Drug screening methods based on deep learning
- 15 November 2022
- conference paper
- Published by SPIE-Intl Soc Optical Eng
- Vol. 12448, 233-239
Abstract
Drug screening is an important step in the development of new drugs. Through appropriate experimental methods and screening models, drugs with specific bioactivity can be transferred from laboratory research to clinical application. Nowadays, traditional efficiency of drug experimentation has been unable to meet the needs of our society. With the rapid development of computer technology, computer-assisted diagnosis and treatment have been gradually accepted and recognized by clinicians and patients. Drug screening process at the cellular level was studied in this paper. We not only compared the advantages and disadvantages of deep learning models and traditional machine learning methods, but also analyzed the performance of different deep learning models. First, Hela cells injected with different anti-stress drugs were divided into groups for experiment. G3BP, TIA-1 and the nucleus were labeled, respectively. The images were obtained using a single-photon microscope. Then, we distinguished the images of Hela cells treated with different drugs through visual observation, traditional machine learning (LBP/Gabor+SVM) and deep learning algorithms (VGGNet, GoogLeNet, ResNext and DenseNet), respectively. Experimental results showed that compared with visual observation, traditional machine learning and deep learning algorithms had better objectivity. Furthermore, deep learning models all had good classification performance. The highest average correct recognition rate was 92.97%, while that of the traditional method was only 80.93%. Therefore, drug screening methods based on deep learning could assist in screening the optimal treatment drugs, which help clinicians choose appropriate therapy.Keywords
This publication has 5 references indexed in Scilit:
- Recent Progress of Deep Learning in Drug DiscoveryCurrent Pharmaceutical Design, 2021
- Comparative analysis of image classification algorithms based on traditional machine learning and deep learningPattern Recognition Letters, 2021
- Rapid prediction of drug inhibition under heat stress: single-photon imaging combined with a convolutional neural networkNanoscale, 2020
- Machine Learning-based Virtual Screening and Its Applications to Alzheimer’s Drug Discovery: A ReviewCurrent Pharmaceutical Design, 2018
- Comparison of Deep Learning With Multiple Machine Learning Methods and Metrics Using Diverse Drug Discovery Data SetsMolecular Pharmaceutics, 2017