From 174959037c7e937cfc462608ad1c770555e8c15a Mon Sep 17 00:00:00 2001 From: Johannes Liermann Date: Thu, 11 Jul 2024 18:36:18 +0200 Subject: [PATCH 1/8] chore: upgrade packages --- package.json | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/package.json b/package.json index 5552cc0e..e251ac33 100644 --- a/package.json +++ b/package.json @@ -15,10 +15,10 @@ "crowdin": "crowdin" }, "dependencies": { - "@crowdin/cli": "^3.19.3", - "@docusaurus/core": "^3.3.2", - "@docusaurus/preset-classic": "^3.3.2", - "@easyops-cn/docusaurus-search-local": "^0.40.1", + "@crowdin/cli": "^4.0.0", + "@docusaurus/core": "^3.4.0", + "@docusaurus/preset-classic": "^3.4.0", + "@easyops-cn/docusaurus-search-local": "^0.44.3", "@fontsource/ibm-plex-sans": "^5.0.20", "@mdx-js/react": "^3.0.1", "clsx": "^2.1.1", @@ -31,8 +31,8 @@ "video-privacy": "^1.0.2" }, "devDependencies": { - "@docusaurus/module-type-aliases": "^3.3.2", - "@docusaurus/types": "3.3.2" + "@docusaurus/module-type-aliases": "^3.4.0", + "@docusaurus/types": "3.4.0" }, "browserslist": { "production": [ From 95d3ae6b5fc7c9e52fc73179a108c501138dd351 Mon Sep 17 00:00:00 2001 From: Johannes Liermann Date: Thu, 11 Jul 2024 18:41:38 +0200 Subject: [PATCH 2/8] fix: svg warnings --- ...raphical_Abstract_Ontologies4Chem_2021.svg | 194 ++++- .../topics/Overview_Ontologies4Chem_2021.svg | 672 +++++++++++++++++- 2 files changed, 860 insertions(+), 6 deletions(-) diff --git a/static/img/topics/Graphical_Abstract_Ontologies4Chem_2021.svg b/static/img/topics/Graphical_Abstract_Ontologies4Chem_2021.svg index ef2df5b7..60e7d7bf 100644 --- a/static/img/topics/Graphical_Abstract_Ontologies4Chem_2021.svg +++ b/static/img/topics/Graphical_Abstract_Ontologies4Chem_2021.svg @@ -1,4 +1,192 @@ - - -

Solvent-Free Diels–Alder Reaction in a Closed Batch System

Solvent-Free Diels–Alder Reaction in a Closed Batch System...DOI: 10.1246/bcsj.20120247
RXNO:0000006
RXNO:0000006
AFP:0002833 (temperature control process)
AFP:0002833 (temper...
30°C, 2h
30°C, 2h CHEBI:474859CHEBI:39478PUBCHEM:CID6810
CHMO:0000835 (NMR spectrum)
CHMO:0000835 (NMR spectrum)
NMR:1002007
NMR:1002007
Spectra Data
Spectra Data
CHMO:0000806 (mass spectrum)
CHMO:0000806 (mass spectrum)
MS:1000442
MS:1000442
Experimental Description
Experimental Description
IAO:0000317 (experimental section)
IAO:0000317 (experimental sectio...
Bioactivity
Bioactivity
ORCID:0000-0002-3913-8571
ORCID:0000-0002-3913-8571
CHMO:0002533
(gel filtration chromatogram)
CHMO:0002533...
CHEMINF:000113 (InChI descriptor)
CHEMINF:000113 (InChI descriptor)
InChI=1S/C8H8O3/c9-7-5-3-1-2-4-6(5)8(10)11-7/h1-2,5-6H,3-4H2
InChI=1S/C8H8O3/c9-7-5-3-1-2-4-...Text is not SVG - cannot display \ No newline at end of file + + + + + + + + + + Solvent-Free Diels–Alder Reaction in a Closed Batch System... + + + + DOI: 10.1246/bcsj.20120247 + + + RXNO:0000006 + + AFP:0002833 (temper... + + 30°C, 2h + + + CHEBI:474859 + + + + + + CHEBI:39478 + + + + PUBCHEM:CID6810 + + + + + + + + + + CHMO:0000835 (NMR spectrum) + + NMR:1002007 + + Spectra Data + + CHMO:0000806 (mass spectrum) + + MS:1000442 + + + Experimental Description + + IAO:0000317 (experimental sectio... + + + Bioactivity + + + + ORCID:0000-0002-3913-8571 + + CHMO:0002533... + + + CHEMINF:000113 (InChI descriptor) + + InChI=1S/C8H8O3/c9-7-5-3-1-2-4-... + + + + + Text is not SVG - cannot display + + \ No newline at end of file diff --git a/static/img/topics/Overview_Ontologies4Chem_2021.svg b/static/img/topics/Overview_Ontologies4Chem_2021.svg index 14dcd131..9c90c409 100644 --- a/static/img/topics/Overview_Ontologies4Chem_2021.svg +++ b/static/img/topics/Overview_Ontologies4Chem_2021.svg @@ -1,4 +1,670 @@ - - -
 application ontologies
 application ontologies
 upper ontologies 
 upper ontologies 
* not BFO alligned by default
* not BFO alligned by def...

bfo:specifically dependent continuant 

bfo:s...
bfo:generically dependent continuant
bfo:g...bfo:continuant
bfo:occurrent
bfo:o...
bfo:entity
bfo:e...
bfo:independent continuant
bfo:i...
iao:information content entity

iao:i...bfo:material entity
bfo:realizable entity
bfo:r...
bfo:role
bfo:r...
bfo:function
bfo:f...
bfo:disposition
bfo:d...
AFO
AFO
bfo:quality
bfo:q...
MS (CV)*
MS (CV)*
bfo:process
bfo:p...
obi:planned process
obi:p...
