adding to_datacite method

.github/workflows/test.yml

@@ -11,6 +11,7 @@ jobs:
     runs-on: ${{ matrix.os }}
     env:
       NO_ET: 1
+      DATACITE_DEV_PASSWORD: ${{ secrets.DATACITE_DEV_PASSWORD }}
 
     strategy:
       fail-fast: false

dandi/models.py

@@ -116,6 +116,188 @@ def diff_models(model1, model2):
             print(f"{field} is different")
 
 
+DATACITE_CONTRTYPE = {
+    "ContactPerson",
+    "DataCollector",
+    "DataCurator",
+    "DataManager",
+    "Distributor",
+    "Editor",
+    "HostingInstitution",
+    "Producer",
+    "ProjectLeader",
+    "ProjectManager",
+    "ProjectMember",
+    "RegistrationAgency",
+    "RegistrationAuthority",
+    "RelatedPerson",
+    "Researcher",
+    "ResearchGroup",
+    "RightsHolder",
+    "Sponsor",
+    "Supervisor",
+    "WorkPackageLeader",
+    "Other",
+}
+
+
+DATACITE_IDENTYPE = {
+    "ARK",
+    "arXiv",
+    "bibcode",
+    "DOI",
+    "EAN13",
+    "EISSN",
+    "Handle",
+    "IGSN",
+    "ISBN",
+    "ISSN",
+    "ISTC",
+    "LISSN",
+    "LSID",
+    "PMID",
+    "PURL",
+    "UPC",
+    "URL",
+    "URN",
+    "w3id",
+}
+DATACITE_MAP = dict([(el.lower(), el) for el in DATACITE_IDENTYPE])
+
+
+def to_datacite(meta):
+    dandiset_id = meta.identifier.split(":")[1]
+    doi = meta.doi
+
+    attributes = {}
+    attributes["identifiers"] = [
+        # TODO: the first elementis ignored, not sure how to fix it...
+        {"identifier": f"https://doi.org/{doi}", "identifierType": "DOI"},
+        {
+            "identifier": f"https://identifiers.org/DANDI:{dandiset_id}/{meta.version}",
+            "identifierType": "URL",
+        },
+    ]
+
+    attributes["doi"] = doi
+    attributes["titles"] = [{"title": meta.name}]
+    attributes["descriptions"] = [
+        {"description": meta.description, "descriptionType": "Abstract"}
+    ]
+    attributes["publisher"] = "DANDI Archive"
+    attributes["publicationYear"] = str(meta.datePublished.year)
+    # not sure about it dandi-api had "resourceTypeGeneral": "NWB"
+    attributes["types"] = {"resourceType": "NWB", "resourceTypeGeneral": "Dataset"}
+    # meta has also attribute url, but it often empty
+    attributes["url"] = meta.url
+    # assuming that all licenses are from SPDX?
+    attributes["rightsList"] = [
+        {
+            "schemeURI": "https://spdx.org/licenses/",
+            "rightsIdentifierScheme": "SPDX",
+            "rightsIdentifier": el.name,
+        }
+        for el in meta.license
+    ]
+    attributes["schemaVersion"] = "http://datacite.org/schema/kernel-4"
+
+    contributors = []
+    creators = []
+    for contr_el in meta.contributor:
+        if RoleType("dandi:Sponsor") in contr_el.roleName:
+            # no info about "funderIdentifierType", "awardUri", "awardTitle"
+            dict_fund = {"funderName": contr_el.name}
+            if contr_el.identifier:
+                dict_fund["funderIdentifier"] = contr_el.identifier
+            if contr_el.awardNumber:
+                dict_fund["awardNumber"] = contr_el.awardNumber
+            attributes.setdefault("fundingReferences", []).append(dict_fund)
+            # if no more roles, it shouldn't be added to creators or contributors
+            contr_el.roleName.remove(RoleType("dandi:Sponsor"))
+            if not contr_el.roleName:
+                continue
+
+        contr_dict = {
+            "name": contr_el.name,
+            "contributorName": contr_el.name,
+            "schemeURI": "orcid.org",
+        }
+        if isinstance(contr_el, Person):
