From 3b7a986b94241f731ba0d30dfbc30c69c9fce7bb Mon Sep 17 00:00:00 2001 From: smit684 Date: Mon, 23 Jun 2025 12:21:41 -0700 Subject: [PATCH 01/19] add isotope slot --- src/mixs/schema/mixs.yaml | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/src/mixs/schema/mixs.yaml b/src/mixs/schema/mixs.yaml index 993f6bda1d..7a24e530d6 100644 --- a/src/mixs/schema/mixs.yaml +++ b/src/mixs/schema/mixs.yaml @@ -1252,6 +1252,16 @@ 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 slots: migs_ba_data: description: Data that comply with checklist MigsBa @@ -14737,6 +14747,16 @@ 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 + + classes: MigsBa: description: 'Minimal Information about a Genome Sequence: cultured bacteria/archaea' From 21eee1415b0742aaf2c2406bc512f0702604f18a Mon Sep 17 00:00:00 2001 From: smit684 Date: Mon, 23 Jun 2025 12:36:05 -0700 Subject: [PATCH 02/19] add isotopolog & iso label --- src/mixs/schema/mixs.yaml | 25 ++++++++++++++++++++++++- 1 file changed, 24 insertions(+), 1 deletion(-) diff --git a/src/mixs/schema/mixs.yaml b/src/mixs/schema/mixs.yaml index 7a24e530d6..6579a1697b 100644 --- a/src/mixs/schema/mixs.yaml +++ b/src/mixs/schema/mixs.yaml @@ -1262,6 +1262,10 @@ enums: description: Hydrogen with 2H isotope 18O: description: Oxygen with 18O isotope + IsotopologLabelEnum: + permissible_values: + isotopically labeled: + natural abundance: slots: migs_ba_data: description: Data that comply with checklist MigsBa @@ -14755,7 +14759,26 @@ slots: examples: - value: 13C - value: 13C; 15N - + 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: text + examples: + - value: toluene [pubchem.compound:1140] + - value: toluene [pubchem.compound:1140]; water [pubchem.compound:962] + - value: "0" + 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 + + classes: MigsBa: From d63c0b0d47192bff84cd09f6926ecc69ba86de3c Mon Sep 17 00:00:00 2001 From: smit684 Date: Mon, 23 Jun 2025 12:41:19 -0700 Subject: [PATCH 03/19] add gradient --- src/mixs/schema/mixs.yaml | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) diff --git a/src/mixs/schema/mixs.yaml b/src/mixs/schema/mixs.yaml index 6579a1697b..e4cb8048bb 100644 --- a/src/mixs/schema/mixs.yaml +++ b/src/mixs/schema/mixs.yaml @@ -1266,6 +1266,10 @@ enums: permissible_values: isotopically labeled: natural abundance: + IsotopologApproachEnum: + permissible_values: + single: + multiple: slots: migs_ba_data: description: Data that comply with checklist MigsBa @@ -14777,7 +14781,23 @@ slots: examples: - value: natural abundance - value: isotopically labeled - + 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 + 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 + + + classes: From 0c2eb164a0063ebaf7ebb3620e803e3fb19d1990 Mon Sep 17 00:00:00 2001 From: smit684 Date: Mon, 23 Jun 2025 12:43:22 -0700 Subject: [PATCH 04/19] string, not text! --- src/mixs/schema/mixs.yaml | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/src/mixs/schema/mixs.yaml b/src/mixs/schema/mixs.yaml index e4cb8048bb..ef78f12797 100644 --- a/src/mixs/schema/mixs.yaml +++ b/src/mixs/schema/mixs.yaml @@ -14769,7 +14769,7 @@ slots: 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: text + range: string examples: - value: toluene [pubchem.compound:1140] - value: toluene [pubchem.compound:1140]; water [pubchem.compound:962] @@ -14795,7 +14795,7 @@ slots: examples: - value: 1 - value: -1 - + From c84ed4dbd6e7965f516706f2cefbee41429c9a48 Mon Sep 17 00:00:00 2001 From: smit684 Date: Mon, 23 Jun 2025 12:54:41 -0700 Subject: [PATCH 05/19] add gradient pos density --- src/mixs/schema/mixs.yaml | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/src/mixs/schema/mixs.yaml b/src/mixs/schema/mixs.yaml index