MS (CV)*
MS (CV)*
chemical entities
chemical entities
material tools used in chemical contexts
material tools used in...
roles, functions, dispositions and qualities
of chemical entities and of the tools used to interact with these
roles, functions, dispositions and qualities...
information entities needed to refer to things in a chemical context
information entities need...
processes in chemistry
processes in chemistry
nmrCV
nmrCV
nmrCV
nmrCVChEBIChemOnt*
CHMO
CHMO
CHMO
CHMO
CHEMINF
CHEMINF
CHIRO
CHIRO
CHMO
CHMO
MOP
MOP
MOP
MOPPROCOPROCO
RXNO
RXNOPROCO
 domain ontologies
 domain ontologiesViewer does not support full SVG 1.1 \ No newline at end of file + + + + + + + +  application ontologies + +  upper ontologies  + * not BFO alligned by def... + + bfo:s... + + bfo:g... + + + + + + + bfo:continuant + + + bfo:o... + + + + + + bfo:e... + + bfo:i... + + + + iao:i... + + + + + bfo:material entity + + + + + bfo:r... + + + + bfo:r... + + + + bfo:f... + + + + bfo:d... + + + + AFO + + bfo:q... + + + + MS (CV)* + + bfo:p... + + + + obi:p... + + + + MS (CV)* + + chemical entities + material tools used in... + roles, functions, dispositions and qualities... + information entities need... + processes in chemistry + + + nmrCV + + nmrCV + + + ChEBI + + + + ChemOnt* + + + CHMO + + CHMO + + CHEMINF + + CHIRO + + CHMO + + MOP + + MOP + + + PROCO + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + PROCO + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + RXNO + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + PROCO + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +  domain ontologies + + + Viewer does not support full SVG 1.1 + + + \ No newline at end of file From 40eba3cdeca8ff7024d0305914e748b59f7a5c85 Mon Sep 17 00:00:00 2001 From: Johannes Liermann Date: Thu, 11 Jul 2024 19:07:03 +0200 Subject: [PATCH 3/8] fix: broken anchors --- docs/00_intro/10_fair.mdx | 44 +++++++-------- docs/20_role/50_core_facility_manager.mdx | 56 +++++++++++-------- docs/50_data_publication/10_repositories.mdx | 2 +- docs/50_data_publication/25_best_practice.mdx | 48 +++++++--------- .../50_data_availability_statement.mdx | 2 +- 5 files changed, 76 insertions(+), 76 deletions(-) diff --git a/docs/00_intro/10_fair.mdx b/docs/00_intro/10_fair.mdx index 1c7e146b..bfcb71d4 100644 --- a/docs/00_intro/10_fair.mdx +++ b/docs/00_intro/10_fair.mdx @@ -2,6 +2,7 @@ title: "FAIR Data Principles" slug: "/fair" --- + # FAIR Data Principles ![FAIR Data](/img/topics/FAIR_data_principles.png) @@ -23,7 +24,6 @@ In chemistry, the deposition of crystallographic data in a standardized file for In the following, we answer the questions: What makes data FAIR? What do researchers and those who provide data preservation services need to consider? - ## Findable Researchers — and the computers working on their behalf — must be able to find datasets to be able to reuse them. Therefore, the first guideline of the FAIR Data Principles outlines methods to ensure a dataset’s discovery. @@ -38,11 +38,11 @@ A common example of a citable PID is the Digital Object Identifier, or [DOI](htt Data need to be sufficiently described in order to make them both findable and reusable. Hence, the specific focus here lies on making the (meta)data findable by using rich discovery [metadata](/docs/metadata) in a standardized format and allowing computers and humans to quickly understand the dataset’s contents. This is an essential component in the plurality of metadata described by [R1](#r1-metadata-are-richly-described-with-a-plurality-of-accurate-and-relevant-attributes) below. This information may include, but is not limited to: -- the context on what the dataset is, how it was generated, and how it can be interpreted, -- the data quality, -- licensing and (re)use agreements, -- what other data may be related (linked via its PID), and -- associated journal publications and their DOI. +- the context on what the dataset is, how it was generated, and how it can be interpreted, +- the data quality, +- licensing and (re)use agreements, +- what other data may be related (linked via its PID), and +- associated journal publications and their DOI. Repositories should provide researchers with a fillable [application profile](https://en.wikipedia.org/wiki/Application_profile) that allows researchers to give extensive and precise information on their deposited datasets. For example, the Chemotion Repository uses, among others, the [Datacite Metadata Schema](http://doi.org/10.5438/0012) to build its application profile, a schema specifically created for the publication and citation of research data. [RADAR](https://radar.products.fiz-karlsruhe.de/en), including the variant [RADAR4Chem](https://www.nfdi4chem.de/index.php/2650-2/), has also built [its metadata schema](https://radar.products.fiz-karlsruhe.de/en/radarfeatures/radar-metadatenschema) on Datacite. These include an assortment of mandatory, recommended, and optional metadata properties, allowing for a rich description of the deposited dataset. For those publishing data, always keep in mind: the more information provided, the better. @@ -106,17 +106,17 @@ Many of the previous points lead to one key aspect of data sharing: data reusabi Related to [F2](#f2-data-are-described-with-rich-metadata-defined-by-r1-below) above, the focus here lies on whether the data, once found, is useable to the person or computer searching. It also stresses giving the data as many attributes as possible. Researchers should not assume the person—or that person’s computer—looking to re(use) their data is completely familiar with the discipline. Examples of information to assign here include (non-exhaustive list): -- What the dataset contains, including whether the data is raw and/or processed -- How the data was processed -- How the data can be reused -- Who created the data -- Date of creation -- Variable names -- Standard methods used -- Scope of the data and project -- Lab conditions -- Any limitations to the data -- Software and versions used for acquisition and processing. +- What the dataset contains, including whether the data is raw and/or processed +- How the data was processed +- How the data can be reused +- Who created the data +- Date of creation +- Variable names +- Standard methods used +- Scope of