+            contr_dict["nameType"] = "Personal"
+            if len(contr_el.name.split(",")) == 2:
+                contr_dict["familyName"], contr_dict["givenName"] = contr_el.name.split(
+                    ","
+                )
+            if getattr(contr_el, "affiliation"):
+                contr_dict["affiliation"] = [
+                    {"name": el.name} for el in contr_el.affiliation
+                ]
+            else:
+                contr_dict["affiliation"] = []
+        elif isinstance(contr_el, Organization):
+            contr_dict["nameType"] = "Organizational"
+
+        if RoleType("dandi:Author") in getattr(contr_el, "roleName"):
+            create_dict = deepcopy(contr_dict)
+            create_dict["creatorName"] = create_dict.pop("contributorName")
+            creators.append(create_dict)
+            contr_el.roleName.remove(RoleType("dandi:Author"))
+            # if no more roles, it shouldn't be added to contributors
+            if not contr_el.roleName:
+                continue
+
+        if getattr(contr_el, "roleName"):
+            contr_all = [
+                el.name for el in contr_el.roleName if el.name in DATACITE_CONTRTYPE
+            ]
+            if contr_all:
+                contr_dict["contributorType"] = contr_all[0]
+            else:
+                contr_dict["contributorType"] = "Other"
+        contributors.append(contr_dict)
+
+    # if there are no creators, the first contributor is also treated as the creator
+    if not creators and contributors:
+        creators = [deepcopy(contributors[0])]
+        creators[0]["creatorName"] = creators[0].pop("contributorName")
+        creators[0].pop("contributorType")
+
+    attributes["contributors"] = contributors
+    attributes["creators"] = creators
+
+    if getattr(meta, "relatedResource"):
+        attributes["relatedIdentifiers"] = []
+        for rel_el in meta.relatedResource:
+            ident = rel_el.identifier.split(":")
+            if len(ident) == 2:
+                ident_tp, ident_nr = ident
+                if ident_tp.lower() in DATACITE_MAP:
+                    ident_tp = DATACITE_MAP[ident_tp.lower()]
+                else:
+                    raise ValueError(
+                        f"identifier has to be from the list: {DATACITE_IDENTYPE}, "
+                        f"but {ident_tp} provided"
+                    )
+            else:
+                raise ValueError(
+                    "identifier is expected to be type:number,"
+                    f" got {rel_el.identifier}"
+                )
+            rel_dict = {
+                "relatedIdentifier": ident_nr,
+                # in theory it should be from the specific list that contains e.g. DOI, arXiv, ...
+                "relatedIdentifierType": ident_tp,
+                "relationType": rel_el.relation.name,
+            }
+            attributes["relatedIdentifiers"].append(rel_dict)
+
+    if getattr(meta, "keywords"):
+        attributes["subjects"] = [{"subject": el} for el in meta.keywords]
+
+    datacite_dict = {"data": {"id": doi, "type": "dois", "attributes": attributes}}
+    return datacite_dict
+
+
 def _sanitize(o):
     if isinstance(o, dict):
         return {_sanitize(k): _sanitize(v) for k, v in o.items()}
@@ -977,7 +1159,6 @@ class Publishable(DandiBaseModel):
 class PublishedDandisetMeta(DandisetMeta, Publishable):
     version: str = Field(readOnly=True, nskey="schema")
     doi: str = Field(
-        None,
         title="DOI",
         readOnly=True,
         regex=r"^10\.[A-Za-z0-9.\/-]+",

