AI in Biological Modelling

Abstract : Systems Biology aims at elucidating the high-level functions of the cell from their biochemical basis at the molecular level. A lot of work has been done for collecting genomic and post-genomic data, making them available in databases and ontologies, building dynamical models of cell metabolism, signalling, division cycle , apoptosis, and publishing them in model repositories. In this chapter we review different applications of AI to biological systems modelling. We focus on cell processes at the unicellular level which constitutes most of the work achieved in the last two decades in the domain of Systems Biology. We show how rule-based languages and logical methods have played an important role in the study of molecular interaction networks and of their emergent properties responsible for cell behaviours. In particular, we present some results obtained with SAT and Constraint Logic Programming solvers for the static analysis of large interaction networks, with Model-Checking and Evolutionary Algorithms for the analysis and synthesis of dynamical models, and with Machine Learning techniques for the current challenges of infering mechanistic models from temporal data and automating the design of biological experiments.
Document type :
Preprints, Working Papers, ...
Complete list of metadatas

Cited literature [118 references]  Display  Hide  Download

https://hal.inria.fr/hal-01409753
Contributor : François Fages <>
Submitted on : Thursday, May 11, 2017 - 3:29:23 PM
Last modification on : Tuesday, April 17, 2018 - 9:04:14 AM
Long-term archiving on : Saturday, August 12, 2017 - 1:48:17 PM

File

Fages16ai.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01409753, version 2

Collections

Citation

François Fages. AI in Biological Modelling. 2016. ⟨hal-01409753v2⟩

Share

Metrics

Record views

433

Files downloads

523