Skip to main content
Fig. 1 | BMC Bioinformatics

Fig. 1

From: A two-layer integration framework for protein complex detection

Fig. 1

Schematic overview of our proposed TINCD model. TINCD first constructs two consensus matrices (C (1) and C (2)) based on the complex knowledge discovered by various graph clustering algorithms from PPI and TAP data. Second, a similarity network fusion (SNF) strategy is employed by TINCD to combine these two consensus matrices with the score matrix obtained from TAP data (C (3)) to obtain a final co-complex score matrix. Finally, a novel graph regularized doubly stochastic matrix decomposition model is proposed to detect overlapping protein complexes from the final score matrix

Back to article page