GANDALF
Generative ANsatz for DNA damage evALuation and Forecast. A neural network-based regression for estimating early DNA damage across micro-nano scales
Alberto Sciuto (INFN - Laboratori Nazionali del Sud)
Serena Fattori (INFN - Laboratori Nazionali del Sud)
Farmesk Abubaker (INFN - Laboratori Nazionali del Sud, Charmo University)
Sahar Arjmand (INFN - Laboratori Nazionali del Sud)
Roberto Catalano (INFN - Laboratori Nazionali del Sud)
Konstantinos Chatzipapas (Univ. Brest/CNRS/Ifremer/IRD)
Giacomo Cuttone (INFN - Laboratori Nazionali del Sud)
Fateme Farokhi (INFN - Laboratori Nazionali del Sud)
Mariacristina Guarrera (INFN - Laboratori Nazionali del Sud)
Ali Hassan (INFN - Laboratori Nazionali del Sud)
Sebastien Incerti (Université de Bordeaux)
Alma Kurmanova (University of Catania, INFN - Laboratori Nazionali del Sud)
Demetrio Oliva (INFN - Laboratori Nazionali del Sud)
Alfio D. Pappalardo (INFN - Laboratori Nazionali del Sud)
Giada Petringa (INFN - Laboratori Nazionali del Sud)
Dousatsu Sakata (University of Bristol, University of Wollongong, Osaka University)
Hoang N. Tran (Université de Bordeaux)
G. A.Pablo Cirrone (INFN - Laboratori Nazionali del Sud, Centro Siciliano di Fisica Nucleare e Struttura della Materia)
More Info
expand_more
Abstract
Purpose: This study aims to develop a comprehensive simulation framework to connect radiation effects from the microscopic to the nanoscopic scale. Method: The process begins with a Geant4-DNA simulation based on the example ”molecularDNA”, producing a dataset of twelve different types of early DNA damages within an Escherichia coli (E. coli) bacterium, generated by proton irradiation at different kinetic energies, giving a nano-scale view of the particle–matter interaction. Then we pass to the micro-scale with a Geant4 simulation, based on the example ”radiobiology”, providing a microscopic view of proton interactions with matter through the Linear Energy Transfer (LET). Then GANDALF (Generative ANsatz for DNA damage evALuation and Forecast) Machine Learning (ML) toolkit, a Neural Network (NN)-based regression system, is employed to correlate the micro-scale LET data with the nano-scale occurrences of DNA damages in the E. coli bacterium. Results: The trained ML algorithm provides a practical tool to convert LET curves versus depth in a water phantom into DNA damage curves for twelve distinct types of DNA damage. To assess the performance, we evaluated the choice and optimization of the regression system based on its interpolation and extrapolation capabilities, ensuring the model could reliably predict DNA damage under various conditions. Conclusions: Through the synergistic integration of Geant4, Geant4-DNA and ML, the study provides a tool to easily convert the results at the micro-scale of Geant4 to those at the nano-scale of Geant4-DNA without having to deal with the high CPU time requirements of the latter.
No files available
Metadata only record. There are no files for this record.