the data and project +- Lab conditions +- Any limitations to the data +- Software and versions used for acquisition and processing. An important piece of information for chemical data are [machine-readable chemical structures](/docs/machine-readable_chemical_structures). This should be included within the dataset and/or metadata and aids computers in finding the correct data in their queries. @@ -141,8 +141,8 @@ Where required, format converters should be linked in the dataset’s metadata. ## Sources and further information -- [FORCE 11: FAIR Data Principles](https://www.force11.org/group/fairgroup/fairprinciples) -- [Go-FAIR initiative: FAIR Principles](https://www.go-fair.org/fair-principles/) -- [TIB Blog: The FAIR Data Principles for Research Data](https://blogs.tib.eu/wp/tib/2017/09/12/the-fair-data-principles-for-research-data/) -- [FAIRsFAIR: How to be FAIR with your data. A teaching and training handbook for higher education institutions](https://doi.org/10.5281/zenodo.6674301) & [Engelhardt et al. (book version)](10.17875/gup2022-1915) & [Gitbook version](https://fairsfair.gitbook.io/fair-teaching-handbook) -- [Checklist: How FAIR are your data?](https://doi.org/10.5281/zenodo.1065991) [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.1065991.svg)](https://doi.org/10.5281/zenodo.1065991) +- [FORCE 11: FAIR Data Principles](https://www.force11.org/group/fairgroup/fairprinciples) +- [Go-FAIR initiative: FAIR Principles](https://www.go-fair.org/fair-principles/) +- [TIB Blog: The FAIR Data Principles for Research Data](https://blogs.tib.eu/wp/tib/2017/09/12/the-fair-data-principles-for-research-data/) +- [FAIRsFAIR: How to be FAIR with your data. A teaching and training handbook for higher education institutions](https://doi.org/10.5281/zenodo.6674301) & [Engelhardt et al. (book version)](https://doi.org/10.17875/gup2022-1915) & [Gitbook version](https://fairsfair.gitbook.io/fair-teaching-handbook) +- [Checklist: How FAIR are your data?](https://doi.org/10.5281/zenodo.1065991) [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.1065991.svg)](https://doi.org/10.5281/zenodo.1065991) diff --git a/docs/20_role/50_core_facility_manager.mdx b/docs/20_role/50_core_facility_manager.mdx index 76a18b1f..6908e3e2 100644 --- a/docs/20_role/50_core_facility_manager.mdx +++ b/docs/20_role/50_core_facility_manager.mdx @@ -3,7 +3,7 @@ title: "Core facility manager" slug: "/core_facility_manager" --- -import useBaseUrl from '@docusaurus/useBaseUrl'; +import useBaseUrl from "@docusaurus/useBaseUrl"; :::info Applies to: This article applies to core facility managers and heads of analytical service units. @@ -11,7 +11,12 @@ This article applies to core facility managers and heads of analytical service u ## Motivation -Data LifeCycle +Data LifeCycle In the chemistry data lifecycle, core facilities play an important role as major producers of chemical data. For modern analytical techniques such as mass spectrometry or NMR spectroscopy, data are usually recorded digitally and the challenges lie less in digitalisation but management issues. @@ -23,7 +28,7 @@ When thinking about how to store data and make them available, an important star ### The Situation in Germany -The German Research Council ([DFG](https://www.dfg.de)) summarizes the consensus on the *fundamental principles and standards of good practice* in science in their Code fo Conduct *Guidelines for Safeguarding Good Research Practice* [\[1\]](#dfg_code). In guideline 17, a storage of all research data for the period of ten years is demanded, starting from the date of publication. Data storage strategies should therefore contain longterm storage for at least that time. +The German Research Council ([DFG](https://www.dfg.de)) summarizes the consensus on the _fundamental principles and standards of good practice_ in science in their Code fo Conduct _Guidelines for Safeguarding Good Research Practice_ [\[1\]](#dfg_code). In guideline 17, a storage of all research data for the period of ten years is demanded, starting from the date of publication. Data storage strategies should therefore contain longterm storage for at least that time. ## How to start @@ -41,24 +46,24 @@ In addition, [backup strategies](/docs/data_storage/) for all instrument worksta While most of the scientific work still lies ahead, there are already valuable metadata to be harvested and digested at the early stage of sample submission. These can include, among many others: -- Date -- Creator (person, group) -- Project -- Sample identifier -- Molecular structure(s), and derived properties: - - Molecular formula - - Molecular weight - - Elemental composition - - Physicochemical properties -- Solvent or solubility -- Purity -- Experiment information of interest, such as: - - Retation time - - Polarity - - Ionisation method - - NMR nuclei and experiments - - Chiroptical data -- Biological properties +- Date +- Creator (person, group) +- Project +- Sample identifier +- Molecular structure(s), and derived properties: + - Molecular formula + - Molecular weight + - Elemental composition + - Physicochemical properties +- Solvent or solubility +- Purity +- Experiment information of interest, such as: + - Retation time + - Polarity + - Ionisation method + - NMR nuclei and experiments + - Chiroptical data +- Biological properties The challenge of digesting those metadata according to [FAIR guiding principles](/docs/fair/) can be a challenge for core facilities and essentially come down to two possible strategies: @@ -67,5 +72,10 @@ The challenge of digesting those metadata according to [FAIR guiding principles] ## Sources -1. Deutsche Forschungsgemeinschaft (DFG), Guidelines for Safeguarding Good Research Practice. Code of Conduct, September 2019, DOI -2. See Microsoft documentation for robocopy or manpage for rsync. +1. + Deutsche Forschungsgemeinschaft (DFG), *Guidelines for Safeguarding Good Research + Practice. Code of Conduct*, September 2019, [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.3923602.svg)](https://doi.org/10.5281/zenodo.3923602) + +2. + See [Microsoft documentation](https://docs.microsoft.com/en-us/windows-server/administration/windows-commands/robocopy) + for `robocopy` or [manpage](https://linux.die.net/man/1/rsync) for `rsync`. diff --git