diff --git a/examples/MixsCompliantData-MimsSoil-example.yaml b/examples/MixsCompliantData-MimsSoil-example.yaml index 7d7c29d722..946e2a2581 100644 --- a/examples/MixsCompliantData-MimsSoil-example.yaml +++ b/examples/MixsCompliantData-MimsSoil-example.yaml @@ -1,4 +1,4 @@ -mims_soil_data: +mimsmisip_soil_data: - collection_date: "2013-03-25T12:42:31+01:00" depth: 1.234 units elev: 1.234 units @@ -11,15 +11,17 @@ mims_soil_data: samp_name: msd1 samp_taxon_id: Gut Metagenome [NCBITaxon:749906] seq_meth: absolutely any text - - collection_date: "2013-03-25T12:42:31+01:00" - depth: 1.234 units - elev: 1.234 units - env_broad_scale: term [ONTOLOGY:123] - env_local_scale: term [ONTOLOGY:123] - env_medium: term [ONTOLOGY:123] - geo_loc_name: "text: text, text" - lat_lon: 45.1 45.9 - project_name: absolutely any text - samp_name: msd2 - samp_taxon_id: Gut Metagenome [NCBITaxon:749906] - seq_meth: absolutely any text + isotope: 13C; 15N + isotopolog: toluene [pubchem.compound:1140]; water [pubchem.compound:962] + isotopolog_label: natural abundance + isotopolog_approach: multiple + gradient_position: 1 + gradient_pos_density: 1.725 g/mL + gradient_pos_rel_am: 10% + sip_method: https://doi.org/10.1038/s41396-018-0279-6 + isotopolog_atom_frac: 0.95 + isotopolog_atom_pos: 1S/C7H8/c1-7-5-3-2-4-6-7/h2-6H,1H3/i1+1,2+1,3+1,4+1,5+1,6+1,7+1; 1S/C6H12O6/c7-1-3(9)5(11)6(12)4(10)2-8/h1,3-6,8-12H,2H2/t3-,4+,5+,6+/m0/s1 + isotopolog_dose: 10 ppm + nucleobase_atom_frac: 25% + isotopolog_incu_time: 12 hour + internal_standard: https://doi.org/10.1101/2022.12.20.521340 \ No newline at end of file diff --git a/src/mixs/schema/mixs.yaml b/src/mixs/schema/mixs.yaml index 993f6bda1d..3e3010c0e7 100644 --- a/src/mixs/schema/mixs.yaml +++ b/src/mixs/schema/mixs.yaml @@ -50,7 +50,7 @@ enums: permissible_values: not applicable: description: > - Information is inappropriate to report, + Information is inappropriate to report, can indicate that the standard itself fails to model or represent the information appropriately aliases: - n/a @@ -79,21 +79,21 @@ enums: description: Information is not applicable as the sample represents a negative control sample collected in a lab. "missing: sample group": description: > - Information is not applicable as the sample represents a group of samples that do not have a single origin. + Information is not applicable as the sample represents a group of samples that do not have a single origin. E.g. for co-assembly or transcriptome assembly. "missing: synthetic construct": description: Information does not exist as the sample represents an ab-initio synthetic construct. "missing: lab stock": description: > - Information was not collected as the sample represents a cultured cell line or model organism + Information was not collected as the sample represents a cultured cell line or model organism under long-term lab control. "missing: third party data": description: > - Information does not exist as the metadata was not collected or reported in records predating the 2023 agreement. + Information does not exist as the metadata was not collected or reported in records predating the 2023 agreement. For use in Third PArty data submissions. "missing: data agreement established pre-2023": description: > - Data agreements were established before the 2023 INSDC standard and metadata can not be provided. + Data agreements were established before the 2023 INSDC standard and metadata can not be provided. A value may be given at a later stage. "missing: endangered species": description: Information can not be reported as the target organism is endangered e.g. on the IUCN red-list. @@ -1252,6 +1252,24 @@ enums: low: middle: top: + IsotopeEnum: + permissible_values: + 13C: + description: Carbon with 13C isotope + 15N: + description: Nitrogen with 15N isotope + 2H: + description: Hydrogen with 2H isotope + 18O: + description: Oxygen with 18O isotope + IsotopologLabelEnum: + permissible_values: + isotopically labeled: + natural abundance: + IsotopologApproachEnum: + permissible_values: + single: + multiple: slots: migs_ba_data: description: Data that comply with checklist