| |
 Programme
Overview
Detailed
Programme
| BioInformatics
and Computational Biology I (invited session) (BCBI) |
CHAIR: MIGUEL ROCHA
Time: Tuesday, March 22nd, 11h00-12h40
| BCBI-1 |
| |
| Title: |
|
|
Evolutionary Algorithms for Static
and Dynamic Optimization of Fed-batch Fermentation Processes |
| Author(s): |
M. Rocha,
J. Neves,
A. Veloso |
| Abstract: |
In this work, Evolutionary Algorithms (EAs)
are used to control a recombinant bacterial fed-batch fermentation
process, that aims at producing a bio-pharmaceutical product.
In a first stage, a novel EA is used to optimize the process,
prior to its start, by multaneously adjusting the feeding
trajectory, the duration of the fermentation and the initial
conditions of the process. In a second stage, dynamic optimization
is proposed, where the EA is running simultaneously with the
fermentation process, receiving information regarding from
the process, updating its internalmodel, eaching new solutions
that will be used for online control. |
 |
| BCBI-2 |
| |
| Title: |
|
|
Benchmark testing of simulated
annealing, adaptive random search and genetic algorithms for
the global optimization of bioprocesses |
| Author(s): |
R. Oliveira,
R. Salcedo |
| Abstract: |
This paper studies the global optimisation of
bioprocesses employing model-based dynamic programming schemes.
Three stochastic optimisation algorithms were tested: simulated
annealing, adaptive random search and genetic algorithms.
The methods were employed for optimising two challenging optimal
control problems of fed-batch bioreactors. The parameterisation
of the control inputs is also discussed. The main results
show that adaptive random search and genetic algorithms are
superior at solving these problems than the simulated annealing
based method, both in accuracy and in the number of function
evaluations. |
|
| BCBI-3 |
| |
| Title: |
|
|
Dynamic modelling and optimisation
of a ammalian cells process using hybrid grey-box systems |
| Author(s): |
A. Teixeira,
A. Cunha,
J. Clemente,
P.M. Alves,
M. J. T Carrondo,
R. Oliveira |
| Abstract: |
In this work a model-based optimisation study
of fed-batch BHK-21 cultures expressing the human fusion glycoprotein
IgG-IL2 was performed. Due to the complexity of the BHK metabolism
it is rather difficult to develop an accurate kinetic model
that could be used for optimisation studies. Many kinetic
expressions and parameters are involved resulting in a complex
identification problem. For this reason an alternative more
cost-effective methodology was adopted, based on hybrid grey-box
models. It was concluded that modulation particularities of
BHK cultures were effectively captured by the hybrid model,
this being of crucial importance for the successful optimisation
of the process operation. From the optimisation study it was
concluded that the glutamine and glucose concentrations should
be maintained at low levels during the exponential growth
phase and then glutamine feeding should be increased. In this
way it is expected that both the cell density and final product
titre can be considerably increased. |
|
| BCBI-4 |
| |
| Title: |
|
|
Adaptive DO-based control of substrate
feeding in high cell density cultures operated under oxygen
transfer limitation |
| Author(s): |
R. Oliveira,
A. Cunha,
J. Clemente,
M. J. T. Carrondo |
| Abstract: |
The carbon source feeding strategy is crucial
for the productivity of many biochemical processes. In high
density and shear sensitive cultures the feed of the carbon
source is frequently constrained by the bioreactor maximum
oxygen transfer capacity. In order to maximise the product
formation, these processes should be operated at low dissolved
oxygen (DO) concentrations close to the limitation level.
This operating strategy may be realised with a closed-loop
controller that regulates the DO concentration through the
manipulation of the carbon source feed rate. The performance
of this controller may have a significant influence on the
final product production and should be as accurate as possible.
In this work we study the application of adaptive control
for solving this problem focusing not only on stability but
also on accuracy. Whenever possible the convergence trajectories
to the set point are characterised mathematically. Concerning
the instrumentation, two situations are covered i) only the
DO Tension (DOT) is measured, ii) both DOT and off-gas composition
are measured on-line. The controllers are tested in a pilot
plant recombinant Pichia pastoris process |
|
| BCBI-5 |
| |
| Title: |
|
|
Evolutionary Design of Neural Networks
for Classification and Regression |
| Author(s): |
Miguel Rocha,
Paulo Cortez,
José Neves |
| Abstract: |
The Multilayer Perceptrons (MLPs) are the most popular class
of Neural Networks. When applying MLPs, the search for the
ideal architecture is a crucial task, since it should should
be complex enough to learn the input/output mapping, without
overfitting the training data. Under this context, the use
of Evolutionary Computation makes a promising global search
approach for model selection. On the other hand, the use of
ensembles (combinations of models), have been boosting the
performance of several Machine Learning (ML) algorithms. In
this work, a novel evolutionary technique for MLP design is
presented, being used also an ensemble based approach. A set
of real world classification and regression tasks was used
test this strategy, comparing it with heuristic model selection,
as well as with other ML algorithms. The results favour the
evolutionary MLP ensemble method. |
|
|