Connectivity in the yeast cell cycle transcription network: inferences from neural networks.

Despite biological and experimental difference between the two datasets, this aobANN delivered a highly significant out-of-sample accuracy of 56%, which is 17 standard deviations from the average linear assignment score (.27 ± 0.017) of a random partitioning of the genes, where class sizes are determined by drawing from a multinomial distribution based on the cluster sizes.

also in 132,142 other papers