MigsBa @@ -3888,7 +3906,7 @@ slots: abs_air_humidity: annotations: Preferred_unit: gram per gram, kilogram per kilogram, kilogram, pound, gram per cubic meter, kilogram per cubic meter, percent - description: Actual mass of water vapor present in the air water vapor mixture. + description: Actual mass of water vapor present in the air water vapor mixture. comments: - Can be calculated via mass of water vapor divided by the volume of the air and water vapor mixture. title: absolute air humidity @@ -5420,7 +5438,7 @@ slots: interpolated: true partial_match: true climate_environment: - deprecated: true, slot is inconsistently used and provides redundant information to other slots, https://github.com/GenomicsStandardsConsortium/mixs/issues/591 and https://github.com/microbiomedata/nmdc-schema/issues/586 + deprecated: true, slot is inconsistently used and provides redundant information to other slots, https://github.com/GenomicsStandardsConsortium/mixs/issues/591 and https://github.com/microbiomedata/nmdc-schema/issues/586 description: Treatment involving an exposure to a particular climate; treatment regimen including how many times the treatment was repeated, how long each treatment lasted, and the start and end time of the entire treatment; can include multiple @@ -9712,7 +9730,7 @@ slots: History of nose/mouth/teeth/throat disorders; can include multiple disorders. The terms should be chosen from the DO (Human Disease Ontology) at http://www.disease-ontology.org, nose disease (https://disease-ontology.org/?id=DOID:2825), - mouth disease (https://disease-ontology.org/?id=DOID:403), + mouth disease (https://disease-ontology.org/?id=DOID:403), tooth disease (https://disease-ontology.org/?id=DOID:1091), or upper respiratory tract disease (https://disease-ontology.org/?id=DOID:974) title: nose/mouth/teeth/throat disorder @@ -9721,10 +9739,10 @@ slots: slot_uri: MIXS:0000283 multivalued: true range: string - deprecated: true, replace with MIXS:0000270 https://github.com/GenomicsStandardsConsortium/mixs/issues/743 + deprecated: true, replace with MIXS:0000270 https://github.com/GenomicsStandardsConsortium/mixs/issues/743 nose_throat_disord: description: > - Report any history of nose, mouth, teeth and/or throat disorders in the subject. + Report any history of nose, mouth, teeth and/or throat disorders in the subject. May include multiple disorders. title: nose throat disorder keywords: @@ -9733,8 +9751,8 @@ slots: aliases: nose_mouth_teeth_throat_disord comments: - > - The terms should be chosen from the DO (Human Disease Ontology) - at http://www.disease-ontology.org, lung disease (https://disease-ontology.org/?id=DOID:850), + The terms should be chosen from the DO (Human Disease Ontology) + at http://www.disease-ontology.org, lung disease (https://disease-ontology.org/?id=DOID:850), upper respiratory tract disease (https://disease-ontology.org/?id=DOID:974) multivalued: true range: string @@ -14737,7 +14755,275 @@ slots: syntax: ^{scientific_float}( *- *{scientific_float})? *{text}$ interpolated: true partial_match: true + isotope: + title: isotope + description: The target isotope for measurement in the experimental sample. List both the element and the atomic mass. + range: IsotopeEnum + multivalued: true + examples: + - value: 13C + - value: 13C; 15N + required: true + isotopolog: + title: isotopolog + description: Isotopologue (isotope source/substrate/molecule) added to the biological sample. + comments: List the PubChem Compound Identification (CID) number. If it's an undefined mixture, enter 0. If more than one isotopologue was used in this sample, use a ; to delimit each isotopolog. + structured_pattern: + syntax: ^{termLabel} {[termID]} + range: string + examples: + - value: toluene [pubchem.compound:1140] + - value: toluene [pubchem.compound:1140]; water [pubchem.compound:962] + - value: "0" + required: true + isotopolog_label: + title: isotopolog label status + description: List whether the isotopologue added to this biological sample was heavy-labelled or natural abundance + range: IsotopologLabelEnum + examples: + - value: natural abundance + - value: