Sharif Digital Repository

Cancer is a life-threatening group of diseases that arises from the uncontrolled growth and division of cells in the body. Treatment options for cancer include surgery, chemotherapy, radiation therapy, immunotherapy, targeted therapy, and hormone therapy. However, resistance to anticancer drugs can develop through a variety of mechanisms, such as the upregulation of drug efflux pumps and alterations in DNA repair mechanisms. One common mechanism of drug resistance is through changes in metabolism, where cancer cells switch to alternative metabolic pathways to survive and evade the effects of anticancer drugs. The development of new drugs targeting specific molecules and pathways involved in... 

Nowadays, chemotherapy is one of the common ways to treat cancer. Although, chemotherapy is used to kill cancer cells , chemotherapy drugs also target healthy cells and tissues of the body. In practice, it is difficult to strike a balance between injectable doses of drugs and toxicity in the body, and physicians are always looking for an effective treatment plan. One of the most common drugs that physicians use in chemotherapy is cell-cycle-specific drugs. These types of chemotherapy drugs affect only a certain phase of cell cycle and to a certain extent. Since the lifetime of the cancer cells is uncertain, the effective use of these drugs depends on the correct injection time of the drugs... 

In this study, we aim to learn representations from microscopic cell images that effectively capture the features of drugs affecting the cells, allowing us to identify effective drugs for treating a disease. We employ two parallel learning paths using predictive and generative models. Specifically, we have achieved a predictive model on the RxRx19a dataset that, unlike previous models, is interpretable, optimized, and robust to dras- tic changes in drug properties. Additionally, we have developed the first generative model on this dataset, which not only generates high-quality images but also discovers a meaningful latent space. This latent space divides the representation into relevant...