ef78f12797..8c74739ee9 100644 --- a/src/mixs/schema/mixs.yaml +++ b/src/mixs/schema/mixs.yaml @@ -14795,10 +14795,16 @@ slots: examples: - value: 1 - value: -1 - - - - + 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 classes: MigsBa: From cc4472e05a9617eb636804ad98b2c9494a2eea20 Mon Sep 17 00:00:00 2001 From: "Mark A. Miller" Date: Tue, 1 Jul 2025 11:56:23 -0400 Subject: [PATCH 06/19] yaml linting errors --- src/mixs/schema/mixs.yaml | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/src/mixs/schema/mixs.yaml b/src/mixs/schema/mixs.yaml index 8c74739ee9..7071d9dee1 100644 --- a/src/mixs/schema/mixs.yaml +++ b/src/mixs/schema/mixs.yaml @@ -14782,7 +14782,7 @@ slots: - value: natural abundance - value: isotopically labeled isotopolog_approach: - title: Labeling approach (number of labeled isotopologs supplied) + 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: @@ -22020,7 +22020,7 @@ 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))?)?)?)?$' dna: '^[ACGT]+$' From 2592a7f7379a40afeb60477b6a4aec5ee0acceee Mon Sep 17 00:00:00 2001 From: smit684 Date: Mon, 28 Jul 2025 17:57:27 -0700 Subject: [PATCH 07/19] add remaining slots and class --- src/mixs/schema/mixs.yaml | 230 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 230 insertions(+) diff --git a/src/mixs/schema/mixs.yaml b/src/mixs/schema/mixs.yaml index 8c74739ee9..4884ff0de4 100644 --- a/src/mixs/schema/mixs.yaml +++ b/src/mixs/schema/mixs.yaml @@ -14805,8 +14805,238 @@ slots: examples: - value: 1.725 g/mL - value: 1.725 - 1.735 g/mL + 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 + 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}$ + 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}$ + 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: undefined + structured_pattern: + syntax: ^{termLabel} {[termID]}|{text}$ + isotopolog_dose: + title: dose of isotopolog + description: Total dose of isotopolog added to the system in grams + annotations: + Preferred_unit: ppm + range: string + examples: + - value: 10 ppm + structured_pattern: + syntax: ^{float} {unit}$ + 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}$ + 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}$ + 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}$ classes: + MimsMisip: + description: Metagenome or Environmental with SIP + title: MISIP-MIMS + aliases: + - misip + - mims + 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 + isotope: + required: true + isotopolog: + required: true + isotopolog_label: + required: true + isotopolog_approach: + required: true + gradient_position: + required: true + gradient_pos_density: + recommended: true + gradient_pos_rel_am: + recommended: true + sip_method: + recommended: true + isotopolog_atom_frac: + recommended: true + isotopolog_atom_pos: + recommended: true + isotopolog_dose: + recommended: true + nucleobase_atom_frac: + recommended: true + isotopolog_incu_time: + recommended: true + internal_standard: + recommended: true + #class_uri: + + + MigsBa: description: 'Minimal Information about a Genome Sequence: cultured bacteria/archaea' title: MIGS bacteria From 5af32786b714f935d66fec7753783fe53c218851 Mon Sep 17 00:00:00 2001 From: smit684 Date: Mon, 28 Jul 2025 17:59:28 -0700 Subject: [PATCH 08/19] update class --- src/mixs/schema/mixs.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/mixs/schema/mixs.yaml b/src/mixs/schema/mixs.yaml index 9127225750..7c36bdebb2 100644 --- a/src/mixs/schema/mixs.yaml +++ b/src/mixs/schema/mixs.yaml @@ -14879,7 +14879,7 @@ slots: syntax: ^{PMID}|{DOI}|{URL}$ classes: - MimsMisip: + MisipMims: description: Metagenome or Environmental with SIP title: MISIP-MIMS aliases: From b481cfabe3878c081e10953035280d18fe59ae69 Mon Sep 17 00:00:00 2001 From: smit684 Date: Tue, 29 Jul 2025 11:11:25 -0700 Subject: [PATCH 09/19] lint error? --- src/mixs/schema/mixs.