isotopically labeled + required: true + isotopolog_approach: + title: Labeling approach (number of labeled isotopologs supplied) + description: The labelling approach of this SIP experiment. Details if multiple isotopically labelled isotopologues were added to samples ("multiple"), or was only one isotopologue added to each sample ("single"). + range: IsotopologApproachEnum + examples: + - value: single + - value: multiple + required: true + gradient_position: + title: gradient position + description: A number designating the gradient position from heaviest (=1) to lightest. Unfractionated samples, from which fractionated samples were derived, should be denoted with –1. + range: integer + examples: + - value: 1 + - value: -1 + required: true + gradient_pos_density: + title: density of gradient position + description: Buoyant density of this fraction + structured_pattern: + syntax: ^{float}-{float} {unit} | {float} {unit} + annotations: + Preferred_unit: g/mL + examples: + - value: 1.725 g/mL + - value: 1.725 - 1.735 g/mL + recommended: true + gradient_pos_rel_am: + title: relative amount of nucleic acids in the gradient position + description: Percent of total nucleic acids loaded onto the column in this fraction. If uploading 16S rRNA gene (or other amplicon) sequencing data, this value should be calculated from qPCR data. If uploading untargetted sequencing data, this value should be calculated from total DNA concentration. + structured_pattern: + syntax: ^{float} {unit}$ + annotations: + Preferred_unit: percent + examples: + - value: 10% + range: string + recommended: true + sip_method: + title: method for SIP fractionating + description: Method used to fractionate nucleic acids. + range: string + examples: + - value: https://doi.org/10.1038/s41396-018-0279-6 + structured_pattern: + syntax: ^{PMID}|{DOI}|{URL}$ + recommended: true + isotopolog_atom_frac: + title: atom fraction of isotopolog + description: The fraction of heavy-labelled atoms out of all atoms of a given element in the isotopolog. Multiple values allowed, separated by a ; and should be orded the same as the isotopolog. + range: string + examples: + - value: 0.99 or 0.99 + - value: 0.95 + structured_pattern: + syntax: ^{float}|{float}-{float}$ + recommended: true + isotopolog_atom_pos: + title: set of labeled atoms in isotopologue + description: InChI label designating set of all isotopically enriched atoms in isotopologue. Multiple values allowed, separated by a ; and should be orded the same as the isotopolog. + range: string + examples: + - value: 1S/C7H8/c1-7-5-3-2-4-6-7/h2-6H,1H3/i1+1,2+1,3+1,4+1,5+1,6+1,7+1 + - value: 1S/C7H8/c1-7-5-3-2-4-6-7/h2-6H,1H3/i1+1,2+1,3+1,4+1,5+1,6+1,7+1; 1S/C6H12O6/c7-1-3(9)5(11)6(12)4(10)2-8/h1,3-6,8-12H,2H2/t3-,4+,5+,6+/m0/s1 + - value: undefined + structured_pattern: + syntax: ^{termLabel} {[termID]}|{text}$ + recommended: true + isotopolog_dose: + title: dose of isotopolog + description: Total dose of isotopolog added to the system in grams. Multiple values allowed, separated by a ; and should be orded the same as the isotopolog. + annotations: + Preferred_unit: ppm + range: string + examples: + - value: 10 ppm + structured_pattern: + syntax: ^{float} {unit}$ + recommended: true + nucleobase_atom_frac: + title: nucleobase excess atom fraction + description: Excess atom fraction of the nucleobases in this fraction + range: string + examples: + - value: 25% + structured_pattern: + syntax: ^{float}{unit}$ + recommended: true + isotopolog_incu_time: + title: isotopolog incubation time + description: Total time of incubation after isotopologue addition in hours + annotations: + Preferred_unit: hours + range: string + examples: + - value: 12 hour + structured_pattern: + syntax: ^{float} {unit}$ + recommended: true + internal_standard: + title: internal standard method + description: Method used for internal standard for SIP fractionation, if an internal standard was used (i.e., spiking in a heavy-labelled DNA sequence). + range: string + examples: + - value: https://doi.org/10.1101/2022.12.20.521340 + structured_pattern: + syntax: ^{PMID}|{DOI}|{URL}$ + recommended: true + classes: + MimsMisip: + description: Metagenome or Environmental with SIP + comments: Any changes made to MIMS should be reflected here, in MIMS-MISIP. This checklist includes all MIMS terms and additional MISIP terms. + todos: + - Add a validation or test to check the MIMS slots and MIMS-MISIP slots don't diverge + title: MIMS-MISIP + aliases: + - misip + is_a: Checklist + mixin: true + slots: + - samp_name + - size_frac + - lib_screen + - ref_db + - nucl_acid_amp + - lib_size + - mid + - assembly_name + - temp + - nucl_acid_ext + - samp_size + - alt + - source_mat_id + - samp_vol_we_dna_ext + - lib_reads_seqd + - rel_to_oxygen + - samp_collect_device + - number_contig + - lib_layout + - assembly_qual + - ref_biomaterial + - project_name + - lib_vector + - adapters + - neg_cont_type + - assembly_software + - annot + - pos_cont_type + - feat_pred + - env_local_scale + - samp_mat_process + - sim_search_meth + - depth + - samp_collect_method + - env_medium + - samp_taxon_id + - geo_loc_name + - collection_date + - seq_meth + - lat_lon + - elev + - env_broad_scale + - tax_class + - experimental_factor + - associated_resource + - sop + - isotope + - isotopolog + - isotopolog_label + - isotopolog_approach + - gradient_position + - gradient_pos_density + - gradient_pos_rel_am + - sip_method + - isotopolog_atom_frac + - isotopolog_atom_pos + - isotopolog_dose + - nucleobase_atom_frac + - isotopolog_incu_time + - internal_standard + slot_usage: + adapters: + recommended: true + alt: + recommended: true + annot: + recommended: true + assembly_name: + recommended: true + assembly_qual: + recommended: true + assembly_software: + recommended: true + depth: + examples: + - value: 10 meter + recommended: true + elev: + recommended: true + experimental_factor: + recommended: true + lib_layout: + recommended: true + lib_reads_seqd: + recommended: true + lib_screen: + recommended: true + lib_size: + recommended: true + lib_vector: + recommended: true + mid: + recommended: true + nucl_acid_amp: + recommended: true + nucl_acid_ext: + recommended: true + number_contig: + recommended: true + samp_collect_device: + examples: + - value: swab, biopsy, niskin bottle, push core, drag swab [GENEPIO:0002713] + recommended: true + samp_collect_method: + examples: + - value: swabbing + recommended: true + samp_mat_process: + recommended: true + samp_size: + recommended: true + sop: + recommended: true + source_mat_id: + recommended: true + temp: + recommended: true + # class_uri: + MigsBa: description: 'Minimal Information about a Genome Sequence: cultured bacteria/archaea' title: MIGS bacteria @@ -16124,9 +16410,9 @@ classes: class_uri: MIXS:0010012 Agriculture: description: >- - A collection of terms appropriate when sequencing samples obtained in an agricultural environment. - Suitable to capture metadata appropriate to enhance crop productivity and agroecosystem health - with the aim to facilitate research of agricultural microbiomes and their relationships to plant productivity + A collection of terms appropriate when sequencing samples obtained in an agricultural environment. + Suitable to capture metadata appropriate to enhance crop productivity and agroecosystem health + with the aim to facilitate research of agricultural microbiomes and their relationships to plant productivity and sustainable crop production from diverse crop management contexts. title: agriculture is_a: Extension @@ -16597,8 +16883,8 @@ classes: use_cases: bioaerosol samples, pathogen load in urban air, aerosols BuiltEnvironment: description: >- - A collection of terms appropriate when collecting samples and sequencing samples obtained in the - built-up environment, which includes terms for surface material, humidity, temperature, moisture and + A collection of terms appropriate when collecting samples and sequencing samples obtained in the + built-up environment, which includes terms for surface material, humidity, temperature, moisture and occupancy type along with specific metadata terms describing the indoor air, building and sample properties. title: built environment is_a: Extension @@ -16796,7 +17082,7 @@ classes: use_cases: microbiology studies of the built environment, NASA space station sampling, MetaSUB transit system sampling, home, hospitals, office buildings FoodAnimalAndAnimalFeed: description: >- - A collection of terms appropriate when collecting samples and performing sequencing of samples + A collection of terms appropriate when collecting samples and performing sequencing of samples obtained from farm animals and their feed. comments: - This extension is intended to work alongside the other food extensions @@ -16946,7 +17232,7 @@ classes: use_cases: Microbiome of farm animals, their feed, and pet food. FoodFarmEnvironment: description: >- - A collection of terms appropriate when collecting samples and performing sequencing of samples + A collection of terms appropriate when collecting samples and performing sequencing of samples obtained from the farm environment, including soil, manure, and food harvesting equipment. comments: - This extension is intended to work alongside the other food extensions @@ -17172,7 +17458,7 @@ classes: use_cases: Microbiome of farm and field crops as well as environmental samples including irrigation, soil amendments, and farm equipment. FoodFoodProductionFacility: description: >- - A collection of terms appropriate when collecting samples and performing sequencing of samples + A collection of terms appropriate when collecting samples and performing sequencing of samples obtained from food production facilities. comments: - This extension is intended to work alongside the other food extensions @@ -17330,7 +17616,7 @@ classes: use_cases: Microbiome of food production facilities/factories FoodHumanFoods: description: >- - A collection of terms appropriate when collecting samples and performing sequencing of samples + A collection of terms appropriate when collecting samples and performing sequencing of samples obtained from human food products. comments: - This extension is intended to work alongside the other food extensions @@ -17480,7 +17766,7 @@ classes: use_cases: Microbiome of foods intended for human consumption. HostAssociated: description: >- - A collection of terms appropriate when collecting samples and sequencing samples + A collection of terms appropriate when collecting samples and sequencing samples obtained from a non-human host, to examine the host-associated microbiome or genome. comments: - This is a very broad package, intended to capture many kinds of sequences derived @@ -17615,8 +17901,8 @@ classes: use_cases: elephant fecal matter or cat oral cavity HumanAssociated: description: >- - A collection of terms appropriate when collecting samples and sequencing samples - obtained from a person to examine their human-associated microbiome or genome, + A collection of terms appropriate when collecting samples and sequencing samples + obtained from a person to examine their human-associated microbiome or genome, that does not have a specific extension (e.g., skin, gut, vaginal). comments: - For stool samples use MIxS-human-gut extension. @@ -17726,7 +18012,7 @@ classes: use_cases: blood samples or biopsy samples. HumanGut: description: >- - A collection of terms appropriate when collecting samples and sequencing samples + A collection of terms appropriate when collecting samples and sequencing samples obtained from a person to examine their gut-associated microbiome. title: human-gut is_a: Extension @@ -17818,7 +18104,7 @@ classes: use_cases: human stool or fecal samples, or samples collected directly from the gut. HumanOral: description: >- - A collection of terms appropriate when collecting samples and sequencing samples + A collection of terms appropriate when collecting samples and sequencing samples obtained from a person to examine their oral-associated microbiome. title: human-oral is_a: Extension @@ -17910,7 +18196,7 @@ classes: use_cases: mouth swab sampling, dental microbiome samples, microbiome of oral swabs, nasal, mouth, throat, teeth, tongue microbiome studies HumanSkin: description: >- - A collection of terms appropriate when collecting samples and sequencing samples + A