Skip to main content
Fig. 1 | BMC Bioinformatics

Fig. 1

From: Discriminate the response of Acute Myeloid Leukemia patients to treatment by using proteomics data and Answer Set Programming

Fig. 1

Workflow for our method. a PKN construction. In this step we pass the proteins present in our DREAM 9 dataset as input to the Cytoscape plug-in Reactome FI to construct the PKN. This plug-in finds all the paths between the input proteins across several databases, after that we select only relations coming from KEGG. b Protein and patient selection. This step consists on selecting k proteins from the dataset for which there is a maximum number of pairs of patients that have identical values in the k proteins but that belong to different response classes. c Learning. This step consists on finding the BNs for the two classes CR-PR corresponding to the two datasets obtained in step (b). (d) Classification. This step consists on classifying unknown patients datasets by using our learned logic models

Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us