A tree-like Bayesian structure learning algorithm for small-sample datasets from complex biological model systems

BMC Systems Biology

Table 4 Features in the child network selected for model inclusion using a dimensional-reduction screening procedure, with node 2 (selected automatically) as the root

Sample size	Indices of features identified as significant	Fraction of real features selected	Fraction of noisy features selected
50	Real features: 3,4,5,6,7,8,9,12,14,15,20	58 %	2.5 %
50	Noisy features: 96,113,119,174,175	58 %	2.5 %
100	Real features: 1,4,5,6,7,8,9,11,12,14,15,20	63 %	0.5 %
100	Noisy features: 161	63 %	0.5 %
150	Real features: 3,4,5,6,7,8,9,11,12,14,15,20	63 %	2 %
150	Noisy features: 70,79,116,208	63 %	2 %
200	Real features: 3,4,5,6,7,8,9,11,12,14,15,20	63 %	1 %
200	Noisy features: 75,94	63 %	1 %
300	Real features: 3,4,5,6,7,8,9,10,11,12,14,15,20	68 %	3.5 %
300	Noisy features: 121,126,198,205,207,209,211	68 %	3.5 %
400	Real features: 1,3,4,5,6,7,8,9,10,11,12,14,15,20	74 %	2.5 %
400	Noisy features: 31,55,94,113,195	74 %	2.5 %
500	Real features: 1,3,4,5,6,7,8,9,10,11,12,13,14,15,19,20	84 %	3.5 %
500	Noisy features: 22,122,152,157,166,192,218	84 %	3.5 %

ISSN: 1752-0509