[{"_1":2,"_159":-5,"_160":-5},"loaderData",{"_3":4,"_17":18,"_25":26,"_138":139},"root",{"_5":-5,"_6":-7,"_7":8,"_9":-7,"_10":11,"_12":-7,"_13":14,"_15":16},"currentUser","primaryEmail","siteVerification","6LeIxAcTAAAAAJcZVRqyHh71UMIEGNQ_MXjiZKhI","toast","enableDev",false,"incidentStatus","theme","system","contrast","normal","routes/_layout",{"_19":-5,"_20":21,"_22":21,"_23":11,"_24":21},"username","isAskGordonEnabled",true,"isUsingNewTemplate","showMinimalLanding","showHoneypotTrap","routes/_layout.r.$namespace.$reponame",{"_27":28,"_29":-5,"_30":11,"_31":11,"_32":33,"_34":35,"_36":-5,"_37":11,"_38":39,"_88":-5,"_89":90,"_129":-5,"_130":11,"_131":21,"_132":11,"_133":-5,"_134":11,"_135":-5,"_136":137},"canonicalUrl","https://hub.docker.com/r/mircare/porter5/tags","mcpServer","canSeeDockerfile","canSeeAutobuilds","namespace","mircare","reponame","porter5","cloudBuildSource","isAutobuildsAvailable","repo",{"_40":41,"_42":43,"_45":46,"_47":48,"_49":11,"_50":51,"_52":53,"_54":55,"_57":35,"_32":33,"_58":59,"_60":44,"_61":62,"_63":64,"_65":66,"_67":-5,"_68":62,"_69":70,"_71":11,"_72":33,"_73":74,"_79":11,"_80":81,"_85":33,"_86":87},"categories",[],"content_types",[44],"image","date_registered","2019-05-30T11:43:13.427122Z","description","Fast, state-of-the-art ab initio prediction of protein secondary structure in 3 and 8 classes","is_private","last_updated","2020-05-21T08:44:49.775131Z","last_modified","2024-10-16T13:48:34.145251Z","media_types",[56],"application/vnd.docker.container.image.v1+json","name","pull_count",484,"repository_type","star_count",0,"status",1,"status_description","active","source","collaborator_count","full_description","[![PWC](https://camo.githubusercontent.com/6887feb0136db5156c4f4146e3dd2681d06d9c75/68747470733a2f2f692e6372656174697665636f6d6d6f6e732e6f72672f6c2f62792d6e632d73612f342e302f38387833312e706e67)](https://github.com/mircare/Porter5/#license)\n[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/deeper-profiles-and-cascaded-recurrent-and/protein-secondary-structure-prediction-on-2)](https://paperswithcode.com/sota/protein-secondary-structure-prediction-on-2?p=deeper-profiles-and-cascaded-recurrent-and) \n\n\n# Porter 5 \n### Light, fast and high quality prediction of protein secondary structure in 3 and 8 classes\n\nThe web server, train and test sets of Porter 5 are available at http://distilldeep.ucd.ie/porter/. \nThe docker container is available at https://hub.docker.com/r/mircare/porter5 ([HOWTO](https://github.com/mircare/Porter5/#use-the-docker-image)). \n\nSee https://github.com/mircare/Brewery to predict more protein structure annotations, *and download **COVID-19** predictions*.\n\n

$\"Pipeline$ Diagram of the pipeline we propose to gather and exploit deeper profiles.

