lgaalves / hctsaPhenotypingWorm

Machine learning classification using scikit-learn and features from hctsa analysis on movement speed data of five strains of the nematode worm Caenorhabditis elegans

hctsa: time-series phenotyping of Caenorhabditis elegans

Machine learning classification using scikit-learn and features from hctsa analysis on movement speed data of five strains of the nematode worm Caenorhabditis elegans: the CB4856 (Hawaiian wild isolate), and N2 (lab) strains, the mutants dpy-20(e1282) (morphological mutant), unc-9(e101) (neural mutant), and unc-38(e264) (neural mutant).

Full story: Fulcher, Ben D., and Nick S. Jones. "hctsa: A computational framework for automated time-series phenotyping using massive feature extraction." Cell Systems 5, no. 5 (2017): 527-531..

Directory Structure

• python -- python notebook worm_classification.ipynb with all code
• data -- hctsa data from Cell Systems 5, no. 5 (2017): 527-531