Here is an interview about the SegMine methodology with dr. Helena Motaln from Department of Genetic Toxicology and Cancer Biology, National Institute of Biology, Ljubljana, Slovenia. She shares her opinion on using SegMine in expert data analysis and comments its abilities.

We present an example of analysis performed using SegMine. Two datasets were included: the acute lymphoblastic leukemia (ALL) dataset (Chiaretti et al., 2004) and a dataset on senescence of human mesenhymal stem cells (hMSC) (Wagner et al., 2008 and Schallmoser et al., 2010).

Three main methods were performed in the experiments:
  1. rule discovery using the SEGS algorithm
  2. rule clustering using interactive hierarchical clustering
  3. link discovery with the Biomine system

Both datasets in correctly preprocessed format are available on this page. They can be used as test samples when starting with SegMine:  ALLhMSC.

SegMine workflows, ready to be used in Orange4WS are also provided: simple workflow, complex workflow, advanced workflow. To use them, just download the selected one and click open in the main Orange4WS menu to load.

The results of running the SEGS algorithm can be downloaded here: ALL, hMSC. To load and explore them, download and use this simple workflow.

Here are some sample Biomine graphs. The first one is ALL gene cluster 0 (view, download) and the second is a graph of connections between genes from hMSC clusters 0 and cluster 1 (view, download). Downloaded graphs can be visualized using this simple workflow.

SegMine news
  • SegMine for metabolomics is under development.
  • SegMine for ClowdFlows is under development
  • Version 0.7.2 is out!
  • Web services used in SegMine are now hosted on a powerful new server with plenty of memory and processors.
Authors and institutions