piaco(Protein Interface Analysis using COvarying signals) is a statistical classifier model for interfaces in protein crystals. Currently, piaco utilizes random forest model, some typical known features in this field, and covarying signals computed by PSICOV. Concept of piaco is simple, and it can be extended with different algorithms or features.
This project is mainly coded in Java (partly in python), and some of dependency can be automatically solved by Maven.
mvn package
Dependency for Java:
- biojava
- args4j
- Apache Commons Codec
- Apache Commons Math
Dependency for Python:
- scikit-learn
External softwares:
- HHblits
- jackhmmer (HMMER suite ver 3.1)
- PSICOV (modified version is included)
- UCSFChimera
Before starting you need to change some default values in my.properties.
Read comments in the file and set them correctly in your environment.
To be written.
- Fork it!
- Create your feature branch:
git checkout -b my-new-feature
- Commit your changes:
git commit -am 'Add some feature'
- Push to the branch:
git push origin my-new-feature
- Submit a pull request :D
Yoshinori Fukasawa