Inspiration
I did a lot of research in high school about cancer and genomics, but never got the opportunity to relate the two. I had done some work trying to link the two, mainly identifying trends in cancer patients, but I wanted to build a machine learning algorithm that could train and test data with breast cancer patients.
What it does
My algorithm takes a data set containing both breast cancer patients and healthy patients (0 is healthy and 1 is unhealthy) and their genome counts of various genomes. I then use 80% of the data to train the algorithms (Support Vector Machine, K-Nearest Neighbors, Decision Tree, and Naive Bayes), select the algorithm with the best accuracy, and then display the results of the best algorithm.
How we built it
I utilized sklearn to import all of the algorithms and then coded the terminal to outputs of the training, and then used a heatmap to visualize the data.
Challenges we ran into
I had a lot of trouble using Python, because I had very little prior Python experience.
Accomplishments that we're proud of
I'm happy I got a better grasp on Python as well as Machine Learning Algorithms!
What we learned
I learned how to use Python as well as various Machine Learning Algorithms.
What's next for Determining the best ML Algorithm for Breast Cancer patients
Make a User Interface that allows the User to interact with and see the results more directly.
Log in or sign up for Devpost to join the conversation.