Design of tissue-specific mammalian enhancers that function in vivo

This repository contains the code used to train models, including transfer learning across different data modalities, generate predictions, compute contribution tracks, and design synthetic enhancers. All source code is provided in DeepSTARR_Mouse_codes.zip, which preserves the original project directory structure. The archive contains the following modules: bin/ – auxiliary functions and shared utilities Accessibility_model_training/ – scripts for training chromatin accessibility prediction models Enhancer_activity_model_training/ – scripts for training enhancer activity prediction models Ledidi_enhancer_design/ – scripts for Ledidi-based synthetic enhancer design Model_evaluation/ – scripts for model evaluation and control model training replacement_transfer_learning/ – scripts for replacement-based transfer learning experiments motif_syntax_rules_analysis/ – scripts used to analyze motif syntax rules