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/mixs/schema/mixs.yaml b/src/mixs/schema/mixs.yaml index 7c36bdebb2..45b6d38053 100644 --- a/src/mixs/schema/mixs.yaml +++ b/src/mixs/schema/mixs.yaml @@ -22250,7 +22250,7 @@ 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))?)?)?)?$' dna: '^[ACGT]+$' From 1a1b6655c8ec659e830663e9c0c7c0d81a823e40 Mon Sep 17 00:00:00 2001 From: smit684 Date: Tue, 29 Jul 2025 11:20:01 -0700 Subject: [PATCH 10/19] question --- src/mixs/schema/mixs.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/mixs/schema/mixs.yaml b/src/mixs/schema/mixs.yaml index 45b6d38053..ed9160c400 100644 --- a/src/mixs/schema/mixs.yaml +++ b/src/mixs/schema/mixs.yaml @@ -21563,7 +21563,7 @@ classes: mixins: - MimarksS class_uri: MIXS:0010008_0016014 - MimsAgriculture: + MimsAgriculture: ##for each checklist + extension, do I need to make an MIMS-MISIP + extension? description: MIxS Data that comply with the Mims checklist and the Agriculture Extension title: Mims combined with Agriculture From d65d04d0c343f234b845bc31a7173ba9779736ab Mon Sep 17 00:00:00 2001 From: smit684 Date: Tue, 29 Jul 2025 11:24:51 -0700 Subject: [PATCH 11/19] remove excess space --- src/mixs/schema/mixs.yaml | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/src/mixs/schema/mixs.yaml b/src/mixs/schema/mixs.yaml index ed9160c400..f211f9eee9 100644 --- a/src/mixs/schema/mixs.yaml +++ b/src/mixs/schema/mixs.yaml @@ -15033,9 +15033,7 @@ classes: recommended: true internal_standard: recommended: true - #class_uri: - - + # class_uri: MigsBa: description: 'Minimal Information about a Genome Sequence: cultured bacteria/archaea' From 44292e67fd3d099210bf338656eb2154325bb74b Mon Sep 17 00:00:00 2001 From: smit684 Date: Tue, 29 Jul 2025 16:09:53 -0700 Subject: [PATCH 12/19] move requirements to slot and off slot usage --- src/mixs/schema/mixs.yaml | 42 +++++++++++++-------------------------- 1 file changed, 14 insertions(+), 28 deletions(-) diff --git a/src/mixs/schema/mixs.yaml b/src/mixs/schema/mixs.yaml index f211f9eee9..270bbe0214 100644 --- a/src/mixs/schema/mixs.yaml +++ b/src/mixs/schema/mixs.yaml @@ -14763,6 +14763,7 @@ slots: examples: - value: 13C - value: 13C; 15N + required: true isotopolog: title: isotopolog description: Isotopologue (isotope source/substrate/molecule) added to the biological sample. @@ -14774,6 +14775,7 @@ slots: - 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 @@ -14781,6 +14783,7 @@ slots: 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"). @@ -14788,6 +14791,7 @@ slots: 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. @@ -14795,6 +14799,7 @@ slots: examples: - value: 1 - value: -1 + required: true gradient_pos_density: title: density of gradient position description: Buoyant density of this fraction @@ -14805,6 +14810,7 @@ slots: 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. @@ -14815,6 +14821,7 @@ slots: examples: - value: 10% range: string + recommended: true sip_method: title: method for SIP fractionating description: Method used to fractionate nucleic acids. @@ -14823,6 +14830,7 @@ slots: - 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. @@ -14832,6 +14840,7 @@ slots: - 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. @@ -14841,6 +14850,7 @@ slots: - 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 @@ -14851,6 +14861,7 @@ slots: - 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 @@ -14859,6 +14870,7 @@ slots: - 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 @@ -14869,6 +14881,7 @@ slots: - 