collection of terms appropriate when collecting samples and sequencing samples obtained from a person to examine their skin-associated microbiome. title: human-skin is_a: Extension @@ -18002,7 +18288,7 @@ classes: use_cases: swab samples taken on a person’s skin surface. HumanVaginal: description: >- - A collection of terms appropriate when collecting samples and sequencing samples + A collection of terms appropriate when collecting samples and sequencing samples obtained from a person to examine their vaginal-associated microbiome. title: human-vaginal is_a: Extension @@ -18101,7 +18387,7 @@ classes: use_cases: vaginal swabbing HydrocarbonResourcesCores: description: >- - A collection of terms appropriate when collecting samples and sequencing samples + A collection of terms appropriate when collecting samples and sequencing samples obtained from environments pertaining to hydrocarbon resources, specifically core samples. title: hydrocarbon resources-cores is_a: Extension @@ -18227,7 +18513,7 @@ classes: use_cases: The microbial characterization of hydrocarbon occurrences, defined as the natural and artificial environmental features that are rich in hydrocarbons, from hydrocarbon rich formations, such as reservoir cores. HydrocarbonResourcesFluidsSwabs: description: >- - A collection of terms appropriate when collecting samples and sequencing samples + A collection of terms appropriate when collecting samples and sequencing samples obtained from environments pertaining to hydrocarbon resources, specifically run-off liquids samples and swabs. title: hydrocarbon resources-fluids/swabs is_a: Extension @@ -18357,7 +18643,7 @@ classes: use_cases: The microbial characterization of hydrocarbon occurrences, defined as the natural and artificial environmental features that are rich in hydrocarbons, from hydrocarbon resource fluids. MicrobialMatBiofilm: description: >- - A collection of terms appropriate when collecting samples and sequencing samples + A collection of terms appropriate when collecting samples and sequencing samples obtained from biofilm environments including microbial mats. title: microbial mat/biofilm is_a: Extension @@ -18448,7 +18734,7 @@ classes: use_cases: samples from microbial mats at cold seeps MiscellaneousNaturalOrArtificialEnvironment: description: >- - A collection of generic terms appropriate when collecting and sequencing samples + A collection of generic terms appropriate when collecting and sequencing samples obtained from environments, where there is no specific extension already available. title: miscellaneous natural or artificial environment is_a: Extension @@ -18516,7 +18802,7 @@ classes: - MIxS-miscellaneous natural or artificial environment PlantAssociated: description: >- - A collection of terms appropriate when collecting samples and sequencing samples + A collection of terms appropriate when collecting samples and sequencing samples obtained from a plant to examine it’s plant-associated microbiome. title: plant-associated is_a: Extension @@ -18671,7 +18957,7 @@ classes: use_cases: plant surface swabs, root soil or rhizosphere, cultivated plants, plant phenotyping Sediment: description: >- - A collection of terms appropriate when collecting samples and sequencing samples + A collection of terms appropriate when collecting samples and sequencing samples obtained from the sedimentary area of aquatic environments. comments: - Sedimentary layers in terrestrial environments will probably be better served by the soil extension. @@ -18770,7 +19056,7 @@ classes: use_cases: river bed or sea floor. Soil: description: >- - A collection of terms appropriate when collecting samples and sequencing samples + A collection of terms appropriate when collecting samples and sequencing samples obtained from the uppermost layer of Earth's crust, contributed by the Terragenome Consortium. see_also: - https://www.fao.org/agriculture/crops/thematic-sitemap/theme/spi/soil-biodiversity/research-into-soil-biodiversity/the-terragenome-project/en/ @@ -18860,7 +19146,7 @@ classes: use_cases: soil collection, island microbiome sampling, farm land or forest