dandi/tests/data/metadata/meta_000004.json

@@ -0,0 +1 @@
+{"id": "DANDI:000004/draft", "name": "A NWB-based dataset and processing pipeline of human single-neuron activity during a declarative memory task", "about": [{"name": "Medial Temporal Lobe", "schemaKey": "GenericType"}], "access": [{"status": "dandi:Open"}], "license": ["spdx:CC-BY-4.0"], "keywords": ["cognitive neuroscience", "data standardization", "decision making", "declarative memory", "neurophysiology", "neurosurgery", "NWB", "open source", "single-neurons"], "identifier": "DANDI:000004", "repository": "https://dandiarchive.org/", "contributor": [{"name": "Chandravadia, Nand", "email": "nandc10@gmail.com", "roleName": ["dandi:Author", "dandi:ContactPerson", "dandi:DataCurator", "dandi:DataManager", "dandi:FormalAnalysis", "dandi:Investigation", "dandi:Maintainer", "dandi:Methodology", "dandi:ProjectLeader", "dandi:ProjectManager", "dandi:ProjectMember", "dandi:Researcher", "dandi:Software", "dandi:Validation", "dandi:Visualization"], "schemaKey": "Person", "identifier": "0000-0003-0161-4007", "affiliation": [{"name": "Department of Neurosurgery, Cedars-Sinai Medical Center, Los Angeles, CA, USA", "schemaKey": "Organization", "includeInCitation": false}], "includeInCitation": true}, {"name": "Liang, Dehua", "email": "liang134@mail.chapman.edu", "roleName": ["dandi:Author", "dandi:Methodology", "dandi:ProjectMember", "dandi:Software", "dandi:Validation"], "schemaKey": "Person", "affiliation": [{"name": "Institute for Interdisciplinary Brain and Behavioral Sciences, Crean College of Health and Behavioral Sciences, Schmid College of Science and Technology, Chapman University, Orange, CA, USA", "schemaKey": "Organization", "includeInCitation": false}], "includeInCitation": true}, {"name": "Schjetnan, Andrea Gomez Palacio", "email": "Andrea.Schjetan@uhnresearch.ca", "roleName": ["dandi:Author", "dandi:DataCollector", "dandi:ProjectMember", "dandi:Validation"], "schemaKey": "Person", "identifier": "0000-0002-4319-7689", "affiliation": [{"name": "Krembil Brain Institute, Toronto Western Hospital, Toronto, Canada", "schemaKey": "Organization", "includeInCitation": false}], "includeInCitation": true}, {"name": "Carlson, April", "email": "april.carlson@tufts.edu", "roleName": ["dandi:Author", "dandi:DataCurator", "dandi:ProjectMember", "dandi:Validation"], "schemaKey": "Person", "identifier": "0000-0002-9207-7069", "affiliation": [{"name": "Department of Neurosurgery, Cedars-Sinai Medical Center, Los Angeles, CA, USA", "schemaKey": "Organization", "includeInCitation": false}], "includeInCitation": true}, {"name": "Faraut, Mailys", "email": "mailyscm.faraut@gmail.com", "roleName": ["dandi:Author", "dandi:DataCollector", "dandi:ProjectMember", "dandi:Validation"], "schemaKey": "Person", "affiliation": [{"name": "Department of Neurosurgery, Cedars-Sinai Medical Center, Los Angeles, CA, USA", "schemaKey": "Organization", "includeInCitation": false}], "includeInCitation": true}, {"name": "Chung, Jeffrey M.", "email": "Jeffrey.Chung@cshs.org", "roleName": ["dandi:Author", "dandi:ProjectMember", "dandi:Validation"], "schemaKey": "Person", "affiliation": [{"name": "Department of Neurology, Cedars-Sinai Medical Center, Los Angeles, CA, USA", "schemaKey": "Organization", "includeInCitation": false}], "includeInCitation": true}, {"name": "Reed, Chrystal M.", "email": "Chrystal.Reed@csmc.edu", "roleName": ["dandi:Author", "dandi:ProjectMember", "dandi:Validation"], "schemaKey": "Person", "affiliation": [{"name": "Department of Neurology, Cedars-Sinai Medical Center, Los Angeles, CA, USA", "schemaKey": "Organization", "includeInCitation": false}], "includeInCitation": true}, {"name": "Dichter, Ben", "email": "ben.dichter@gmail.com", "roleName": ["dandi:Author", "dandi:Software", "dandi:ProjectMember", "dandi:Validation"], "schemaKey": "Person", "affiliation": [{"name": "Biological Systems & Engineering Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA", "schemaKey": "Organization", "includeInCitation": false}, {"name": "Department of Neurosurgery, Stanford University, Stanford, CA, USA", "schemaKey": "Organization", "includeInCitation": false}], "includeInCitation": true}, {"name": "Maoz, Uri", "email": "maoz.uri@gmail.com", "roleName": ["dandi:Author", "dandi:Conceptualization", "dandi:ProjectMember", "dandi:Validation"], "schemaKey": "Person", "affiliation": [{"name": "Institute for Interdisciplinary Brain and Behavioral Sciences, Crean College of Health and Behavioral Sciences, Schmid College of Science and Technology, Chapman University, Orange, CA, USA", "schemaKey": "Organization", "includeInCitation": false}, {"name": "Division of Biology and Biological Engineering, California Institute of Technology, Pasadena, CA, USA", "schemaKey": "Organization", "includeInCitation": false}], "includeInCitation": true}, {"name": "Kalia, Suneil K.", "email": "suneil.kalia@uhn.ca", "roleName": ["dandi:Author", "dandi:ProjectMember", "dandi:Validation"], "schemaKey": "Person", "affiliation": [{"name": "Division of