Phenotype Driven Data Augmentation Methods for Transcriptomic Data

<p>This repository contains the data and associated results of all experiments conducted in our work "<em>Phenotype Driven Data Augmentation Methods for Transcriptomic Data</em>". In this work, we introduce two classes of phenotype driven data augmentation approaches &ndash; signature-dependent and signature-independent. The signature-dependent methods assume the existence of distinct gene signatures describing some phenotype and are simple, non-parametric, and novel data augmentation methods. The signature-independent methods are a modification of the established Gamma-Poisson and Poisson sampling methods for gene expression data. We benchmark our proposed methods against random oversampling, SMOTE, unmodified versions of Gamma-Poisson and Poisson sampling, and unaugmented data.&nbsp;<br>&nbsp;</p> <p>This repository contains data used for all our experiments. This includes the original data based off which augmentation was performed, the cross validation split indices as a json file, the training and validation data augmented by the various augmentation methods mentioned in our study, a test set (containing only real samples) and an external test set standardised accordingly with respect to each augmentation method and training data per CV split.&nbsp;</p> <p>The compressed files&nbsp;<code>5x5stratified_{x}percent.zip</code>&nbsp;contains data that were augmented on <code>x%</code> of the available real data.&nbsp;<code>brca_public.zip</code> contains data used for the breast cancer experiments. <code>distribution_size_effect.zip</code> contains data used for hyperparameter tuning the reference set size for the modified Poisson and Gamma-Poisson methods.&nbsp;</p> <p>The compressed file&nbsp;<code>results.zip</code>&nbsp;contains all the results from all the experiments. This includes the parameter files used to train the various models, the metrics (balanced accuracy and auc-roc) computed including p-values, as well as the latent space of train, validation and test (for the (N)VAE) for all 25 (5x5) CV splits.</p> <p><strong>PLEASE NOTE:</strong>&nbsp;If any part of this repository is used in any form for your work, please&nbsp;<strong>attribute</strong>&nbsp;the following, in addition to attributing the original data source &nbsp;- TCGA, CPTAC, GSE20713 and METABRIC, accordingly:</p> <pre>@article{janakarajan2025phenotype,<br>&nbsp; title={Phenotype driven data augmentation methods for transcriptomic data},<br>&nbsp; author={Janakarajan, Nikita and Graziani, Mara and Rodr{\'\i}guez Mart{\'\i}nez, Mar{\'\i}a},<br>&nbsp; journal={Bioinformatics Advances},<br>&nbsp; volume={5},<br>&nbsp; number={1},<br>&nbsp; pages={vbaf124},<br>&nbsp; year={2025},<br>&nbsp; publisher={Oxford University Press}<br>}</pre> <p>&nbsp;</p>