A method for high-throughput screening of DNA damage response inhibitors

Abstract

The invention discloses a method for high-throughput screening of DNA damage response inhibitors, comprising the following steps: S1, training a cell nucleus segmentation network model based on a U-Net network; S2, constructing and training a cell nucleus category determination network model; S3. Use a high-content imaging device to photograph the cells subjected to the DNA damage response inhibitor to obtain an image to be analyzed; input the to-be-analyzed image into the cell nucleus segmentation network model, and then input the cell nucleus type determination network model, and count each DNA damage response inhibitor The corresponding proportion of damaged nuclei, the smaller the proportion of damaged nuclei, the better the effect of DNA damage response inhibitor. The method of the present invention can automatically and batchly perform segmentation and classification decisions for images obtained by high-content imaging equipment, and compounds with further research value can be preliminarily screened out through statistical analysis.

Description

technical field [0001] The invention relates to the technical fields of DNA damage, drug screening and deep learning, in particular to a method for high-throughput screening of DNA damage response inhibitors. Background technique [0002] DNA damage is caused when organisms are exposed to various endogenous and exogenous factors such as reactive oxygen species, DNA replication errors, ultraviolet radiation, ionizing radiation, and genotoxic agents. The accumulation of DNA damage has been shown to be closely related to organ aging and cancer development. [0003] Although it is questionable whether inhibiting DNA damage or optimizing the DNA repair process delays aging in humans, evidence suggests that preventing DNA damage and promoting DNA repair are key to age-related diseases, including vascular disease, metabolic disease, neurodegenerative disease therapeutic target. [0004] In addition, DNA damage response inhibitors (DDR) are also useful in the treatment of cancer d...

AI Technical Summary

Problems solved by technology

[0010] FindFoci allows manual training of parameters, but human labeling Foci (focus) is laborious and error-prone, especially in the case of large background noise

In addition, when the cell density is high, there will be some nuclei that adhere to each other, which cannot be well segmented using the above threshold-based segmentation method

Images