diff --git a/src/schema/nmdc.yaml b/src/schema/nmdc.yaml index 7d13c6f7c5..b8da2dbab9 100644 --- a/src/schema/nmdc.yaml +++ b/src/schema/nmdc.yaml @@ -713,6 +713,28 @@ enums: meaning: OBI:0000103 comments: - credit enums come from https://casrai.org/credit/ + processing_institution_enum: + name: processing_institution_enum + comments: + - This will become the range of processing_institution.omics processing + - use ROR meanings like https://ror.org/0168r3w48 for UCSD + from_schema: NMDC_enums_roundtrip + permissible_values: + UCSD: + text: UCSD + title: University of California, San Diego + meaning: https://ror.org/0168r3w48 + JGI: + text: JGI + title: Joint Genome Institute + meaning: https://ror.org/04xm1d337 + EMSL: + text: EMSL + title: Environmental Molecular Sciences Laboratory + meaning: https://ror.org/04rc0xn13 + comments: + - replaces Environmental Molecular Science Laboratory + - replaces Environmental Molecular Sciences Lab slots: ess dive datasets: diff --git a/util/fetch_omics_processing_set.py b/util/fetch_omics_processing_set.py new file mode 100644 index 0000000000..2de72b6ddc --- /dev/null +++ b/util/fetch_omics_processing_set.py @@ -0,0 +1,43 @@ +import csv +import pprint + +from pymongo import MongoClient + +client = MongoClient( + "mongodb://mam:NJAxcszXBt3fu%21q@localhost:27027/?authSource=admin&readPreference=primary&directConnection=true&ssl=false" +) + +id_inst_file ="../target/omics_processing_id_inst.tsv" + +# on the verbose side for just retrieving a collection +result_filter = {} +result = client["nmdc"]["omics_processing_set"].find(filter=result_filter) + +# print(type(result)) +# + +# ['GOLD_sequencing_project_identifiers', +# '_id', +# 'add_date', +# 'has_input', +# 'has_output', +# 'id', +# 'mod_date', +# 'name', +# 'ncbi_project_name', +# 'omics_type', +# 'part_of', +# 'principal_investigator', +# 'processing_institution', +# 'type'] + +id_inst = [] +for i in result: + id_inst.append( + {"id": i["id"], "processing_institution": i["processing_institution"]} + ) + +with open(id_inst_file, 'w') as f: + csv_writer = csv.DictWriter(f, list(id_inst[0].keys()), delimiter="\t") + csv_writer.writeheader() + csv_writer.writerows(id_inst) diff --git a/util/generated_NMDC_enums.tsv b/util/generated_NMDC_enums.tsv new file mode 100644 index 0000000000..7e9c7a0cd2 --- /dev/null +++ b/util/generated_NMDC_enums.tsv @@ -0,0 +1,993 @@ +enum permissible_value meaning aliases broad_mappings close_mappings comments deprecated deprecated_element_has_exact_replacement deprecated_element_has_possible_replacement description exact_mappings examples from_schema imported_from in_language in_subset mappings narrow_mappings notes rank related_mappings see_also source title todos file_name_pattern +> enum permissible_value meaning aliases broad_mappings close_mappings comments deprecated deprecated_element_has_exact_replacement deprecated_element_has_possible_replacement description exact_mappings examples from_schema imported_from in_language in_subset mappings narrow_mappings notes rank related_mappings see_also source title todos annotations +> "internal_separator: ""|""" "internal_separator: ""|""" "internal_separator: ""|""" "internal_separator: ""|""" "internal_separator: ""|""" "internal_separator: ""|""" "internal_separator: ""|""" "internal_separator: ""|""" "internal_separator: ""|""" "internal_separator: ""|""" "internal_separator: ""|""" "internal_separator: ""|""" "internal_separator: ""|""" inner_key: file_name_pattern +file type enum https://microbiomedata/schema +file type enum FT ICR-MS Analysis Results FT ICR-MS-based molecular formula assignment results table +file type enum GC-MS Metabolomics Results GC-MS-based metabolite assignment results table +file type enum Metaproteomics Workflow Statistics Aggregate workflow statistics file +file type enum Protein Report Filtered protein report file +file type enum Peptide Report Filtered peptide report file +file type enum Unfiltered Metaproteomics Results MSGFjobs and MASIC output file +file type enum Read Count and RPKM Annotation read count and RPKM per feature JSON +file type enum QC non-rRNA R2 QC removed rRNA reads (R2) fastq +file type enum QC non-rRNA R1 QC removed rRNA reads (R1) fastq +file type enum Metagenome Bins Metagenome bin contigs fasta +file type enum CheckM Statistics CheckM statistics report +file type enum GOTTCHA2 Krona Plot GOTTCHA2 krona plot HTML file +file type enum GOTTCHA2 Classification Report GOTTCHA2 classification report file +file type enum GOTTCHA2 Report Full GOTTCHA2 report file +file type enum Kraken2 Krona Plot Kraken2 krona plot HTML file +file type enum Centrifuge Krona Plot Centrifug krona plot HTML file +file type enum Centrifuge output report file Centrifug output report file +file type enum Kraken2 Classification Report Kraken2 output report file +file type enum Kraken2 Taxonomic Classification Kraken2 output read classification file +file type enum Centrifuge Classification Report Centrifuge output report file +file type enum Centrifuge Taxonomic Classification Centrifuge output read classification file +file type enum Structural Annotation GFF GFF3 format file with structural annotations +file type enum Functional Annotation GFF GFF3 format file with functional annotations +file type enum Annotation Amino Acid FASTA FASTA amino acid file for annotated proteins +file type enum Annotation Enzyme Commission Tab delimited file for EC annotation +file type enum Annotation KEGG Orthology Tab delimited file for KO annotation +file type enum Assembly Coverage BAM Sorted bam file of reads mapping back to the final assembly +file type enum Assembly AGP An AGP format file that describes the assembly +file type enum Assembly Scaffolds Final assembly scaffolds fasta +file type enum Assembly Contigs Final assembly contigs fasta +file type enum Assembly Coverage Stats Assembled contigs coverage information +file type enum Filtered Sequencing Reads Reads QC result fastq (clean data) +file type enum QC Statistics Reads QC summary statistics +file type enum TIGRFam Annotation GFF GFF3 format file with TIGRfam [GOLD-AP]_tigrfam.gff +file type enum CRT Annotation GFF GFF3 format file with CRT +file type enum Genmark Annotation GFF GFF3 format file with Genmark +file type enum Prodigal Annotation GFF GFF3 format file with Prodigal +file type enum TRNA Annotation GFF GFF3 format file with TRNA +file type enum Misc Annotation GFF GFF3 format file with Misc +file type enum RFAM Annotation GFF GFF3 format file with RFAM +file type enum TMRNA Annotation GFF GFF3 format file with TMRNA +file type enum KO_EC Annotation GFF GFF3 format file with KO_EC +file type enum Product Names Product names file +file type enum Gene Phylogeny tsv Gene Phylogeny tsv +file type enum Crisprt Terms Crisprt Terms +file type enum Clusters of Orthologous Groups (COG) Annotation GFF GFF3 format file with COGs [GOLD-AP]_cog.gff +file type enum CATH FunFams (Functional Families) Annotation GFF GFF3 format file with CATH FunFams [GOLD-AP]_cath_funfam.gff +file type enum SUPERFam Annotation GFF GFF3 format file with SUPERFam [GOLD-AP]_supfam.gff +file type enum SMART Annotation GFF GFF3 format file with SMART [GOLD-AP]_smart.gff +file type enum Pfam Annotation GFF GFF3 format file with Pfam [GOLD-AP]_pfam.gff +file type enum Direct Infusion FT ICR-MS Raw Data Direct infusion 21 Tesla Fourier Transform ion cyclotron resonance mass spectrometry raw data acquired in broadband full scan mode +credit enum credit enums come from https://casrai.org/credit/ https://microbiomedata/schema +credit enum Conceptualization Conceptualization +credit enum Data curation Data curation +credit enum Formal Analysis Formal Analysis +credit enum Funding acquisition Funding acquisition +credit enum