a/docs/50_data_publication/10_repositories.mdx b/docs/50_data_publication/10_repositories.mdx index e4c8fa11..2e925aa9 100644 --- a/docs/50_data_publication/10_repositories.mdx +++ b/docs/50_data_publication/10_repositories.mdx @@ -25,7 +25,7 @@ Some, but not all, repositories curate and review the data before **ingestion** In order to allow data reuse by other researchers, [metadata](/docs/metadata), including [provenance information](/docs/provenance/), are required beside the actual data. Metadata describe the research data and provide information about its creation, the methods or software used as well as legal aspects. Metadata can be either added manually via a metadata editor or can be provided through other applications. The process to manually add metadata via a metadata editor can be compared to the process of submitting a manuscript to a publisher via the publishers submission system. -One main function of repositories is to provide a search function, with which users and machines can find, view, and download data. In order to ensure that data are permanently referenced and can be [linked and cited](/docs/best_practice/#how-to-use-dataset-pids-in-scientific-articles), repositories assign unique [persistent identifiers](/docs/pid) (PIDs). This also enhances the findability and accessibility of research data. +One main function of repositories is to provide a search function, with which users and machines can find, view, and download data. In order to ensure that data are permanently referenced and can be [linked and cited](/docs/best_practice/), repositories assign unique [persistent identifiers](/docs/pid) (PIDs). This also enhances the findability and accessibility of research data. Repositories can also be certified (e.g. CoreTrustSeal). Such certification ensures that the data is citable, preserved in the long run, and may also cover aspects of data curation and data quality. diff --git a/docs/50_data_publication/25_best_practice.mdx b/docs/50_data_publication/25_best_practice.mdx index 3568b77d..67050e6e 100644 --- a/docs/50_data_publication/25_best_practice.mdx +++ b/docs/50_data_publication/25_best_practice.mdx @@ -8,14 +8,14 @@ import useBaseUrl from "@docusaurus/useBaseUrl"; # Best Practices :::info Info: -On this page, we provide best practices for the publication of data in field-specific as well as generic research data repositories. +On this page, we provide best practices for the publication of data in field-specific as well as generic research data repositories. ::: ## Best practices for field-specific repositories -For the field-specific repositories [Chemotion Repository](/docs/choose_repository/#chemotion-repository---repository-for-molecules-and-research-data) in combination with [Chemotion ELN](/docs/chemotion_eln), the data is collected along the scientific workflows, analytical data files are automatically converted to open formats, controlled vocabularies or ontologies are used to describe data, and analysis data is interconnected to reactions and samples, hence, chemical structures. The entire Chemotion package allows researchers to collect, analyse, process, store, and publish various types of analytical data attached to reactions and samples in one [digital environment](/docs/smartlab). FAIRification of data along this [data life cycle](/docs/data_life_cycle) is mainly handled by Chemotion. During the seamless export from the ELN into the repository, [PIDs](/docs/pid) (in this case [DOIs](https://www.doi.org/)) are assigned to the deposited data. Chemotion Repository [provides](https://www.chemotion.net/docs/repo/doi) DOIs for reactions, samples, analysis data, and collections (Collection DOI). +For the field-specific repositories [Chemotion Repository](/docs/chemotion_repository) in combination with [Chemotion ELN](/docs/chemotion_eln), the data is collected along the scientific workflows, analytical data files are automatically converted to open formats, controlled vocabularies or ontologies are used to describe data, and analysis data is interconnected to reactions and samples, hence, chemical structures. The entire Chemotion package allows researchers to collect, analyse, process, store, and publish various types of analytical data attached to reactions and samples in one [digital environment](/docs/smartlab). FAIRification of data along this [data life cycle](/docs/data_life_cycle) is mainly handled by Chemotion. During the seamless export from the ELN into the repository, [PIDs](/docs/pid) (in this case [DOIs](https://www.doi.org/)) are assigned to the deposited data. Chemotion Repository [provides](https://www.chemotion.net/docs/repo/doi) DOIs for reactions, samples, analysis data, and collections (Collection DOI). -Other field-specific repositories such as [CSD and ICSD](/docs/choose_repository/#csd-icsd---joint-ccdcfiz-access-structures-service), [Strenda DB](/docs/choose_repository/#strenda-db---repository-for-reporting-rnzymology-data), [SupraBank](/docs/choose_repository/#suprabank), [NOMAD](/docs/choose_repository/#nomad), and [Chemotion Repository](/docs/choose_repository/#chemotion-repository---repository-for-molecules-and-research-data), if used independently from Chemotion ELN, offer built-in workflows for the aggregation of structured data along the submission pathways, aligned with the [FAIR Data Principles](/docs/fair). This greatly facilitates the publication of FAIR data. +Other field-specific repositories such as [CSD and ICSD](/docs/csd_icsd), [Strenda DB](/docs/strenda_db), [SupraBank](/docs/suprabank), [NOMAD](/docs/nomad), and [Chemotion Repository](/docs/chemotion_repository), if used independently from Chemotion ELN, offer built-in workflows for the aggregation of structured data along the submission pathways, aligned with the [FAIR Data Principles](/docs/fair). This greatly facilitates the publication of FAIR data. Further aspects to consider are to provide rich metadata, which could be [domain-independent](/docs/metadata/#domain-independent-metadata) metadata or [domain-specific](/docs/metadata/#domain-specific-metadata) metadata, and should also include [provenance information](/docs/provenance), which previously would have typically been included in the supplemental PDF section on general information