Introduction
Systems Biology and learning machine share a commonplace on their endeavors. My main motivation for creating this blog was the decision of Wikipedia to delete my article Systems Biology and Machine Learning. Further, I have spent some time on this direction for a while.
As highlights Hamid (2008)
"If we could start with
complete knowledge of a system, we might construct a very detailed model and
then find approximation that hold true under conditions of interest. However,
in GRN modeling, we are often faced with the opposite situation. We do not know
the mechanisms that cause an observed outcome. In such cases, we typically
construct models in three steps: 1) use biological knowledge to hypothesize the
nature of the interactions in the system; 2) propose an approximate model (e.g
a rate law) for each interaction; and 3) find parameters values that minimize
the error between the model and the data. " This and other statements
surely pinpoint the natural sinergy between systems biology and machine
learning based models.
Reference
PIRES J. G. On the applicability of Computational Intelligence in Transcription Network Modeling. Thesis of master of science. Faculty of Applied Physics and Mathematics, Gdansk University of Technology, Poland. 74:1:46. 2012.
Pires JG (2013). On the
mathematical modelling in gene expression estimation. II Workshop and School on
Dynamics, Transport and Control in Complex Networks (ComplexNet), Ribeirão
Preto , SP, Brazil
Pires JG (2013). Neural
Networks in Transcription Networks: An alternative and complementary approach
for the observer-based method. 1st BRICS Countries & 11th Brazilian Congress on
Computational Intelligence. Brazil 2.
