Skip to main content
zenodoopen

Enhancer design manuscript data and models

<p>This repository holds the&nbsp;trained DNA accessibility and enhancer activity models, and the data&nbsp;used to train and evaluate the model.</p> <p>&nbsp;</p> <p><strong>Files for DNA accessibility models:</strong></p> <ul> <li><strong>Accessibility_models_training_data.tar.gz</strong> <ul> <li>&lt;fold&gt;_sequences_&lt;set&gt;.fa <ul> <li>FASTA files with DNA sequences of genomic regions from train/val/test sets.</li> </ul> </li> <li>&lt;fold&gt;_sequences_activity_&lt;set&gt;.txt <ul> <li>Files with accessibility scores for sequences from train/val/test sets.</li> </ul> </li> </ul> </li> <li><strong>Accessibility_model_files.tar.gz</strong> <ul> <li>model.h5 and model.json files for each&nbsp;Results_&lt;fold&gt;_&lt;tissue&gt;_DeepSTARR2_&lt;rep&gt;</li> </ul> </li> <li><strong>Accessibility_models_test_set_predictions.rds</strong> <ul> <li>RDS object with predictions for accessibility</li> </ul> </li> </ul> <p>&nbsp;</p> <p><strong>Files for enhancer activity models:</strong></p> <ul> <li><strong>EnhancerActivity_model_files.tar.gz</strong> <ul> <li>&lt;fold&gt;_sequences_&lt;set&gt;.fa <ul> <li>FASTA files with DNA sequences of genomic regions from train/val/test sets.</li> </ul> </li> <li>&lt;fold&gt;_sequences_activity_&lt;set&gt;.txt <ul> <li>Files with enhancer activity labels for sequences from train/val/test sets.</li> </ul> </li> </ul> </li> <li><strong>EnhancerActivity_model_files.tar.gz</strong> <ul> <li>model.h5, model.json and&nbsp;Model_evaluation.pdf files for each&nbsp;Results_&lt;fold&gt;_&lt;tissue&gt;_&lt;rep&gt;</li> </ul> </li> <li><strong>EnhancerActivity_models_clean_evaluation_data.rds</strong> <ul> <li>RDS object with sequences used for final evaluation of the models</li> </ul> </li> <li><strong>EnhancerActivity_models_results_per_tissue_test_set.rds</strong> <ul> <li>RDS object with predictions and results of the enhancer activity models</li> </ul> </li> </ul>

ShareScore

32/100

Overall dataset sharing score

Score breakdown

These five areas show where the dataset supports — or may limit — practical reuse.

Stewardship
4
Harmonization
4
Access
16
Reuse readiness
8
Engagement
0