and protocols. [Minimum information requirements](/docs/metadata/#minimum-information-standards-mi) should be followed, as set by the chemistry community, and implemented in articles and previously also in supplementary PDFs. @@ -27,8 +27,8 @@ Are you asking yourself right now, "That's it?" Yes, that's it! As mentioned abo For a better understanding of data publishing in field-specific repositories and how this data could be linked to related journal publications, the following examples including their data can be accessed via the following Lead by Example pages: -- in Chemotion Repository: [Modular Synthesis of New Pyrroloquinoline Quinone Derivatives](/docs/datasets/?doi=10.1055/s-0041-1738426). -- in Chemotion Repository and CSD/CCDC: [Modular Synthesis of trans‐A2B2‐Porphyrins with Terminal Esters: Systematically Extending the Scope of Linear Linkers for Porphyrin‐Based MOFs](/docs/datasets/?doi=10.1002/chem.202003885). +- in Chemotion Repository: [Modular Synthesis of New Pyrroloquinoline Quinone Derivatives](/docs/datasets/?doi=10.1055/s-0041-1738426). +- in Chemotion Repository and CSD/CCDC: [Modular Synthesis of trans‐A2B2‐Porphyrins with Terminal Esters: Systematically Extending the Scope of Linear Linkers for Porphyrin‐Based MOFs](/docs/datasets/?doi=10.1002/chem.202003885). ## Best practices for generic repositories @@ -37,44 +37,34 @@ While field-specific repositories provide significant support for the [FAIRifica To start, all data to be published should be collected and ordered in a logical folder structure, e.g. a folder for NMR and another folder for MS data (figure 1). Nested folder structures should be avoided and aspects of [data organisation](/docs/data_organisation), such as file naming, should be taken into account. Researchers should aim for a data package which is as self-explanatory as the supplemental PDFs, they have previously published along scientific articles. **Figure 1:** Example folder structure and content of the [Lead by Example](/docs/lbe_intro) dataset of [Linderazuelene](/docs/datasets/?doi=10.1002/ciuz.201900868). For further aspects to consider, we provide a non-exhaustive list of generic best practices on what a chemistry dataset should contain and how the chemical data should be represented and described. Please note, that [domain-specific](/docs/domain_guide) aspects also need to be considered. -- **Data should be published in open formats along the original raw data in proprietary formats.**
[Open formats](/docs/format_standards) for analytical data should be the main choice. However, many analytical instruments provide data in proprietary formats. Not all data in these formats is necessarily also included in the selected open format it was converted to, depending on the specification of the format applied. Hence, the original raw data (in proprietary formats) should also be published, although this data may have limited interoperability. Publishing original raw data is a measure of scientific integrity and allows for unbiased reprocessing and reuse of data. If no open format exists, export as text file, i.e. without any format specification, should be considered. -- **Data should be linked to chemical structures and reactions.**
As analytical data are usually named following lab journal entries, the dataset must include a description of which data correspond to which sample, molecule, or experiment. This should be included in the format used for analytical data. Another solution on that is to provide a [supplementary table](/docs/machine-readable_chemical_structures/#provide-machine-readable-data-as-supplementary-table) (figure 1) within the data package, which should include InChI structure identifiers and SMILES structure codes and additional information such as RInChI reaction identifiers. Second-tier, chemical structures might also be added and represented as [CT files](/docs//ct_files) such as mol or SDfiles (figure 1). [RXNfiles](/docs//ct_files) may be used to describe chemical reactions in a machine readable way. -- **Datasets should include scripts and workflows and information on software used.**
Workflows, i.e. scripts used for data processing, and input parameters for semi-automatic scripts, should be included. The metadata of the whole dataset should describe the language and version of scripts used as well as other software applied. Best practice is not only to include the code but to add notebooks such as R Notebooks or Jupyther notebooks. -- **Data should be described with metadata and minimum information standards should be followed.**
[Domain-independent](/docs/metadata/#domain-independent-metadata) metadata, via the repository's metadata editor, should be provided. Additionally, [domain-specific](/docs/metadata/#domain-specific-metadata) metadata should be published via the metadata editor, if supported by the repository of choice, or within the analytical data or an additional README file. [Minimum information requirements](/docs/metadata/#minimum-information-standards-mi) as set by the chemistry community and followed in manuscripts and previously also in supplementary PDFs should be included. -- **The provenance information of data should be included.**
Part of that [provenance information](/docs/provenance) is part of the dataset's metadata and should be added via the metadata editor of the repository. All information which previously would have typically been included in the supplemental PDF section on general information and protocols, e.g. information on methods and instruments used, are provenance information and should be added to a README file, as long as no domain-specific metadata schema is available. This README could be a text file, or written in Markdown, while also a human-readable rendered representation as HTML could be provided. +- **Data should be published in open formats along the original raw data in proprietary formats.**