Investigation Investigation +credit enum Methodology Methodology +credit enum Project administration Project administration +credit enum Resources Resources +credit enum Software Software +credit enum Supervision Supervision +credit enum Validation Validation +credit enum Visualization Visualization +credit enum Writing original draft Writing – original draft +credit enum Writing review and editing Writing – review & editing +credit enum Principal Investigator OBI:0000103 principal investigator role +analysis_type_enum https://microbiomedata/schema/sample_id +analysis_type_enum metabolomics +analysis_type_enum metagenomics +analysis_type_enum metaproteomics +analysis_type_enum metatranscriptomics +analysis_type_enum natural organic matter +dnase_rna_enum https://microbiomedata/schema/jgi_metatranscriptomics +dnase_rna_enum no +dnase_rna_enum yes +rna_cont_type_enum https://microbiomedata/schema/jgi_metatranscriptomics +rna_cont_type_enum plate +rna_cont_type_enum tube +rna_sample_format_enum https://microbiomedata/schema/jgi_metatranscriptomics +rna_sample_format_enum 10 mM Tris-HCl +rna_sample_format_enum DNAStable +rna_sample_format_enum Ethanol +rna_sample_format_enum Low EDTA TE +rna_sample_format_enum MDA reaction buffer +rna_sample_format_enum PBS +rna_sample_format_enum Pellet +rna_sample_format_enum RNAStable +rna_sample_format_enum TE +rna_sample_format_enum Water +dna_cont_type_enum https://microbiomedata/schema/jgi_metagenomics +dna_cont_type_enum plate +dna_cont_type_enum tube +dna_dnase_enum https://microbiomedata/schema/jgi_metagenomics +dna_dnase_enum no +dna_dnase_enum yes +dna_sample_format_enum https://microbiomedata/schema/jgi_metagenomics +dna_sample_format_enum 10 mM Tris-HCl +dna_sample_format_enum DNAStable +dna_sample_format_enum Ethanol +dna_sample_format_enum Low EDTA TE +dna_sample_format_enum MDA reaction buffer +dna_sample_format_enum PBS +dna_sample_format_enum Pellet +dna_sample_format_enum RNAStable +dna_sample_format_enum TE +dna_sample_format_enum Water +sample_type_enum https://microbiomedata/schema/emsl +sample_type_enum soil +sample_type_enum water_extract_soil +arch_struc_enum https://microbiomedata/schema/mixs +arch_struc_enum building +arch_struc_enum shed +arch_struc_enum home +biol_stat_enum https://microbiomedata/schema/mixs +biol_stat_enum wild +biol_stat_enum natural +biol_stat_enum semi-natural +biol_stat_enum inbred line +biol_stat_enum breeder's line +biol_stat_enum hybrid +biol_stat_enum clonal selection +biol_stat_enum mutant +biotic_relationship_enum https://microbiomedata/schema/mixs +biotic_relationship_enum free living +biotic_relationship_enum parasite +biotic_relationship_enum commensal +biotic_relationship_enum symbiont +build_docs_enum https://microbiomedata/schema/mixs +build_docs_enum building information model +build_docs_enum commissioning report +build_docs_enum complaint logs +build_docs_enum contract administration +build_docs_enum cost estimate +build_docs_enum janitorial schedules or logs +build_docs_enum maintenance plans +build_docs_enum schedule +build_docs_enum sections +build_docs_enum shop drawings +build_docs_enum submittals +build_docs_enum ventilation system +build_docs_enum windows +build_occup_type_enum https://microbiomedata/schema/mixs +build_occup_type_enum office +build_occup_type_enum market +build_occup_type_enum restaurant +build_occup_type_enum residence +build_occup_type_enum school +build_occup_type_enum residential +build_occup_type_enum commercial +build_occup_type_enum low rise +build_occup_type_enum high rise +build_occup_type_enum wood framed +build_occup_type_enum health care +build_occup_type_enum airport +build_occup_type_enum sports complex +building_setting_enum https://microbiomedata/schema/mixs +building_setting_enum urban +building_setting_enum suburban +building_setting_enum exurban +building_setting_enum rural +ceil_cond_enum https://microbiomedata/schema/mixs +ceil_cond_enum new +ceil_cond_enum visible wear +ceil_cond_enum needs repair +ceil_cond_enum damaged +ceil_cond_enum rupture +ceil_finish_mat_enum https://microbiomedata/schema/mixs +ceil_finish_mat_enum drywall +ceil_finish_mat_enum mineral fibre +ceil_finish_mat_enum tiles +ceil_finish_mat_enum PVC +ceil_finish_mat_enum plasterboard +ceil_finish_mat_enum metal +ceil_finish_mat_enum fiberglass +ceil_finish_mat_enum stucco +ceil_finish_mat_enum mineral wool/calcium silicate +ceil_finish_mat_enum wood +ceil_texture_enum https://microbiomedata/schema/mixs +ceil_texture_enum crows feet +ceil_texture_enum crows-foot stomp +ceil_texture_enum double skip +ceil_texture_enum hawk and trowel +ceil_texture_enum knockdown +ceil_texture_enum popcorn +ceil_texture_enum orange peel +ceil_texture_enum rosebud stomp +ceil_texture_enum Santa-Fe texture +ceil_texture_enum skip trowel +ceil_texture_enum smooth +ceil_texture_enum stomp knockdown +ceil_texture_enum swirl +ceil_type_enum https://microbiomedata/schema/mixs +ceil_type_enum cathedral +ceil_type_enum dropped +ceil_type_enum concave +ceil_type_enum barrel-shaped +ceil_type_enum coffered +ceil_type_enum cove +ceil_type_enum stretched +cur_land_use_enum https://microbiomedata/schema/mixs +cur_land_use_enum cities +cur_land_use_enum farmstead +cur_land_use_enum industrial areas +cur_land_use_enum roads/railroads +cur_land_use_enum rock +cur_land_use_enum sand +cur_land_use_enum gravel +cur_land_use_enum mudflats +cur_land_use_enum salt flats +cur_land_use_enum badlands +cur_land_use_enum permanent snow or ice +cur_land_use_enum saline seeps +cur_land_use_enum mines/quarries +cur_land_use_enum oil waste areas +cur_land_use_enum small grains +cur_land_use_enum row crops +cur_land_use_enum vegetable crops +cur_land_use_enum horticultural plants (e.g. tulips) +cur_land_use_enum marshlands (grass,sedges,rushes) +cur_land_use_enum tundra (mosses,lichens) +cur_land_use_enum rangeland +cur_land_use_enum pastureland (grasslands used for livestock grazing) +cur_land_use_enum hayland +cur_land_use_enum meadows (grasses,alfalfa,fescue,bromegrass,timothy) +cur_land_use_enum shrub land (e.g. mesquite,sage-brush,creosote bush,shrub oak,eucalyptus) +cur_land_use_enum successional shrub land (tree saplings,hazels,sumacs,chokecherry,shrub dogwoods,blackberries) +cur_land_use_enum shrub crops (blueberries,nursery ornamentals,filberts) +cur_land_use_enum vine crops (grapes) +cur_land_use_enum conifers (e.g. pine,spruce,fir,cypress) +cur_land_use_enum hardwoods (e.g. oak,hickory,elm,aspen) +cur_land_use_enum intermixed hardwood and conifers +cur_land_use_enum tropical (e.g. mangrove,palms) +cur_land_use_enum rainforest (evergreen forest receiving greater than 406 cm annual rainfall) +cur_land_use_enum swamp (permanent or semi-permanent water body dominated by woody plants) +cur_land_use_enum crop trees (nuts,fruit,christmas trees,nursery trees) +depos_env_enum https://microbiomedata/schema/mixs +depos_env_enum Continental - Alluvial +depos_env_enum Continental - Aeolian +depos_env_enum Continental - Fluvial +depos_env_enum Continental - Lacustrine +depos_env_enum Transitional - Deltaic +depos_env_enum Transitional - Tidal +depos_env_enum Transitional - Lagoonal +depos_env_enum Transitional - Beach +depos_env_enum Transitional - Lake +depos_env_enum Marine - Shallow +depos_env_enum Marine - Deep +depos_env_enum Marine - Reef +depos_env_enum Other - Evaporite +depos_env_enum Other - Glacial +depos_env_enum Other - Volcanic +depos_env_enum other +door_comp_type_enum https://microbiomedata/schema/mixs +door_comp_type_enum metal covered +door_comp_type_enum revolving +door_comp_type_enum sliding +door_comp_type_enum telescopic +door_cond_enum https://microbiomedata/schema/mixs +door_cond_enum damaged +door_cond_enum needs repair +door_cond_enum new +door_cond_enum rupture +door_cond_enum visible wear +door_direct_enum https://microbiomedata/schema/mixs +door_direct_enum inward +door_direct_enum outward +door_direct_enum sideways +door_loc_enum https://microbiomedata/schema/mixs +door_loc_enum north +door_loc_enum south +door_loc_enum east +door_loc_enum west +door_mat_enum https://microbiomedata/schema/mixs +door_mat_enum aluminum +door_mat_enum cellular PVC +door_mat_enum engineered plastic +door_mat_enum fiberboard +door_mat_enum fiberglass +door_mat_enum metal +door_mat_enum thermoplastic alloy +door_mat_enum vinyl +door_mat_enum wood +door_mat_enum wood/plastic composite +door_move_enum https://microbiomedata/schema/mixs +door_move_enum collapsible +door_move_enum folding +door_move_enum revolving +door_move_enum rolling shutter +door_move_enum sliding +door_move_enum swinging +door_type_enum https://microbiomedata/schema/mixs +door_type_enum composite +door_type_enum metal +door_type_enum wooden +door_type_metal_enum https://microbiomedata/schema/mixs +door_type_metal_enum collapsible +door_type_metal_enum corrugated steel +door_type_metal_enum hollow +door_type_metal_enum rolling shutters +door_type_metal_enum steel plate +door_type_wood_enum https://microbiomedata/schema/mixs +door_type_wood_enum bettened and ledged +door_type_wood_enum battened +door_type_wood_enum ledged and braced +door_type_wood_enum ledged and framed +door_type_wood_enum ledged, braced and frame +door_type_wood_enum framed and paneled +door_type_wood_enum glashed or sash +door_type_wood_enum flush +door_type_wood_enum louvered +door_type_wood_enum wire gauged +drainage_class_enum https://microbiomedata/schema/mixs +drainage_class_enum very poorly +drainage_class_enum poorly +drainage_class_enum somewhat poorly +drainage_class_enum moderately well +drainage_class_enum well +drainage_class_enum excessively drained +drawings_enum https://microbiomedata/schema/mixs +drawings_enum operation +drawings_enum as built +drawings_enum construction +drawings_enum bid +drawings_enum design +drawings_enum building navigation map +drawings_enum diagram +drawings_enum sketch +ext_wall_orient_enum https://microbiomedata/schema/mixs +ext_wall_orient_enum north +ext_wall_orient_enum south +ext_wall_orient_enum east +ext_wall_orient_enum west +ext_wall_orient_enum northeast +ext_wall_orient_enum southeast +ext_wall_orient_enum southwest +ext_wall_orient_enum northwest +ext_window_orient_enum https://microbiomedata/schema/mixs +ext_window_orient_enum north +ext_window_orient_enum south +ext_window_orient_enum east +ext_window_orient_enum west +ext_window_orient_enum northeast +ext_window_orient_enum southeast +ext_window_orient_enum southwest +ext_window_orient_enum northwest +fao_class_enum https://microbiomedata/schema/mixs +fao_class_enum Acrisols +fao_class_enum Andosols +fao_class_enum Arenosols +fao_class_enum Cambisols +fao_class_enum Chernozems +fao_class_enum Ferralsols +fao_class_enum Fluvisols +fao_class_enum Gleysols +fao_class_enum Greyzems +fao_class_enum Gypsisols +fao_class_enum Histosols +fao_class_enum Kastanozems +fao_class_enum Lithosols +fao_class_enum Luvisols +fao_class_enum Nitosols +fao_class_enum Phaeozems +fao_class_enum Planosols +fao_class_enum Podzols +fao_class_enum Podzoluvisols +fao_class_enum Rankers +fao_class_enum Regosols +fao_class_enum Rendzinas +fao_class_enum Solonchaks +fao_class_enum Solonetz +fao_class_enum Vertisols +fao_class_enum Yermosols +filter_type_enum https://microbiomedata/schema/mixs +filter_type_enum particulate air filter +filter_type_enum chemical air filter +filter_type_enum low-MERV pleated media +filter_type_enum HEPA +filter_type_enum electrostatic +filter_type_enum gas-phase or ultraviolet air treatments +floor_cond_enum https://microbiomedata/schema/mixs +floor_cond_enum new +floor_cond_enum visible wear +floor_cond_enum needs repair +floor_cond_enum damaged +floor_cond_enum rupture +floor_finish_mat_enum https://microbiomedata/schema/mixs +floor_finish_mat_enum tile +floor_finish_mat_enum wood strip or parquet +floor_finish_mat_enum carpet +floor_finish_mat_enum rug +floor_finish_mat_enum laminate wood +floor_finish_mat_enum lineoleum +floor_finish_mat_enum vinyl composition tile +floor_finish_mat_enum sheet vinyl +floor_finish_mat_enum stone +floor_finish_mat_enum bamboo +floor_finish_mat_enum cork +floor_finish_mat_enum terrazo +floor_finish_mat_enum concrete +floor_finish_mat_enum none +floor_finish_mat_enum sealed +floor_finish_mat_enum clear finish +floor_finish_mat_enum paint +floor_finish_mat_enum none or unfinished +floor_struc_enum https://microbiomedata/schema/mixs +floor_struc_enum balcony +floor_struc_enum floating floor +floor_struc_enum glass floor +floor_struc_enum raised floor +floor_struc_enum sprung floor +floor_struc_enum wood-framed +floor_struc_enum concrete +floor_water_mold_enum https://microbiomedata/schema/mixs +floor_water_mold_enum mold odor +floor_water_mold_enum wet floor +floor_water_mold_enum water stains +floor_water_mold_enum wall discoloration +floor_water_mold_enum floor discoloration +floor_water_mold_enum ceiling discoloration +floor_water_mold_enum peeling paint or wallpaper +floor_water_mold_enum bulging walls +floor_water_mold_enum condensation +freq_clean_enum https://microbiomedata/schema/mixs +freq_clean_enum Daily +freq_clean_enum Weekly +freq_clean_enum Monthly +freq_clean_enum Quarterly +freq_clean_enum Annually +freq_clean_enum other +furniture_enum https://microbiomedata/schema/mixs +furniture_enum cabinet +furniture_enum chair +furniture_enum desks +gender_restroom_enum https://microbiomedata/schema/mixs +gender_restroom_enum all gender +gender_restroom_enum female +gender_restroom_enum gender neurtral +gender_restroom_enum male +gender_restroom_enum male and female +gender_restroom_enum unisex +growth_habit_enum https://microbiomedata/schema/mixs +growth_habit_enum erect +growth_habit_enum semi-erect +growth_habit_enum spreading +growth_habit_enum prostrate +handidness_enum https://microbiomedata/schema/mixs +handidness_enum ambidexterity +handidness_enum left handedness +handidness_enum mixed-handedness +handidness_enum right handedness +hc_produced_enum https://microbiomedata/schema/mixs +hc_produced_enum Oil +hc_produced_enum Gas-Condensate +hc_produced_enum Gas +hc_produced_enum Bitumen +hc_produced_enum Coalbed Methane +hc_produced_enum other +hcr_enum https://microbiomedata/schema/mixs +hcr_enum Oil Reservoir +hcr_enum Gas Reservoir +hcr_enum Oil Sand +hcr_enum Coalbed +hcr_enum Shale +hcr_enum Tight Oil Reservoir +hcr_enum Tight Gas Reservoir +hcr_enum other +hcr_geol_age_enum https://microbiomedata/schema/mixs +hcr_geol_age_enum Archean +hcr_geol_age_enum Cambrian +hcr_geol_age_enum Carboniferous +hcr_geol_age_enum Cenozoic +hcr_geol_age_enum Cretaceous +hcr_geol_age_enum Devonian +hcr_geol_age_enum Jurassic +hcr_geol_age_enum Mesozoic +hcr_geol_age_enum Neogene +hcr_geol_age_enum Ordovician +hcr_geol_age_enum Paleogene +hcr_geol_age_enum Paleozoic +hcr_geol_age_enum Permian +hcr_geol_age_enum Precambrian +hcr_geol_age_enum Proterozoic +hcr_geol_age_enum Silurian +hcr_geol_age_enum Triassic +hcr_geol_age_enum other +heat_cool_type_enum https://microbiomedata/schema/mixs +heat_cool_type_enum radiant system +heat_cool_type_enum heat pump +heat_cool_type_enum forced air system +heat_cool_type_enum steam forced heat +heat_cool_type_enum wood stove +heat_deliv_loc_enum https://microbiomedata/schema/mixs +heat_deliv_loc_enum north +heat_deliv_loc_enum south +heat_deliv_loc_enum east +heat_deliv_loc_enum west +horizon_enum https://microbiomedata/schema/mixs +horizon_enum O horizon +horizon_enum A horizon +horizon_enum E horizon +horizon_enum B horizon +horizon_enum C horizon +horizon_enum R layer +horizon_enum Permafrost +host_sex_enum