Draft: add MISIP-MIMS

src/mixs/schema/mixs.yaml

@@ -1252,6 +1252,24 @@
       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
@@ -14737,7 +14755,288 @@
       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
+  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"
+  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
+  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
+  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
+  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:
+  MisipMims:
+    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
@@ -21264,7 +21563,7 @@
     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