Peer Reviewed Journal via three different mandatory reviewing processes, since 2006, and, from September 2020, a fourth mandatory peer-editing has been added.
This paper provides continuation and extensions of
previous research by Segall and Pierce (2009a) that
discussed data mining for micro-array databases of
Leukemia cells for primarily self-organized maps (SOM).
As Segall and Pierce (2009a) and Segall and Pierce
(2009b) the results of applying data mining are shown
and discussed for the data categories of microarray
databases of HL60, Jurkat, NB4 and U937 Leukemia
cells that are also described in this article.
First, a background section is provided on the work of
others pertaining to the applications of data mining to
micro-array databases of Leukemia cells and micro-array
databases in general. As noted in predecessor article by
Segall and Pierce (2009a), micro-array databases are one
of the most popular functional genomics tools in use
today.
This research in this paper is intended to use advanced
data mining technologies for better interpretations and
knowledge discovery as generated by the patterns of gene
expressions of HL60, Jurkat, NB4 and U937 Leukemia
cells. The advanced data mining performed entailed using
other data mining tools such as cubic clustering criterion,
variable importance rankings, decision trees, and more
detailed examinations of data mining statistics and study
of other self-organized maps (SOM) clustering regions of
workspace as generated by SAS Enterprise Miner version
4. Conclusions and future directions of the research are
also presented.
