Download the datasets
The training and the testing parts of the three datasets can be downloaded here.
Dataset 1 (FASTA)
This is the original dataset used by MemType-2L (Chou, K.C. and Shen, H.B., Biochem. Biophys. Res. Commun. 360, 339-345, 2007)
training set
testing set
Dataset 2 (FASTA)
This is Dataset 1's homology-reduced version.
training set
testing set
Dataset 3 (FASTA)
This is the in-house prepared dataset, using Swiss-Prot version 72, October, 2011.
training set
testing set
Dataset 3 (the encoded feature vectors)
the training set
type 1 membrane proteins
type 2 membrane proteins
type 3 membrane proteins
type 4 membrane proteins
type 5 membrane proteins
type 6 membrane proteins
type 7 membrane proteins
type 8 membrane proteins
the testing set
type 1 membrane proteins
type 2 membrane proteins
type 3 membrane proteins
type 4 membrane proteins
type 5 membrane proteins
type 6 membrane proteins
type 7 membrane proteins
type 8 membrane proteins
Feature list
the list of the sequence features