Using Machine Learning to Model Cancer in The Human Genome

Team: 5

School: Taos High

Area of Science: Biology


Proposal: Current methods of predicting and diagnosing cancer based on genomic data are inefficient and inaccurate. Currently there is no truly adequate method of cataloging and modeling the vast amount of research into cancer and its markers within the human genome. A tool to accurately catalog and model genetic causes of cancer would allow for quicker diagnosis and treatment of the terminal disease. We hope that our model will be able to accurately depict a person's risk of cancer based on their genome. We plan to source accurate data on the genetic causes of cancer. We will use this data and machine learning techniques to train a model to find patterns and make predictions on the risks of cancer in an individual’s genome. The main challenge will be sourcing accurate data to ensure that our model is as accurate as possible. We intend to implement our model in Python using preexisting machine learning libraries.


Team Members:

  Haven Hennelly
  Sawyer Solfest
  Max Meadowcroft

Sponsoring Teacher: Tracy Galligan

Mail the entire Team