Figure 5

Comparison with InterPro2GO2EC and testing on TrEMBL. Left panel: The results of the internal cross-evaluation of the entire SwissProt$\bowtie$KEGG and Swiss-Prot datasets are compared with the direct transitive annotation using InterPro2GO and EC2GO lists. The results of training on the SwissProt$\bowtie$KEGG dataset and testing on the TrEMBL$\bowtie$KEGG dataset are also included. The x axis (accuracy, precision, recall) starts at 50%. Right panel: Comparison of the EC digits in the predicted and actual EC numbers for the TrEMBL$\bowtie$KEGG dataset. All predictions$=$ all the EC annotations emitted by training on SwissProt$\bowtie$KEGG and predicting the unlabelled TrEMBL$\bowtie$KEGG (true positives, true negatives, false positives, false negatives). Correct predictions $=$ only the predictions corresponding to true, correct annotations existing in TrEMBL$\bowtie$KEGG (true positives and true negatives). Wrong predictions $=$ false positives and false negatives. The data files used (SwissProt$\bowtie$KEGG and TrEMBL$\bowtie$KEGG) are available as Additional file 3. The full cross evaluation results are available in Additional file 7: all_cross_evaluation_results.csv