Data Sets used to implement BaCelLo

Datasets derived from Swiss-Prot 48:

  Animals Fungi Plants
  animals_dataset fungi_dataset plants_dataset


Dataset for independent test:

  Animals Fungi Plants  
Train animals_train fungi_train plants_train up to Swiss-Prot 41
Test animals_test fungi_test plants_test from Swiss-Prot 42 to 48



Dataset used in other comparisons:

"The prediction of protein subcellular localization from sequence: a shortcut to functional genome annotation"
Brief Funct Gen Prot

Complete Set Animals Fungi Plants
Reduced Set Animals Fungi Plants
Homology Clusters Animals Fungi Plants