Support information

The benchmark dataset S includes 6,539 locative protein sequences (3,919 different proteins), classified into 20 animal subcellular locations. Among the 3,919 different protein sequences, 2,113 belong to one location, 1,293 to two locations, 286 to three locations, 173 to four locations, 43 to five locations, 5 to six locations, 3 to seven locations, and 3 to eight locations. Both the accession numbers and sequences are given. None of the proteins has more than 40% sequence identical to any other in the same subset (subcellular location).

Click download to get the benchmark dataset S1
Click download to get the benchmark dataset S2
Click download to get the benchmark dataset S3
Click download to get the benchmark dataset S4

Go back       Close