Multiparameter immune profiling of operational tolerance in liver transplantation.

Immunosuppressive drugs can be completely withdrawn in up to 20% of liver transplant recipients, commonly referred to as 'operationally' tolerant. Immune characterization of these patients, however, has not been performed in detail, and we lack tests capable of identifying tolerant patients among recipients receiving maintenance immunosuppression. In the current study we have analyzed a variety of biological traits in peripheral blood of operationally tolerant liver recipients in an attempt to define a multiparameter 'fingerprint' of tolerance. Thus, we have performed peripheral blood gene expression profiling and extensive blood cell immunophenotyping on 16 operationally tolerant liver recipients, 16 recipients requiring on-going immunosuppressive therapy, and 10 healthy individuals. Microarray profiling identified a gene expression signature that could discriminate tolerant recipients from immunosuppression-dependent patients with high accuracy. This signature included genes encoding for gammadelta T-cell and NK receptors, and for proteins involved in cell proliferation arrest. In addition, tolerant recipients exhibited significantly greater numbers of circulating potentially regulatory T-cell subsets (CD4+ CD25+ T-cells and Vdelta1+ T cells) than either non-tolerant patients or healthy individuals. Our data provide novel mechanistic insight on liver allograft operational tolerance, and constitute a first step in the search for a non-invasive diagnostic signature capable of predicting tolerance before undergoing drug weaning.

Gene expression changes in peripheral blood cells provide insight into the biological mechanisms associated with regimen-related toxicities in patients being treated for head and neck cancers.

UNLABELLED: Patients treated with radiotherapy are prone to a constellation of local and systemic toxicities including mucositis, xerostomia, fatigue and anorexia. The biological complexities and similarities underlying the development of toxicities have recently been realized. Mucosal barrier injury is one of the best studied, and gene expression patterns, based on animal tissue samples, have added to its understanding. While investigations gene expression based on tissue samples was valuable, its use precludes more generalizable conclusions relative to common pathogenic mechanisms. Additionally, attempting to define the kinetics of changes in gene expression by sequential sampling is pragmatically unrealistic. Our objectives were: 1. to determine if changes in gene expression could be detected during toxicity development using PBM from patients receiving chemoradiation; 2. to characterize the relationship of expressed genes using graph theory and pathway analysis; and 3. to evaluate potential relationships between the expression of particular genes, canonical pathways, and functional networks in explaining the pathogenesis of regimen-related toxicities. DESIGN: Microarray analysis was performed using PBM-derived cRNA obtained before and 2 weeks after the initiation of chemoradiation in five patients with head and neck cancer who developed documented regimen-related toxicities. We created a database of those genes newly expressed at 2 weeks and evaluated their potential significance relative to toxicity, by canonical pathway analysis, compilation of regional networks around focus genes, and development of a model globalizing the individual functional networks. There was strong concordance between known pathogenic mechanisms of toxicity and the genes, pathways, and networks developed by our data. A role was elicited for unsuspected genes in toxicity development. Our results support the concept that radiation induced toxicities have common underlying mechanisms and demonstrate the utility of PBM as an RNA source for genetic studies. This methodology could be broadly applicable to the study of regimen-related toxicities.

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

With the completion of the Human Genome Project and the growing computational challenges presented by the large amount of genomic data available today, machine learning is becoming an integral part of biomedical research and plays a major role in the emerging fields of bioinformatics and computational biology. This situation offers unparalleled opportunities and unprecedented challenges to machine learning research in general and to Bayesian learning methods in particular. This paper outlines some of the opportunities and the challenges of this endeavor, it describes where the efforts of "cracking the code of life" can most benefit from a Bayesian approach, and it identifies some potential applications of Bayesian machine learning methods to the genomic analysis of squamous cell carcinomas of the head and neck.

Robust outcome prediction for intensive-care patients.

Missing data are a major plague of medical databases in general, and of Intensive Care Unit databases in particular. The time pressure of work in an Intensive Care Unit pushes the physicians to omit randomly or selectively record data. These different omission strategies give rise to different patterns of missing data and the recommended approach of completing the database using median imputation and fitting a logistic regression model can lead to significant biases. This paper applies a new classification method, called robust Bayes classifier, which does not rely on any particular assumption about the pattern of missing data and compares it to the median imputation approach using a database of 324 Intensive Care Unit patients.

An ignorant belief network to forecast glucose concentration from clinical databases.

Ignorant Belief Networks (IBNs) are a class of Bayesian Belief Networks (BBNs) able to reason on the basis of incomplete probabilistic information and to incrementally refine the precision of the inferred probabilities as more information becomes available. In this paper, we will describe how can be used to develop a system able to forecast blood glucose concentration in patients affected by insulin dependent diabetes mellitus (IDDM). The major difference between our approach and the traditional ones is that probability distributions over the IBN are not provided by some human expert or by the current literature but they are directly extracted from a clinical database of IDDM patients. This choice capitalizes on the large amount of information generated by the daily control of blood glucose and allows the system to improve the accuracy of predictions as more information becomes available. We will show how, even with a very small subset of the information needed to specify a BBN, the IBN is able to carry out predictions about the future blood glucose concentration in a patient by explicitly taking into consideration the level of ignorance embedded in the network.