Skip to main content
. 2016 Jun 11;32(12):i18–i27. doi: 10.1093/bioinformatics/btw244

Fig. 4.

Fig. 4.

Complementarity between component methods. The 200 drugs correctly predicted for a new given target by each method is compared with that of another. The comparison is between (a) k-NN versus BLM-svr, (b) NetLapRLS versus BLM-svr, (c) WNN-GIP versus NetLapRLS and (d) BLM-svr versus WNN-GIP