Bayesian machine learning and its potential applications to the genomic study of oral oncology

Peripheral blood gene expression profiles in COPD subjects

To identify non-invasive gene expression markers for chronic obstructive pulmonary disease (COPD), we performed genome-wide expression profiling of peripheral blood samples from 12 subjects with significant airflow obstruction and an equal number of non-obstructed controls. RNA was isolated from Peripheral Blood Mononuclear Cells (PBMCs) and gene expression was assessed using Affymetrix U133 Plus 2.0 arrays.

Tests for gene expression changes that discriminate between COPD cases (FEV₁< 70% predicted, FEV₁/FVC < 0.7) and controls (FEV₁> 80% predicted, FEV₁/FVC > 0.7) were performed using Significance Analysis of Microarrays (SAM) and Bayesian Analysis of Differential Gene Expression (BADGE). Using either test at high stringency (SAM median FDR = 0 or BADGE p < 0.01) we identified differential expression for 45 known genes. Correlation of gene expression with lung function measurements (FEV₁ & FEV₁/FVC), using both Pearson and Spearman correlation coefficients (p < 0.05), identified a set of 86 genes. A total of 16 markers showed evidence of significant correlation (p < 0.05) with quantitative traits and differential expression between cases and controls. We further compared our peripheral gene expression markers with those we previously identified from lung tissue of the same cohort. Two genes, RP9and NAPE-PLD, were identified as decreased in COPD cases compared to controls in both lung tissue and blood. These results contribute to our understanding of gene expression changes in the peripheral blood of patients with COPD and may provide insight into potential mechanisms involved in the disease.

Factors affecting the clinical approach to impacted maxillary canines: A Bayesian network analysis

INTRODUCTION

The aim of this study was to apply Bayesian networks to evaluate the relative role and possible causal relationships among various factors affecting the diagnosis and final treatment outcome of impacted maxillary canines.

METHODS

A total of 168 patients with infraosseous impacted maxillary canines had a combined surgical-orthodontic approach aimed to guide the impacted tooth to the center of the alveolar ridge. Demographic, orthodontic, and periodontal variables were recorded and analyzed by means of Bayesian network analysis.

RESULTS

All 168 impacted canines were successfully moved and aligned in the dental arches with healthy periodontiums. According to the Bayesian network analysis, bilateral impaction was associated with palatal impaction and longer treatment; the pretreatment alpha-angle was a determinant for the duration of orthodontic traction, also because of the associations between greater angulation of impacted canines with more severe tooth displacement and with greater distance of the impacted canine from the occlusal plane; the posttreatment periodontal outcome was not related to the pretreatment radiographic variables.

CONCLUSIONS

Bayesian network analysis was useful to identify possible relationships among the variables considered for diagnosis and treatment of impacted canines.

Characteristics of transcriptional activity in nonlinear dynamics of genetic regulatory networks

Microarray measurements of mRNA abundances is a standard tool for evaluation of transcriptional activity in functional genomics. The methodology underlying these measurements assumes existence of a direct link between transcription levels, that is, gene-specific mRNA copy numbers present in the cell, and transcription rates, that is, the numbers of gene-specific mRNA molecules synthesized per unit of time. In this paper, the question of whether or not such a tight interdependence may exist is examined in the context of nonlinear dynamics of genetic regulatory networks. Using the equations of chemical kinetics, a model has been constructed that is capable of explicitly taking into consideration nonlinear interactions between the genes through the teamwork of transcription factors. Jacobian analysis of stability has shown that steady state equilibrium is impossible in such systems. However, phase space compressibility is found to be negative, thus suggesting that asymptotic stability may exist and assume either the form of limit cycle or of a chaotic attractor. It is argued that in rapidly fluctuating or chaotic systems, direct evaluation of transcription rates through transcription levels is highly problematic. It is also noted that even if a hypothetical steady state did exist, the knowledge of transcription levels alone would not be sufficient for the evaluation of transcription rates; an additional set of parameters, namely the mRNA decay rates, would be required. An overall conclusion of the work is that the measurements of mRNA abundances are not truly representative of the functionality of genes and structural fidelity of the genetic codes.

