{"id":32139372,"url":"https://github.com/mxfold/mxfold2","last_synced_at":"2026-02-23T04:32:55.169Z","repository":{"id":44447608,"uuid":"286628838","full_name":"mxfold/mxfold2","owner":"mxfold","description":"MXfold2: RNA secondary structure prediction using deep learning with thermodynamic integration","archived":false,"fork":false,"pushed_at":"2026-01-29T08:50:08.000Z","size":14699,"stargazers_count":157,"open_issues_count":16,"forks_count":36,"subscribers_count":5,"default_branch":"master","last_synced_at":"2026-01-29T23:23:47.364Z","etag":null,"topics":["deep-learning","rna-secondary-structure-prediction"],"latest_commit_sha":null,"homepage":"","language":"Python","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/mxfold.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,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2020-08-11T02:44:43.000Z","updated_at":"2026-01-27T20:23:52.000Z","dependencies_parsed_at":"2025-12-12T02:04:18.300Z","dependency_job_id":null,"html_url":"https://github.com/mxfold/mxfold2","commit_stats":{"total_commits":197,"total_committers":2,"mean_commits":98.5,"dds":"0.010152284263959421","last_synced_commit":"51b213676708bebd664f0c40873a46e09353e1ee"},"previous_names":["keio-bioinformatics/mxfold2"],"tags_count":3,"template":false,"template_full_name":null,"purl":"pkg:github/mxfold/mxfold2","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mxfold%2Fmxfold2","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mxfold%2Fmxfold2/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mxfold%2Fmxfold2/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mxfold%2Fmxfold2/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mxfold","download_url":"https://codeload.github.com/mxfold/mxfold2/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mxfold%2Fmxfold2/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29738079,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-23T02:24:00.660Z","status":"ssl_error","status_checked_at":"2026-02-23T02:22:56.087Z","response_time":90,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: 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","rna-secondary-structure-prediction"],"created_at":"2025-10-21T05:42:23.551Z","updated_at":"2026-02-23T04:32:55.160Z","avatar_url":"https://github.com/mxfold.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# MXfold2\nRNA secondary structure prediction using deep learning with thermodynamic integration\n\n## Installation\n\n### System requirements\n* python (\u003e=3.7)\n* pytorch (\u003e=1.4)\n* C++17 compatible compiler (tested on Apple clang version 12.0.0 and GCC version 7.4.0) (optional)\n\n### Install from wheel\n\nWe provide the wheel python packages for several platforms at [the release](https://github.com/mxfold/mxfold2/releases). You can download an appropriate package and install it as follows:\n\n    % pip3 install mxfold2-0.1.2-cp310-cp310-manylinux_2_17_x86_64.whl\n\n### Install from sdist\n\nYou can build and install from the source distribution downloaded from [the release](https://github.com/mxfold/mxfold2/releases) as follows:\n\n    % pip3 install mxfold2-0.1.2.tar.gz\n\nTo build MXfold2 from the source distribution, you need a C++17 compatible compiler.\n\n## Prediction\n\nYou can predict RNA secondary structures of given FASTA-formatted RNA sequences like:\n\n    % mxfold2 predict test.fa\n    \u003eDS4440\n    GGAUGGAUGUCUGAGCGGUUGAAAGAGUCGGUCUUGAAAACCGAAGUAUUGAUAGGAAUACCGGGGGUUCGAAUCCCUCUCCAUCCG\n    (((((((........(((((..((((.....))))...)))))...................(((((.......)))))))))))). (24.8)\n\nBy default, MXfold2 employs the parameters trained from TrainSetA and TrainSetB (see our paper).\n\nWe provide other pre-trained models used in our paper. You can download [``models-0.1.0.tar.gz``](https://github.com/mxfold/mxfold2/releases/download/v0.1.0/models-0.1.0.tar.gz) and extract the pre-trained models from it as follows:\n\n    % tar -zxvf models-0.1.0.tar.gz\n\nThen, you can predict RNA secondary structures of given FASTA-formatted RNA sequences like:\n\n    % mxfold2 predict @./models/TrainSetA.conf test.fa\n    \u003eDS4440\n    GGAUGGAUGUCUGAGCGGUUGAAAGAGUCGGUCUUGAAAACCGAAGUAUUGAUAGGAAUACCGGGGGUUCGAAUCCCUCUCCAUCCG\n    (((((((.((....))...........(((((.......))))).(((((......))))).(((((.......)))))))))))). (24.3)\n\nHere, ``./models/TrainSetA.conf`` specifies a lot of parameters including hyper-parameters of DNN models.\n\n## Training\n\nMXfold2 can train its parameters from BPSEQ-formatted RNA sequences. You can also download the datasets used in our paper at [the release](https://github.com/mxfold/mxfold2/releases/tag/v0.1.0). \n\n    % mxfold2 train --model MixC --param model.pth --save-config model.conf data/TrainSetA.lst\n\nYou can specify a lot of model's hyper-parameters. See ``mxfold2 train --help``. In this example, the model's hyper-parameters and the trained parameters are saved in ``model.conf`` and ``model.pth``, respectively.\n\n## Web server\n\nA web server is working at http://www.dna.bio.keio.ac.jp/mxfold2/.\n\n\n## References\n\n* Sato, K., Akiyama, M., Sakakibara, Y.: RNA secondary structure prediction using deep learning with thermodynamic integration. *Nat Commun* **12**, 941 (2021). https://doi.org/10.1038/s41467-021-21194-4\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmxfold%2Fmxfold2","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmxfold%2Fmxfold2","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmxfold%2Fmxfold2/lists"}