Dataset Information

Feature genes predicting the FLT3/ITD mutation in acute myeloid leukemia.

ABSTRACT: In the present study, gene expression profiles of acute myeloid leukemia (AML) samples were analyzed to identify feature genes with the capacity to predict the mutation status of FLT3/ITD. Two machine learning models, namely the support vector machine (SVM) and random forest (RF) methods, were used for classification. Four datasets were downloaded from the European Bioinformatics Institute, two of which (containing 371 samples, including 281 FLT3/ITD mutation-negative and 90 mutation?positive samples) were randomly defined as the training group, while the other two datasets (containing 488 samples, including 350 FLT3/ITD mutation-negative and 138 mutation-positive samples) were defined as the test group. Differentially expressed genes (DEGs) were identified by significance analysis of the microarray data by using the training samples. The classification efficiency of the SCM and RF methods was evaluated using the following parameters: Sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and the area under the receiver operating characteristic curve. Functional enrichment analysis was performed for the feature genes with DAVID. A total of 585 DEGs were identified in the training group, of which 580 were upregulated and five were downregulated. The classification accuracy rates of the two methods for the training group, the test group and the combined group using the 585 feature genes were >90%. For the SVM and RF methods, the rates of correct determination, specificity and PPV were >90%, while the sensitivity and NPV were >80%. The SVM method produced a slightly better classification effect than the RF method. A total of 13 biological pathways were overrepresented by the feature genes, mainly involving energy metabolism, chromatin organization and translation. The feature genes identified in the present study may be used to predict the mutation status of FLT3/ITD in patients with AML.

SUBMITTER: Li C

PROVIDER: S-EPMC4918602 | biostudies-literature | 2016 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Feature genes predicting the FLT3/ITD mutation in acute myeloid leukemia.

Li Chenglong C Zhu Biao B Chen Jiao J Huang Xiaobing X

Molecular medicine reports 20160512 1

In the present study, gene expression profiles of acute myeloid leukemia (AML) samples were analyzed to identify feature genes with the capacity to predict the mutation status of FLT3/ITD. Two machine learning models, namely the support vector machine (SVM) and random forest (RF) methods, were used for classification. Four datasets were downloaded from the European Bioinformatics Institute, two of which (containing 371 samples, including 281 FLT3/ITD mutation-negative and 90 mutation‑positive sa ...[more]

PMID: 27177049

Similar Datasets

Project description:Acute myeloid leukemia (AML) is an aggressive hematologic malignancy which is cured in a minority of patients. A FLT3-internal tandem duplication (ITD) mutation, found in approximately a quarter of patients with de novo AML, imparts a particularly poor prognosis. Patients with FLT3-ITD AML often present with more aggressive disease and have a significantly higher propensity for relapse after remission. The therapeutic approach for these patients has traditionally included intensive induction chemotherapy, followed by consolidative chemotherapy or hematopoietic cell transplantation (HCT). In recent years, multiple small molecule inhibitors of the FLT3 tyrosine kinase have been studied preclinically and in clinical trials. The earlier generation of these agents, often non-specific and impacting a variety of tyrosine kinases, produced at best transient peripheral blood responses in early clinical trials. Additionally, the combination of FLT3 inhibitors with cytotoxic regimens has not, as of yet, demonstrated an improvement in overall survival. Nevertheless, multiple current trials, including those with sorafenib, lestaurtinib, and midostaurin, continue to study the combination of FLT3 inhibitors with standard chemotherapy. Factors such as sustained FLT3 inhibition, protein binding, pharmacokinetics, and the presence of elevated FLT3-ligand levels appear to significantly impact the potency of these agents in vivo. In recent years, the development of more specific and potent agents has generated hope that FLT3 inhibitors may play a more prominent role in the treatment of FLT3-ITD AML in the near future. Nevertheless, questions remain regarding the optimal timing and schedule for incorporation of FLT3 inhibitors. The suitability, type, and timing of allogeneic HCT in the therapeutic approach for these patients are also issues which require further study and definition. Recent retrospective data appears to support the efficacy of allogeneic HCT in first complete remission, possibly due to a graft versus leukemia effect. However, larger prospective studies are necessary to further elucidate the role of HCT and its potential combination with FLT3 inhibitor therapy. We are hopeful that current clinical investigation will lead to an optimization and improvement of outcomes for these patients.

Dataset Information

Feature genes predicting the FLT3/ITD mutation in acute myeloid leukemia.

Publications

Feature genes predicting the FLT3/ITD mutation in acute myeloid leukemia.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets