Speos: An ensemble graph representation framework to predict core genes for complex diseases (Datasets)

the "data.tar.gz" tarball contains the unprocessed or minimally processed data used by Speos. If you intend to use the framework or want to inspect the data, download this part of the dataset. The "final_datasets.tar.gz" tarball contains tsv-formatted, processed data matrices which are directly used as input features for the ensemble models. There are two tsv-files per disease, one labeled "normal", which contains the p input features alongside the gene identifiers and a column which indicates if the gene is labeled as Mendelian or not, and another file labeled "with_n2v_vectors", which also contains the 100-dimensional vectors produced by Node2Vec so the N2V+MLP method can be reproduced with the exact same parameters. All files contain a header row which describes the column and no index column. The "model_parameters.tar.gz" tarball contains the model parameters for all ensemble models used to produce the candidate genes.