Databases on lncRNA annotation and subcellular localization



Dataset used in existing tools performing subcellular localization prediction

On this page, we have enlisted the datasets used in tools that perform subcellular localization prediction.The dataset statistics for each subcellular location is provided in the table. Majority of the tools perform prediction in five primary sucellular locations - Nucleus, Cytoplasm, Cytosol, Ribosome and Exosome. The first column represents the Name of the tool, and the rest of the columns represents the Dataset type, Cytoplasm, Cytosol, Exosome, Nucleus and Ribosome.


ToolsDataset typeCytoplasmCytosolExosomeNucleusRibosomeTotal
lncLocator Benchmark 301 91 25 152 43 612
iLoc-lncRNA Benchmark 426 30 156 43 655
DeepLncRNA Benchmark 4380 4298 8678
LncLocation Benchmark 426 240 344 314 1324
Locate-R Benchmark 426 240 314 344 1324
lncLocPred Benchmark 426 30 156 43 655
Independent 199 16 82 99 396
KD-KLNMF Benchmark 417 417 417 417 1668
Independent 14 35 45 84 178
DeepLncLoc Benchmark 328 88 28 325 88 857
Test 20 10 7 20 10 67
GM-lncLoc Dataset1 292 292 292 292 292 1460
Dataset2 417 417 417 417 1668
Independent set 198 16 82 99 395