Neurosurgery, Department of Surgery, University of Toronto, Toronto, Canada", "schemaKey": "Organization", "includeInCitation": false}, {"name": "Krembil Brain Institute, Toronto Western Hospital, Toronto, Canada", "schemaKey": "Organization", "includeInCitation": false}], "includeInCitation": true}, {"name": "Valiante, Taufik A.", "email": "Taufik.Valiante@uhn.ca", "roleName": ["dandi:Author", "dandi:ProjectMember", "dandi:Validation"], "schemaKey": "Person", "affiliation": [{"name": "Krembil Brain Institute, Toronto Western Hospital, Toronto, Canada", "schemaKey": "Organization", "includeInCitation": false}, {"name": "Division of Neurosurgery, Department of Surgery, University of Toronto, Toronto, Canada", "schemaKey": "Organization", "includeInCitation": false}], "includeInCitation": true}, {"name": "Mamelak, Adam N.", "email": "Adam.Mamelak@cshs.org", "roleName": ["dandi:Author", "dandi:ProjectMember", "dandi:Validation"], "schemaKey": "Person", "affiliation": [{"name": "Department of Neurosurgery, Cedars-Sinai Medical Center, Los Angeles, CA, USA", "schemaKey": "Organization", "includeInCitation": false}], "includeInCitation": true}, {"name": "Rutishauser, Ueli", "email": "Ueli.Rutishauser@cshs.org", "roleName": ["dandi:Author", "dandi:Conceptualization", "dandi:FundingAcquisition", "dandi:ProjectMember", "dandi:Resources", "dandi:Software", "dandi:Supervision", "dandi:Validation"], "schemaKey": "Person", "identifier": "0000-0002-9207-7069", "affiliation": [{"name": "Department of Neurosurgery, Cedars-Sinai Medical Center, Los Angeles, CA, USA", "schemaKey": "Organization", "includeInCitation": false}, {"name": "Department of Neurology, Cedars-Sinai Medical Center, Los Angeles, CA, USA", "schemaKey": "Organization", "includeInCitation": false}, {"name": "Division of Biology and Biological Engineering, California Institute of Technology, Pasadena, CA, USA", "schemaKey": "Organization", "includeInCitation": false}, {"name": "Computational and Neural Systems Program, California Institute of Technology, Pasadena, CA, USA", "schemaKey": "Organization", "includeInCitation": false}, {"name": "Center for Neural Science and Medicine, Department of Biomedical Science, Cedars-Sinai Medical Center, Los Angeles, CA, USA", "schemaKey": "Organization", "includeInCitation": false}], "includeInCitation": true}, {"name": "Stroke, National Institute of Neurological Disorders and", "roleName": ["dandi:Sponsor"], "schemaKey": "Organization", "awardNumber": "U01NS103792", "includeInCitation": false}, {"name": "Foundation, National Science", "roleName": ["dandi:Sponsor"], "schemaKey": "Organization", "awardNumber": "1554105", "includeInCitation": false}, {"name": "Health, National Institute of Mental", "roleName": ["dandi:Sponsor"], "schemaKey": "Organization", "awardNumber": "R01MH110831", "includeInCitation": false}, {"name": "Neuroscience, McKnight Endowment for", "roleName": ["dandi:Sponsor"], "schemaKey": "Organization", "includeInCitation": false}, {"name": "Foundation, NARSAD Young Investigator grant from the Brain & Behavior Research", "roleName": ["dandi:Sponsor"], "schemaKey": "Organization", "includeInCitation": false}, {"name": "Foundation, Kavli", "roleName": ["dandi:Sponsor"], "schemaKey": "Organization", "includeInCitation": false}, {"name": "initiative, BRAIN", "roleName": ["dandi:Sponsor"], "schemaKey": "Organization", "awardNumber": "U19NS104590", "includeInCitation": false}], "description": "A challenge for data sharing in systems neuroscience is the multitude of different data formats used. Neurodata Without Borders: Neurophysiology 2.0 (NWB:N) has emerged as a standardized data format for the storage of cellular-level data together with meta-data, stimulus information, and behavior. A key next step to facilitate NWB:N adoption is to provide easy to use processing pipelines to import/export data from/to NWB:N. Here, we present a NWB-formatted dataset of 1863 single neurons recorded from the medial temporal lobes of 59 human subjects undergoing intracranial monitoring while they performed a recognition memory task. We provide code to analyze and export/import stimuli, behavior, and electrophysiological recordings to/from NWB in both MATLAB and Python. The data files are NWB:N compliant, which affords interoperability between programming languages and operating systems. This combined data and code release is a case study for how to utilize NWB:N for human single-neuron recordings and enables easy re-use of this hard-to-obtain data for both teaching and research on the mechanisms of human memory.", "schemaVersion": "0.3.0", "relatedResource": [{"url": "https://osf.io/hv7ja/", "name": "A NWB-based Dataset and Processing Pipeline of Human Single-Neuron Activity During a Declarative Memory Task", "relation": "dandi:IsDerivedFrom", "identifier": "DOI:10.17605/OSF.IO/HV7JA", "repository": "Open Science Framework"}, {"url": "https://www.nature.com/articles/s41597-020-0415-9", "relation": "dandi:IsDescribedBy", "identifier": "DOI:10.1038/s41597-020-0415-9"}]}