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). @@ -14877,6 +14890,7 @@ slots: - value: https://doi.org/10.1101/2022.12.20.521340 structured_pattern: syntax: ^{PMID}|{DOI}|{URL}$ + recommended: true classes: MisipMims: @@ -15005,34 +15019,6 @@ classes: recommended: true temp: recommended: true - isotope: - required: true - isotopolog: - required: true - isotopolog_label: - required: true - isotopolog_approach: - required: true - gradient_position: - required: true - gradient_pos_density: - recommended: true - gradient_pos_rel_am: - recommended: true - sip_method: - recommended: true - isotopolog_atom_frac: - recommended: true - isotopolog_atom_pos: - recommended: true - isotopolog_dose: - recommended: true - nucleobase_atom_frac: - recommended: true - isotopolog_incu_time: - recommended: true - internal_standard: - recommended: true # class_uri: MigsBa: From 7865c9ade9abc3ba666a4f96f004969ce2be49d2 Mon Sep 17 00:00:00 2001 From: smit684 Date: Tue, 29 Jul 2025 16:12:08 -0700 Subject: [PATCH 13/19] update misip name --- src/mixs/schema/mixs.yaml | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/src/mixs/schema/mixs.yaml b/src/mixs/schema/mixs.yaml index 270bbe0214..501c13c5a2 100644 --- a/src/mixs/schema/mixs.yaml +++ b/src/mixs/schema/mixs.yaml @@ -14893,12 +14893,11 @@ slots: recommended: true classes: - MisipMims: + MimsMisip: description: Metagenome or Environmental with SIP - title: MISIP-MIMS + title: MIMS-MISIP aliases: - misip - - mims is_a: Checklist mixin: true slots: From 9878d253b78ce02ccd55d76c7cfa0c118273d57c Mon Sep 17 00:00:00 2001 From: smit684 Date: Tue, 29 Jul 2025 16:33:08 -0700 Subject: [PATCH 14/19] clarify multivalued slots --- src/mixs/schema/mixs.yaml | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/src/mixs/schema/mixs.yaml b/src/mixs/schema/mixs.yaml index 501c13c5a2..fed0a984b0 100644 --- a/src/mixs/schema/mixs.yaml +++ b/src/mixs/schema/mixs.yaml @@ -14847,13 +14847,14 @@ slots: 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 + 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 From 429273f906711350cfdd909d1f81fe91d26a6fe1 Mon Sep 17 00:00:00 2001 From: smit684 Date: Tue, 29 Jul 2025 17:01:05 -0700 Subject: [PATCH 15/19] dd MimsMisip + extension combinations --- src/mixs/schema/mixs.yaml | 226 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 226 insertions(+) diff --git a/src/mixs/schema/mixs.yaml b/src/mixs/schema/mixs.yaml index fed0a984b0..9cd5f3d277 100644 --- a/src/mixs/schema/mixs.yaml +++ b/src/mixs/schema/mixs.yaml @@ -14896,6 +14896,9 @@ slots: 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 @@ -21770,6 +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 + #lass_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 From 489ad279c791d0da571a80988a735ffff84c2998 Mon Sep 17 00:00:00 2001 From: smit684 Date: Tue, 29 Jul 2025 17:35:15 -0700 Subject: [PATCH 16/19] add mims example --- .../MixsCompliantData-MimsSoil-example.yaml | 28 ++++++++++--------- src/mixs/schema/mixs.yaml | 2 +- 2 files changed, 16 insertions(+), 14 deletions(-) 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 9cd5f3d277..d4712c1993 100644 --- a/src/mixs/schema/mixs.yaml +++ b/src/mixs/schema/mixs.yaml @@ -21550,7 +21550,7 @@ classes: mixins: - MimarksS class_uri: MIXS:0010008_0016014 - MimsAgriculture: ##for each checklist + extension, do I need to make an MIMS-MISIP + extension? + MimsAgriculture: description: MIxS Data that comply with the Mims checklist and the Agriculture Extension title: Mims combined with Agriculture From 100cb742c785d30a74d239d2da94d076e72ea774 Mon Sep 17 00:00:00 2001 From: Montana <44581429+mslarae13@users.noreply.github.com> Date: Wed, 30 Jul 2025 17:09:57 -0700 Subject: [PATCH 