[Open formats](/docs/format_standards) for analytical data should be the main choice. However, many analytical instruments provide data in proprietary formats. Not all data in these formats is necessarily also included in the selected open format it was converted to, depending on the specification of the format applied. Hence, the original raw data (in proprietary formats) should also be published, although this data may have limited interoperability. Publishing original raw data is a measure of scientific integrity and allows for unbiased reprocessing and reuse of data. If no open format exists, export as text file, i.e. without any format specification, should be considered. +- **Data should be linked to chemical structures and reactions.**
As analytical data are usually named following lab journal entries, the dataset must include a description of which data correspond to which sample, molecule, or experiment. This should be included in the format used for analytical data. Another solution on that is to provide a [supplementary table](/docs/machine-readable_chemical_structures/#provide-machine-readable-data-as-supplementary-table) (figure 1) within the data package, which should include InChI structure identifiers and SMILES structure codes and additional information such as RInChI reaction identifiers. Second-tier, chemical structures might also be added and represented as [CT files](/docs/ct_files) such as mol or SDfiles (figure 1). [RXNfiles](/docs/ct_files) may be used to describe chemical reactions in a machine readable way. +- **Datasets should include scripts and workflows and information on software used.**
Workflows, i.e. scripts used for data processing, and input parameters for semi-automatic scripts, should be included. The metadata of the whole dataset should describe the language and version of scripts used as well as other software applied. Best practice is not only to include the code but to add notebooks such as R Notebooks or Jupyther notebooks. +- **Data should be described with metadata and minimum information standards should be followed.**
[Domain-independent](/docs/metadata/#domain-independent-metadata) metadata, via the repository's metadata editor, should be provided. Additionally, [domain-specific](/docs/metadata/#domain-specific-metadata) metadata should be published via the metadata editor, if supported by the repository of choice, or within the analytical data or an additional README file. [Minimum information requirements](/docs/metadata/#minimum-information-standards-mi) as set by the chemistry community and followed in manuscripts and previously also in supplementary PDFs should be included. +- **The provenance information of data should be included.**
Part of that [provenance information](/docs/provenance) is part of the dataset's metadata and should be added via the metadata editor of the repository. All information which previously would have typically been included in the supplemental PDF section on general information and protocols, e.g. information on methods and instruments used, are provenance information and should be added to a README file, as long as no domain-specific metadata schema is available. This README could be a text file, or written in Markdown, while also a human-readable rendered representation as HTML could be provided. :::danger Notice: -Does that sound like a lot of manual work? Avoid extra work by using a [smart lab](/docs/smartlab) digital environments for collecting, processing, analysing, and publishing research data, such as [Chemotion ELN](/docs/chemotion_eln) in combination with [Chemotion Repository](/docs/choose_repository/#chemotion-repository---repository-for-molecules-and-research-data)! Plus, you may omit the preparation of supplementary PDFs and use the saved work time to prepare your dataset for publication! +Does that sound like a lot of manual work? Avoid extra work by using a [smart lab](/docs/smartlab) digital environments for collecting, processing, analysing, and publishing research data, such as [Chemotion ELN](/docs/chemotion_eln) in combination with [Chemotion Repository](/docs/chemotion_repository)! Plus, you may omit the preparation of supplementary PDFs and use the saved work time to prepare your dataset for publication! ::: ### Best practice examples for generic repositories For a better understanding of data publishing in generic repositories and how this data could be linked to related journal publications, the following examples, including their data, can be accessed via the following Lead by Example pages: -- in RADAR4Chem: [Linderazulen aus einer invasiven Pflanze - Delphi und sein violettes Wunder](/docs/datasets/?doi=10.1002/ciuz.201900868). -- in Zenodo: [A dataset of 255,000 randomly selected and manually classified extracted ion chromatograms for evaluation of peak detection methods](/docs/datasets/?doi=10.3390/metabo10040162). -- in RADAR: [Synthesis and biological evaluation of highly potent fungicidal deoxy-hygrophorones](/docs/datasets/?doi=10.1002/ejoc.202100729). -- in DaRus: [Predictive design of ordered mesoporous silica with well-defined, ultra-large mesopores](/docs/datasets/?doi=10.1039/D2ME00107A). - - +- in RADAR4Chem: [Linderazulen aus einer invasiven Pflanze - Delphi und sein violettes Wunder](/docs/datasets/?doi=10.1002/ciuz.201900868). +- in Zenodo: [A dataset of 255,000 randomly selected and manually classified extracted ion chromatograms for evaluation of peak detection methods](/docs/datasets/?doi=10.3390/metabo10040162). +- in RADAR: [Synthesis and biological evaluation of highly potent fungicidal deoxy-hygrophorones](/docs/datasets/?doi=10.1002/ejoc.202100729). +- in DaRus: [Predictive design of ordered mesoporous silica with well-defined, ultra-large mesopores](/docs/datasets/?doi=10.1039/D2ME00107A). --- diff --git a/docs/50_data_publication/50_data_availability_statement.mdx b/docs/50_data_publication/50_data_availability_statement.mdx index 8ba45ced..ec52b097 100644 --- a/docs/50_data_publication/50_data_availability_statement.mdx +++ b/docs/50_data_publication/50_data_availability_statement.mdx @@ -9,7 +9,7 @@ slug: "/data_availability_statement" The data availability statement or a similarly termed section, depending on the publisher, is part of the back matter of a manuscript. The back matter usually also contains information on conflicts of interest, author information, acknowledgements and the references. -The data availability statement enhances findability and enables [linking of the manuscript](/docs/best_practice/#how-to-use-dataset-pids-in-scientific-articles) to the corresponding FAIR dataset in