use cases
MGnify oriented implementation for the Marine Genomic Observatories oriented pipeline, developed in the framework of an EOSC-Life funded project
An example of a RO-Crate metadata .json file
Here is the ro-crate-metada.json file that describes the RO-Crate built for the TARA OCEAN sample (ERR599171) that was analysed as part of the metaGOflow manuscript.
{
"@context": "https://w3id.org/ro/crate/1.1/context",
"@graph": [
{
"@id": "ro-crate-metadata.json",
"@type": "CreativeWork",
"about": {
"@id": "./"
},
"conformsTo": {
"@id": "https://w3id.org/ro/crate/1.1"
}
},
{
"@id": "./",
"@type": "Dataset",
"datePublished": "2023-05-10T09:59:46+00:00",
"hasPart": [
{
"@id": "results/"
},
{
"@id": "ERR599171.yml"
},
{
"@id": "config.yml"
},
{
"@id": "results/sequence-categorisation/"
},
{
"@id": "results/taxonomy-summary/"
},
{
"@id": "results/functional-annotation/"
},
{
"@id": "results/final.contigs.fa"
},
{
"@id": "results/fastp.html"
},
{
"@id": "results/ERR599171_1.fastq.trimmed.fasta"
},
{
"@id": "results/ERR599171_2.fastq.trimmed.fasta"
},
{
"@id": "results/ERR599171.merged.fasta"
},
{
"@id": "results/ERR599171.merged.qc_summary"
},
{
"@id": "results/ERR599171.merged.motus.tsv"
},
{
"@id": "results/ERR599171.merged.unfiltered_fasta"
},
{
"@id": "results/ERR599171.merged.cmsearch.all.tblout.deoverlapped"
},
{
"@id": "results/ERR599171.merged_CDS.faa"
},
{
"@id": "results/ERR599171.merged_CDS.ffn"
},
{
"@id": "results/ERR599171_1.fastq.trimmed.qc_summary"
},
{
"@id": "results/ERR599171_2.fastq.trimmed.qc_summary"
},
{
"@id": "results/RNA-counts"
},
{
"@id": "results/sequence-categorisation/5_8S.fa.gz"
},
{
"@id": "results/sequence-categorisation/LSU_rRNA_archaea.RF02540.fa.gz"
},
{
"@id": "results/sequence-categorisation/LSU_rRNA_bacteria.RF02541.fa.gz"
},
{
"@id": "results/sequence-categorisation/LSU_rRNA_eukarya.RF02543.fa.gz"
},
{
"@id": "results/sequence-categorisation/SSU_rRNA_archaea.RF01959.fa.gz"
},
{
"@id": "results/sequence-categorisation/SSU_rRNA_bacteria.RF00177.fa.gz"
},
{
"@id": "results/sequence-categorisation/SSU_rRNA_eukarya.RF01960.fa.gz"
},
{
"@id": "results/sequence-categorisation/Bacteria_large_SRP.RF01854.fasta.gz"
},
{
"@id": "results/sequence-categorisation/Bacteria_small_SRP.RF00169.fasta.gz"
},
{
"@id": "results/sequence-categorisation/RNaseP_bact_a.RF00010.fasta.gz"
},
{
"@id": "results/sequence-categorisation/alpha_tmRNA.RF01849.fasta.gz"
},
{
"@id": "results/sequence-categorisation/cyano_tmRNA.RF01851.fasta.gz"
},
{
"@id": "results/sequence-categorisation/tRNA-Sec.RF01852.fasta.gz"
},
{
"@id": "results/sequence-categorisation/tRNA.RF00005.fasta.gz"
},
{
"@id": "results/sequence-categorisation/tmRNA.RF00023.fasta.gz"
},
{
"@id": "results/taxonomy-summary/SSU/"
},
{
"@id": "results/taxonomy-summary/LSU/"
},
{
"@id": "results/taxonomy-summary/SSU/ERR599171.merged_SSU.fasta.mseq.gz"
},
{
"@id": "results/taxonomy-summary/SSU/ERR599171.merged_SSU.fasta.mseq.tsv"
},
{
"@id": "results/taxonomy-summary/SSU/ERR599171.merged_SSU.fasta.mseq.txt"
},
{
"@id": "results/taxonomy-summary/SSU/krona.html"
},
{
"@id": "results/taxonomy-summary/SSU/ERR599171.merged_SSU.fasta.mseq_hdf5.biom"
},
{
"@id": "results/taxonomy-summary/SSU/ERR599171.merged_SSU.fasta.mseq_json.biom"
},
{
"@id": "results/taxonomy-summary/LSU/ERR599171.merged_LSU.fasta.mseq.gz"
},
{
"@id": "results/taxonomy-summary/LSU/ERR599171.merged_LSU.fasta.mseq.tsv"
},
{
"@id": "results/taxonomy-summary/LSU/ERR599171.merged_LSU.fasta.mseq.txt"
},
{
"@id": "results/taxonomy-summary/LSU/krona.html"
},
{
"@id": "results/taxonomy-summary/LSU/ERR599171.merged_LSU.fasta.mseq_hdf5.biom"
},
{
"@id": "results/taxonomy-summary/LSU/ERR599171.merged_LSU.fasta.mseq_json.biom"
},
{
"@id": "results/functional-annotation/stats/"
},
{
"@id": "results/functional-annotation/ERR599171.merged.summary.ips"
},
{
"@id": "results/functional-annotation/ERR599171.merged.summary.ko"
},
{
"@id": "results/functional-annotation/ERR599171.merged.summary.pfam"
},
{
"@id": "results/functional-annotation/ERR599171.merged.summary.go"
},
{
"@id": "results/functional-annotation/ERR599171.merged.summary.go_slim"
},
{
"@id": "results/functional-annotation/ERR599171.merged.hmm.tsv.gz"
},
{
"@id": "results/functional-annotation/ERR599171.merged_CDS.I5.tsv.gz"
},
{
"@id": "results/functional-annotation/ERR599171.merged.hmm.tsv.chunks"
},
{
"@id": "results/functional-annotation/ERR599171.merged_CDS.I5.tsv.chunks"
},
{
"@id": "results/functional-annotation/stats/interproscan.stats"
},
{
"@id": "results/functional-annotation/stats/go.stats"
},
{
"@id": "results/functional-annotation/stats/ko.stats"
},
{
"@id": "results/functional-annotation/stats/pfam.stats"
},
{
"@id": "results/functional-annotation/stats/orf.stats"
}
],
"name": "MetaGoFlow Results",
"publisher": {
"@id": "https://ror.org/0038zss60"
}
},
{
"@id": "results/",
"@type": "Dataset"
},
{
"@id": "ERR599171.yml",
"@type": "File"
},
{
"@id": "config.yml",
"@type": "File",
"description": "The configuration file through which the user sets the values of the metaGOflow parameters.",
"encodingFormat": "text/yaml",
"name": "MetaGOflow configuration file"
},
{
"@id": "results/sequence-categorisation/",
"@type": "Dataset",
"description": "Identify specific loci in the sample.",
"name": "Sequence categorisation"
},
{
"@id": "results/taxonomy-summary/",
"@type": "Dataset"
},
{
"@id": "results/functional-annotation/",
"@type": "Dataset"
},
{
"@id": "results/final.contigs.fa",
"@type": "File",
"description": "These are the assembled contig sequences from the merged reads in FASTA format",
"encodingFormat": "text/plain",
"name": "FASTA formatted contig sequences"
},
{
"@id": "results/fastp.html",
"@type": "File",
"description": "Quality control and preprocessing of FASTQ files",
"encodingFormat": "text/html",
"name": "FASTP analysis of raw sequence data"
},
{
"@id": "results/ERR599171_1.fastq.trimmed.fasta",
"@type": "File",
"encodingFormat": "text/plain",
"name": "Filtered .fastq file of the single-end reads (forward/reverse)."
},
{
"@id": "results/ERR599171_2.fastq.trimmed.fasta",
"@type": "File",
"encodingFormat": "text/plain",
"name": "Filtered .fastq file of the single-end reads (forward/reverse)."
},
{
"@id": "results/ERR599171.merged.fasta",
"@type": "File",
"encodingFormat": "text/plain",
"name": "Merged filtered reads."