17/19] comment lint error --- src/mixs/schema/mixs.yaml | 46 +++++++++++++++++++-------------------- 1 file changed, 23 insertions(+), 23 deletions(-) diff --git a/src/mixs/schema/mixs.yaml b/src/mixs/schema/mixs.yaml index d4712c1993..987d145f3f 100644 --- a/src/mixs/schema/mixs.yaml +++ b/src/mixs/schema/mixs.yaml @@ -21782,7 +21782,7 @@ classes: is_a: Agriculture mixins: - MimsMisip - #class_uri: + # class_uri: MimsMisipAir: description: MIxS Data that comply with the MimsMisip checklist and the Air Extension title: MimsMisip combined with Air @@ -21791,7 +21791,7 @@ classes: is_a: Air mixins: - MimsMisip - #class_uri: + # class_uri: MimsMisipBuiltEnvironment: description: MIxS Data that comply with the MimsMisip checklist and the BuiltEnvironment Extension @@ -21801,7 +21801,7 @@ classes: is_a: BuiltEnvironment mixins: - MimsMisip - #class_uri: + # class_uri: MimsMisipFoodAnimalAndAnimalFeed: description: MIxS Data that comply with the MimsMisip checklist and the FoodAnimalAndAnimalFeed Extension @@ -21811,7 +21811,7 @@ classes: is_a: FoodAnimalAndAnimalFeed mixins: - MimsMisip - #class_uri: + # class_uri: MimsMisipFoodFarmEnvironment: description: MIxS Data that comply with the MimsMisip checklist and the FoodFarmEnvironment Extension @@ -21821,7 +21821,7 @@ classes: is_a: FoodFarmEnvironment mixins: - MimsMisip - #class_uri: + # class_uri: MimsMisipFoodFoodProductionFacility: description: MIxS Data that comply with the MimsMisip checklist and the FoodFoodProductionFacility Extension @@ -21831,7 +21831,7 @@ classes: is_a: FoodFoodProductionFacility mixins: - MimsMisip - #class_uri: + # class_uri: MimsMisipFoodHumanFoods: description: MIxS Data that comply with the MimsMisip checklist and the FoodHumanFoods Extension @@ -21841,7 +21841,7 @@ classes: is_a: FoodHumanFoods mixins: - MimsMisip - #class_uri: + # class_uri: MimsMisipHostAssociated: description: MIxS Data that comply with the MimsMisip checklist and the HostAssociated Extension @@ -21851,7 +21851,7 @@ classes: is_a: HostAssociated mixins: - MimsMisip - #class_uri: + # class_uri: MimsMisipHumanAssociated: description: MIxS Data that comply with the MimsMisip checklist and the HumanAssociated Extension @@ -21861,7 +21861,7 @@ classes: is_a: HumanAssociated mixins: - MimsMisip - #class_uri: + # class_uri: MimsMisipHumanGut: description: MIxS Data that comply with the MimsMisip checklist and the HumanGut Extension title: MimsMisip combined with HumanGut @@ -21870,7 +21870,7 @@ classes: is_a: HumanGut mixins: - MimsMisip - #class_uri: + # class_uri: MimsMisipHumanOral: description: MIxS Data that comply with the MimsMisip checklist and the HumanOral Extension title: MimsMisip combined with HumanOral @@ -21879,7 +21879,7 @@ classes: is_a: HumanOral mixins: - MimsMisip - #class_uri: + # class_uri: MimsMisipHumanSkin: description: MIxS Data that comply with the MimsMisip checklist and the HumanSkin Extension title: MimsMisip combined with HumanSkin @@ -21888,7 +21888,7 @@ classes: is_a: HumanSkin mixins: - MimsMisip - #class_uri: + # class_uri: MimsMisipHumanVaginal: description: MIxS Data that comply with the MimsMisip checklist and the HumanVaginal Extension @@ -21898,7 +21898,7 @@ classes: is_a: HumanVaginal mixins: - MimsMisip - #class_uri: + # class_uri: MimsMisipHydrocarbonResourcesCores: description: MIxS Data that comply with the MimsMisip checklist and the HydrocarbonResourcesCores Extension @@ -21908,7 +21908,7 @@ classes: is_a: HydrocarbonResourcesCores mixins: - MimsMisip - #class_uri: + # class_uri: MimsMisipHydrocarbonResourcesFluidsSwabs: description: MIxS Data that comply with the MimsMisip checklist and the HydrocarbonResourcesFluidsSwabs Extension @@ -21918,7 +21918,7 @@ classes: is_a: HydrocarbonResourcesFluidsSwabs mixins: - MimsMisip - #class_uri: + # class_uri: MimsMisipMicrobialMatBiofilm: description: MIxS Data that comply with the MimsMisip checklist and the MicrobialMatBiofilm Extension @@ -21928,7 +21928,7 @@ classes: is_a: MicrobialMatBiofilm mixins: - MimsMisip - #class_uri: + # class_uri: MimsMisipMiscellaneousNaturalOrArtificialEnvironment: description: MIxS Data that comply with the MimsMisip checklist and the MiscellaneousNaturalOrArtificialEnvironment Extension @@ -21938,7 +21938,7 @@ classes: is_a: MiscellaneousNaturalOrArtificialEnvironment mixins: - MimsMisip - #class_uri: + # class_uri: MimsMisipPlantAssociated: description: MIxS Data that comply with the MimsMisip checklist and the PlantAssociated Extension @@ -21948,7 +21948,7 @@ classes: is_a: PlantAssociated mixins: - MimsMisip - #class_uri: + # class_uri: MimsMisipSediment: description: MIxS Data that comply with the MimsMisip checklist and the Sediment Extension title: MimsMisip combined with Sediment @@ -21957,7 +21957,7 @@ classes: is_a: Sediment mixins: - MimsMisip - #class_uri: + # class_uri: MimsMisipSoil: description: MIxS Data that comply with the MimsMisip checklist and the Soil Extension title: MimsMisip combined with Soil @@ -21966,7 +21966,7 @@ classes: is_a: Soil mixins: - MimsMisip - #class_uri: + # class_uri: MimsMisipSymbiontAssociated: description: MIxS Data that comply with the MimsMisip checklist and the SymbiontAssociated Extension @@ -21976,7 +21976,7 @@ classes: is_a: SymbiontAssociated mixins: - MimsMisip - #lass_uri: + # class_uri: MimsMisipWastewaterSludge: description: MIxS Data that comply with the MimsMisip checklist and the WastewaterSludge Extension @@ -21986,7 +21986,7 @@ classes: is_a: WastewaterSludge mixins: - MimsMisip - #class_uri: + # class_uri: MimsMisipWater: description: MIxS Data that comply with the MimsMisip checklist and the Water Extension title: MimsMisip combined with Water @@ -21995,7 +21995,7 @@ classes: is_a: Water mixins: - MimsMisip - #class_uri: + # class_uri: MisagAgriculture: description: MIxS Data that comply with the Misag checklist and the Agriculture Extension From 5f3bc2b6d1e6a1f68c7152c0ff82b80a6e693763 Mon Sep 17 00:00:00 2001 From: Sierra Taylor Moxon Date: Thu, 14 Aug 2025 17:10:44 -0700 Subject: [PATCH 18/19] fix indentation --- src/mixs/schema/mixs.yaml | 130 +++++++++++++++++++------------------- 1 file changed, 65 insertions(+), 65 deletions(-) diff --git a/src/mixs/schema/mixs.yaml b/src/mixs/schema/mixs.yaml index 987d145f3f..fc23134d5d 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. @@ -3906,7 +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 @@ -5438,7 +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 @@ -9730,7 +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 @@ -9739,10 +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: @@ -9751,8 +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 @@ -14764,9 +14764,9 @@ slots: - value: 13C - value: 13C; 15N required: true - isotopolog: + isotopolog: title: isotopolog - description: Isotopologue (isotope source/substrate/molecule) added to the biological sample. + 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]} @@ -14896,7 +14896,7 @@ slots: 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. + 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 @@ -15022,7 +15022,7 @@ classes: recommended: true temp: recommended: true - # class_uri: + # class_uri: MigsBa: description: 'Minimal Information about a Genome Sequence: cultured bacteria/archaea' @@ -16410,9 +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 @@ -16883,8 +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 @@ -17082,7 +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 @@ -17232,7 +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 @@ -17458,7 +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 @@ -17616,7 +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 @@ -17766,7 +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 @@ -17901,8 +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. @@ -18012,7 +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 @@ -18104,7 +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 @@ -18196,7 +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 @@ -18288,7 +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 @@ -18387,7 +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 @@ -18513,7 +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 @@ -18643,7 +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 @@ -18734,7 +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 @@ -18802,7 +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 @@ -18957,7 +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. @@ -19056,7 +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/ @@ -19146,7 +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 @@ -19268,7 +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 @@ -19328,7 +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 @@ -21782,7 +21782,7 @@ classes: is_a: Agriculture mixins: - MimsMisip - # class_uri: + # class_uri: MimsMisipAir: description: MIxS Data that comply with the MimsMisip checklist and the Air Extension title: MimsMisip combined with Air @@ -21791,7 +21791,7 @@ classes: is_a: Air mixins: - MimsMisip - # class_uri: + # class_uri: MimsMisipBuiltEnvironment: description: MIxS Data that comply with the MimsMisip checklist and the BuiltEnvironment Extension @@ -21801,7 +21801,7 @@ classes: is_a: BuiltEnvironment mixins: - MimsMisip - # class_uri: + # class_uri: MimsMisipFoodAnimalAndAnimalFeed: description: MIxS Data that comply with the MimsMisip checklist and the FoodAnimalAndAnimalFeed Extension @@ -21811,7 +21811,7 @@ classes: is_a: FoodAnimalAndAnimalFeed mixins: - MimsMisip - # class_uri: + # class_uri: MimsMisipFoodFarmEnvironment: description: MIxS Data that comply with the MimsMisip checklist and the FoodFarmEnvironment Extension @@ -21821,7 +21821,7 @@ classes: is_a: FoodFarmEnvironment mixins: - MimsMisip - # class_uri: + # class_uri: MimsMisipFoodFoodProductionFacility: description: MIxS Data that comply with the MimsMisip checklist and the FoodFoodProductionFacility Extension @@ -21831,7 +21831,7 @@ classes: is_a: FoodFoodProductionFacility mixins: - MimsMisip - # class_uri: + # class_uri: MimsMisipFoodHumanFoods: description: MIxS Data that comply with the MimsMisip checklist and the FoodHumanFoods Extension @@ -21841,7 +21841,7 @@ classes: is_a: FoodHumanFoods mixins: - MimsMisip - # class_uri: + # class_uri: MimsMisipHostAssociated: description: MIxS Data that comply with the MimsMisip checklist and the HostAssociated Extension @@ -21851,7 +21851,7 @@ classes: is_a: HostAssociated mixins: - MimsMisip - # class_uri: + # class_uri: MimsMisipHumanAssociated: description: MIxS Data that comply with the MimsMisip checklist and the HumanAssociated Extension @@ -21861,7 +21861,7 @@ classes: is_a: HumanAssociated mixins: - MimsMisip - # class_uri: + # class_uri: MimsMisipHumanGut: description: MIxS Data that comply with the MimsMisip checklist and the HumanGut Extension title: MimsMisip combined with HumanGut @@ -21870,7 +21870,7 @@ classes: is_a: HumanGut mixins: - MimsMisip - # class_uri: + # class_uri: MimsMisipHumanOral: description: MIxS Data that comply with the MimsMisip checklist and the HumanOral Extension title: MimsMisip