research data [repositories](/docs/repositories) via [PIDs](/docs/pid) such as DOIs, alternatively using the repository-specific identifiers or accession numbers. +The data availability statement enhances findability and enables [linking of the manuscript](/docs/best_practice/) to the corresponding FAIR dataset in research data [repositories](/docs/repositories) via [PIDs](/docs/pid) such as DOIs, alternatively using the repository-specific identifiers or accession numbers. Depending on the publisher, the data availability statement may be directly added to the manuscript submitted or is automatically added during manuscript submission via the respective publishers submission system. From a937b74215d58ba8d7db9b197644810f4de3a645 Mon Sep 17 00:00:00 2001 From: Johannes Liermann Date: Tue, 16 Jul 2024 18:45:39 +0200 Subject: [PATCH 4/8] feat: add imprint --- footer.json | 2 +- src/pages/imprint.mdx | 48 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 49 insertions(+), 1 deletion(-) create mode 100644 src/pages/imprint.mdx diff --git a/footer.json b/footer.json index 5c8c8b90..7f0a109c 100644 --- a/footer.json +++ b/footer.json @@ -46,7 +46,7 @@ }, { "label": "Legal Notice", - "href": "https://www.uni-mainz.de/en/legal-notice/" + "href": "imprint" }, { "label": "Privacy", diff --git a/src/pages/imprint.mdx b/src/pages/imprint.mdx new file mode 100644 index 00000000..2eac03ea --- /dev/null +++ b/src/pages/imprint.mdx @@ -0,0 +1,48 @@ +--- +title: Imprint +slug: /imprint +--- + +## Editor + +Johannes Gutenberg University Mainz +Saarstraße 21 +55122 Mainz + +phone: +49 6131 39-0 +email: registratur@uni-mainz.de + +VAT ID: DE 149 065 685 +Johannes Gutenberg University Mainz is a public corporation. +It is legally represented by its President, Professor Georg Krausch. + +## Competent supervisory authority + +Rhineland-Palatinate Ministry of Science and Health +[Ministerium für Wissenschaft und Gesundheit des Landes Rheinland-Pfalz] +Mittlere Bleiche 61 +55116 Mainz + +## Editorial staff + +Department of Chemistry +Mail: nfdi4chem@uni-mainz.de + +## Webmaster + +Technical questions and suggestions concerning the operation of this website should be directed to the JGU webmaster. Please always include the relevant URL. +email: nfdi4chem@uni-mainz.de + +## Accessibility + +We have tried hard to make our website as accessible as possible pursuant to the Ordinance on the Creation of Accessible Information Technology in Accordance with the Act on Equal Opportunities of Persons with Disabilities (BITV). Further information is available in the JGU accessibility statement. + +## Liability / Disclaimer + +Johannes Gutenberg University Mainz endeavors to ensure that the information provided on its website is accurate and up to date. Nevertheless, we cannot exclude potential errors and ambiguities. Johannes Gutenberg University Mainz assumes no responsibility for the currentness, correctness, completeness, or quality of the information contained herein. + +Johannes Gutenberg University Mainz is not liable for material or immaterial damage or losses that are caused directly or indirectly through the use or non-use of the information presented, unless Johannes Gutenberg University Mainz can be charged with willful or negligent intent. + +Johannes Gutenberg University Mainz reserves the right to change, supplement, or delete its website, in part or in whole, without prior notice, or to remove publication from the internet temporarily or permanently. + +The website of Johannes Gutenberg University Mainz contains direct and indirect links to external third-party websites on the content of which Johannes Gutenberg University Mainz has no influence. Responsibility for this external content lies with the provider or operator of the external website. Johannes Gutenberg University Mainz is not aware of any illegal or offensive content on the websites of external providers that can be accessed through our website. At the time that we created links to each of these websites, we checked for possible violations of law but did not find any illegal or offensive content. If the pages of external providers for which we provide links contain illegal or offensive content, Johannes Gutenberg University Mainz expressly distances itself from this content and will immediately remove the link in question as soon as we become aware of it. From 59de65160a51eca207b4e51f359dbd45888b1550 Mon Sep 17 00:00:00 2001 From: Johannes Liermann Date: Tue, 16 Jul 2024 18:46:40 +0200 Subject: [PATCH 5/8] fix: legal notice / privacy links --- src/pages/about.mdx | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/src/pages/about.mdx b/src/pages/about.mdx index 3fd2937d..b120d6ca 100644 --- a/src/pages/about.mdx +++ b/src/pages/about.mdx @@ -4,7 +4,6 @@ title: About slug: /about --- - # About The NFDI4Chem Knowledge Base is hosted by the Johannes Gutenberg University Mainz. @@ -18,5 +17,5 @@ Department of Chemistry
Germany
Mail: [nfdi4chem@uni-mainz.de](mailto:nfdi4chem@uni-mainz.de) -[Legal Notice](https://www.uni-mainz.de/eng/102.php)
-[Privacy](https://www.uni-mainz.de/eng/144.php) +[Legal Notice](imprint)
+[Privacy](https://www.uni-mainz.de/en/privacy/) From 03918622d9d19cfa2d8827d0c3081e0bb6263ca6 Mon Sep 17 00:00:00 2001 From: Johannes Liermann Date: Tue, 16 Jul 2024 18:54:41 +0200 Subject: [PATCH 6/8] fix: line breaks --- src/pages/about.mdx | 12 ++++++------ src/pages/imprint.mdx | 18 ++++++++++-------- 2 files changed, 16 insertions(+), 14 deletions(-) diff --git a/src/pages/about.mdx b/src/pages/about.mdx index b120d6ca..934d7654 100644 --- a/src/pages/about.mdx +++ b/src/pages/about.mdx @@ -10,12 +10,12 @@ The NFDI4Chem Knowledge Base is hosted by the Johannes Gutenberg University Main ## Responsible Spokesperson -Dr. Johannes Liermann
-Johannes Gutenberg University Mainz
-Department of Chemistry
-55099 Mainz
-Germany
+Dr. Johannes Liermann +Johannes Gutenberg University Mainz +Department of Chemistry +55099 Mainz +Germany Mail: [nfdi4chem@uni-mainz.de](mailto:nfdi4chem@uni-mainz.de) -[Legal Notice](imprint)
