{"id":15132637,"url":"https://github.com/rosettacommons/rosettafold","last_synced_at":"2025-05-15T09:04:04.658Z","repository":{"id":39537997,"uuid":"381498685","full_name":"RosettaCommons/RoseTTAFold","owner":"RosettaCommons","description":"This package contains deep learning models and related scripts for RoseTTAFold","archived":false,"fork":false,"pushed_at":"2024-02-15T15:28:32.000Z","size":176112,"stargazers_count":2128,"open_issues_count":94,"forks_count":446,"subscribers_count":59,"default_branch":"main","last_synced_at":"2025-04-07T03:16:22.690Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/RosettaCommons.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},"funding":"This work was supported by Microsoft (MB, DB, and generous gifts of Azure compute time and expertise), Eric and Wendy Schmidt by recommendation of the Schmidt Futures program (FD, HP), Open Philanthropy (DB, GRL), The Washington Research Foundation (MB, GRL, JW), National Science Foundation Cyberinfrastructure for Biological Research, Award"},"created_at":"2021-06-29T21:14:40.000Z","updated_at":"2025-04-07T01:42:31.000Z","dependencies_parsed_at":"2024-09-21T05:12:26.498Z","dependency_job_id":null,"html_url":"https://github.com/RosettaCommons/RoseTTAFold","commit_stats":{"total_commits":40,"total_committers":6,"mean_commits":6.666666666666667,"dds":0.35,"last_synced_commit":"fcf9125c59e3dd84cf511dcb475ddd81a23613f5"},"previous_names":[],"tags_count":2,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RosettaCommons%2FRoseTTAFold","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RosettaCommons%2FRoseTTAFold/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RosettaCommons%2FRoseTTAFold/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RosettaCommons%2FRoseTTAFold/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/RosettaCommons","download_url":"https://codeload.github.com/RosettaCommons/RoseTTAFold/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248890623,"owners_count":21178472,"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":[],"created_at":"2024-09-26T04:22:04.855Z","updated_at":"2025-04-14T13:46:49.169Z","avatar_url":"https://github.com/RosettaCommons.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# *RoseTTAFold* \nThis package contains deep learning models and related scripts to run RoseTTAFold.  \nThis repository is the official implementation of RoseTTAFold: Accurate prediction of protein structures and interactions using a 3-track network.\n\n## Installation\n\n1. Clone the package\n```\ngit clone https://github.com/RosettaCommons/RoseTTAFold.git\ncd RoseTTAFold\n```\n\n2. Create conda environment using `RoseTTAFold-linux.yml` file and `folding-linux.yml` file. The latter is required to run a pyrosetta version only (run_pyrosetta_ver.sh).\n```\n# create conda environment for RoseTTAFold\n#   If your NVIDIA driver compatible with cuda11\nconda env create -f RoseTTAFold-linux.yml\n#   If not (but compatible with cuda10)\nconda env create -f RoseTTAFold-linux-cu101.yml\n\n# create conda environment for pyRosetta folding \u0026 running DeepAccNet\nconda env create -f folding-linux.yml\n```\n\n3. Download network weights (under Rosetta-DL Software license -- please see below)  \nWhile the code is licensed under the MIT License, the trained weights and data for RoseTTAFold are made available for non-commercial use only under the terms of the Rosetta-DL Software license. You can find details at https://files.ipd.uw.edu/pub/RoseTTAFold/Rosetta-DL_LICENSE.txt\n\n[Update Nov/02/2021] It's now including the weights (RF2t.pt) for RoseTTAFold-2track model used for yeast PPI screening. If you want to use it, please re-download weights. The original RoseTTAFold weights are not changed.\n\n```\nwget https://files.ipd.uw.edu/pub/RoseTTAFold/weights.tar.gz\ntar xfz weights.tar.gz\n```\n\n4. Download and install third-party software.