Dataset Information

Consistent quantitative gene product expression: #1. Automated identification of regenerating bone marrow cell populations using support vector machines.

ABSTRACT: Identification and quantification of maturing hematopoietic cell populations in flow cytometry data sets is a complex and sometimes irreproducible step in data analysis. Supervised machine learning algorithms present promise to automatically classify cells into populations, reducing subjective bias in data analysis. We describe the use of support vector machines (SVMs), a supervised algorithm, to reproducibly identify two distinctly different populations of normal hematopoietic cells, mature lymphocytes and uncommitted progenitor cells, in the challenging setting of pediatric bone marrow specimens obtained 1 month after chemotherapy. Four-color flow cytometry data were collected on a FACS Calibur for 77 randomly selected postchemotherapy pediatric patients enrolled on the Children's Oncology Group clinical trial AAML1031. These patients demonstrated no evidence of detectable residual disease and were divided into training (n?=?27) and testing (n?=?50) cohorts. SVMs were trained to identify mature lymphocytes and uncommitted progenitor cells in the training cohort before independent evaluation of prediction efficiency in the testing cohort. Both SVMs demonstrated high predictive performance (lymphocyte SVM: sensitivity >0.99, specificity >0.99; uncommitted progenitor cell SVM: sensitivity?=?0.94, specificity >0.99) and closely mirrored manual cell classifications by two expert-analysts. SVMs present an efficient, automated methodology for identifying normal cell populations even in stressed bone marrows, replicating the performance of an expert while reducing the intrinsic bias of gating procedures between multiple analysts. © 2016 The Authors. Cytometry Part A published by Wiley Periodicals, Inc. on behalf of ISAC.

SUBMITTER: Voigt AP

PROVIDER: S-EPMC5132084 | biostudies-literature | 2016 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Consistent quantitative gene product expression: #1. Automated identification of regenerating bone marrow cell populations using support vector machines.

Voigt Andrew P AP Eidenschink Brodersen Lisa L Pardo Laura L Meshinchi Soheil S Loken Michael R MR

Cytometry. Part A : the journal of the International Society for Analytical Cytology 20160714 11

Identification and quantification of maturing hematopoietic cell populations in flow cytometry data sets is a complex and sometimes irreproducible step in data analysis. Supervised machine learning algorithms present promise to automatically classify cells into populations, reducing subjective bias in data analysis. We describe the use of support vector machines (SVMs), a supervised algorithm, to reproducibly identify two distinctly different populations of normal hematopoietic cells, mature lym ...[more]

PMID: 27416291

Similar Datasets

Project description:Five reference populations in bone marrow specimens were identified by flow cytometry using specific combinations of reagents in order define the variation of gene product expression intensities both within and between individuals. Mature lymphocytes, uncommitted progenitor cells, promyelocytes, mature monocytes and mature neutrophils can be reproducibly identified as distinct clusters of events in heterogeneous, maturing bone marrow specimens. Support Vector Machines were used to identify the reference populations in order to reduce subjective bias in manually defining boundaries of these populations since they were not discretely separated from the remainder of the cells. Reference populations were identified in 50 randomly selected bone marrow aspirates obtained over a period spanning 3 years and 6 months from pediatric patients following chemotherapy for acute myeloid leukemia (AML). The quantitative expression of gene products (cell surface antigens) and light scattering characteristics on these stressed specimens were demonstrated to be tightly regulated both within individuals and between individuals. Within an individual most gene products (CD45, CD34, CD14, CD16, CD64, CD33) demonstrated limited variability with a standard deviation of <0.20 log units while CD13 and CD36 exhibited broader variation >0.25 log units. Surprisingly, with the exception of CD33, the variation of the mean intensities of each antigen between individuals was even less than the variation within an individual. These data confirm that the amounts of gene products expressed on normal developing cells are highly regulated but differ in intensities between different lineages and during the maturational pathway of those lineages. The amounts of gene products expressed at specific stages of development of each lineage are a biologic constant with minimal variation within or between individuals. © 2016 The Authors. Cytometry Part A Published by Wiley Periodicals, Inc. on behalf of ISAC.

Project description:BACKGROUND:While the genomes of hundreds of organisms have been sequenced and good approaches exist for finding protein encoding genes, an important remaining challenge is predicting the functions of the large fraction of genes for which there is no annotation. Large gene expression datasets from microarray experiments already exist and many of these can be used to help assign potential functions to these genes. We have applied Support Vector Machines (SVM), a sigmoid fitting function and a stratified cross-validation approach to analyze a large microarray experiment dataset from Drosophila melanogaster in order to predict possible functions for previously un-annotated genes. A total of approximately 5043 different genes, or about one-third of the predicted genes in the D. melanogaster genome, are represented in the dataset and 1854 (or 37%) of these genes are un-annotated. RESULTS:39 Gene Ontology Biological Process (GO-BP) categories were found with precision value equal or larger than 0.75, when recall was fixed at the 0.4 level. For two of those categories, we have provided additional support for assigning given genes to the category by showing that the majority of transcripts for the genes belonging in a given category have a similar localization pattern during embryogenesis. Additionally, by assessing the predictions using a confidence score, we have been able to provide a putative GO-BP term for 1422 previously un-annotated genes or about 77% of the un-annotated genes represented on the microarray and about 19% of all of the un-annotated genes in the D. melanogaster genome. CONCLUSIONS:Our study successfully employs a number of SVM classifiers, accompanied by detailed calibration and validation techniques, to generate a number of predictions for new annotations for D. melanogaster genes. The applied probabilistic analysis to SVM output improves the interpretability of the prediction results and the objectivity of the validation procedure.

Dataset Information

Consistent quantitative gene product expression: #1. Automated identification of regenerating bone marrow cell populations using support vector machines.

Publications

Consistent quantitative gene product expression: #1. Automated identification of regenerating bone marrow cell populations using support vector machines.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure