Gating mass cytometry data by deep learning

Li, Huamin; Shaham, Uri; Stanton, Kelly P.; Yao, Yi; Montgomery, Ruth R.; Kluger, Yuval

doi:10.1093/bioinformatics/btx448

Cited by 89 publications

(117 citation statements)

References 28 publications

Supporting

Mentioning

115

Contrasting

Order By: Relevance

“…In recent years, deep learning methods have showed impressive performance in various applications, such as image analysis, natural language processing, and pattern recognition . Deep learning typically requires very large numbers of training instances.…”

Section: Cell Population Identificationmentioning

confidence: 99%

“…Deep learning typically requires very large numbers of training instances. In each FCM experiment, approximately 10 5 ‐10 6 cells are collected, so that the number of instances (cells or events inside one sample) is several times higher than the number of explanatory variables . In other words, deep learning algorithms perform well with huge multidimensional datasets that are datasets characterized by a high number of events and a high number of markers.…”

Section: Cell Population Identificationmentioning

confidence: 99%

See 1 more Smart Citation

Flow cytometry data analysis: Recent tools and algorithms

Montante

Brinkman

2019

Int J Lab Hematology

View full text Add to dashboard Cite

Flow cytometry (FCM) allows scientists to rapidly quantify up to 50 parameters for millions of cells per sample. The bottleneck in the application of the technology is data analysis, and the high number of parameters measured by the current generation of instruments requires the use of advanced computational algorithms to make full use of their capabilities. This review summarizes the main steps of FCM data analysis, focusing on the use of the most recent bioinformatic tools developed for an R‐based programming environment. In particular, for each stage of the data analysis, libraries and packages currently available are listed, and a brief description of their functioning is included.

show abstract

Section: Cell Population Identificationmentioning

confidence: 99%

Section: Cell Population Identificationmentioning

confidence: 99%

Flow cytometry data analysis: Recent tools and algorithms

Montante

Brinkman

2019

Int J Lab Hematology

View full text Add to dashboard Cite

show abstract

“…High F-measure values have been reported by Li et al(25) who proposed a deep learning algorithm, DeepCyTOF; these values, however, are not comparable to those of unsupervised algorithms; in a very recent paper, Lux et al(26) report rather modest F-measure values for DeepCyTOF. High F-measure values have been reported by Li et al(25) who proposed a deep learning algorithm, DeepCyTOF; these values, however, are not comparable to those of unsupervised algorithms; in a very recent paper, Lux et al(26) report rather modest F-measure values for DeepCyTOF.…”

mentioning

confidence: 94%

cytometree: A binary tree algorithm for automatic gating in cytometry analysis

et al. 2018

View full text Add to dashboard Cite

Flow cytometry is a powerful technology that allows the high-throughput quantification of dozens of surface and intracellular proteins at the single-cell level. It has become the most widely used technology for immunophenotyping of cells over the past three decades. Due to the increasing complexity of cytometry experiments (more cells and more markers), traditional manual flow cytometry data analysis has become untenable due to its subjectivity and time-consuming nature. We present a new unsupervised algorithm called "cytometree" to perform automated population identification (aka gating) in flow cytometry. cytometree is based on the construction of a binary tree, the nodes of which are subpopulations of cells. At each node, the marker distributions are modeled by mixtures of normal distributions. Node splitting is done according to a model selection procedure based on a normalized difference of Akaike information criteria between two competing models. Post-processing of the tree structure and derived populations allows us to complete the annotation of the populations. The algorithm is shown to perform better than the state-of-the-art unsupervised algorithms previously proposed on panels introduced by the Flow Cytometry: Critical Assessment of Population Identification Methods project. The algorithm is also applied to a T-cell panel proposed by the Human Immunology Project Consortium (HIPC) program; it also outperforms the best unsupervised open-source available algorithm while requiring the shortest computation time. © 2018 International Society for Advancement of Cytometry

show abstract

“…Data were generated using DuraClone's dry reagent technology (Beckman Coulter) preformatted panel antibody cocktails. Machine learning holds the promise of reducing the time required to parameterize supervised algorithms (20,21). In addition, we compared the reference manual values with those obtained by two additional manual analyzers who followed an identical gating strategy.…”

mentioning

confidence: 99%

Improving the Rigor and Reproducibility of Flow Cytometry‐Based Clinical Research and Trials Through Automated Data Analysis

Brinkman

2019

Cytometry Pt A

View full text Add to dashboard Cite

The steps that characterize data analysis for flow cytometrybased clinical trials can be grouped into quality assessment, compensation, normalization, transformation, cell population identification, cross-sample comparison (population mapping or matching), feature extraction, visualization, and interpretation. Of these steps, cell population identification (i.e., gating), which generates reportables such as cell population counts/percentages and MFI, is the focus of significant efforts to improve the rigor and reproducibility of data analysis. Here, rigor is the application of the scientific method to ensure unbiased and well-controlled analysis, interpretation, and reporting of results. Reproducibility is important as analyses are only validated when they can be duplicated by multiple scientists. It is especially important for clinical studies due to what has been deemed a reproducibility crisis in medicine, as only 11% of a series of preclinical cancer studies could be replicated (1).While manual gating is the gold standard and current practice for cell population identification, assessments of its reproducibility have recognized it as a significant contributor of variation in flow cytometry studies, with interlaboratory C.V.s up to 30% (2). While having a single operator analyze all the data can significantly reduce variability, the chosen individual is still influenced by the same personal biases that result in inconsistencies within and across individuals, centers, and time. Resorting to a single operator to improve reproducibility does not scale for large studies as manual gating can take from 45 to 90 min for one clinical sample (3). With clinical trials now involving thousands of patients assayed with 18 parameters, the challenges associated with the rigor and reproducibility of manual analysis of flow cytometry-based clinical data have only become more apparent and pressing.The first algorithm for automated flow cytometry cell population identification was published in 1985, where it was noted that: "Unfortunately, the use of three or more independent fluorescent parameters complicates the analysis of the resulting data significantly" (4). While data complexity has increased significantly since then, automated analysis approaches for flow cytometry data have also matured. The state of the art is at a stage where results from automated data analysis algorithms have reached a level of maturity that enables them to match, and in many cases exceed, the results produced by human experts. The maturity and acceptance has gone as far as being included as part of the documentation for the FDA approval of a first in class CAR-T therapy (5-7).The overwhelming majority of automated gating methods are unsupervised. Unsupervised algorithms are those approaches that work on data that do not come with predefined labels. With respect to FCM data, these algorithms

show abstract

Gating mass cytometry data by deep learning

Abstract: Supplementary data are available at Bioinformatics online.

Cited by 89 publications

References 28 publications

Flow cytometry data analysis: Recent tools and algorithms

Flow cytometry data analysis: Recent tools and algorithms

cytometree: A binary tree algorithm for automatic gating in cytometry analysis

Improving the Rigor and Reproducibility of Flow Cytometry‐Based Clinical Research and Trials Through Automated Data Analysis

Contact Info

Product

Resources

About