{"id":42269182,"url":"https://github.com/kundajelab/dragonn","last_synced_at":"2026-01-27T07:11:06.780Z","repository":{"id":8914346,"uuid":"60218942","full_name":"kundajelab/dragonn","owner":"kundajelab","description":"A toolkit to learn how to model and interpret regulatory sequence data using deep learning.","archived":false,"fork":false,"pushed_at":"2023-08-01T06:04:46.000Z","size":173212,"stargazers_count":263,"open_issues_count":17,"forks_count":67,"subscribers_count":24,"default_branch":"master","last_synced_at":"2025-12-06T20:28:12.290Z","etag":null,"topics":["deep-learning","genomics"],"latest_commit_sha":null,"homepage":"http://kundajelab.github.io/dragonn/","language":"Jupyter Notebook","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/kundajelab.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGES.txt","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":"2016-06-02T00:03:18.000Z","updated_at":"2025-10-12T10:52:18.000Z","dependencies_parsed_at":"2023-01-11T20:11:32.154Z","dependency_job_id":"b30f70b4-fbed-4ae8-ab44-524ca6911e78","html_url":"https://github.com/kundajelab/dragonn","commit_stats":null,"previous_names":[],"tags_count":4,"template":false,"template_full_name":null,"purl":"pkg:github/kundajelab/dragonn","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kundajelab%2Fdragonn","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kundajelab%2Fdragonn/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kundajelab%2Fdragonn/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kundajelab%2Fdragonn/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/kundajelab","download_url":"https://codeload.github.com/kundajelab/dragonn/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kundajelab%2Fdragonn/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28807479,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-27T06:25:51.065Z","status":"ssl_error","status_checked_at":"2026-01-27T06:25:50.640Z","response_time":168,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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"],"created_at":"2026-01-27T07:11:06.050Z","updated_at":"2026-01-27T07:11:06.774Z","avatar_url":"https://github.com/kundajelab.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# [DragoNN](http://kundajelab.github.io/dragonn/)\n[![Build Status](https://travis-ci.org/kundajelab/dragonn.svg?branch=master)](https://travis-ci.org/kundajelab/dragonn)\n[![license](https://img.shields.io/github/license/mashape/apistatus.svg?maxAge=2592000)](https://github.com/kundajelab/dragonn/blob/master/LICENSE)\n\nThe `dragonn` package implements Deep RegulAtory GenOmic Neural Networks (DragoNNs) for predictive modeling of regulatory genomics, nucleotide-resolution feature discovery, and simulations for systematic development and benchmarking.\n\n![demo](http://i.imgur.com/1fAgrt2.gif)\n\n## Installation\nTo install the latest released version of DragoNN, install the [Anaconda](https://www.continuum.io/downloads) python distribution. Then, run:\n```\nconda install dragonn -c kundajelab\n```\nDragoNN is compatible with Python2 and Python3. Specific optional features such as [DeepLIFT](https://github.com/kundajelab/deeplift) and [MOE](https://github.com/Yelp/MOE) are compatible with Python2 only.\n\n\n## 15 seconds to your first DragoNN model\nThe `dragonn` package provides a simple command line interface to train DragoNN models, test them, and predict on sequence data. Train an example model by running:\n\n```\ndragonn train --pos-sequences examples/example_pos_sequences.fa --neg-sequences examples/example_neg_sequences.fa --prefix training_example\n```\n\nThis will store a model file, training_example.model.json, with the model architecture and a weights file, training_example.weights.h5, with the parameters of the trained model. Test the model by running:\n\n```\ndragonn test --pos-sequences examples/example_pos_sequences.fa --neg-sequences examples/example_neg_sequences.fa --arch-file training_example.arch.json --weights-file training_example.weights.h5\n```\n\nThis will print the model's test performance metrics. Model predictions on sequence data can be obtained by running:\n\n```\ndragonn predict --sequences examples/example_pos_sequences.fa --arch-file training_example.arch.json --weights-file training_example.weights.h5 --output-file example_predictions.txt\n```\n\nThis will store the model predictions for sequences in example_pos_sequences.fa in the output file example_predictions.txt. Interpret sequence data with a dragonn model by running:\n\n```\ndragonn interpret --sequences examples/example_pos_sequences.fa --arch-file training_example.arch.json --weights-file training_example.weights.h5 --prefix example_interpretation\n```\n\nThis will write the most important subsequence in each input sequence along with its location in the input sequence in the file example_interpretation.task_0.important_sequences.txt.\nNote: by default, only examples with predicted positive class probability \u003e0.5 are interpreted. Examples below this threshold yield important subsequence of Ns with location -1. This default can be changed with the flag --pos-threshold.\n\nWe encourage DragoNN users to share models in the [Kipoi Genomics Model Zoo](http://kipoi.org/). Enjoy!\n\n## DragoNN paper supplement\n\nWe provide trained models, data, and code in the [paper supplement](paper_supplement) to reproduce results in the DragoNN manuscript.","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkundajelab%2Fdragonn","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkundajelab%2Fdragonn","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkundajelab%2Fdragonn/lists"}