SLPred: A multi-view subcellular localization prediction tool

We present SLPred, a sequence-based multi-view and multi-label protein subcellular localization prediction tool. For a query protein sequence, SLPred provides predictions for nine main subcellular locations using independent prediction models trained for each location. We used UniProtKB/Swiss-Prot human protein entries and their subcellular location (SL) annotations as our source dataset. We re-organized the SL hierarchy based on the corresponding term relationships in the cellular component category of Gene Ontology, to construct a training dataset that is both reliable and large-scale. We tested SLPred using multiple benchmarking datasets including our-in house sets, and compared against five state-of-the-art methods. Results indicated that SLPred outperforms other tools in the majority of cases.