+[Legal Notice](imprint) [Privacy](https://www.uni-mainz.de/en/privacy/) diff --git a/src/pages/imprint.mdx b/src/pages/imprint.mdx index 2eac03ea..f4bfbd30 100644 --- a/src/pages/imprint.mdx +++ b/src/pages/imprint.mdx @@ -1,19 +1,21 @@ --- -title: Imprint +title: Legal Notice slug: /imprint --- +# Legal Notice + ## Editor -Johannes Gutenberg University Mainz -Saarstraße 21 +Johannes Gutenberg University Mainz +Saarstraße 21 55122 Mainz -phone: +49 6131 39-0 +phone: +49 6131 39-0 email: registratur@uni-mainz.de -VAT ID: DE 149 065 685 -Johannes Gutenberg University Mainz is a public corporation. +VAT ID: DE 149 065 685 +Johannes Gutenberg University Mainz is a public corporation. It is legally represented by its President, Professor Georg Krausch. ## Competent supervisory authority @@ -25,12 +27,12 @@ Mittlere Bleiche 61 ## Editorial staff -Department of Chemistry +Department of Chemistry / NFDI4Chem Mail: nfdi4chem@uni-mainz.de ## Webmaster -Technical questions and suggestions concerning the operation of this website should be directed to the JGU webmaster. Please always include the relevant URL. +Technical questions and suggestions concerning the operation of this website should be directed to the JGU webmaster. Please always include the relevant URL. email: nfdi4chem@uni-mainz.de ## Accessibility From 333a30f847bb95c26b1c246721cee65a050ffb76 Mon Sep 17 00:00:00 2001 From: Johannes Liermann Date: Tue, 16 Jul 2024 19:14:11 +0200 Subject: [PATCH 7/8] fix: imprint urls --- footer.json | 4 ++-- src/pages/about.mdx | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/footer.json b/footer.json index 7f0a109c..dfdeedb6 100644 --- a/footer.json +++ b/footer.json @@ -42,11 +42,11 @@ "items": [ { "label": "About", - "to": "about" + "to": "/about" }, { "label": "Legal Notice", - "href": "imprint" + "href": "/imprint" }, { "label": "Privacy", diff --git a/src/pages/about.mdx b/src/pages/about.mdx index 934d7654..b1ca63dd 100644 --- a/src/pages/about.mdx +++ b/src/pages/about.mdx @@ -17,5 +17,5 @@ Department of Chemistry Germany Mail: [nfdi4chem@uni-mainz.de](mailto:nfdi4chem@uni-mainz.de) -[Legal Notice](imprint) +[Legal Notice](/imprint) [Privacy](https://www.uni-mainz.de/en/privacy/) From f91b472b12ef3e255915fa558871306d696e05b3 Mon Sep 17 00:00:00 2001 From: Johannes Liermann Date: Tue, 16 Jul 2024 19:16:33 +0200 Subject: [PATCH 8/8] fix: url --- docs/40_smartlab/00_smartlab.mdx | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/docs/40_smartlab/00_smartlab.mdx b/docs/40_smartlab/00_smartlab.mdx index 37f6d9d6..2e289688 100644 --- a/docs/40_smartlab/00_smartlab.mdx +++ b/docs/40_smartlab/00_smartlab.mdx @@ -4,19 +4,23 @@ slug: "/smartlab" id: "smartlab" --- -import IntroButton from '@site/src/components/IntroButton.js'; -import useBaseUrl from '@docusaurus/useBaseUrl'; +import IntroButton from "@site/src/components/IntroButton.js"; +import useBaseUrl from "@docusaurus/useBaseUrl"; # Smart Laboratory (Smart Lab) ![smartlab_flow](/img/smartlab/smartlab_flow2.png) -A smart lab represents a holistic approach to [data management](/docs/data_guide) in chemistry with seamless data flows. What does this mean? It means that all steps within a researcher's [workflow](/docs/domain_guide) across the [research data lifecycle](/docs/data_life_cycle) are interconnected in a digital way. The key difference to a [Laboratory Management System (LIMS)](https://en.wikipedia.org/wiki/Laboratory_information_management_system) is that the Smart Lab's main focus is the realisation of the [FAIR data principles](/docs/fair). For example, a researcher plans and [documents](/docs/data_documentation) their experiment in an [electronic lab notebook (ELN)](/docs/eln). Any experimental data from devices such as spectrometers are then directly ingested by the ELN via [Application Programming Interfaces (APIs)](https://en.wikipedia.org/wiki/API). +A smart lab represents a holistic approach to [data management](/docs/data_guide) in chemistry with seamless data flows. What does this mean? It means that all steps within a researcher's [workflow](/docs/domain_guide) across the [research data lifecycle](/docs/data_life_cycle) are interconnected in a digital way. The key difference to a [Laboratory Management System (LIMS)](https://en.wikipedia.org/wiki/Laboratory_information_management_system) is that the Smart Lab's main focus is the realisation of the [FAIR data principles](/docs/fair). For example, a researcher plans and [documents](/docs/data_documentation) their experiment in an [electronic lab notebook (ELN)](/docs/eln). Any experimental data from devices such as spectrometers are then directly ingested by the ELN via [Application Programming Interfaces (APIs)](https://en.wikipedia.org/wiki/API). -The ELN then ideally assigns all the necessary [metadata](/docs/metadata) automatically and appropriately for a corresponding workflow and converts proprietary [data formats](/docs/format_standards) to open data formats. The ELN structures the (meta)data and experimental descriptions in a meaningful and sustainable way which is both human- and machine-readable (e.g., via the use of [machine-readable chemical structures](/docs/machine-readable_chemical_structures). When the researcher chooses to [publish](/docs/data_publishing) or [archive](/docs/data_storage) their data, it is then ingested seamlessly by a data [repository](/docs/repositories) or archive without much further work as the ELN has already appropriately prepared the dataset to meet a repository’s or archive’s [requirements](/docs//choose_repository). +The ELN then ideally assigns all the necessary [metadata](/docs/metadata) automatically and appropriately for a corresponding workflow and converts proprietary [data formats](/docs/format_standards) to open data formats. The ELN structures the (meta)data and experimental descriptions in a meaningful and sustainable way which is both human- and machine-readable (e.g., via the use of [machine-readable chemical structures](/docs/machine-readable_chemical_structures). When the researcher chooses to [publish](/docs/data_publishing) or [archive](/docs/data_storage) their data, it is then ingested seamlessly by a data [repository](/docs/repositories) or archive without much further work as the ELN has already appropriately prepared the dataset to meet a repository’s or archive’s [requirements](/docs/choose_repository). In this section, key components of the smart lab will be introduced to you. ## Get started: - +