An Overview of in Silico Methods for the Prediction of Ionizing Radiation Resistance in Bacteria

Manel Zoghlami (1, 2) , Sabeur Aridhi (3) , Mondher Maddouri (4, 5) , Engelbert Mephu Nguifo (1)

1 LIMOS - Laboratoire d'Informatique, de Modélisation et d'Optimisation des Systèmes
2 LIPAH - Laboratoire d'Informatique, Programmation, Algorithmique et Heuristique
3 CAPSID - Computational Algorithms for Protein Structures and Interactions
4 Taibah University
5 University of Jeddah

Ionizing-radiation-resistant bacteria (IRRB) could be used for biore-mediation of radioactive wastes and in the therapeutic industry. Limited computational works are available for the prediction of bacterial ionizing radiation resistance (IRR). In this chapter, we present some works that study the causes of the high resistance of IRRB to ionizing radiation. Then we focus on presenting in silico approaches that use protein sequences of bacteria in order to predict if an unknown bacterium belongs to IRRB or ionizing-radiation-sensitive bacteria (IRSB). These approaches formulate the problem of predicting bacterial IRR as a multiple instance learning (MIL) problem where bacteria represent the bags and * Corresponding Author: [e-mail]. 2 Manel Zoghlami, Sabeur Aridhi, Mondher Maddouri et al. primary structure of basal DNA repair proteins of each bacterium represent the instances inside the bags. We also present a formulation of the problem of MIL in sequence data and explain how it could be used to solve the problem of IRR prediction in bacteria. A brief comparison of the presented approaches is provided.

Mots clés: phenotype prediction; bacterial ionizing radiation resistance; multiple instance learning

Domaines: Bio-informatique [q-bio.QM]; Intelligence artificielle [cs.AI]; Apprentissage [cs.LG]

Manel Zoghlami, Sabeur Aridhi, Mondher Maddouri, Engelbert Mephu Nguifo. An Overview of in Silico Methods for the Prediction of Ionizing Radiation Resistance in Bacteria. Tamar Reeve. Ionizing Radiation: Advances in Research and Applications, Nova science publishers, pp.241-256, 2018, Physics Research and Technology Series, 978-1-53613-539-8. ⟨hal-01807944⟩