Skip to main content
. 2013 Nov 21;9(11):e1003361. doi: 10.1371/journal.pcbi.1003361

Figure 8. Optimal algorithm selection based on similarity among expression datasets and its potential to improve network-inference accuracy.

Figure 8

Red lines show performance of TopkNet integrating algorithms that are optimal for a dataset with high-similarity, while green lines show that with low-similarity. Blue lines show performance of TopkNet integrating top 10 highest-performance algorithms. Dashed lines in red, green, and blue represent performance of community prediction integrating algorithms that are optimal for a dataset with high-similarity, that with low-similarity, and top 10 highest-performance algorithms, respectively. (A) AUC-PR for E. coli dataset. (B) AUC-ROC for E. coli dataset. (C) Max f-score for E. coli dataset. (D) AUC-PR for S. cerevisiae dataset. (E) AUC-ROC for S. cerevisiae dataset. (F) Max f-score for S. cerevisiae dataset.