{"id":19839848,"url":"https://github.com/qdata/deepmotif","last_synced_at":"2025-07-25T11:40:27.548Z","repository":{"id":83652129,"uuid":"54785426","full_name":"QData/DeepMotif","owner":"QData","description":"Deep Motif (ICLR16)/ Deep Motif Dashboard (PSB17): Visualizing Genomic Sequence Classifications","archived":false,"fork":false,"pushed_at":"2019-04-19T20:19:53.000Z","size":5115,"stargazers_count":46,"open_issues_count":0,"forks_count":14,"subscribers_count":13,"default_branch":"master","last_synced_at":"2025-04-06T17:05:27.267Z","etag":null,"topics":["deep-learning","genomics","torch"],"latest_commit_sha":null,"homepage":"http://www.deepmotif.org","language":"Lua","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/QData.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2016-03-26T15:30:52.000Z","updated_at":"2024-12-30T12:35:25.000Z","dependencies_parsed_at":"2023-03-12T18:59:24.811Z","dependency_job_id":null,"html_url":"https://github.com/QData/DeepMotif","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/QData%2FDeepMotif","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/QData%2FDeepMotif/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/QData%2FDeepMotif/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/QData%2FDeepMotif/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/QData","download_url":"https://codeload.github.com/QData/DeepMotif/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":251932525,"owners_count":21667159,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["deep-learning","genomics","torch"],"created_at":"2024-11-12T12:24:34.809Z","updated_at":"2025-05-01T19:30:25.575Z","avatar_url":"https://github.com/QData.png","language":"Lua","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Deep Motif Dashboard: Visualizing and Understanding Genomic Sequences Using Deep Neural Networks\n### Jack Lanchantin, Ritambhara Singh, Beilun Wang, and Yanjun Qi\n### Pacific Symposium on Biocomputing (PSB) 2017\nhttps://arxiv.org/abs/1608.03644\n\n### Talk slides:\nhttps://github.com/QData/DeepMotif/blob/master/psb_talk_slides.pdf\n\n### bibtex:\n```\n@inproceedings{lanchantin2017deep,\n  title={Deep motif dashboard: Visualizing and understanding genomic sequences using deep neural networks},\n  author={Lanchantin, Jack and Singh, Ritambhara and Wang, Beilun and Qi, Yanjun},\n  booktitle={PACIFIC SYMPOSIUM ON BIOCOMPUTING 2017},\n  pages={254--265},\n  year={2017},\n  organization={World Scientific}\n}\n```\n\n[![LICENSE](https://img.shields.io/badge/license-MIT-brightgreen.svg)](https://github.com/QData/DeepMotif/blob/master/LICENSE)\n\n\n# Installation\n\n\n## Lua setup\nThe main modeling code is written in Lua using [torch](http://torch.ch)\nInstallation instructions are located [here](http://torch.ch/docs/getting-started.html#_)\n\nAfter installing torch, install / update these packages by running the following:\n\n```bash\nluarocks install torch\nluarocks install nn\nluarocks install optim\n```\n\n### CUDA support (Optional)\nTo enable GPU acceleration with [CUDA](https://developer.nvidia.com/cuda-downloads), you'll need to install CUDA 6.5 or higher as well as [cutorch](https://github.com/torch/cutorch) and [cunn](https://github.com/torch/cunn). You can install / update the torch CUDA libraries by running:\n\n```bash\nluarocks install cutorch\nluarocks install cunn\n```\n\n## LFS\n\nInstall git large file storage (LFS) in order to download the dataset directly from this git repository.\n\nhttps://git-lfs.github.com/\n\n\n## Visualization Method Dependencies\n\nWeblogo: http://weblogo.berkeley.edu/\n\nR: https://www.r-project.org/\n\n\n# Usage\n\n\n## Step 1: Get the Data\ntar xvzf data/deepbind.tar.gz -C data/\n\n\n## Step 2: Train the model\nYou can train one of the 3 types of models (CNN, RNN, or CNN-RNN). Check the flags in main.lua for parameters to run the code.\n\nFor CNN model:\n```bash\nth main.lua -cnn\n```\n\nFor CNN model:\n```bash\nth main.lua -rnn\n```\n\nFor CNN-RNN model:\n```bash\nth main.lua -cnn -rnn\n```\n\n## Step 3: Visualize the Model's Predictions\nOnce you have trained models, you can visualize the predictions. \n\n\nSaliency Map\n```bash\nth saliency_map.lua\n```\n\nTemporal Output Values\n```bash\nth temporal_output_values.lua\n```\n\nClass Optimization\n```bash\nth class_optimization.lua\n```\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fqdata%2Fdeepmotif","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fqdata%2Fdeepmotif","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fqdata%2Fdeepmotif/lists"}