Page 50 - Biosystems Engineering

Micr oarray Data Analysis Using Machine Learning Methods 31

Glossary of Terms

©
Affymetrix GeneChips Microarrays in which the probes are oligonucleotides
synthesized directly on the chip through a photolithography process.
cDNA arrays Microarrays in which the probes are extracted from cDNA
clones and are robotically printed onto a glass slide and subsequently
hybridized to two differentially fluorescently labeled targets.
classification Involves the automated grouping of objects into prespecified
categories.
clustering Helps discover common properties contained within the data
and create groups of objects according to their properties.
defuzzification Conversion of a fuzzy output value into to a crisp value.
DNA microarray A tool for obtaining high-throughput global gene expression
data.
feedforward neural network A neural network with all connections are
feedforward; that is, information transfer results only from an earlier
layer to the next consecutive layers. Neurons within a layer are not
connected, and neurons in nonadjacent layers are not connected.
fuzzification Conversion of a crisp value of a variable into degrees of
membership using membership functions assigned to the variable.
fuzzy logic A superset of conventional two-valued (Boolean) logic that
has been extended to handle the concept of partial truth.
gene expression Rate at which a gene is used to produce functional RNA
transcripts.

Gene expression data matrix A matrix where each entry corresponds to
the expression level of a gene for a given condition or sample.
genetic algorithms Global optimization algorithms that originated from
mechanics of natural genetics and selection.

genetic network Conceptual network of interaction among gene expression
events.
inference Process of evaluating which and how fuzzy rules should be
executed.
machine learning Field of scientific study that concentrates on induction
algorithms and on other algorithms that can be said to learn.
neural networks Information processing systems that have certain
performance characteristics in common with biological neural networks.