Fig. 5
From: A learning-based method to predict LncRNA-disease associations by combining CNN and ELM
The process of the semantics similarity calculation between diseases “lupus erythematosus, systemic” and “acne vulgaris”. (1) Construct their own directed acyclic graphs according to the rules; (2) Calculate the contribution of various diseases (nodes) to “lupus erythematosus, systemic” and “acne vulgaris” in the directed acyclic graph, of which the lowest level is “lupus” “erythematosus, systemic” and “acne vulgaris” contribute 1 to themselves, and the parent node decays layer by layer, “autoimmune diseases”, “connective tissue diseases”, etc. contribute 0.5, and so on; (3) Calculate “lupus erythematosus, systemic” and “acne vulgaris” constitute the total contribution of directed acyclic graphs. \(DV\left( {{\text{lupus erythematosus}},{\text{ systemic}}} \right) = 1 + 2 \times 0.5 + 2 \times 0.25 = 2.5\), \(DV\left( {\text{acne vulgaris}} \right) = 1 + 2 \times 0.5 + 1 \times 0.25 + 1 \times 0.125 = 2.375\). \(Similarity\left( {{\text{lupus erythematosus}},{\text{systemic}},{\text{acne vulgaris}}} \right) = \frac{0.25 + 0.125}{{2.5 + 2.375}} = 0.0769\)