floor. SymbiontAssociated: description: >- - A collection of terms appropriate when collecting samples and sequencing samples + A collection of terms appropriate when collecting samples and sequencing samples obtained from an organism that lives in close association with any other organism(s). title: symbiont-associated is_a: Extension @@ -18982,7 +19268,7 @@ classes: use_cases: the microbiome sequence of a flea sampled from a farm animal WastewaterSludge: description: >- - A collection of terms appropriate when collecting samples and sequencing samples + A collection of terms appropriate when collecting samples and sequencing samples obtained from any solid, semisolid or liquid waste. title: wastewater/sludge is_a: Extension @@ -19042,7 +19328,7 @@ classes: use_cases: sewerage or industrial wastewater Water: description: >- - A collection of terms appropriate when collecting samples and sequencing water samples + A collection of terms appropriate when collecting samples and sequencing water samples obtained from any aquatic environment. title: water is_a: Extension @@ -21487,6 +21773,229 @@ classes: mixins: - Mims class_uri: MIXS:0010007_0016014 + MimsMisipAgriculture: + description: MIxS Data that comply with the MimsMisip checklist and the Agriculture + Extension + title: MimsMisip combined with Agriculture + in_subset: + - combination_classes + is_a: Agriculture + mixins: + - MimsMisip + # class_uri: + MimsMisipAir: + description: MIxS Data that comply with the MimsMisip checklist and the Air Extension + title: MimsMisip combined with Air + in_subset: + - combination_classes + is_a: Air + mixins: + - MimsMisip + # class_uri: + MimsMisipBuiltEnvironment: + description: MIxS Data that comply with the MimsMisip checklist and the BuiltEnvironment + Extension + title: MimsMisip combined with BuiltEnvironment + in_subset: + - combination_classes + is_a: BuiltEnvironment + mixins: + - MimsMisip + # class_uri: + MimsMisipFoodAnimalAndAnimalFeed: + description: MIxS Data that comply with the MimsMisip checklist and the FoodAnimalAndAnimalFeed + Extension + title: MimsMisip combined with FoodAnimalAndAnimalFeed + in_subset: + - combination_classes + is_a: FoodAnimalAndAnimalFeed + mixins: + - MimsMisip + # class_uri: + MimsMisipFoodFarmEnvironment: + description: MIxS Data that comply with the MimsMisip checklist and the FoodFarmEnvironment + Extension + title: MimsMisip combined with FoodFarmEnvironment + in_subset: + - combination_classes + is_a: FoodFarmEnvironment + mixins: + - MimsMisip + # class_uri: + MimsMisipFoodFoodProductionFacility: + description: MIxS Data that comply with the MimsMisip checklist and the FoodFoodProductionFacility + Extension + title: MimsMisip combined with FoodFoodProductionFacility + in_subset: + - combination_classes + is_a: FoodFoodProductionFacility + mixins: + - MimsMisip + # class_uri: + MimsMisipFoodHumanFoods: + description: MIxS Data that comply with the MimsMisip checklist and the FoodHumanFoods + Extension + title: MimsMisip combined with FoodHumanFoods + in_subset: + - combination_classes + is_a: FoodHumanFoods + mixins: + - MimsMisip + # class_uri: + MimsMisipHostAssociated: + description: MIxS Data that comply with the MimsMisip checklist and the HostAssociated + Extension + title: MimsMisip combined with HostAssociated + in_subset: + - combination_classes + is_a: HostAssociated + mixins: + - MimsMisip + # class_uri: + MimsMisipHumanAssociated: + description: MIxS Data that comply with the MimsMisip checklist and the HumanAssociated + Extension + title: MimsMisip combined with HumanAssociated + in_subset: + - combination_classes + is_a: HumanAssociated + mixins: + - MimsMisip + # class_uri: + MimsMisipHumanGut: + description: MIxS Data that comply with the MimsMisip checklist and the HumanGut Extension + title: MimsMisip combined with HumanGut + in_subset: + - combination_classes + is_a: HumanGut + mixins: + - MimsMisip + # class_uri: + MimsMisipHumanOral: + description: MIxS Data that comply with the MimsMisip checklist and the HumanOral Extension + title: MimsMisip combined with HumanOral + in_subset: + - combination_classes + is_a: HumanOral + mixins: + - MimsMisip + # class_uri: + MimsMisipHumanSkin: + description: MIxS Data that comply with the MimsMisip checklist and the HumanSkin Extension + title: MimsMisip combined with HumanSkin + in_subset: + - combination_classes + is_a: HumanSkin + mixins: + - MimsMisip + # class_uri: + MimsMisipHumanVaginal: + description: MIxS Data that comply with the MimsMisip checklist and the HumanVaginal + Extension + title: MimsMisip combined with HumanVaginal + in_subset: + - combination_classes + is_a: HumanVaginal + mixins: + - MimsMisip + # class_uri: + MimsMisipHydrocarbonResourcesCores: + description: MIxS Data that comply with the MimsMisip checklist and the HydrocarbonResourcesCores + Extension + title: MimsMisip combined with HydrocarbonResourcesCores + in_subset: + - combination_classes + is_a: HydrocarbonResourcesCores + mixins: + - MimsMisip + # class_uri: + MimsMisipHydrocarbonResourcesFluidsSwabs: + description: MIxS Data that comply with the MimsMisip checklist and the HydrocarbonResourcesFluidsSwabs + Extension + title: MimsMisip combined with HydrocarbonResourcesFluidsSwabs + in_subset: + - combination_classes + is_a: HydrocarbonResourcesFluidsSwabs + mixins: + - MimsMisip + # class_uri: + MimsMisipMicrobialMatBiofilm: + description: MIxS Data that comply with the MimsMisip checklist and the MicrobialMatBiofilm + Extension + title: MimsMisip combined with MicrobialMatBiofilm + in_subset: + - combination_classes + is_a: MicrobialMatBiofilm + mixins: + - MimsMisip + # class_uri: + MimsMisipMiscellaneousNaturalOrArtificialEnvironment: + description: MIxS Data that comply with the MimsMisip checklist and the MiscellaneousNaturalOrArtificialEnvironment + Extension + title: MimsMisip combined with MiscellaneousNaturalOrArtificialEnvironment + in_subset: + - combination_classes + is_a: MiscellaneousNaturalOrArtificialEnvironment + mixins: + - MimsMisip + # class_uri: + MimsMisipPlantAssociated: + description: MIxS Data that comply with the MimsMisip checklist and the PlantAssociated + Extension + title: MimsMisip combined with PlantAssociated + in_subset: + - combination_classes + is_a: PlantAssociated + mixins: + - MimsMisip + # class_uri: + MimsMisipSediment: + description: MIxS Data that comply with the MimsMisip checklist and the Sediment Extension + title: MimsMisip combined with Sediment + in_subset: + - combination_classes + is_a: Sediment + mixins: + - MimsMisip + # class_uri: + MimsMisipSoil: + description: MIxS Data that comply with the MimsMisip checklist and the Soil Extension + title: MimsMisip combined with Soil + in_subset: + - combination_classes + is_a: Soil + mixins: + - MimsMisip + # class_uri: + MimsMisipSymbiontAssociated: + description: MIxS Data that comply with the MimsMisip checklist and the SymbiontAssociated + Extension + title: MimsMisip combined with SymbiontAssociated + in_subset: + - combination_classes + is_a: SymbiontAssociated + mixins: + - MimsMisip + # class_uri: + MimsMisipWastewaterSludge: + description: MIxS Data that comply with the MimsMisip checklist and the WastewaterSludge + Extension + title: MimsMisip combined with WastewaterSludge + in_subset: + - combination_classes + is_a: WastewaterSludge + mixins: + - MimsMisip + # class_uri: + MimsMisipWater: + description: MIxS Data that comply with the MimsMisip checklist and the Water Extension + title: MimsMisip combined with Water + in_subset: + - combination_classes + is_a: Water + mixins: + - MimsMisip + # class_uri: MisagAgriculture: description: MIxS Data that comply with the Misag checklist and the Agriculture Extension @@ -21951,7 +22460,7 @@ settings: adapter_A_DNA_sequence: '[ACGTRKSYMWBHDVN]+' adapter_B_DNA_sequence: '[ACGTRKSYMWBHDVN]+' ambiguous_nucleotides: '[ACGTRKSYMWBHDVN]+' - boolean: '(?:yes|no)' # a non-capturing group matching either 'yes' or 'no' + boolean: '(?:yes|no)' # a non-capturing group matching either 'yes' or 'no' country: ([^\s-]{1,2}|[^\s-]+.+[^\s-]+) date_time_stamp: '(\d{4})(-(0[1-9]|1[0-2])(-(0[1-9]|[12]\d|3[01])(T([01]\d|2[0-3]):([0-5]\d):([0-5]\d)(\.\d+)?(Z|([+-][01]\d:[0-5]\d))?)?)?)?$' dna: '^[ACGT]+$'