Background Biological data has grown explosively with the advance of next-generation sequencing. However, annotating protein function with wet lab experiments is time-consuming. Fortunately, computational function prediction can help wet labs formulate biological hypotheses and prioritize experiments. Gene Ontology (GO) is a framework for unifying the representation of protein function in a hierarchical tree composed of GO terms. Results We propose GODoc, a general protein GO prediction framework based on sequence information which combines feature engineering, feature reduction, and a novel k -nearest-neighbor algorithm to resolve the multiple GO prediction problem. Comprehensive evaluation on CAFA2 shows that GODoc performs better than two baseline models. In the CAFA3 competition (68 teams), GODoc ranks 10th in Cellular Component Ontology. Regarding the species-specific task, the proposed method ranks 10th and 8th in the eukaryotic Cellular Component Ontology and the prokaryotic Molecular Function Ontology, respectively. In the term-centric task, GODoc performs third and is tied for first for the biofilm formation of Pseudomonas aeruginosa and the long-term memory of Drosophila melanogaster , respectively. Conclusions We have developed a novel and effective strategy to incorporate a training procedure into the k -nearest neighbor algorithm (instance-based learning) which is capable of solving the Gene Ontology multiple-label prediction problem, which is especially notable given the thousands of Gene Ontology terms.
Many machine learning methods have been used to predict prokaryotic and eukaryotic protein subcellular localization. As most algorithms involve specific feature engineering, we carry out prediction using the feature-free property of deep learning methods. We present PSLCNN, a model using deep neural networks to predict protein subcellular localization for eukaryotes and prokaryotes. Only sequence information is needed (FASTA format). The model uses 1D convolution and predicts where the query localizes. It was trained and tested on an un-redundant dataset from the latest UniProt release, only for data with experimental annotation. Compared with the state-of-the-art tools, PSLCNN achieves the best performance for prokaryotes and is comparable for eukaryotes. We have also implemented a free PSLCNN web service available at https://github.com/changlabtw/PSLCNN.