\n\n## Setup\n```\n$ git clone https://github.com/mircare/Porter5/ --depth 1 && rm -rf Porter5/.git\n```\n\n### Requirements\n1. Python3 (https://www.python.org/downloads/);\n1. NumPy (https://www.scipy.org/scipylib/download.html);\n1. HHblits (https://github.com/soedinglab/hh-suite/);\n1. uniprot20 (http://wwwuser.gwdg.de/~compbiol/data/hhsuite/databases/hhsuite_dbs/old-releases/uniprot20_2016_02.tgz).\n\n#### Optionally (for more accurate predictions):\n1. PSI-BLAST (ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/LATEST/); \n1. UniRef90 (ftp://ftp.uniprot.org/pub/databases/uniprot/uniref/uniref90/uniref90.fasta.gz).\n\n\n## How to run Porter 5\n```\n# For fast and accurate predictions (exploiting HHblits only)\n$ python3 Porter5/Porter5.py -i Porter5/example/2FLGA.fasta --cpu 4 --fast\n\n# For very accurate predictions (exploiting both HHblits and PSI-BLAST)\n$ python3 Porter5/Porter5.py -i Porter5/example/2FLGA.fasta --cpu 4\n```\n\n### How to run Porter 5 on multiple sequences\n```\n# To split a FASTA file with multiple sequences (Optional)\n$ python3 Porter5/split_fasta.py many_sequences.fasta\n\n# To predict all the fasta files in a given directory (Fastas)\n$ python3 Porter5/multiple_fasta.py -i Fastas/ --cpu 4 --fast\n\n# To run multiple predictions in parallel (using a total of 8 cores)\n$ python3 Porter5/multiple_fasta.py -i Fastas/ --cpu 4 --parallel 2 --fast\n```\n\n### Use the docker image\n```\n# Set-up docker image\n$ docker pull mircare/porter5\n\n# set the absolute PATHs for databases and query sequences (stored locally)\n$ docker run --name porter5 -v /**PATH_to_uniprot20_2016_02**:/uniprot20 \\\n-v /**PATH_to_UniRef90_optional**:/uniref90 -v /**PATH_to_fasta_to_predict**:/Porter5/query \\\n--cap-add IPC_LOCK mircare/porter5 sleep infinity &\n\n# How to run a prediction using 5 cores and HHblits only\n$ docker exec porter5 python3 Porter5.py -i query/2FLGA.fasta --cpu 5 --fast\n```\n\n\n## Performances in 3 states on large independent test set\n| Method | Q3 per AA | SOV'99 per AA | Q3 per protein | SOV'99 per protein |\n| :--- | :---: | :---: | :---: | :---: |\n| **Porter 5** | **83.81%** | **80.41%** | **84.32%** | **81.05%** |\n| SPIDER 3 | 83.15% | 79.43% | 83.42% | 79.79% |\n| **Porter 5 *HHblits only*** | **83.06%** | **79.49%** | **83.68%** | **80.26%** |\n| SSpro 5.1 *with templates* | 82.58% | 78.54% | 83.94% | 80.29% |\n| PSIPRED 4.01 | 81.88% | 77.36% | 82.48% | 78.22% |\n| RaptorX-Property | 81.86% | 78.08% | 82.57% | 78.99% |\n| Porter 4 | 81.66% | 78.05% | 82.29% | 78.61% | \n| SSpro 5.1 *ab initio* | 81.17% | 76.87% | 81.10% | 76.92% |\n| DeepCNF | 81.04% | 76.74% | 81.16% | 76.99% |\n\nCalculated with http://dna.cs.miami.edu/SOV/.\n\n## Performances in 8 states on large independent test set in \n| Method | Q8 per AA | SOV8'99 per AA | Q8 per protein | SOV8'99 per protein |\n| :--- | :---: | :---: | :---: | :---: |\n| **Porter 5** | **73.02%** | **69.91%** | **73.92%** | **70.76%** |\n| SSpro 5.1 *with templates* | 71.91% | 68.68% | 74.46% | 71.74% |\n| **Porter 5 *HHblits only*** | **71.8%** | **68.87%** | **72.83%** | **69.79%** |\n| RaptorX-Property | 70.74% | 67.59% | 71.78% | 68.36% |\n| DeepCNF | 69.76% | 66.42% | 70.14% | 66.44% |\n| SSpro 5.1 *ab initio* | 68.85% | 65.33% | 69.27% | 65.97% |\n\nCalculated with http://dna.cs.miami.edu/SOV/.\n\n## Citation\nIf you use Porter 5, please cite our Scientific Reports paper:\n```\n@article{torrisi_porter_2019,\n\ttitle = {Deeper Profiles and Cascaded Recurrent and Convolutional Neural Networks for state-of-the-art Protein Secondary Structure Prediction},\n\tvolume = {9},\n\tissn = {2045-2322},\n\tdoi = {10.1038/s41598-019-48786-x},\n\tjournal = {Scientific Reports},\n\tauthor = {Torrisi, Mirko and Kaleel, Manaz and Pollastri, Gianluca},\n\tmonth = aug,\n\tyear = {2019}\n}\n```\n\n## References\nDeeper Profiles and Cascaded Recurrent and Convolutional Neural Networks for state-of-the-art Protein Secondary Structure Prediction, Scientific Reports, Nature Publishing Group;
