Figure 2From: Validating module network learning algorithms using simulated dataBayesian score as a function of the number of modules and experiments. Bayesian score as a function of the number of modules for data sets with 10, 100 and 300 experiments (top to bottom). The score is normalized by the number of genes times the number of experiments. The curves are least squares fits of the data to a linear non-polynomial model of the form a 0 + ∑ k = 1 n a k x k − 1 e − x / 500 MathType@MTEF@5@5@+=feaafiart1ev1aaatCvAUfKttLearuWrP9MDH5MBPbIqV92AaeXatLxBI9gBaebbnrfifHhDYfgasaacH8akY=wiFfYdH8Gipec8Eeeu0xXdbba9frFj0=OqFfea0dXdd9vqai=hGuQ8kuc9pgc9s8qqaq=dirpe0xb9q8qiLsFr0=vr0=vr0dc8meaabaqaciaacaGaaeqabaqabeGadaaakeaacqWGHbqydaWgaaWcbaGaeGimaadabeaakiabgUcaRmaaqadabaGaemyyae2aaSbaaSqaaiabdUgaRbqabaGccqWG4baEdaahaaWcbeqaaiabdUgaRjabgkHiTiabigdaXaaakiabdwgaLnaaCaaaleqabaGaeyOeI0IaemiEaGNaei4la8IaeGynauJaeGimaaJaeGimaadaaaqaaiabdUgaRjabg2da9iabigdaXaqaaiabd6gaUbqdcqGHris5aaaa@461A@ with x the number of modules and n = 6.Back to article page