International journal of radiation biology · 2025
Application of an imaging flow cytometry γ-H2AX assay for biodosimetry using supervised machine learning.
СтатьяНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Hassan Eman M, Puzantian Benjamin, Mayenburg Jessica M, Li Melody, Rashid Mehreen, Wilkins Ruth C, Beaton-Green Lindsay A
Аннотация
PURPOSE: Phosphorylation of the histone H2AX (γ-H2AX) is a rapid response to radiation-induced DNA double strand breaks (DSBs) and is a good biomarker for exposure to ionizing radiation. The signal has traditionally been detected by microscopy (spot counting) or by flow cytometry (fluorescent intensity). An imaging flow cytometry (IFC) method has been developed, which combines the high resolution of microscopy with the statistical power of flow cytometry methods to measure γ-H2AX in human lymphocytes.
MATERIALS AND METHODS: The assay was optimized and validated for both sample acquisition and data analysis, in the dose range of 0-10 Gy. For data analysis, mean fluorescence intensity (MFI), spot count (foci per cell), and average area of the spots were used with the supervised machine learning (SML) K-Nearest Neighbors (K-NN) algorithm to estimate doses. These dose estimates were compared to the traditional flow cytometry method of estimating doses from an MFI-based dose response curve.
RESULTS: A statistical analysis of both methodologies showed that SML K-NN method was able to determine the dose delivered to blind, irradiated samples more accurately than when using a linear fit of the MFI response alone, especially in the 7-10 Gy dose range.
CONCLUSIONS: The efficiency of the γ-H2AX-IFC assay, 1 hour post-exposure, has been improved and validated using the SML K-NN methodology for dose estimation. This study could help establish the γ-H2AX assay as a triage tool for the rapid screening of a large number of samples.
MATERIALS AND METHODS: The assay was optimized and validated for both sample acquisition and data analysis, in the dose range of 0-10 Gy. For data analysis, mean fluorescence intensity (MFI), spot count (foci per cell), and average area of the spots were used with the supervised machine learning (SML) K-Nearest Neighbors (K-NN) algorithm to estimate doses. These dose estimates were compared to the traditional flow cytometry method of estimating doses from an MFI-based dose response curve.
RESULTS: A statistical analysis of both methodologies showed that SML K-NN method was able to determine the dose delivered to blind, irradiated samples more accurately than when using a linear fit of the MFI response alone, especially in the 7-10 Gy dose range.
CONCLUSIONS: The efficiency of the γ-H2AX-IFC assay, 1 hour post-exposure, has been improved and validated using the SML K-NN methodology for dose estimation. This study could help establish the γ-H2AX assay as a triage tool for the rapid screening of a large number of samples.