dandi/tests/data/metadata/meta_000008.json

@@ -0,0 +1 @@
+{"id": "DANDI:000008/draft", "name": "Phenotypic variation within and across transcriptomic cell types in mouse motor cortex", "access": [{"status": "dandi:Open"}], "license": ["spdx:CC-BY-4.0"], "identifier": "DANDI:000008", "repository": "https://dandiarchive.org/", "contributor": [{"name": "Scala, Federico", "roleName": ["dandi:DataCollector", "dandi:Author", "dandi:ContactPerson"], "schemaKey": "Person", "includeInCitation": true}, {"name": "Kobak, Dmitry", "roleName": ["dandi:Author"], "schemaKey": "Person", "identifier": "0000-0002-5639-7209", "includeInCitation": true}, {"name": "Bernabucci, Matteo", "roleName": ["dandi:Author"], "schemaKey": "Person", "identifier": "0000-0003-4458-117X", "includeInCitation": true}, {"name": "Bernaerts, Yves", "roleName": ["dandi:Author"], "schemaKey": "Person", "includeInCitation": true}, {"name": "Cadwell, Cathryn Rene", "roleName": ["dandi:Author"], "schemaKey": "Person", "identifier": "0000-0003-1963-8285", "includeInCitation": true}, {"name": "Castro, Jesus Ramon", "roleName": ["dandi:Author"], "schemaKey": "Person", "includeInCitation": true}, {"name": "Hartmanis, Leonard", "roleName": ["dandi:Author"], "schemaKey": "Person", "identifier": "0000-0002-4922-8781", "includeInCitation": true}, {"name": "Jiang, Xiaolong", "roleName": ["dandi:Author"], "schemaKey": "Person", "identifier": "0000-0001-8066-1383", "includeInCitation": true}, {"name": "Laturnus, Sophie", "roleName": ["dandi:Author"], "schemaKey": "Person", "identifier": "0000-0001-9532-788X", "includeInCitation": true}, {"name": "Miranda, Elanine", "roleName": ["dandi:Author"], "schemaKey": "Person", "includeInCitation": true}, {"name": "Mulherkar, Shalaka", "roleName": ["dandi:Author"], "schemaKey": "Person", "identifier": "0000-0001-8736-527X", "includeInCitation": true}, {"name": "Tan, Zheng Huan", "roleName": ["dandi:Author"], "schemaKey": "Person", "includeInCitation": true}, {"name": "Yao, Zizhen", "roleName": ["dandi:Author"], "schemaKey": "Person", "identifier": "0000-0002-9361-5607", "includeInCitation": true}, {"name": "Zeng, Hongkui", "roleName": ["dandi:Author"], "schemaKey": "Person", "identifier": "0000-0002-0326-5878", "includeInCitation": true}, {"name": "Sandberg, Rickard", "roleName": ["dandi:Author"], "schemaKey": "Person", "identifier": "0000-0001-6473-1740", "includeInCitation": true}, {"name": "Berens, Philipp", "roleName": ["dandi:Author"], "schemaKey": "Person", "identifier": "0000-0002-0199-4727", "includeInCitation": true}, {"name": "Tolias, Andreas Savas", "roleName": ["dandi:Author", "dandi:ContactPerson"], "schemaKey": "Person", "identifier": "0000-0002-4305-6376", "includeInCitation": true}], "description": "Data from the Tolias Lab shared in the BICCN project", "schemaVersion": "0.3.0", "relatedResource": [{"url": "https://www.biorxiv.org/content/10.1101/2020.02.03.929158v1.full", "relation": "dandi:IsDescribedBy", "identifier": "doi:10.1101/2020.02.03.929158"}]}