Personalized prediction of the secondary oocytes number after ovarian stimulation: a machine learning model based on clinical and genetic data
To train models specified in the publication, custom functions define in lib were used.
As using third-party data prevents us to publish reusable version of the script (we cannot share the data), we shared the notebooks with printed results and visualizations of the experiments. To analyze basic statistics and models described in the publication, go to "Dataset summary_publication_plots.ipynb." To see the process of SOM and CA gene selection, see "Gene_data_mining-SOM_CA.ipynb". Feature selection is divided into 3 parts: Feature_selection_boruta.ipynb, Feature_selection_combinations.ipynb and Feature_selection_subsets_experiments.ipynb. To check the impact of haplotypes, check Haplotype_analysis.ipynb. Pipeline to shorten the haplotypes is inclued in Summary_of_experiments.ipynb (chapter Searching for optimal Haplotypes).
For any additional questions please contact us at [email protected]. For ML related questions write to [email protected].
Thanks!