string(13) "dissertations"
  • Γνώσεις θεωρίας πιθανοτήτων. Γνώσεις μηχανικής μάθησης.
  • Γνώσεις αναπαράστασης γνώσης και συμπερασμού. Γνώσεις συναρτησιακού προγραμματισμού.
  • Alexandros Artikis
  • a.artikis [at]
  • The AI Lab

In silico biology attempts to simulate large-scale biological processes in order to extract meaningful insights without having to study them through possibly harmful experimental procedures. However, the amount of data generated by such simulations and, more importantly, the complexity of the underlying mechanisms involved, render naive and exhaustive approaches inappropriate for the analysis of the generated data. As a result, big data technologies, in combination with machine learning and artificial intelligence techniques, are required in order to perform efficient and timely analysis of these simulations. The goal of this project is to develop machine learning methods to study simulations of the behavior of tumor cells undergoing drug treatments. As a first step, simulations will be analyzed in an online fashion, as they run, with the goal of predicting whether a single drug will turn out to be efficacious or not. At a more advanced level, the capacity of machine learning methods for suggesting the most promising scheduling of drug dosages will be tested. The final goal is to investigate which combinations of drugs can work in synergy so as to further enhance the efficacy of cancer treatments.

Indicative bibliography:

  • Stoll et al, Continuous time boolean modeling for biological signaling: application of Gillespie algorithm, BMC Systems Biology, 2012, link
  • Flobak et al., Discovery of Drug Synergies in Gastric Cancer Cells Predicted by Logical Modeling, PLOS Computational biology, 2015, link
Skip to content