Multimodal learning of noncoding variant effects using genome sequence and chromatin structure

ncVarPred-1D3D:

The data used for testing the inconsistency among genome sequence, epigenetic profile, and later, to show its relation to 3D chromatin structure can be found in sanity_check_data.tar.gz.

Some trained model for noncoding mutation effect prediction (mapping genome sequence to epigenetic profile) can be found in CNN_MLP, CNN_GCN, CNN_RNN_MLP, CNN_RNN_GCN.tar.gz.

The trained model for pathogenic variants prediction can be found in fewshot_pathogenic_model.tar.gz. 

The training data can be found in training_data.tar.gz.

Some noncoding variant effects prediction results, e.g. eQTL and pathogenic variants, can be replicated using the data shared in ncVar_data.tar.gz.