10-fold Cross-Validation Area-Under-the-Curve scores (mean ± st.dev.) of domain vs non-domain representations in the protein inference tasks. Overall, there is consistency between region enrichment of the top Hist-8000 features selected and best-performing Hist-8000 region-specific representations, between domain and non-domain regions per task (tasks 1-8). Best-performing methods in bold. See section ‘Protein inference problems’ for tasks sources. Hist-8000: Histogram-8000, SoT: Sum-of-learnt-Trigrams, AUC: Area Under the Curve, 10foldCV: 10-fold Cross-Validation, VFs: Virulence Factors, Gram-pos: Gram-positive, Gram-neg: Gram-negative, st.dev: standard deviation, doms: domains, non-doms: non-domains, #Top feats: number of top features.

10-fold Cross-Validation Area-Under-the-Curve scores (mean ± st.dev.) of domain vs non-domain representations in the protein inference tasks. Overall, there is consistency between region enrichment of the top Hist-8000 features selected and best-performing Hist-8000 region-specific representations, between domain and non-domain regions per task (tasks 1-8). Best-performing methods in bold. See section ‘Protein inference problems’ for tasks sources. Hist-8000: Histogram-8000, SoT: Sum-of-learnt-Trigrams, AUC: Area Under the Curve, 10foldCV: 10-fold Cross-Validation, VFs: Virulence Factors, Gram-pos: Gram-positive, Gram-neg: Gram-negative, st.dev: standard deviation, doms: domains, non-doms: non-domains, #Top feats: number of top features.