Dataset Information

Predicting relapse prior to transplantation in chronic myeloid leukemia by integrating expert knowledge and expression data.

ABSTRACT: Selecting a small number of signature genes for accurate classification of samples is essential for the development of diagnostic tests. However, many genes are highly correlated in gene expression data, and hence, many possible sets of genes are potential classifiers. Because treatment outcomes are poor in advanced chronic myeloid leukemia (CML), we hypothesized that expression of classifiers of advanced phase CML when detected in early CML [chronic phase (CP) CML], correlates with subsequent poorer therapeutic outcome.We developed a method that integrates gene expression data with expert knowledge and predicted functional relationships using iterative Bayesian model averaging. Applying our integrated method to CML, we identified small sets of signature genes that are highly predictive of disease phases and that are more robust and stable than using expression data alone. The accuracy of our algorithm was evaluated using cross-validation on the gene expression data. We then tested the hypothesis that gene sets associated with advanced phase CML would predict relapse after allogeneic transplantation in 176 independent CP CML cases. Our gene signatures of advanced phase CML are predictive of relapse even after adjustment for known risk factors associated with transplant outcomes.

SUBMITTER: Yeung KY

PROVIDER: S-EPMC3307121 | biostudies-literature | 2012 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predicting relapse prior to transplantation in chronic myeloid leukemia by integrating expert knowledge and expression data.

Yeung K Y KY Gooley T A TA Zhang A A Raftery A E AE Radich J P JP Oehler V G VG

Bioinformatics (Oxford, England) 20120131 6

<h4>Motivation</h4>Selecting a small number of signature genes for accurate classification of samples is essential for the development of diagnostic tests. However, many genes are highly correlated in gene expression data, and hence, many possible sets of genes are potential classifiers. Because treatment outcomes are poor in advanced chronic myeloid leukemia (CML), we hypothesized that expression of classifiers of advanced phase CML when detected in early CML [chronic phase (CP) CML], correlate ...[more]

PMID: 22296787

Similar Datasets

Project description:Regardless of line of therapy, treatment goals in chronic phase chronic myeloid leukemia (CML) are: avoid progression to accelerated phase or blast crisis CML such that patients achieve a life expectancy comparable with that of the general population; avoid adverse events (AEs); and restore and maintain quality of life. The most important prognostic factor for achieving these goals is response to tyrosine kinase inhibitors (TKIs) at key milestones. For patients failing a TKI, a treatment change is mandatory to limit the risk of progression and death. There is currently no precise guideline for patients that fail a second-generation TKI, and there is a paucity of data to guide clinical decision making in this setting. There is, therefore, an unmet need for practical and actionable guidance on how to manage patients who fail a second-generation TKI. Although the term 'failure' includes patients failing for resistance or intolerance, the focus of this paper is failure of a second-generation TKI because of resistance. CML patients who fail their first second-generation TKI for true resistance need a more potent therapy. In these patients, the key issues to consider are the relative appropriateness of early allogeneic hematopoietic stem cell transplantation or the use of a further TKI. Selection of the next line of treatment after second-generation TKI resistance should be individualized and must be based on patient-specific factors including cytogenetics, mutation profile, comorbidities, age, previous history of AEs with prior TKI therapy, and risk profile for AEs on specific TKIs. This expert opinion paper is not in conflict with existing recommendations, but instead represents an evolution of previous notions, based on new data, insights, and clinical experience. We review the treatment options for patients resistant to second-generation TKI therapy and provide our clinical opinions and guidance on key considerations for treatment decision making.

Dataset Information

Predicting relapse prior to transplantation in chronic myeloid leukemia by integrating expert knowledge and expression data.

Publications

Predicting relapse prior to transplantation in chronic myeloid leukemia by integrating expert knowledge and expression data.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets