategy of potential impact for people with trisomy of the APP gene on chromosome 21, which is a phenotype long associated with Down syndrome (DS) that can also cause familial Alzheimer's disease.