Material Detail

Prediction of DNA-binding proteins from structural features

Prediction of DNA-binding proteins from structural features

This video was recorded at 4th International Workshop on Machine Learning in Systems Biology (MLSB), Edinburgh 2010. We use logic-based machine learning to distinguish DNAbinding proteins from non-binding proteins. We combine previously suggested coarse-grained features (such as the dipole moment) with automatically constructed structural (spatial) features. Prediction based only on structural features already improves on the state-of-the-art predictive accuracies achieved in previous work with coarse-grained features. Accuracies are further improved when the combination of both feature categories is used. An important factor contributing to accurate prediction is that structural features are not Boolean but rather interpreted by counting the number of their occurences in a learning example.


  • User Rating
  • Comments
  • Learning Exercises
  • Bookmark Collections
  • Course ePortfolios
  • Accessibility Info

More about this material


Log in to participate in the discussions or sign up if you are not already a MERLOT member.