\nMirko Torrisi, Manaz Kaleel and Gianluca Pollastri; doi: https://doi.org/10.1038/s41598-019-48786-x.\n\nProtein Structure Annotations; Essentials of Bioinformatics, Volume I. Springer Nature
\nMirko Torrisi and Gianluca Pollastri; doi: https://doi.org/10.1007/978-3-030-02634-9_10.\n\nBrewery: Deep Learning and deeper profiles for the prediction of 1D protein structure annotations,
\nBioinformatics, Oxford University Press; Mirko Torrisi and Gianluca Pollastri;
\nToll-free link: https://academic.oup.com/bioinformatics/advance-article/doi/10.1093/bioinformatics/btaa204/5811232?guestAccessKey=9a73ae2a-2cb6-4fe1-b333-a4f3261f02cf.\n\nPorter 5: fast, state-of-the-art ab initio prediction of protein secondary structure in 3 and 8 classes
\nMirko Torrisi, Manaz Kaleel and Gianluca Pollastri; bioRxiv 289033; doi: https://doi.org/10.1101/289033.\n\n\n## License\nThis work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.\n\nEmail us at gianluca[dot]pollastri[at]ucd[dot]ie if you wish to use it for purposes not permitted by the CC BY-NC-SA 4.0.\n\n $\"Creative$ \n","has_starred","hub_user","immutable_tags_settings",{"_75":11,"_76":77},"enabled","rules",[78],".*","is_automated","permissions",{"_82":21,"_83":11,"_84":11},"read","write","admin","user","storage_size",1679268935,"orgData","recentTags",[91],{"_92":44,"_93":94,"_95":96,"_97":98,"_99":100,"_50":118,"_119":94,"_120":33,"_121":56,"_57":122,"_123":124,"_125":109,"_126":118,"_127":66,"_128":21},"content_type","creator",5857526,"full_size",244104604,"id",57451918,"images",[101],{"_102":103,"_104":105,"_106":107,"_108":109,"_110":111,"_112":113,"_114":107,"_115":-5,"_116":96,"_63":66,"_117":-5},"architecture","amd64","digest","sha256:0a915367c03a9020461bf5e3bdc9983c15afa6ab7ed01b15d42363ecd0f461cd","features","","last_pulled","2026-09-29T20:18:20.24087141Z","last_pushed","2020-05-21T08:41:53Z","os","linux","os_features","os_version","size","variant","2020-05-21T08:44:49.453712Z","last_updater","last_updater_username","media_type","latest","repository",7194571,"tag_last_pulled","tag_last_pushed","tag_status","v2","sbxKitMetadata","isPotentialSpam","isHubSbxKitsEnabled","showSbxLogoOverride","sbxTrademarkText","displaySecurityMetadata","tagAttestations","tagsHaveAttestations",[],"routes/_layout.r.$namespace.$reponame.tags",{"_38":140,"_147":148,"_136":157,"_158":11},{"_40":141,"_42":142,"_45":46,"_47":48,"_49":11,"_50":51,"_52":53,"_54":143,"_57":35,"_32":33,"_58":59,"_60":44,"_61":62,"_63":64,"_65":66,"_67":-5,"_68":62,"_69":70,"_71":11,"_72":33,"_73":144,"_79":11,"_80":146,"_85":33,"_86":87},[],[44],[56],{"_75":11,"_76":145},[78],{"_82":21,"_83":11,"_84":11},"tags",{"_149":64,"_150":-5,"_151":-5,"_152":153},"count","next","previous","results",[154],{"_92":44,"_93":94,"_95":96,"_97":98,"_99":155,"_50":118,"_119":94,"_120":33,"_121":56,"_57":122,"_123":124,"_125":109,"_126":118,"_127":66,"_128":21},[156],{"_102":103,"_104":105,"_106":107,"_108":109,"_110":111,"_112":113,"_114":107,"_115":-5,"_116":96,"_63":66,"_117":-5},[],"canDeleteTags","actionData","errors"]

mircare/porter5

Tags for mircare/porter5