\n```\n./install_dependencies.sh\n```\n\n5. Download sequence and structure databases\n```\n# uniref30 [46G]\nwget http://wwwuser.gwdg.de/~compbiol/uniclust/2020_06/UniRef30_2020_06_hhsuite.tar.gz\nmkdir -p UniRef30_2020_06\ntar xfz UniRef30_2020_06_hhsuite.tar.gz -C ./UniRef30_2020_06\n\n# BFD [272G]\nwget https://bfd.mmseqs.com/bfd_metaclust_clu_complete_id30_c90_final_seq.sorted_opt.tar.gz\nmkdir -p bfd\ntar xfz bfd_metaclust_clu_complete_id30_c90_final_seq.sorted_opt.tar.gz -C ./bfd\n\n# structure templates (including *_a3m.ffdata, *_a3m.ffindex) [over 100G]\nwget https://files.ipd.uw.edu/pub/RoseTTAFold/pdb100_2021Mar03.tar.gz\ntar xfz pdb100_2021Mar03.tar.gz\n# for CASP14 benchmarks, we used this one: https://files.ipd.uw.edu/pub/RoseTTAFold/pdb100_2020Mar11.tar.gz\n```\n\n6. Obtain a [PyRosetta licence](https://els2.comotion.uw.edu/product/pyrosetta) and install the package in the newly created `folding` conda environment ([link](http://www.pyrosetta.org/downloads)).\n\n## Usage\n\n```\n# For monomer structure prediction\ncd example\n../run_[pyrosetta, e2e]_ver.sh input.fa .\n\n# For complex modeling\n# please see README file under example/complex_modeling/README for details.\npython network/predict_complex.py -i paired.a3m -o complex -Ls 218 310 \n\n# For PPI screening using faster 2-track version (example input and output are at example/complex_2track)\npython network_2track/predict_msa.py -msa [paired MSA file in a3m format] -npz [output npz file name] -L1 [Length of first chain]\ne.g. python network_2track/predict_msa.py -msa input.a3m -npz complex.npz -L1 218\n```\n\n## Expected outputs\nFor the pyrosetta version, user will get five final models having estimated CA rms error at the B-factor column (model/model_[1-5].crderr.pdb).  \nFor the end-to-end version, there will be a single PDB output having estimated residue-wise CA-lddt at the B-factor column (t000_.e2e.pdb).\n\n## FAQ\n1. Segmentation fault while running hhblits/hhsearch  \nFor easy install, we used a statically compiled version of hhsuite (installed through conda). Currently, we're not sure what exactly causes segmentation fault error in some cases, but we found that it might be resolved if you compile hhsuite from source and use this compiled version instead of conda version. For installation of hhsuite, please see [here](https://github.com/soedinglab/hh-suite).\n\n2. Submitting jobs to computing nodes  \nThe modeling pipeline provided here (run_pyrosetta_ver.sh/run_e2e_ver.sh) is a kind of guidelines to show how RoseTTAFold works. For more efficient use of computing resources, you might want to modify the provided bash script to submit separate jobs with proper dependencies for each of steps (more cpus/memory for hhblits/hhsearch, using gpus only for running the networks, etc). \n\n## Links:\n\n* [Robetta server](https://robetta.bakerlab.org/) (RoseTTAFold option)\n* [RoseTTAFold models for CASP14 targets](https://files.ipd.uw.edu/pub/RoseTTAFold/casp14_models.tar.gz) [input MSA and hhsearch files are included]\n\n## Credit to performer-pytorch and SE(3)-Transformer codes\nThe code in the network/performer_pytorch.py is strongly based on [this repo](https://github.com/lucidrains/performer-pytorch) which is pytorch implementation of [Performer architecture](https://arxiv.org/abs/2009.14794).\nThe codes in network/equivariant_attention is from the original SE(3)-Transformer [repo](https://github.com/FabianFuchsML/se3-transformer-public) which accompanies [the paper](https://arxiv.org/abs/2006.10503) 'SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks' by Fabian et al.\n\n\n## References\n\nM. Baek, et al., Accurate prediction of protein structures and interactions using a three-track neural network, Science (2021). [link](https://www.science.org/doi/10.1126/science.abj8754)\n\nI.R. Humphreys, J. Pei, M. Baek, A. Krishnakumar, et al, Computed structures of core eukaryotic protein complexes, Science (2021). [link](https://www.science.org/doi/10.1126/science.abm4805)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frosettacommons%2Frosettafold","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Frosettacommons%2Frosettafold","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frosettacommons%2Frosettafold/lists"}