{"id":13676386,"url":"https://github.com/bids-apps/hyperalignment","last_synced_at":"2026-05-29T00:03:31.820Z","repository":{"id":66671869,"uuid":"64789816","full_name":"bids-apps/hyperalignment","owner":"bids-apps","description":"Hyperalignment is a functional alignment method that aligns subjects' brain data in a high-dimensional space of voxels/features.","archived":false,"fork":false,"pushed_at":"2025-09-22T20:02:04.000Z","size":47,"stargazers_count":17,"open_issues_count":2,"forks_count":6,"subscribers_count":5,"default_branch":"master","last_synced_at":"2025-09-22T22:06:52.137Z","etag":null,"topics":["bids","bidsapp"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/bids-apps.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":"2016-08-02T20:19:39.000Z","updated_at":"2025-04-14T12:44:10.000Z","dependencies_parsed_at":"2023-11-14T11:28:59.920Z","dependency_job_id":"3a751024-112e-4277-9b38-d5d3975dce5c","html_url":"https://github.com/bids-apps/hyperalignment","commit_stats":null,"previous_names":[],"tags_count":3,"template":false,"template_full_name":null,"purl":"pkg:github/bids-apps/hyperalignment","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bids-apps%2Fhyperalignment","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bids-apps%2Fhyperalignment/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bids-apps%2Fhyperalignment/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bids-apps%2Fhyperalignment/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/bids-apps","download_url":"https://codeload.github.com/bids-apps/hyperalignment/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bids-apps%2Fhyperalignment/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33631002,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-05-28T02:00:06.440Z","response_time":99,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":["bids","bidsapp"],"created_at":"2024-08-02T13:00:24.806Z","updated_at":"2026-05-29T00:03:31.792Z","avatar_url":"https://github.com/bids-apps.png","language":"Python","funding_links":[],"categories":["BIDS Apps"],"sub_categories":["others"],"readme":"## Hyperalignment BIDS App (WiP)\n\n### Description\n\nHyperalignment is a functional alignment method that aligns subjects' brain data in a\nhigh-dimensional space of voxels/features. We showed that this alignment aligns subjects\nat a fine-scale affording between-subject decoding and encoding\n[Guntupalli et al. 2016](http://cercor.oxfordjournals.org/content/26/6/2919). This app runs searchlight\nhyperalignment, which runs hyperalignment in multiple searchlights across the whole brain and\naggregates them into a single transformation per subject.\nFor now, many parameters such as searchlight size, sparsity of centers, etc., are fixed.\nPlease use PyMVPA to modify these and other parameters for your use case.\n\n### Documentation\n\nFor a detailed documentation and examples, please see:\nHyperalignment in a ROI:\nhttp://www.pymvpa.org/generated/mvpa2.algorithms.hyperalignment.Hyperalignment.html\nSearchlight Hyperalignment:\nhttps://github.com/PyMVPA/PyMVPA/blob/master/mvpa2/algorithms/searchlight_hyperalignment.py\nExample in PyMVPA:\nhttp://www.pymvpa.org/examples/hyperalignment.html\n\n### Acknowledgements\n\nIf you use this in your project, please cite [Guntupalli et al. 2016](http://cercor.oxfordjournals.org/content/26/6/2919).\n\n### Report Bugs/Issues\n\nPlease use PyMVPA on github to report any bugs/issues or to contribute:\nhttps://github.com/PyMVPA/PyMVPA\n\n### Usage\n\n\t\tusage: run.py [-h]\n\t\t              [--participant_label PARTICIPANT_LABEL [PARTICIPANT_LABEL ...]\n\t\t              --task TASK_LABEL --run RUN_LABEL]\n\t\t              bids_dir output_dir {participant,group}\n\n\t\tExample BIDS App entrypoint script.\n\n\t\tpositional arguments:\n\t\t  bids_dir              The directory with the input dataset formatted\n\t\t                        according to the BIDS standard.\n\t\t  output_dir            The directory where the output files should be stored.\n\t\t                        If you are running group level analysis this folder\n\t\t                        should be prepopulated with the results of\n\t\t                        theparticipant level analysis.\n\t\t  {participant,group}   Level of the analysis that will be performed. Multiple\n\t\t                        participant level analyses can be run independently\n\t\t                        (in parallel).\n\n\t\toptional arguments:\n\t\t  -h, --help            show this help message and exit\n\t\t  --participant_label PARTICIPANT_LABEL [PARTICIPANT_LABEL ...]\n\t\t                        The label(s) of the participant(s) that should be\n\t\t                        analyzed. The label corresponds to\n\t\t                        sub-\u003cparticipant_label\u003e from the BIDS spec (so it does\n\t\t                        not include \"sub-\"). If this parameter is not provided\n\t\t                        all subjects should be analyzed. Multiple participants\n\t\t                        can be specified with a space separated list.\n\t\t  --task TASK_LABEL     Name of the task that should be used for hyperalignment.\n\t\t                        This correspnds to task-\u003cTASK_LABEL\u003e from the BIDS spec\n\t\t                        (so it does not include \"task-\").\n\t\t  --run RUN_LABEL       Name of the run that should be used for hyperalignment.\n\t\t                        This correspnds to run-\u003cTASK_LABEL\u003e from the BIDS spec\n\t\t                        (so it does not include \"run-\").\n\n\nParticipant level mode prepares the data for hyperalignment.\nFor now, it loads the data from nifti image into PyMVPA readable datasets after applying\nbrain mask. In future, this will be modified to compute individual subject connectomes.\n\n    docker run -i --rm \\\n        -v /Users/swaroop/ds005-deriv/derivatives:/bids_dataset \\\n        -v /Users/swaroop/outputs:/outputs \\\n        bids/hyperalignment \\\n        /bids_dataset /outputs participant \\\n        --task mixedgamblestask --run 01 --participant_label 01\n\nAfter running participant level (potentially in parallel), group level analysis\nruns hyperalignment and saves transformation parameters.\n\n    docker run -i --rm -v \\\n        /Users/swaroop/ds005-deriv/derivatives:/bids_dataset \\\n        -v /Users/swaroop/outputs:/outputs \\\n        bids/hyperalignment \\\n        /bids_dataset /outputs group\n\n### Special requirements\n\nHyperalignment works on preprocessed data with all the subjects' data aligned to the same template.\n\n### Relevant references\n\n1. Guntupalli, J. S., Hanke, M., Halchenko, Y. O., Connolly, A. C., Ramadge, P. J. \u0026 Haxby, J. V. (2016). A Model of Representational Spaces in Human Cortex. Cerebral Cortex.\n    DOI: http://dx.doi.org/10.1093/cercor/bhw068\n2. Haxby, J. V., Guntupalli, J. S., Connolly, A. C., Halchenko, Y. O., Conroy, B. R., Gobbini, M. I., Hanke, M. \u0026 Ramadge, P. J. (2011). A Common, High-Dimensional Model of the Representational Space in Human Ventral Temporal Cortex. Neuron, 72, 404–416.\n    DOI: http://dx.doi.org/10.1016/j.neuron.2011.08.026\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbids-apps%2Fhyperalignment","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbids-apps%2Fhyperalignment","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbids-apps%2Fhyperalignment/lists"}