| Proj No. | A3205-251 |
| Title | Developing a Deep Learning Model for Predicting Antibiotic Mechanisms Using Bacterial Cytological Profiles |
| Summary | This project aims to develop a deep learning model capable of predicting the mechanisms of action (MOA) of antibiotics by analyzing bacterial cytological profiles. Building upon the methodology described by Nonejuie et al. in "Bacterial cytological profiling rapidly identifies the cellular pathways targeted by antibacterial molecules" (Proceedings of the National Academy of Sciences, vol. 110, no. 46, pp. 18549–18554, 2013), the student will utilize high-content imaging data to train a convolutional neural network (CNN) that can classify antibiotics based on their induced morphological changes in bacterial cells. The dataset for this project is available at https://www.pnas.org/doi/10.1073/pnas.1311066110. The student will preprocess the images, augment the data to enhance model robustness, and fine-tune the CNN architecture to achieve high classification accuracy. The outcome will be a validated model that can assist in the rapid identification of antibiotic MOAs, potentially accelerating the drug discovery process. |
| Supervisor | A/P Wang Lipo (Loc:S1 > S1 B1C > S1 B1C 98, Ext: +65 67906372) |
| Co-Supervisor | - |
| RI Co-Supervisor | - |
| Lab | Computer Engineering I (Loc: S2-B4c-15) |
| Single/Group: | Single |
| Area: | Digital Media Processing and Computer Engineering |
| ISP/RI/SMP/SCP?: |