Skip to content

Prediction of transcription factor binding based on DNA sequence

Notifications You must be signed in to change notification settings

ScienceMoo/DNA_structure_ML

Repository files navigation

Prediction of transcription factor binding based on DNA sequence

Machine learning notebooks

MATLAB for pre-processing the data

  • main.mlx Get all the binding and non-binding sites for a particular TF, includes figures and instructions throughout
    • predict_positions.m Function that takes as input a full chromosome sequence, a PWM and a score threshhold and returns the positions of all the regions from that sequence that have a score above the threshhold.
      • get_score.m Function that returns the score for a possible binding sequence given a PWM.
    • check_found.m Filter the sequences into binding and not binding
  • getTFsequences.mlx Get all the actual binding sequences for a particular transcription factor and analyze them.
  • calculate_shapes.mlx Calulate DNA physical shape using pentamer method

Data Sources

About

Prediction of transcription factor binding based on DNA sequence

Topics

Resources

Stars

Watchers

Forks

Languages