combined with HumanOral @@ -21879,7 +21879,7 @@ classes: is_a: HumanOral mixins: - MimsMisip - # class_uri: + # class_uri: MimsMisipHumanSkin: description: MIxS Data that comply with the MimsMisip checklist and the HumanSkin Extension title: MimsMisip combined with HumanSkin @@ -21888,7 +21888,7 @@ classes: is_a: HumanSkin mixins: - MimsMisip - # class_uri: + # class_uri: MimsMisipHumanVaginal: description: MIxS Data that comply with the MimsMisip checklist and the HumanVaginal Extension @@ -21898,7 +21898,7 @@ classes: is_a: HumanVaginal mixins: - MimsMisip - # class_uri: + # class_uri: MimsMisipHydrocarbonResourcesCores: description: MIxS Data that comply with the MimsMisip checklist and the HydrocarbonResourcesCores Extension @@ -21908,7 +21908,7 @@ classes: is_a: HydrocarbonResourcesCores mixins: - MimsMisip - # class_uri: + # class_uri: MimsMisipHydrocarbonResourcesFluidsSwabs: description: MIxS Data that comply with the MimsMisip checklist and the HydrocarbonResourcesFluidsSwabs Extension @@ -21918,7 +21918,7 @@ classes: is_a: HydrocarbonResourcesFluidsSwabs mixins: - MimsMisip - # class_uri: + # class_uri: MimsMisipMicrobialMatBiofilm: description: MIxS Data that comply with the MimsMisip checklist and the MicrobialMatBiofilm Extension @@ -21928,7 +21928,7 @@ classes: is_a: MicrobialMatBiofilm mixins: - MimsMisip - # class_uri: + # class_uri: MimsMisipMiscellaneousNaturalOrArtificialEnvironment: description: MIxS Data that comply with the MimsMisip checklist and the MiscellaneousNaturalOrArtificialEnvironment Extension @@ -21938,7 +21938,7 @@ classes: is_a: MiscellaneousNaturalOrArtificialEnvironment mixins: - MimsMisip - # class_uri: + # class_uri: MimsMisipPlantAssociated: description: MIxS Data that comply with the MimsMisip checklist and the PlantAssociated Extension @@ -21948,7 +21948,7 @@ classes: is_a: PlantAssociated mixins: - MimsMisip - # class_uri: + # class_uri: MimsMisipSediment: description: MIxS Data that comply with the MimsMisip checklist and the Sediment Extension title: MimsMisip combined with Sediment @@ -21957,7 +21957,7 @@ classes: is_a: Sediment mixins: - MimsMisip - # class_uri: + # class_uri: MimsMisipSoil: description: MIxS Data that comply with the MimsMisip checklist and the Soil Extension title: MimsMisip combined with Soil @@ -21966,7 +21966,7 @@ classes: is_a: Soil mixins: - MimsMisip - # class_uri: + # class_uri: MimsMisipSymbiontAssociated: description: MIxS Data that comply with the MimsMisip checklist and the SymbiontAssociated Extension @@ -21976,7 +21976,7 @@ classes: is_a: SymbiontAssociated mixins: - MimsMisip - # class_uri: + # class_uri: MimsMisipWastewaterSludge: description: MIxS Data that comply with the MimsMisip checklist and the WastewaterSludge Extension @@ -21986,7 +21986,7 @@ classes: is_a: WastewaterSludge mixins: - MimsMisip - # class_uri: + # class_uri: MimsMisipWater: description: MIxS Data that comply with the MimsMisip checklist and the Water Extension title: MimsMisip combined with Water @@ -21995,7 +21995,7 @@ classes: is_a: Water mixins: - MimsMisip - # class_uri: + # class_uri: MisagAgriculture: description: MIxS Data that comply with the Misag checklist and the Agriculture Extension From a4d4ea9de355cad4430a5aee56813f77a3803d1f Mon Sep 17 00:00:00 2001 From: Sierra Taylor Moxon Date: Thu, 14 Aug 2025 17:12:00 -0700 Subject: [PATCH 19/19] fix comment spaces --- src/mixs/schema/mixs.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/mixs/schema/mixs.yaml b/src/mixs/schema/mixs.yaml index fc23134d5d..3e3010c0e7 100644 --- a/src/mixs/schema/mixs.yaml +++ b/src/mixs/schema/mixs.yaml @@ -22460,7 +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))?)?)?)?$' dna: '^[ACGT]+$'