Produce examples from existing datalad-powered catalogs

[jsheunis]

SFB1451: https://data.sfb1451.de/

• schema: https://github.com/sfb1451/crc-schema-draft

ABCD-J: https://data.abcd-j.de/

• schema: https://github.com/abcd-j/schema
• records: https://github.com/abcd-j/data (in tabby format)

[jsheunis]

E.g. record at https://github.com/abcd-j/data/tree/main/UKD/ocr-PIRA-cohort, loaded using tabby_load (https://docs.datalad.org/projects/tabby/en/latest/generated/datalad.api.tabby_load.html#datalad.api.tabby_load) and a custom tabby convention (https://github.com/abcd-j/data-catalog/tree/main/inputs/tby-abcdjv0), and then compacted with a custom context (https://github.com/abcd-j/data-catalog/blob/main/code/utils.py#L260):

{
    "@context": {
        "schema": "https://schema.org/",
        "afo": "http://purl.allotrope.org/ontologies/result#",
        "bibo": "https://purl.org/ontology/bibo/",
        "dcterms": "https://purl.org/dc/terms/",
        "nfo": "https://www.semanticdesktop.org/ontologies/2007/03/22/nfo/#",
        "obo": "https://purl.obolibrary.org/obo/",
        "openminds": "https://openminds.ebrains.eu/controlledTerms/",
        "name": "schema:name",
        "title": "schema:title",
        "description": "schema:description",
        "doi": "bibo:doi",
        "version": "schema:version",
        "license": "schema:license",
        "authors": "schema:author",
        "orcid": "obo:IAO_0000708",
        "email": "schema:email",
        "keywords": "schema:keywords",
        "funding": {
            "@id": "schema:funding",
            "@context": {
                "name": "schema:funder",
                "identifier": "schema:identifier"
            }
        },
        "publications": {
            "@id": "schema:citation",
            "@context": {
                "doi": "schema:identifier",
                "datePublished": "schema:datePublished",
                "citation": "schema:citation"
            }
        },
        "fileList": {
            "@id": "dcterms:hasPart",
            "@context": {
                "contentbytesize": "nfo:fileSize",
                "md5sum": "obo:NCIT_C171276",
                "path": "schema:name",
                "url": "schema:contentUrl"
            }
        },
        "subdatasets": {
            "@id": "schema:Dataset",
            "@context": {
                "dataset_type": "schema:Text",
                "identifier": "schema:identifier",
                "path_posix": "afo:AFR_0001928",
                "version": "schema:version",
                "url": "schema:contentUrl"
            }
        },
        "address": "schema:PostalAddress",
        "homepage": "schema:mainEntityOfPage",
        "dataController": "https://w3id.org/dpv#hasDataController",
        "usedFor": {
            "@id": "http://www.w3.org/ns/prov#hadUsage",
            "@context": {
                "url": "schema:url"
            }
        },
        "sampleOrganism": "openminds:Species",
        "samplePart": "openminds:UBERONParcellation"
    },
    "usedFor": {
        "@type": "http://www.w3.org/ns/prov#Activity",
        "title": "Progression independent from relapse in ocrelizumab-treated relapsing multiple sclerosis cohort"
    },
    "sampleOrganism": "NCBITaxon:9606",
    "samplePart": "UBERON:0000955",
    "fileList": {
        "@type": "schema:DigitalDocument",
        "name": {
            "@type": "afo:AFR_0001928",
            "@value": "cPIRA_OCR_ps_220918_w_CD19.xlsx"
        },
        "contentbytesize": {
            "@type": "http://www.w3.org/2001/XMLSchema#integer",
            "@value": "62318"
        }
    },
    "authors": [
        {
            "@type": "schema:Person",
            "name": "Jens Ingwersen"
        },
        {
            "@id": "https://orcid.org/0000-0003-2496-1415",
            "@type": "schema:Person",
            "orcid": "0000-0003-2496-1415",
            "name": "Lars Masanneck"
        },
        {
            "@type": "schema:Person",
            "name": "Marc Pawlitzki"
        },
        {
            "@type": "schema:Person",
            "name": "Sara Samadzadeh"
        },
        {
            "@type": "schema:Person",
            "name": "Margit Weise"
        },
        {
            "@type": "schema:Person",
            "name": "Orhan Aktas"
        },
        {
            "@type": "schema:Person",
            "name": "Sven G. Meuth"
        },
        {
            "@type": "schema:Person",
            "name": "Philipp Albrecht"
        }
    ],
    "publications": {
        "@type": "schema:CreativeWork",
        "citation": "Ingwersen, J., Masanneck, L., Pawlitzki, M. et al. Real-world evidence of ocrelizumab-treated relapsing multiple sclerosis cohort shows changes in progression independent of relapse activity mirroring phase 3 trials. Sci Rep 13, 15003 (2023).",
        "datePublished": "2023-09-11",
        "doi": "https://doi.org/10.1038/s41598-023-40940-w",
        "schema:url": "https://www.nature.com/articles/s41598-023-40940-w"
    },
    "schema:dateModified": "2023-03-01",
    "description": "A clinical dataset of ocrelizumab treated multiple sclerosis patients at the HHU University Clinic Düsseldorf with routinely collected clinical, imaging and OCT results (no imaging data). Data was collected for routine visits from 2018 to 2022. ",
    "keywords": [
        "clinical data",
        "multiple sclerosis",
        "ocrelizumab",
        "PIRA",
        "EDSS"
    ],
    "name": "ocr-PIRA-cohort",
    "title": "Longitudinal clinical data in Ocrelizumab-treated multiple sclerosis patients",
    "version": "0.1.0",
    "dataController": {
        "address": "Geb. 13.53, Moorenstraße 5, 40225 Düsseldorf",
        "email": "[email protected]",
        "name": "Lars Masanneck"
    }
}