APARENT2 Training Data and Models

<p>Processed training data for the APARENT2 model (measurements from the random MPRA and designed oligo pool originally published by Bogard et al., 2019; see&nbsp;https://doi.org/10.1016/j.cell.2019.04.046&nbsp;for reference). This repository also contains the APARENT2 model file. For more information on the training procedure, see&nbsp;the <em>Genome Biology</em> article &quot;Deciphering the impact of genetic variation on human polyadenylation using APARENT2&quot; (https://genomebiology.biomedcentral.com/articles/10.1186/s13059-022-02799-4). Two versions of the model&nbsp;are available:</p> <p>(a)&nbsp;aparent_all_libs_resnet_no_clinvar_wt_ep_5.h5: The originally trained APARENT2 model.<br> (b)&nbsp;aparent_all_libs_resnet_no_clinvar_wt_ep_5_var_batch_size_inference_mode_no_drop.h5: Identical weights and predictions as model (a), but&nbsp;the normalization layers have been set to inference mode and the dropout layers have been removed (thus making it compatible with the scrambler pipeline).</p>