A fast and accurate high-throughput drug screening system based on deep learning

Abstract

The invention discloses a fast, accurate and high-throughput drug screening system based on deep learning. The drug screening system includes a picture preprocessing module and a neural network module. The picture preprocessing module includes a channel combining module and a picture standardization module; channel combining The module merges different cell single-color channel pictures into a multi-channel picture representation, and the combined picture tensor is expressed as [H, W, C]; the picture normalization module normalizes the input multi-channel picture data to [70, 70, C ] tensor representation; the neural network module undertakes the picture standardization module, and its input data is a standardized picture tensor, and the final prediction and classification judgment is obtained through the trained neural network. The deep learning-based drug screening system DeepScreen established by the present invention has the advantages of high throughput, precision, high efficiency, fast and convenient, low cost and anti-interference, and has a promising practical application prospect.

Description

technical field [0001] The invention relates to the technical field of biomedicine, specifically, a fast, accurate and high-throughput drug screening system based on deep learning. Background technique [0002] According to statistics, it takes 10-14 years and more than 200 million U.S. dollars for each new drug to go on the market, from testing to marketing. How to speed up the discovery and testing of new drugs has always been the key and difficulty in accelerating the drug R&D stage. In recent years, the development of biochemistry, physiopathology and other disciplines has provided new means of drug screening, and some drug screening models at the molecular and cellular level have emerged, and with the development of more advanced detection technology, automation technology and computer technology, In the late 1990s, a high throughput screening technology (High throughput screening, HTS) was developed. HTS mainly relies on automated operating systems, namely laboratory ...

AI Technical Summary

Problems solved by technology

Chinese patent 2017101273955 discloses an intelligent lead compound discovery method based on convolutional neural network, which solves the problems of low efficiency and low accuracy of virtual screening of lead compounds. This method first converts the compound structural formula into a plane picture, and performs black and white and Inverse color processing, all pictures are classified according to the activity properties of the compound and digitally labeled according to the category, and input into the system; select a part of the pictures as the training set for the convolutional neural network to perform deep learning on the classification problem, and the rest as the test set to evaluate the model; After the learning is completed, input the same processed pictures other than the training set and the test set for the system to calculate and predict the probability of its corresponding active attribute

However, in the prior art, there is no report about the fast and accurate high-throughput drug screening system based on deep learning of the present invention.

Images