},
{
"@id": "results/ERR599171.merged.qc_summary",
"@type": "File",
"encodingFormat": "text/plain",
"name": "Summary with statistics of the merged reads."
},
{
"@id": "results/ERR599171.merged.motus.tsv",
"@type": "File",
"encodingFormat": "text/plain",
"name": ""
},
{
"@id": "results/ERR599171.merged.unfiltered_fasta",
"@type": "File",
"encodingFormat": "text/plain",
"name": ""
},
{
"@id": "results/ERR599171.merged.cmsearch.all.tblout.deoverlapped",
"@type": "File",
"encodingFormat": "text/plain",
"name": "Sequence hits against covariance model databases. Mandatory to run partially the functional annotation step of metaGOflow."
},
{
"@id": "results/ERR599171.merged_CDS.faa",
"@type": "File",
"encodingFormat": "text/plain",
"name": "Coding sequences with amino acids."
},
{
"@id": "results/ERR599171.merged_CDS.ffn",
"@type": "File",
"encodingFormat": "text/plain",
"name": "Coding sequences with nucleotides."
},
{
"@id": "results/ERR599171_1.fastq.trimmed.qc_summary",
"@type": "File",
"encodingFormat": "text/plain",
"name": "Summary with statistics of the single-end reads (forward/reverse)."
},
{
"@id": "results/ERR599171_2.fastq.trimmed.qc_summary",
"@type": "File",
"encodingFormat": "text/plain",
"name": "Summary with statistics of the single-end reads (forward/reverse)."
},
{
"@id": "results/RNA-counts",
"@type": "File",
"encodingFormat": "text/plain",
"name": "Numbers of RNA's counted"
},
{
"@id": "results/sequence-categorisation/5_8S.fa.gz",
"@type": "File",
"description": "Identify specific loci in the sample.",
"encodingFormat": "application/zip",
"name": "Sequence categorisation"
},
{
"@id": "results/sequence-categorisation/LSU_rRNA_archaea.RF02540.fa.gz",
"@type": "File",
"description": "Identify specific loci in the sample.",
"encodingFormat": "application/zip",
"name": "Sequence categorisation"
},
{
"@id": "results/sequence-categorisation/LSU_rRNA_bacteria.RF02541.fa.gz",
"@type": "File",
"description": "Identify specific loci in the sample.",
"encodingFormat": "application/zip",
"name": "Sequence categorisation"
},
{
"@id": "results/sequence-categorisation/LSU_rRNA_eukarya.RF02543.fa.gz",
"@type": "File",
"description": "Identify specific loci in the sample.",
"encodingFormat": "application/zip",
"name": "Sequence categorisation"
},
{
"@id": "results/sequence-categorisation/SSU_rRNA_archaea.RF01959.fa.gz",
"@type": "File",
"description": "Identify specific loci in the sample.",
"encodingFormat": "application/zip",
"name": "Sequence categorisation"
},
{
"@id": "results/sequence-categorisation/SSU_rRNA_bacteria.RF00177.fa.gz",
"@type": "File",
"description": "Identify specific loci in the sample.",
"encodingFormat": "application/zip",
"name": "Sequence categorisation"
},
{
"@id": "results/sequence-categorisation/SSU_rRNA_eukarya.RF01960.fa.gz",
"@type": "File",
"description": "Identify specific loci in the sample.",
"encodingFormat": "application/zip",
"name": "Sequence categorisation"
},
{
"@id": "results/sequence-categorisation/Bacteria_large_SRP.RF01854.fasta.gz",
"@type": "File",
"description": "Identify specific loci in the sample.",
"encodingFormat": "application/zip",
"name": "Sequence categorisation"
},
{
"@id": "results/sequence-categorisation/Bacteria_small_SRP.RF00169.fasta.gz",
"@type": "File",
"description": "Identify specific loci in the sample.",
"encodingFormat": "application/zip",
"name": "Sequence categorisation"
},
{
"@id": "results/sequence-categorisation/RNaseP_bact_a.RF00010.fasta.gz",
