Biomodeling and Genetic Programming
One of my main research interests is the computational modeling and simulation of biological
In particular, my students and I have been applying
genetic programming towards the modeling of stochastic bio-networks.
1. Genetic Programming and the Stochastic Pi-Calculus
Preliminary research explored the feasibility of using the stochastic pi-calculus as
a target language for genetic programming.
This would enable genetic programming to evolve stochastic models denoted in the
stochastic pi-calculus, or equivalently, automatically construct
stochastic pi-calculus expressions.
Initial work examined simple stochastic pi-calculus models that
had monotonic time-series behaviours.
Later, basic circuits such as the repressilator were successfully evolved.
These required statistical characterizations of the time series (see Janine Imada's research (2) below), to be used by
the genetic programming system during fitness evaluation.
In addition, it was found that multi-objective fitness evaluation was ideal for
this problem, given that many diverse statistics may be required for describing
target network behaviours.
"Evolutionary Learning and Stochastic Process Algebra".
1st International Workshop on Induction of Process Models,
ICML 2007, Corvallis, OR, June 2007.
"Using Genetic Programming to Synthesize Monotonic Stochastic Processes".
B. J. Ross,
Computational Intelligence 2007, Banff, AB, July 2007, pp.71-78.
"Evolving Stochastic Processes Using Feature Tests and Genetic Programming".
B.J. Ross and J. Imada,
Proc. GECCO 2009, Montreal, July 2009. PDF.
"Using Multi-objective Genetic Programming to Synthesize Stochastic Processes".
B.J. Ross and J. Imada,
In Genetic Programming Theory and Practice VII,
R. Riolo, U.-M. O'Reilly and T. McConaghy (eds.), Springer, 2010, pp.159-175.
"Evolution of Stochastic Bio-Networks Using Summed Rank Strategies".
Proc. CEC 2011, New Orleans, June 2011. Slides.
2. Evolutionary Synthesis of Stochastic Gene Network Models using
Feature-based Search Spaces
Janine Imada's MSc research involves the automatic synthesis of stochastic bio-networks
using genetic programming.
A gene gate language proposed by Blossey et al. is used as a target
language for genetic programming.
These gene circuits are implemented in the stochastic pi-calculus (Phillips 2008), which is
a stochastic process algebra.
The gene gate language is more amenable to evolution by genetic programming than models
written in the raw stochastic pi-calculus (see (1) above).
Bio-models are characterized by time-course data, representing varying quantities of
agents over time.
The stochastic nature of the models means that multiple simulations are required.
The overall network behaviour is denoted by examining various statistical features of
the time series output.
Genetic programming then uses these statistical features as objectives during evolution,
in the attempt to construct a bio-model with similar features to the target model.
A number of experiments successfully reconstructed target models, including
repressilators and gene circuit examples.
"Evolutionary Synthesis of Stochastic Gene Network Models using
Feature-based Search Spaces".
J.H. Imada, MSc thesis, Brock University, Canada, 2009.
"Evolutionary Synthesis of Stochastic Gene Network
Models Using Featuer-based Search Spaces".
J.H. Imada and B.J. Ross,
New Generation Computing,
v.29, pp.365-390, 2011.
"Using feature-based fitness evaluation in symbolic regression with added noise",
J.H. Imada and B.J. Ross, Proc. GECCO 08 Late Breaking Papers, ACM, pp. 2153-2158, 2008.
3. Evolving Higher-Level Bio-Models with Genetic Programming
Kahramanogullari and Cardelli (2009) propose a higher-level bio-modeling language called
PIM. PIM permits the description of biological reactions in terms familiar to
biologists. PIM models are then translated into stochastic pi-calculus (SPI) expressions,
and can then be simulated with a SPI interpreter.
I addressed the idea of automatically generating PIM models.
Genetic programming uses PIM as the target language for evolution.
Time series of simulation behaviours are used to guide GP towards models having the
PIM-specific language constraints were necessary, in order to sensibly constrain and
optimize the search space of bio-model networks being evolved.
Results of this research were positive, as a number of target PIM systems were
successfully reverse engineered with genetic programming.
Furthermore, the results showed that alternative models having similar behavioural
equivalence to the target system can arise.
In this way, genetic programming can be a tool for model invention and discovery.
Current research is investigating other bio-modeling languages, such as stochastic
logic gate languages. Stay tuned!
- "The Evolution of Higher-Level Biochemical Reaction Models".
Genetic Programming and Evolvable Machines., v.13, n.1, 2012, pp. 3-31.
- "Using Multi-objective Genetic Programming to Evolve Stochastic Logic Gate Circuits".
B.J. Ross, CIBCB 2015, Niagara Falls, Canada, 2015.
Back up: http://www.cosc.brocku.ca/~bross/