If you use this code, please cite the associated paper: "Giuseppe Magazzù, Guido Zampieri and Claudio Angione - Clinical profiles can modulate the diagnostic accuracy of omics data within machine learning and genome-scale metabolic models of hepatoblastoma". The necessary data and code are provided to reproduce the experiments presented in the paper, figures and analyses on the results included.
The data and the metabolic model necessary to run the code are provided in the folder Data and models.
The code to compute the metabolic fluxes is contained in the folder Metabolic fluxes computation.
To run the machine learning pipelines please use the code in the folder Pipelines.
The figures shown in the paper can be generated with the code present in the folder Results and Figures.
For all other analyses conducted in the paper please refer to the code present in the folder Weights and enrichments analyses.
Finally, in the folder Utils some functions can be found to run the other scripts.
In all the scripts the paths to data, functions and other scripts need to be changed manually.
This is free software for academic use that can be redistributed and/or modified under the terms of the GNU Public License as published by the Free Software Foundation, either version 3 of the License, or any later version.
This code is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Public License for more details.
Giuseppe Magazzù - April 2022