"@type": "File",
"description": "Identify specific loci in the sample.",
"encodingFormat": "application/zip",
"name": "Sequence categorisation"
},
{
"@id": "results/sequence-categorisation/alpha_tmRNA.RF01849.fasta.gz",
"@type": "File",
"description": "Identify specific loci in the sample.",
"encodingFormat": "application/zip",
"name": "Sequence categorisation"
},
{
"@id": "results/sequence-categorisation/cyano_tmRNA.RF01851.fasta.gz",
"@type": "File",
"description": "Identify specific loci in the sample.",
"name": "Sequence categorisation"
},
{
"@id": "results/sequence-categorisation/tRNA-Sec.RF01852.fasta.gz",
"@type": "File",
"description": "Identify specific loci in the sample.",
"encodingFormat": "application/zip",
"name": "Sequence categorisation"
},
{
"@id": "results/sequence-categorisation/tRNA.RF00005.fasta.gz",
"@type": "File",
"description": "Identify specific loci in the sample.",
"encodingFormat": "application/zip",
"name": "Sequence categorisation"
},
{
"@id": "results/sequence-categorisation/tmRNA.RF00023.fasta.gz",
"@type": "File",
"description": "Identify specific loci in the sample.",
"encodingFormat": "application/zip",
"name": "Sequence categorisation"
},
{
"@id": "results/taxonomy-summary/SSU/",
"@type": "Dataset"
},
{
"@id": "results/taxonomy-summary/LSU/",
"@type": "Dataset"
},
{
"@id": "results/taxonomy-summary/SSU/ERR599171.merged_SSU.fasta.mseq.gz",
"@type": "File",
"encodingFormat": "application/zip",
"name": "LSU sequences used for indentification"
},
{
"@id": "results/taxonomy-summary/SSU/ERR599171.merged_SSU.fasta.mseq.tsv",
"@type": "File",
"encodingFormat": "application/json-ld",
"name": "Tab-separated formatted taxon counts for SSU sequences"
},
{
"@id": "results/taxonomy-summary/SSU/ERR599171.merged_SSU.fasta.mseq.txt",
"@type": "File",
"encodingFormat": "application/json-ld",
"name": "Text-based formatted taxon counts for SSU sequences"
},
{
"@id": "results/taxonomy-summary/SSU/krona.html",
"@type": "File",
"encodingFormat": "application/html",
"name": "Krona summary of LSU taxonomic inventory"
},
{
"@id": "results/taxonomy-summary/SSU/ERR599171.merged_SSU.fasta.mseq_hdf5.biom",
"@type": "File",
"encodingFormat": "application/json-ld",
"name": "BIOM formatted hdf5 taxon counts for SSU sequences"
},
{
"@id": "results/taxonomy-summary/SSU/ERR599171.merged_SSU.fasta.mseq_json.biom",
"@type": "File",
"encodingFormat": "application/json-ld",
"name": "BIOM formatted taxon counts for SSU sequences"
},
{
"@id": "results/taxonomy-summary/LSU/ERR599171.merged_LSU.fasta.mseq.gz",
"@type": "File",
"encodingFormat": "application/zip",
"name": "LSU sequences used for indentification"
},
{
"@id": "results/taxonomy-summary/LSU/ERR599171.merged_LSU.fasta.mseq.tsv",
"@type": "File",
"encodingFormat": "application/json-ld",
"name": "Tab-separated formatted taxon counts for LSU sequences"
},
{
"@id": "results/taxonomy-summary/LSU/ERR599171.merged_LSU.fasta.mseq.txt",
"@type": "File",
"encodingFormat": "application/json-ld",
"name": "Text-based taxon counts for LSU sequences"
},
{
"@id": "results/taxonomy-summary/LSU/krona.html",
"@type": "File",
"encodingFormat": "application/html",
"name": "Krona summary of LSU taxonomic inventory"
},
{
"@id": "results/taxonomy-summary/LSU/ERR599171.merged_LSU.fasta.mseq_hdf5.biom",
"@type": "File",
"encodingFormat": "application/json-ld",
"name": "BIOM formatted hdf5 taxon counts for LSU sequences"
},
{
"@id": "results/taxonomy-summary/LSU/ERR599171.merged_LSU.fasta.mseq_json.biom",
