DSM: Deep Sequential Model for Complete Neuronal Morphology Representation and Feature Extraction

This is an open-source repository for hosting codes and data files from research, "DSM: Deep Sequential Model for Complete Neuronal Morphology Representation and Feature Extraction". We also provided a web service based on our methods, please go to http://114.117.165.134:8501/.

(1)raw_dataset.zip: 

1. 1,282 neuron reconstructions from SEU-Allen dataset;
2. 1,002 neuron reconstructions from Janelia dataset;
3. 1,100 neuron reconstructions from ION dataset.

(2)Supplementary.zip: Supplementary information, including tables and figures;

(3)DSM-tools.zip: A python package for converting neuron morphology into sequences and implementing DSM models.

1. NeuronSequenceDataset class: to transform SWC files to sequence dataframes by binary tree traversals, and prepare for the input of DSM networks.
2. DSMDataConverter class: a helper to convert the sequence dataframes for classification and clustering.
3. DSMHierarchicalAttentionNetwork class: classification model, giving a pre-trained DSM-HAN model by default.
4. DSMAutoencoder class: clustering model, giving a pre-trained DSM-AE model by default.

(4)neuron2seq_for_developer.zip: A repository for further development of the models, including source codes and all data files.