Molecular biomarkers for quantitative and discrete COPD phenotypes

Chronic obstructive pulmonary disease (COPD) is an inflammatory lung disorder with complex pathological features and largely unknown etiology. The identification of biomarkers for this disease could aid the development of methods to facilitate earlier diagnosis, the classification of disease subtypes, and provide a means to define therapeutic response. To identify gene expression biomarkers, we completed expression profiling of RNA derived from the lung tissue of 56 subjects with varying degrees of airflow obstruction using the Affymetrix U133 Plus 2.0 array. We applied multiple, independent analytical methods to define biomarkers for either discrete or quantitative disease phenotypes. Analysis of differential expression between cases (n = 15) and controls (n = 18) identified a set of 65 discrete biomarkers. Correlation of gene expression with quantitative measures of airflow obstruction (FEV(1)%predicted or FEV(1)/FVC) identified a set of 220 biomarkers. Biomarker genes were enriched in functions related to DNA binding and regulation of transcription. We used this group of biomarkers to predict disease in an unrelated data set, generated from patients with severe emphysema, with 97% accuracy. Our data contribute to the understanding of gene expression changes occurring in the lung tissue of patients with obstructive lung disease and provide additional insight into potential mechanisms involved in the disease process. Furthermore, we present the first gene expression biomarker for COPD validated in an independent data set.

Systems biology by the rules: hybrid intelligent systems for pathway modeling and discovery

BACKGROUND

Expert knowledge in journal articles is an important source of data for reconstructing biological pathways and creating new hypotheses. An important need for medical research is to integrate this data with high throughput sources to build useful models that span several scales. Researchers traditionally use mental models of pathways to integrate information and development new hypotheses. Unfortunately, the amount of information is often overwhelming and these are inadequate for predicting the dynamic response of complex pathways. Hierarchical computational models that allow exploration of semi-quantitative dynamics are useful systems biology tools for theoreticians, experimentalists and clinicians and may provide a means for cross-communication.

RESULTS

A novel approach for biological pathway modeling based on hybrid intelligent systems or soft computing technologies is presented here. Intelligent hybrid systems, which refers to several related computing methods such as fuzzy logic, neural nets, genetic algorithms, and statistical analysis, has become ubiquitous in engineering applications for complex control system modeling and design. Biological pathways may be considered to be complex control systems, which medicine tries to manipulate to achieve desired results. Thus, hybrid intelligent systems may provide a useful tool for modeling biological system dynamics and computational exploration of new drug targets. A new modeling approach based on these methods is presented in the context of hedgehog regulation of the cell cycle in granule cells. Code and input files can be found at the Bionet website: www.chip.ord/~wbosl/Software/Bionet.

CONCLUSION

This paper presents the algorithmic methods needed for modeling complicated biochemical dynamics using rule-based models to represent expert knowledge in the context of cell cycle regulation and tumor growth. A notable feature of this modeling approach is that it allows biologists to build complex models from their knowledge base without the need to translate that knowledge into mathematical form. Dynamics on several levels, from molecular pathways to tissue growth, are seamlessly integrated. A number of common network motifs are examined and used to build a model of hedgehog regulation of the cell cycle in cerebellar neurons, which is believed to play a key role in the etiology of medulloblastoma, a devastating childhood brain cancer.

Differential gene expression in pulmonary artery endothelial cells exposed to sickle cell plasma

Clinical variability in sickle cell disease (SCD) suggests a role for extra-erythrocytic factors in the pathogenesis of vasoocclusion. We hypothesized that endothelial cell (EC) dysfunction, one possible modifier of disease variability, results from induction of phenotypic changes by circulating factors. Accordingly, we analyzed gene expression in cultured human pulmonary artery ECs (HPAEC) exposed to plasma from 1) sickle acute chest syndrome (ACS) patients, 2) SCD patients at steady state, 3) normal volunteers, and 4) serum-free media, using whole genome microarrays (U133A-B GeneChip, Affymetrix). Data were analyzed by Bayesian analysis of differential gene expression (BADGE). Differential expression was defined by the probability of >1.5 fold change in signal intensity greater than 0.999 and a predicted score of 70-100, measured by cross-validation. Compared with normal plasma, plasma from SCD patients (steady state) resulted in differential expression of 50 genes in HPAEC. Of these genes, molecules involved in cholesterol biosynthesis and lipid transport, the cellular stress response, and extracellular matrix proteins were most prominent. Another 58 genes were differentially expressed in HPAEC exposed to plasma from ACS patients. The pattern of altered gene expression suggests that plasma from SCD patients induces an EC phenotype which is anti-apoptotic and favors cholesterol biosynthesis. An altered EC phenotype elicited by SCD plasma may contribute to the pathogenesis of sickle vasoocclusion.