Welcome to Part 2 of ExploreInformatics! In this project, you will train and test a hidden markov model to detect motif occurrences in a sequence.
Setup
Before starting this portion of the assignment, enter your cs181-projects24 directory and run git pull. This will pull the necessary scripts and support files for this assignment into your directory. Then enter the cs1810 docker container by running ./run-docker. All of the packages needed for this application should already be embedded into the Docker image.
All of the code for this project can be found in the motif_hmm directory in the cs181-user directory. Everything you will need to complete this assignment can be found within that folder.
In particular, you will implement some minor preprocessing of the data we have given you in preprocessing.py. From here, you will implement the training and testing of your HMMs in hmm_traintest.py. Finally, you will make minor edits to explore_hmm.py and run the script to see the results of your implementations (i.e., explore_hmm.py is where you will actually call the functions in the other two files).
:::danger