Subcellular Localization

LocPro localization results for the two rubber dandelion protein FASTA sets, TK1151 and OH-1004; displayed data follow the input ID version.

Dual-reference IDs

Input ID LXL04_022997
TK1151 ID TkA06G419110
OH-1004 ID LXL04_022997

Main locations use complete ESM2 + PROFEAT features and probability calibration against independent experimentally annotated reference proteins. This is not experimental localization in rubber dandelion. Multiple locations are supported, so probabilities need not sum to one. Detailed-location scores remain uncalibrated and are shown separately.

Calibration method and independent validation metrics

Search Results

Download calibrated main-location results

Top1 predicted location Nucleus
Top1 probability (benchmark calibrated) 0.516
Gene ID LXL04_022997
Data version OH-1004
ModelLocPro
Model downloadLocPro model folder
PaperYintao Zhang et al. LocPro: A deep learning-based prediction of protein subcellular localization for promoting multi-directional pharmaceutical research. J Pharm Anal. 2025. doi:10.1016/j.jpha.2025.101255
Nucleus0.516
Rank 1 · LXL04_022997 · OH-1004
Cytoplasm0.478
Rank 2 · LXL04_022997 · OH-1004
Lysosome / Vacuole0.061
Rank 3 · LXL04_022997 · OH-1004
Cell membrane0.051
Rank 4 · LXL04_022997 · OH-1004
Golgi apparatus0.044
Rank 5 · LXL04_022997 · OH-1004

Detailed locations (uncalibrated model scores)

These scores support exploratory ranking and must not be interpreted as localization probabilities. The model contains cross-species categories; these outputs do not establish the corresponding structures or localization in rubber dandelion.

LocationRaw score
Nucleus0.559
Cytoplasm0.361
Cytosol0.185
Nucleoplasm0.144
Chromosome0.125