BioInformatics on Breast Cancer Treatment using Machine Learning

Challenge Background

Breast Cancer Treatment is still a battle that a lot of women still face today. It began in the 20th century with a rapid expansion in medical knowledge and the advancements seen within multiple areas of medicine. The improvements in surgery, radiotherapy, chemotherapy, and endocrine therapy treatment was preceded by an accumulation of knowledge about the pathologic mechanisms of the disease. There was a surgeon by the name of Thomas Beatson, through his animal models experimentations he observed breast tumours in these animals that regressed after oophorectomy (surgical removal of one or both ovaries; ovariectomy). This project will aim to provide a deeper look at the present treatment of breast cancer and the drugs used in today’s regimens. Subsequently, with the current and future technologies of machine learning and data absorption we may be able to help facilitate better treatment regimens that may lower the spread or even eradicate breast cancer for good. We will use machine learning models to determine what drugs are the most potent with the least amount of product. Also, we will try to see if a model can predict if a woman passes a gene down to their offspring, or if there is a carrier cell that can be removed or if there is a drug that removes the cancer causing properties of that cell.

The Problem

Certain factors increase the risk of breast cancer including increasing age, obesity, harmful use of alcohol, family history of breast cancer, history of radiation exposure, reproductive history (such as age that menstrual periods began and age at first pregnancy), tobacco use and postmenopausal hormone therapy.

In 2022, an estimated 287,850 new cases of invasive breast cancer are expected to be diagnosed in women in the U.S. If we can manage to prevent at least a third of this projected crisis we can begin to move the needle forward. But, it starts with more input and dedicated individuals with the same mind and vision. It is Breast Cancer Awareness Month and I chose this project to remain relevant with the important existent trends in the medical and data fields.

Goal of the Project

1. Analysing the performance of various chemical structures used to develop the right medication.

2. Develop a model that can predict the peak performance of the analyzed chemical structures.

3. Provide insights of past performances of analysed chemical structures.

4. Incur feedback from the Omdena Team on the route of the project.

5. Allow for newly found chemical structures to run through the machine learning model for constant improvements.

6. Show predictions of the portfolio, capabilities of the model and possibilities with further research.

Project Timeline

What you'll learn

1. Collection of Data. 2. Data Cleaning. 3. Data Analysis. 4. Exploring the Data. 5. Data Visualization. 6. Deep Learning of Breast Cancer Drug . 7. Breast Cancer Machine Learning Model Deployment for Review