"@type": "File",
"encodingFormat": "application/json-ld",
"name": "BIOM formatted taxon counts for LSU sequences"
},
{
"@id": "results/functional-annotation/stats/",
"@type": "Dataset"
},
{
"@id": "results/functional-annotation/ERR599171.merged.summary.ips",
"@type": "File",
"encodingFormat": "text/plain",
"name": "Merged contigs InterProScan"
},
{
"@id": "results/functional-annotation/ERR599171.merged.summary.ko",
"@type": "File",
"encodingFormat": "text/plain",
"name": "Merged contigs KO summary"
},
{
"@id": "results/functional-annotation/ERR599171.merged.summary.pfam",
"@type": "File",
"encodingFormat": "text/plain",
"name": "Merged contigs PFAM summary"
},
{
"@id": "results/functional-annotation/ERR599171.merged.summary.go",
"@type": "File",
"encodingFormat": "text/plain",
"name": "Merged contigs GO summary"
},
{
"@id": "results/functional-annotation/ERR599171.merged.summary.go_slim",
"@type": "File",
"encodingFormat": "text/plain",
"name": "Merged contigs GO summary"
},
{
"@id": "results/functional-annotation/ERR599171.merged.hmm.tsv.gz",
"@type": "File",
"encodingFormat": "application/zip",
"name": "Merged contigs HMM summary"
},
{
"@id": "results/functional-annotation/ERR599171.merged_CDS.I5.tsv.gz",
"@type": "File",
"encodingFormat": "application/zip",
"name": "Merged contigs CDS I5 summary"
},
{
"@id": "results/functional-annotation/ERR599171.merged.hmm.tsv.chunks",
"@type": "File"
},
{
"@id": "results/functional-annotation/ERR599171.merged_CDS.I5.tsv.chunks",
"@type": "File"
},
{
"@id": "results/functional-annotation/stats/interproscan.stats",
"@type": "File",
"encodingFormat": "text/plain",
"name": "InterProScan summary statistics"
},
{
"@id": "results/functional-annotation/stats/go.stats",
"@type": "File",
"encodingFormat": "text/plain",
"name": "Geno Ontology summary statistics"
},
{
"@id": "results/functional-annotation/stats/ko.stats",
"@type": "File",
"encodingFormat": "text/plain",
"name": "Kegg Ontology summary statistics"
},
{
"@id": "results/functional-annotation/stats/pfam.stats",
"@type": "File",
"encodingFormat": "text/plain",
"name": "Pfam summary statistcs"
},
{
"@id": "results/functional-annotation/stats/orf.stats",
"@type": "File",
"encodingFormat": "text/plain",
"name": "ORF summary statistics"
},
{
"@id": "https://www.apache.org/licenses/LICENSE-2.0",
"@type": "CreativeWork",
"identifier": "https://spdx.org/licenses/Apache-2.0.html",
"name": "Apache License 2.0"
},
{
"@id": "https://creativecommons.org/licenses/by/4.0/legalcode",
"@type": "CreativeWork",
"identifier": "https://spdx.org/licenses/CC-BY-4.0.html",
"name": "Creative Commons (CC-BY 4.0)"
},
{
"@id": "mailto:emobon@embrc.eu",
"@type": "ContactPoint",
"contactType": "Help Desk",
"email": "emobon@embrc.eu",
"identifier": "emobon@embrc.eu",
"url": "https://www.embrc.eu/about-us/contact-us"
},
{
"@id": "https://ror.org/0038zss60",
"@type": "Organization",
"contactPoint": {
"@id": "mailto:emobon@embrc.eu"
},
"name": "European Marine Biological Resource Centre",
"url": "https://ror.org/0038zss60"
},
{
"@id": "#workflow/metaGOflow",
"@type": [
"File",
"SoftwareSourceCode",
"ComputationalWorkflow"
],
"affiliation": "University of Flatland",
"author": {
"@id": "EMO BON"
},
"hasPart": [
{
"@id": "config.yml"
},
{
"@id": "TARA_OCEANS_SAMPLE_3steps/ERR599171.yml"
}
],
"license": {
"@id": "https://www.apache.org/licenses/LICENSE-2.0"
},
"name": "metaGOflow",
"url": "https://github.com/emo-bon/MetaGOflow/releases/tag/v1.0.0"
}
]
}