Skip to main content
Figure 1 | BMC Bioinformatics

Figure 1

From: Multi-level learning: improving the prediction of protein, domain and residue interactions by allowing information flow between levels

Figure 1

Schematic illustration of multi-level learning concepts. (a) The three levels of interactions. Top: the PDB structure 1piw of the homo-dime r yeast. NADP-dependent alcohol dehydrogenase 6. Middle: each chain contains two conserved Pfam domain instances, PF00107 (inner) and PF08240 (outer). The interaction interface is at PF00107. Bottom: two pairs of residues predicted by iPfam to interact: 283 (yellow) with 287 (cyan), and 285 (purple) with 285. (b) The three information flow architectures. i: independent levels, ii: unidirectional flow (illustrated by download flow), iii: bidirectional flow. (c) Coupling mechanisms for passing information from one level to another. 1: passing training information to expand the training set of the next level, 2: passing predictions as an additional feature of the next level, 3: passing predictions to expand the training set of the next level.

Back to article page