Biomedical Engineering Reference
In-Depth Information
Fig. 3.8
Therapeutic cloning
Fig. 3.9
Support Vector Machine: (
a
) separating hyperplane (
b
) maximum margin hyperplane (
c
)
soft margin (from author's collaborative study, published [
20
]
been developed in the machine learning and data mining fields, specific applications
in bioinformatics have led to a wealth of newly proposed techniques [
20
]. In a recent
article, we make the interested reader aware of the possibilities of feature selection,
providing a basic taxonomy of feature selection techniques, and discussing their
use, variety and potential in a number of both common as well as upcoming bioin-
formatics applications. Thus, using
bioinformatics tools
we have realized that
MicroRNAs (miRNAs) may serve as
diagnostic
and
predictive
biomarkers for can-
cer, rapidly and uncontrolled dividing cell conglomerate. A number of biomarkers
for tissue-specific cancer have been confirmed by our techniques [
20
]. In addition,
seven miRNAs have been newly identified by our methodology as possible impor-
tant biomarkers for hepatocellular carcinoma or breast cancer, pending wet lab con-
firmation. In this paper [
20
], these biomarkers were identified from miRNA
expression data sets by combining
multiple feature selection techniques
(i.e., cre-
ating an ensemble), and then classified by different learners. In general, creating a
subset of features by selecting only the highest ranking features (miRNAs) improved
upon results generated when using all the miRNAs, and the ensemble approach out
