Task-driven neural network models predict neural dynamics of proprioception: Experimental data, activations and predictions of neural network models

#############

Task-driven neural network models predict neural dynamics of proprioception, Cell 2024

#############

Authors: Marin Vargas, Alessandro (orcid=0000-0001-7073-4120) and Bisi, Axel (orcid=0009-0006-8602-7555) and Chiappa, Alberto Silvio (orcid=0009-0001-2764-6552) and Versteeg, Christopher (orcid=0000-0002-4269-5109) and Miller, Lee E. (orcid=0000-0001-8675-7140) and Mathis, Alexander (orcid=0000-0002-3777-2202)

Affiliation: EPFL

Date: January, 2024

Link to the Cell article:

https://www.cell.com/cell/pdf/S0092-8674(24)00239-3.pdf

--------------------------------

Here we provide the neural data, activation and predictions for the best models and result dataframes of our article "Task-driven neural network models predict neural dynamics of proprioception".

It contains the behavioral and neural experimental data (cuneate nucleus and somatosensory recordings from the Miller Lab, Northwestern University), the result dataframes for task-driven and untrained models, the activations and predictions for the *best models for all tasks* for active and passive movements and the predictions for linear models for active and passive movements. 

Note, the predictions of other models can be computed from the network weights that were deposited for all trained models. 

The overall structure of the data is:

└── exp_analysis    ├── results                                                                - Contains the result dataframe of the predictions for all models, tasks and primates    ├── activations    │   ├── active                                                            - Contains activations related to active movements    │   └── passive                                                         - Contains activations related to passive movements    ├── predictions    │   ├── active                                                            - Contains predictions related to active movements    │   └── passive                                                         - Contains predictions related to passive movements    └── beh_exp_datasets        ├── matlab_data                                                 - Contains raw behavioral and neural data        ├── MonkeyAlignedDatasets_new                   - Contains padded test behavioral input for generating network activations        ├── MonkeyDatasets                                         - Contains not aligned padded test behavioral input for generating network activations        ├── MonkeySpikeRegressDatasets                 - Contains datasets for training data-driven models        ├── MonkeySpikeRegressDatasets_new        - Contains trial index for regression splits         └── new_beh_exp_dataframe                           - Contains pre-processed behavioral and neural data

--------------------------------

The activations and predictions for the best 3 models and for all tasks are stored in experiments folder (in .h5 format) that follows the same name convention of the checkpoints.

The checkpoints are stored in experiment folders (experiment_***) that follow this scheme:- Task:         shallow exp id,     deep TCNs exp id,     LSTM id.

Experiment IDs for each task:

- Untrained:                                                               15,         115,         45- Classification:                                                        4015,   5015,   4045

- Torque:                                                                    8015,   8030,   8045

- Regress joint pos:                                                 17016,  17031,  17046- Regress joint vel:                                                   17216,  17231,  17246- Regress joint pos & vel::                                       17416,  17431,  17446- Regress joint pos & vel & acc::                            20516,  20531,  20546

- Regress hand pos:                                                 4016,   5016,   4046- Regress hand vel:                                                   17316,  17331,  17346- Regress hand pos & vel:                                        17516,  17531,  17546- Regress hand pos & vel & acc:                             20416,  17831,  17846

- Regress hand and elbow pos:                              20016,  20031,  20046- Regress hand and elbow vel:                                20916,  20931,  20946- Regress hand and elbow pos & vel:                     20616,  20631,  20646- Regress hand and elbow pos & vel & acc:          20816,  20831,  20846

- Redundancy reduction:                                          10020,  10035,  10050- Autoencoder                                                            20716 & 20717, 20731 & 20732,   X

The code to process the behavioral data is available at: https://github.com/amathislab/Task-driven-Proprioception/tree/master/exp_data_processingThe code to load and use the models to generate activations and predictions is available at: https://github.com/amathislab/Task-driven-Proprioception/tree/master/neural_prediction

To reproduce the results, it is possible to reproduce the main figures using the result dataframe. See our repository for more details. 

--------------------------------

The datasets, weights, activations and predictions are released with Creative Commons Attribution 4.0 license.

The code is released under the MIT license, see https://github.com/amathislab/Task-driven-Proprioception

If you find our code, weights, predictions or ideas useful, please cite:

@article{vargas2024task,  title={Task-driven neural network models predict neural dynamics of proprioception},  author={{Marin Vargas}, Alessandro and Bisi, Axel and Chiappa, Alberto S and Versteeg, Chris and Miller, Lee E and Mathis, Alexander},  journal={Cell},  year={2024},  publisher={Elsevier}}