https://microbiomedata/schema/mixs +host_sex_enum female +host_sex_enum hermaphrodite +host_sex_enum male +host_sex_enum neuter +indoor_space_enum https://microbiomedata/schema/mixs +indoor_space_enum bedroom +indoor_space_enum office +indoor_space_enum bathroom +indoor_space_enum foyer +indoor_space_enum kitchen +indoor_space_enum locker room +indoor_space_enum hallway +indoor_space_enum elevator +indoor_surf_enum https://microbiomedata/schema/mixs +indoor_surf_enum cabinet +indoor_surf_enum ceiling +indoor_surf_enum counter top +indoor_surf_enum door +indoor_surf_enum shelving +indoor_surf_enum vent cover +indoor_surf_enum window +indoor_surf_enum wall +int_wall_cond_enum https://microbiomedata/schema/mixs +int_wall_cond_enum new +int_wall_cond_enum visible wear +int_wall_cond_enum needs repair +int_wall_cond_enum damaged +int_wall_cond_enum rupture +light_type_enum https://microbiomedata/schema/mixs +light_type_enum natural light +light_type_enum electric light +light_type_enum desk lamp +light_type_enum flourescent lights +light_type_enum none +lithology_enum https://microbiomedata/schema/mixs +lithology_enum Basement +lithology_enum Chalk +lithology_enum Chert +lithology_enum Coal +lithology_enum Conglomerate +lithology_enum Diatomite +lithology_enum Dolomite +lithology_enum Limestone +lithology_enum Sandstone +lithology_enum Shale +lithology_enum Siltstone +lithology_enum Volcanic +lithology_enum other +mech_struc_enum https://microbiomedata/schema/mixs +mech_struc_enum subway +mech_struc_enum coach +mech_struc_enum carriage +mech_struc_enum elevator +mech_struc_enum escalator +mech_struc_enum boat +mech_struc_enum train +mech_struc_enum car +mech_struc_enum bus +occup_document_enum https://microbiomedata/schema/mixs +occup_document_enum automated count +occup_document_enum estimate +occup_document_enum manual count +occup_document_enum videos +organism_count_enum https://microbiomedata/schema/mixs +organism_count_enum ATP +organism_count_enum MPN +organism_count_enum other +oxy_stat_samp_enum https://microbiomedata/schema/mixs +oxy_stat_samp_enum aerobic +oxy_stat_samp_enum anaerobic +oxy_stat_samp_enum other +plant_growth_med_enum https://microbiomedata/schema/mixs +plant_growth_med_enum other artificial liquid medium +plant_growth_med_enum other artificial solid medium +plant_growth_med_enum peat moss +plant_growth_med_enum perlite +plant_growth_med_enum pumice +plant_growth_med_enum sand +plant_growth_med_enum soil +plant_growth_med_enum vermiculite +plant_growth_med_enum water +plant_sex_enum https://microbiomedata/schema/mixs +plant_sex_enum Androdioecious +plant_sex_enum Androecious +plant_sex_enum Androgynous +plant_sex_enum Androgynomonoecious +plant_sex_enum Andromonoecious +plant_sex_enum Bisexual +plant_sex_enum Dichogamous +plant_sex_enum Diclinous +plant_sex_enum Dioecious +plant_sex_enum Gynodioecious +plant_sex_enum Gynoecious +plant_sex_enum Gynomonoecious +plant_sex_enum Hermaphroditic +plant_sex_enum Imperfect +plant_sex_enum Monoclinous +plant_sex_enum Monoecious +plant_sex_enum Perfect +plant_sex_enum Polygamodioecious +plant_sex_enum Polygamomonoecious +plant_sex_enum Polygamous +plant_sex_enum Protandrous +plant_sex_enum Protogynous +plant_sex_enum Subandroecious +plant_sex_enum Subdioecious +plant_sex_enum Subgynoecious +plant_sex_enum Synoecious +plant_sex_enum Trimonoecious +plant_sex_enum Trioecious +plant_sex_enum Unisexual +profile_position_enum https://microbiomedata/schema/mixs +profile_position_enum summit +profile_position_enum shoulder +profile_position_enum backslope +profile_position_enum footslope +profile_position_enum toeslope +quad_pos_enum https://microbiomedata/schema/mixs +quad_pos_enum North side +quad_pos_enum West side +quad_pos_enum South side +quad_pos_enum East side +rel_samp_loc_enum https://microbiomedata/schema/mixs +rel_samp_loc_enum edge of car +rel_samp_loc_enum center of car +rel_samp_loc_enum under a seat +rel_to_oxygen_enum https://microbiomedata/schema/mixs +rel_to_oxygen_enum aerobe +rel_to_oxygen_enum anaerobe +rel_to_oxygen_enum facultative +rel_to_oxygen_enum microaerophilic +rel_to_oxygen_enum microanaerobe +rel_to_oxygen_enum obligate aerobe +rel_to_oxygen_enum obligate anaerobe +room_condt_enum https://microbiomedata/schema/mixs +room_condt_enum new +room_condt_enum visible wear +room_condt_enum needs repair +room_condt_enum damaged +room_condt_enum rupture +room_condt_enum visible signs of mold/mildew +room_connected_enum https://microbiomedata/schema/mixs +room_connected_enum attic +room_connected_enum bathroom +room_connected_enum closet +room_connected_enum conference room +room_connected_enum elevator +room_connected_enum examining room +room_connected_enum hallway +room_connected_enum kitchen +room_connected_enum mail room +room_connected_enum office +room_connected_enum stairwell +room_loc_enum https://microbiomedata/schema/mixs +room_loc_enum corner room +room_loc_enum interior room +room_loc_enum exterior wall +room_samp_pos_enum https://microbiomedata/schema/mixs +room_samp_pos_enum north corner +room_samp_pos_enum south corner +room_samp_pos_enum west corner +room_samp_pos_enum east corner +room_samp_pos_enum northeast corner +room_samp_pos_enum northwest corner +room_samp_pos_enum southeast corner +room_samp_pos_enum southwest corner +room_samp_pos_enum center +room_type_enum https://microbiomedata/schema/mixs +room_type_enum attic +room_type_enum bathroom +room_type_enum closet +room_type_enum conference room +room_type_enum elevator +room_type_enum examining room +room_type_enum hallway +room_type_enum kitchen +room_type_enum mail room +room_type_enum private office +room_type_enum open office +room_type_enum stairwell +room_type_enum ,restroom +room_type_enum lobby +room_type_enum vestibule +room_type_enum mechanical or electrical room +room_type_enum data center +room_type_enum laboratory_wet +room_type_enum laboratory_dry +room_type_enum gymnasium +room_type_enum natatorium +room_type_enum auditorium +room_type_enum lockers +room_type_enum cafe +room_type_enum warehouse +samp_capt_status_enum https://microbiomedata/schema/mixs +samp_capt_status_enum active surveillance in response to an outbreak +samp_capt_status_enum active surveillance not initiated by an outbreak +samp_capt_status_enum farm sample +samp_capt_status_enum market sample +samp_capt_status_enum other +samp_collect_point_enum https://microbiomedata/schema/mixs +samp_collect_point_enum well +samp_collect_point_enum test well +samp_collect_point_enum drilling rig +samp_collect_point_enum wellhead +samp_collect_point_enum separator +samp_collect_point_enum storage tank +samp_collect_point_enum other +samp_dis_stage_enum https://microbiomedata/schema/mixs +samp_dis_stage_enum dissemination +samp_dis_stage_enum growth and reproduction +samp_dis_stage_enum infection +samp_dis_stage_enum inoculation +samp_dis_stage_enum penetration +samp_dis_stage_enum other +samp_floor_enum https://microbiomedata/schema/mixs +samp_floor_enum 1st floor +samp_floor_enum 2nd floor +samp_floor_enum basement +samp_floor_enum lobby +samp_md_enum https://microbiomedata/schema/mixs +samp_md_enum DF +samp_md_enum RT +samp_md_enum KB +samp_md_enum MSL +samp_md_enum other +samp_subtype_enum https://microbiomedata/schema/mixs +samp_subtype_enum oil phase +samp_subtype_enum water phase +samp_subtype_enum biofilm +samp_subtype_enum not applicable +samp_subtype_enum other +samp_weather_enum https://microbiomedata/schema/mixs +samp_weather_enum clear sky +samp_weather_enum cloudy +samp_weather_enum foggy +samp_weather_enum hail +samp_weather_enum rain +samp_weather_enum snow +samp_weather_enum sleet +samp_weather_enum sunny +samp_weather_enum windy +season_use_enum https://microbiomedata/schema/mixs +season_use_enum Spring +season_use_enum Summer +season_use_enum Fall +season_use_enum Winter +sediment_type_enum https://microbiomedata/schema/mixs +sediment_type_enum biogenous +sediment_type_enum cosmogenous +sediment_type_enum hydrogenous +sediment_type_enum lithogenous +shading_device_cond_enum https://microbiomedata/schema/mixs +shading_device_cond_enum damaged +shading_device_cond_enum needs repair +shading_device_cond_enum new +shading_device_cond_enum rupture +shading_device_cond_enum visible wear +shading_device_type_enum https://microbiomedata/schema/mixs +shading_device_type_enum bahama shutters +shading_device_type_enum exterior roll blind +shading_device_type_enum gambrel awning +shading_device_type_enum hood awning +shading_device_type_enum porchroller awning +shading_device_type_enum sarasota shutters +shading_device_type_enum slatted aluminum +shading_device_type_enum solid aluminum awning +shading_device_type_enum sun screen +shading_device_type_enum tree +shading_device_type_enum trellis +shading_device_type_enum venetian awning +soil_horizon_enum https://microbiomedata/schema/mixs +soil_horizon_enum O horizon +soil_horizon_enum A horizon +soil_horizon_enum E horizon +soil_horizon_enum B horizon +soil_horizon_enum C horizon +soil_horizon_enum R layer +soil_horizon_enum Permafrost +specific_enum https://microbiomedata/schema/mixs +specific_enum operation +specific_enum as built +specific_enum construction +specific_enum bid +specific_enum design +specific_enum photos +sr_dep_env_enum https://microbiomedata/schema/mixs +sr_dep_env_enum Lacustine +sr_dep_env_enum Fluvioldeltaic +sr_dep_env_enum Fluviomarine +sr_dep_env_enum Marine +sr_dep_env_enum other +sr_geol_age_enum https://microbiomedata/schema/mixs +sr_geol_age_enum Archean +sr_geol_age_enum Cambrian +sr_geol_age_enum Carboniferous +sr_geol_age_enum Cenozoic +sr_geol_age_enum Cretaceous +sr_geol_age_enum Devonian +sr_geol_age_enum Jurassic +sr_geol_age_enum Mesozoic +sr_geol_age_enum Neogene +sr_geol_age_enum Ordovician +sr_geol_age_enum Paleogene +sr_geol_age_enum Paleozoic +sr_geol_age_enum Permian +sr_geol_age_enum Precambrian +sr_geol_age_enum Proterozoic +sr_geol_age_enum Silurian +sr_geol_age_enum Triassic +sr_geol_age_enum other +sr_kerog_type_enum https://microbiomedata/schema/mixs +sr_kerog_type_enum Type I +sr_kerog_type_enum Type II +sr_kerog_type_enum Type III +sr_kerog_type_enum Type IV +sr_kerog_type_enum other +sr_lithology_enum https://microbiomedata/schema/mixs +sr_lithology_enum Clastic +sr_lithology_enum Carbonate +sr_lithology_enum Coal +sr_lithology_enum Biosilicieous +sr_lithology_enum other +substructure_type_enum https://microbiomedata/schema/mixs +substructure_type_enum crawlspace +substructure_type_enum slab on grade +substructure_type_enum basement +surf_air_cont_enum https://microbiomedata/schema/mixs +surf_air_cont_enum dust +surf_air_cont_enum organic matter +surf_air_cont_enum particulate matter +surf_air_cont_enum volatile organic compounds +surf_air_cont_enum biological contaminants +surf_air_cont_enum radon +surf_air_cont_enum nutrients +surf_air_cont_enum biocides +surf_material_enum https://microbiomedata/schema/mixs +surf_material_enum adobe +surf_material_enum carpet +surf_material_enum cinder blocks +surf_material_enum concrete +surf_material_enum hay bales +surf_material_enum glass +surf_material_enum metal +surf_material_enum paint +surf_material_enum plastic +surf_material_enum stainless steel +surf_material_enum stone +surf_material_enum stucco +surf_material_enum tile +surf_material_enum vinyl +surf_material_enum wood +tidal_stage_enum https://microbiomedata/schema/mixs +tidal_stage_enum low tide +tidal_stage_enum ebb tide +tidal_stage_enum flood tide +tidal_stage_enum high tide +tillage_enum https://microbiomedata/schema/mixs +tillage_enum drill +tillage_enum cutting disc +tillage_enum ridge till +tillage_enum strip tillage +tillage_enum zonal tillage +tillage_enum chisel +tillage_enum tined +tillage_enum mouldboard +tillage_enum disc plough +train_line_enum https://microbiomedata/schema/mixs +train_line_enum red +train_line_enum green +train_line_enum orange +train_stat_loc_enum https://microbiomedata/schema/mixs +train_stat_loc_enum south station above ground +train_stat_loc_enum south station underground +train_stat_loc_enum south station amtrak +train_stat_loc_enum forest hills +train_stat_loc_enum riverside +train_stop_loc_enum https://microbiomedata/schema/mixs +train_stop_loc_enum end +train_stop_loc_enum mid +train_stop_loc_enum downtown +vis_media_enum https://microbiomedata/schema/mixs +vis_media_enum photos +vis_media_enum videos +vis_media_enum commonly of the building +vis_media_enum site context (adjacent buildings, vegetation, terrain, streets) +vis_media_enum interiors +vis_media_enum equipment +vis_media_enum 3D scans +wall_const_type_enum https://microbiomedata/schema/mixs +wall_const_type_enum frame construction +wall_const_type_enum joisted masonry +wall_const_type_enum light noncombustible +wall_const_type_enum masonry noncombustible +wall_const_type_enum modified fire resistive +wall_const_type_enum fire resistive +wall_finish_mat_enum https://microbiomedata/schema/mixs +wall_finish_mat_enum plaster +wall_finish_mat_enum gypsum plaster +wall_finish_mat_enum veneer plaster +wall_finish_mat_enum gypsum board +wall_finish_mat_enum tile +wall_finish_mat_enum terrazzo +wall_finish_mat_enum stone facing +wall_finish_mat_enum acoustical treatment +wall_finish_mat_enum wood +wall_finish_mat_enum metal +wall_finish_mat_enum masonry +wall_loc_enum https://microbiomedata/schema/mixs +wall_loc_enum north +wall_loc_enum south +wall_loc_enum east +wall_loc_enum west +wall_surf_treatment_enum https://microbiomedata/schema/mixs +wall_surf_treatment_enum painted +wall_surf_treatment_enum wall paper +wall_surf_treatment_enum no treatment +wall_surf_treatment_enum paneling +wall_surf_treatment_enum stucco +wall_surf_treatment_enum fabric +wall_texture_enum https://microbiomedata/schema/mixs +wall_texture_enum crows feet +wall_texture_enum crows-foot stomp +wall_texture_enum +wall_texture_enum double skip +wall_texture_enum hawk and trowel +wall_texture_enum knockdown +wall_texture_enum popcorn +wall_texture_enum orange peel +wall_texture_enum rosebud stomp +wall_texture_enum Santa-Fe texture +wall_texture_enum skip trowel +wall_texture_enum smooth +wall_texture_enum stomp knockdown +wall_texture_enum swirl +water_feat_type_enum https://microbiomedata/schema/mixs +water_feat_type_enum fountain +water_feat_type_enum pool +water_feat_type_enum standing feature +water_feat_type_enum stream +water_feat_type_enum waterfall +weekday_enum https://microbiomedata/schema/mixs +weekday_enum Monday +weekday_enum Tuesday +weekday_enum Wednesday +weekday_enum Thursday +weekday_enum Friday +weekday_enum Saturday +weekday_enum Sunday +window_cond_enum https://microbiomedata/schema/mixs +window_cond_enum damaged +window_cond_enum needs repair +window_cond_enum new +window_cond_enum rupture +window_cond_enum visible wear +window_cover_enum https://microbiomedata/schema/mixs +window_cover_enum blinds +window_cover_enum curtains +window_cover_enum none +window_horiz_pos_enum https://microbiomedata/schema/mixs +window_horiz_pos_enum left +window_horiz_pos_enum middle +window_horiz_pos_enum right +window_loc_enum https://microbiomedata/schema/mixs +window_loc_enum north +window_loc_enum south +window_loc_enum east +window_loc_enum west +window_mat_enum https://microbiomedata/schema/mixs +window_mat_enum clad +window_mat_enum fiberglass +window_mat_enum metal +window_mat_enum vinyl +window_mat_enum wood +window_type_enum https://microbiomedata/schema/mixs +window_type_enum single-hung sash window +window_type_enum horizontal sash window +window_type_enum fixed window +window_vert_pos_enum https://microbiomedata/schema/mixs +window_vert_pos_enum bottom +window_vert_pos_enum middle +window_vert_pos_enum top +window_vert_pos_enum low +window_vert_pos_enum high diff --git a/util/generated_NMDC_enums.yaml b/util/generated_NMDC_enums.yaml new file mode 100644 index 0000000000..59733a5320 --- /dev/null +++ b/util/generated_NMDC_enums.yaml @@ -0,0 +1,2332 @@ +name: NMDC_enums_roundtrip +id: NMDC_enums_roundtrip +imports: +- linkml:types +prefixes: + linkml: + prefix_prefix: linkml + prefix_reference: https://w3id.org/linkml/ + NMDC_enums_roundtrip: + prefix_prefix: NMDC_enums_roundtrip + prefix_reference: https://example.org/NMDC_enums_roundtrip/ +default_prefix: NMDC_enums_roundtrip +default_range: string +enums: + file type enum: + name: file type enum + from_schema: NMDC_enums_roundtrip + permissible_values: + FT ICR-MS Analysis Results: + text: FT ICR-MS Analysis Results + description: FT ICR-MS-based molecular formula assignment results table + GC-MS Metabolomics Results: + text: GC-MS Metabolomics Results + description: GC-MS-based metabolite assignment results table + Metaproteomics Workflow Statistics: + text: Metaproteomics Workflow Statistics + description: Aggregate workflow statistics file + Protein Report: + text: Protein Report + description: Filtered protein report file + Peptide Report: + text: Peptide Report + description: Filtered peptide report file + Unfiltered Metaproteomics Results: + text: Unfiltered Metaproteomics Results + description: MSGFjobs and MASIC output file + Read Count and RPKM: + text: Read Count and RPKM + description: Annotation read count and RPKM per feature JSON + QC non-rRNA R2: + text: QC non-rRNA R2 + description: QC removed rRNA reads (R2) fastq + QC non-rRNA R1: + text: QC non-rRNA R1 + description: QC removed rRNA reads (R1) fastq + Metagenome Bins: + text: Metagenome Bins + description: Metagenome bin contigs fasta + CheckM Statistics: + text: CheckM Statistics + description: CheckM statistics report + GOTTCHA2 Krona Plot: + text: GOTTCHA2 Krona Plot + description: GOTTCHA2 krona plot HTML file + GOTTCHA2 Classification Report: + text: GOTTCHA2 Classification Report + description: GOTTCHA2 classification report file + GOTTCHA2 Report Full: + text: GOTTCHA2 Report Full + description: GOTTCHA2 report file + Kraken2 Krona Plot: + text: Kraken2 Krona Plot + description: Kraken2 krona plot HTML file + Centrifuge Krona Plot: + text: Centrifuge Krona Plot + description: Centrifug krona plot HTML file + Centrifuge output report file: + text: Centrifuge output report file + description: Centrifug output report file + Kraken2 Classification Report: + text: Kraken2 Classification Report + description: Kraken2 output report file + Kraken2 Taxonomic Classification: + text: Kraken2 Taxonomic Classification + description: Kraken2 output read classification file + Centrifuge Classification Report: + text: Centrifuge Classification Report + description: Centrifuge output report file + Centrifuge Taxonomic Classification: + text: Centrifuge Taxonomic Classification + description: Centrifuge output read classification file + Structural Annotation GFF: + text: Structural Annotation GFF + description: GFF3 format file with structural annotations + Functional Annotation GFF: + text: Functional Annotation GFF + description: GFF3 format file with functional annotations + Annotation Amino Acid FASTA: + text: Annotation Amino Acid FASTA + description: FASTA amino acid file for annotated proteins + Annotation Enzyme Commission: + text: Annotation Enzyme Commission + description: Tab delimited file for EC annotation + Annotation KEGG Orthology: + text: Annotation KEGG Orthology + description: Tab delimited file for KO annotation + Assembly Coverage BAM: + text: Assembly Coverage BAM + description: Sorted bam file of reads mapping back to the final assembly + Assembly AGP: + text: Assembly AGP + description: An AGP format file that describes the assembly + Assembly Scaffolds: + text: Assembly Scaffolds + description: Final assembly scaffolds fasta + Assembly Contigs: + text: Assembly Contigs + description: Final assembly contigs fasta + Assembly Coverage Stats: + text: Assembly Coverage Stats + description: Assembled contigs coverage information + Filtered Sequencing Reads: + text: Filtered Sequencing Reads + description: Reads QC result fastq (clean data) + QC Statistics: + text: QC Statistics + description: Reads QC summary statistics + TIGRFam Annotation GFF: + text: TIGRFam Annotation GFF + description: GFF3 format file with TIGRfam + annotations: + file_name_pattern: + tag: file_name_pattern + value: '[GOLD-AP]_tigrfam.gff' + CRT Annotation GFF: + text: CRT Annotation GFF + description: GFF3 format file with CRT + Genmark Annotation GFF: + text: Genmark Annotation GFF + description: GFF3 format file with Genmark + Prodigal Annotation GFF: + text: Prodigal Annotation GFF + description: GFF3 format file with Prodigal + TRNA Annotation GFF: + text: TRNA Annotation GFF + description: GFF3 format file with TRNA + Misc Annotation GFF: + text: Misc Annotation GFF + description: GFF3 format file with Misc + RFAM Annotation GFF: + text: RFAM Annotation GFF + description: GFF3 format file with RFAM + TMRNA Annotation GFF: + text: TMRNA Annotation GFF + description: GFF3 format file with TMRNA + KO_EC Annotation GFF: + text: KO_EC Annotation GFF + description: GFF3 format file with KO_EC + Product Names: + text: Product Names + description: Product names file + Gene Phylogeny tsv: + text: Gene Phylogeny tsv + description: Gene Phylogeny tsv + Crisprt Terms: + text: Crisprt Terms + description: Crisprt Terms + Clusters of Orthologous Groups (COG) Annotation GFF: + text: Clusters of Orthologous Groups (COG) Annotation GFF + description: GFF3 format file with COGs + annotations: + file_name_pattern: + tag: file_name_pattern + value: '[GOLD-AP]_cog.gff' + CATH FunFams (Functional Families) Annotation GFF: + text: CATH FunFams (Functional Families) Annotation GFF + description: GFF3 format file with CATH FunFams + annotations: + file_name_pattern: + tag: file_name_pattern + value: '[GOLD-AP]_cath_funfam.gff' + SUPERFam Annotation GFF: + text: SUPERFam Annotation GFF + description: GFF3 format file with SUPERFam + annotations: + file_name_pattern: + tag: file_name_pattern + value: '[GOLD-AP]_supfam.gff' + SMART Annotation GFF: + text: SMART Annotation GFF + description: GFF3 format file with SMART + annotations: + file_name_pattern: + tag: file_name_pattern + value: '[GOLD-AP]_smart.gff' + Pfam Annotation GFF: + text: Pfam Annotation GFF + description: GFF3 format file with Pfam + annotations: + file_name_pattern: + tag: file_name_pattern + value: '[GOLD-AP]_pfam.gff' + Direct Infusion FT ICR-MS Raw Data: + text: Direct Infusion FT ICR-MS Raw Data + description: Direct infusion 21 Tesla Fourier Transform ion cyclotron resonance + mass spectrometry raw data acquired in broadband full scan mode + credit enum: + name: credit enum + comments: + - credit enums come from https://casrai.org/credit/ + from_schema: NMDC_enums_roundtrip + permissible_values: + Conceptualization: + text: Conceptualization + description: Conceptualization + Data curation: + text: Data curation + description: Data curation + Formal Analysis: + text: Formal Analysis + description: Formal Analysis + Funding acquisition: + text: Funding acquisition + description: Funding acquisition + Investigation: + text: Investigation + description: Investigation + Methodology: + text: Methodology + description: Methodology + Project administration: + text: Project administration + description: Project administration + Resources: + text: Resources + description: Resources + Software: + text: Software + description: Software + Supervision: + text: Supervision + description: Supervision + Validation: + text: Validation + description: Validation + Visualization: + text: Visualization + description: Visualization + Writing original draft: + text: Writing original draft + description: Writing – original draft + Writing review and editing: + text: Writing review and editing + description: Writing – review & editing + Principal Investigator: + text: Principal Investigator + description: principal investigator role + meaning: OBI:0000103 + analysis_type_enum: + name: analysis_type_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + metabolomics: + text: metabolomics + metagenomics: + text: metagenomics + metaproteomics: + text: metaproteomics + metatranscriptomics: + text: metatranscriptomics + natural organic matter: + text: natural organic matter + dnase_rna_enum: + name: dnase_rna_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + 'no': + text: 'no' + 'yes': + text: 'yes' + rna_cont_type_enum: + name: rna_cont_type_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + plate: + text: plate + tube: + text: tube + rna_sample_format_enum: + name: rna_sample_format_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + 10 mM Tris-HCl: + text: 10 mM Tris-HCl + DNAStable: + text: DNAStable + Ethanol: + text: Ethanol + Low EDTA TE: + text: Low EDTA TE + MDA reaction buffer: + text: MDA reaction buffer + PBS: + text: PBS + Pellet: + text: Pellet + RNAStable: + text: RNAStable + TE: + text: TE + Water: + text: Water + dna_cont_type_enum: + name: dna_cont_type_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + plate: + text: plate + tube: + text: tube + dna_dnase_enum: + name: dna_dnase_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + 'no': + text: 'no' + 'yes': + text: 'yes' + dna_sample_format_enum: + name: dna_sample_format_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + 10 mM Tris-HCl: + text: 10 mM Tris-HCl + DNAStable: + text: DNAStable + Ethanol: + text: Ethanol + Low EDTA TE: + text: Low EDTA TE + MDA reaction buffer: + text: MDA reaction buffer + PBS: + text: PBS + Pellet: + text: Pellet + RNAStable: + text: RNAStable + TE: + text: TE + Water: + text: Water + sample_type_enum: + name: sample_type_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + soil: + text: soil + water_extract_soil: + text: water_extract_soil + arch_struc_enum: + name: arch_struc_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + building: + text: building + shed: + text: shed + home: + text: home + biol_stat_enum: + name: biol_stat_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + wild: + text: wild + natural: + text: natural + semi-natural: + text: semi-natural + inbred line: + text: inbred line + breeder's line: + text: breeder's line + hybrid: + text: hybrid + clonal selection: + text: clonal selection + mutant: + text: mutant + biotic_relationship_enum: + name: biotic_relationship_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + free living: + text: free living + parasite: + text: parasite + commensal: + text: commensal + symbiont: + text: symbiont + build_docs_enum: + name: build_docs_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + building information model: + text: building information model + commissioning report: + text: commissioning report + complaint logs: + text: complaint logs + contract administration: + text: contract administration + cost estimate: + text: cost estimate + janitorial schedules or logs: + text: janitorial schedules or logs + maintenance plans: + text: maintenance plans + schedule: + text: schedule + sections: + text: sections + shop drawings: + text: shop drawings + submittals: + text: submittals + ventilation system: + text: ventilation system + windows: + text: windows + build_occup_type_enum: + name: build_occup_type_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + office: + text: office + market: + text: market + restaurant: + text: restaurant + residence: + text: residence + school: + text: school + residential: + text: residential + commercial: + text: commercial + low rise: + text: low rise + high rise: + text: high rise + wood framed: + text: wood framed + health care: + text: health care + airport: + text: airport + sports complex: + text: sports complex + building_setting_enum: + name: building_setting_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + urban: + text: urban + suburban: + text: suburban + exurban: + text: exurban + rural: + text: rural + ceil_cond_enum: + name: ceil_cond_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + new: + text: new + visible wear: + text: visible wear + needs repair: + text: needs repair + damaged: + text: damaged + rupture: + text: rupture + ceil_finish_mat_enum: + name: ceil_finish_mat_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + drywall: + text: drywall + mineral fibre: + text: mineral fibre + tiles: + text: tiles + PVC: + text: PVC + plasterboard: + text: plasterboard + metal: + text: metal + fiberglass: + text: fiberglass + stucco: + text: stucco + mineral wool/calcium silicate: + text: mineral wool/calcium silicate + wood: + text: wood + ceil_texture_enum: + name: ceil_texture_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + crows feet: + text: crows feet + crows-foot stomp: + text: crows-foot stomp + double skip: + text: double skip + hawk and trowel: + text: hawk and trowel + knockdown: + text: knockdown + popcorn: + text: popcorn + orange peel: + text: orange peel + rosebud stomp: + text: rosebud stomp + Santa-Fe texture: + text: Santa-Fe texture + skip trowel: + text: skip trowel + smooth: + text: smooth + stomp knockdown: + text: stomp knockdown + swirl: + text: swirl + ceil_type_enum: + name: ceil_type_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + cathedral: + text: cathedral + dropped: + text: dropped + concave: + text: concave + barrel-shaped: + text: barrel-shaped + coffered: + text: coffered + cove: + text: cove + stretched: + text: stretched + cur_land_use_enum: + name: cur_land_use_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + cities: + text: cities + farmstead: + text: farmstead + industrial areas: + text: industrial areas + roads/railroads: + text: roads/railroads + rock: + text: rock + sand: + text: sand + gravel: + text: gravel + mudflats: + text: mudflats + salt flats: + text: salt flats + badlands: + text: badlands + permanent snow or ice: + text: permanent snow or ice + saline seeps: + text: saline seeps + mines/quarries: + text: mines/quarries + oil waste areas: + text: oil waste areas + small grains: + text: small grains + row crops: + text: row crops + vegetable crops: + text: vegetable crops + horticultural plants (e.g. tulips): + text: horticultural plants (e.g. tulips) + marshlands (grass,sedges,rushes): + text: marshlands (grass,sedges,rushes) + tundra (mosses,lichens): + text: tundra (mosses,lichens) + rangeland: + text: rangeland + pastureland (grasslands used for livestock grazing): + text: pastureland (grasslands used for livestock grazing) + hayland: + text: hayland + meadows (grasses,alfalfa,fescue,bromegrass,timothy): + text: meadows (grasses,alfalfa,fescue,bromegrass,timothy) + shrub land (e.g. mesquite,sage-brush,creosote bush,shrub oak,eucalyptus): + text: shrub land (e.g. mesquite,sage-brush,creosote bush,shrub oak,eucalyptus) + successional shrub land (tree saplings,hazels,sumacs,chokecherry,shrub dogwoods,blackberries): + text: successional shrub land (tree saplings,hazels,sumacs,chokecherry,shrub + dogwoods,blackberries) + shrub crops (blueberries,nursery ornamentals,filberts): + text: shrub crops (blueberries,nursery ornamentals,filberts) + vine crops (grapes): + text: vine crops (grapes) + conifers (e.g. pine,spruce,fir,cypress): + text: conifers (e.g. pine,spruce,fir,cypress) + hardwoods (e.g. oak,hickory,elm,aspen): + text: hardwoods (e.g. oak,hickory,elm,aspen) + intermixed hardwood and conifers: + text: intermixed hardwood and conifers + tropical (e.g. mangrove,palms): + text: tropical (e.g. mangrove,palms) + rainforest (evergreen forest receiving greater than 406 cm annual rainfall): + text: rainforest (evergreen forest receiving greater than 406 cm annual rainfall) + swamp (permanent or semi-permanent water body dominated by woody plants): + text: swamp (permanent or semi-permanent water body dominated by woody plants) + crop trees (nuts,fruit,christmas trees,nursery trees): + text: crop trees (nuts,fruit,christmas trees,nursery trees) + depos_env_enum: + name: depos_env_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + Continental - Alluvial: + text: Continental - Alluvial + Continental - Aeolian: + text: Continental - Aeolian + Continental - Fluvial: + text: Continental - Fluvial + Continental - Lacustrine: + text: Continental - Lacustrine + Transitional - Deltaic: + text: Transitional - Deltaic + Transitional - Tidal: + text: Transitional - Tidal + Transitional - Lagoonal: + text: Transitional - Lagoonal + Transitional - Beach: + text: Transitional - Beach + Transitional - Lake: + text: Transitional - Lake + Marine - Shallow: + text: Marine - Shallow + Marine - Deep: + text: Marine - Deep + Marine - Reef: + text: Marine - Reef + Other - Evaporite: + text: Other - Evaporite + Other - Glacial: + text: Other - Glacial + Other - Volcanic: + text: Other - Volcanic + other: + text: other + door_comp_type_enum: + name: door_comp_type_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + metal covered: + text: metal covered + revolving: + text: revolving + sliding: + text: sliding + telescopic: + text: telescopic + door_cond_enum: + name: door_cond_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + damaged: + text: damaged + needs repair: + text: needs repair + new: + text: new + rupture: + text: rupture + visible wear: + text: visible wear + door_direct_enum: + name: door_direct_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + inward: + text: inward + outward: + text: outward + sideways: + text: sideways + door_loc_enum: + name: door_loc_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + north: + text: north + south: + text: south + east: + text: east + west: + text: west + door_mat_enum: + name: door_mat_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + aluminum: + text: aluminum + cellular PVC: + text: cellular PVC + engineered plastic: + text: engineered plastic + fiberboard: + text: fiberboard + fiberglass: + text: fiberglass + metal: + text: metal + thermoplastic alloy: + text: thermoplastic alloy + vinyl: + text: vinyl + wood: + text: wood + wood/plastic composite: + text: wood/plastic composite + door_move_enum: + name: door_move_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + collapsible: + text: collapsible + folding: + text: folding + revolving: + text: revolving + rolling shutter: + text: rolling shutter + sliding: + text: sliding + swinging: + text: swinging + door_type_enum: + name: door_type_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + composite: + text: composite + metal: + text: metal + wooden: + text: wooden + door_type_metal_enum: + name: door_type_metal_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + collapsible: + text: collapsible + corrugated steel: + text: corrugated steel + hollow: + text: hollow + rolling shutters: + text: rolling shutters + steel plate: + text: steel plate + door_type_wood_enum: + name: door_type_wood_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + bettened and ledged: + text: bettened and ledged + battened: + text: battened + ledged and braced: + text: ledged and braced + ledged and framed: + text: ledged and framed + ledged, braced and frame: + text: ledged, braced and frame + framed and paneled: + text: framed and paneled + glashed or sash: + text: glashed or sash + flush: + text: flush + louvered: + text: louvered + wire gauged: + text: wire gauged + drainage_class_enum: + name: drainage_class_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + very poorly: + text: very poorly + poorly: + text: poorly + somewhat poorly: + text: somewhat poorly + moderately well: + text: moderately well + well: + text: well + excessively drained: + text: excessively drained + drawings_enum: + name: drawings_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + operation: + text: operation + as built: + text: as built + construction: + text: construction + bid: + text: bid + design: + text: design + building navigation map: + text: building navigation map + diagram: + text: diagram + sketch: + text: sketch + ext_wall_orient_enum: + name: ext_wall_orient_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + north: + text: north + south: + text: south + east: + text: east + west: + text: west + northeast: + text: northeast + southeast: + text: southeast + southwest: + text: southwest + northwest: + text: northwest + ext_window_orient_enum: + name: ext_window_orient_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + north: + text: north + south: + text: south + east: + text: east + west: + text: west + northeast: + text: northeast + southeast: + text: southeast + southwest: + text: southwest + northwest: + text: northwest + fao_class_enum: + name: fao_class_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + Acrisols: + text: Acrisols + Andosols: + text: Andosols + Arenosols: + text: Arenosols + Cambisols: + text: Cambisols + Chernozems: + text: Chernozems + Ferralsols: + text: Ferralsols + Fluvisols: + text: Fluvisols + Gleysols: + text: Gleysols + Greyzems: + text: Greyzems + Gypsisols: + text: Gypsisols + Histosols: + text: Histosols + Kastanozems: + text: Kastanozems + Lithosols: + text: Lithosols + Luvisols: + text: Luvisols + Nitosols: + text: Nitosols + Phaeozems: + text: Phaeozems + Planosols: + text: Planosols + Podzols: + text: Podzols + Podzoluvisols: + text: Podzoluvisols + Rankers: + text: Rankers + Regosols: + text: Regosols + Rendzinas: + text: Rendzinas + Solonchaks: + text: Solonchaks + Solonetz: + text: Solonetz + Vertisols: + text: Vertisols + Yermosols: + text: Yermosols + filter_type_enum: + name: filter_type_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + particulate air filter: + text: particulate air filter + chemical air filter: + text: chemical air filter + low-MERV pleated media: + text: low-MERV pleated media + HEPA: + text: HEPA + electrostatic: + text: electrostatic + gas-phase or ultraviolet air treatments: + text: gas-phase or ultraviolet air treatments + floor_cond_enum: + name: floor_cond_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + new: + text: new + visible wear: + text: visible wear + needs repair: + text: needs repair + damaged: + text: damaged + rupture: + text: rupture + floor_finish_mat_enum: + name: floor_finish_mat_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + tile: + text: tile + wood strip or parquet: + text: wood strip or parquet + carpet: + text: carpet + rug: + text: rug + laminate wood: + text: laminate wood + lineoleum: + text: lineoleum + vinyl composition tile: + text: vinyl composition tile + sheet vinyl: + text: sheet vinyl + stone: + text: stone + bamboo: + text: bamboo + cork: + text: cork + terrazo: + text: terrazo + concrete: + text: concrete + none: + text: none + sealed: + text: sealed + clear finish: + text: clear finish + paint: + text: paint + none or unfinished: + text: none or unfinished + floor_struc_enum: + name: floor_struc_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + balcony: + text: balcony + floating floor: + text: floating floor + glass floor: + text: glass floor + raised floor: + text: raised floor + sprung floor: + text: sprung floor + wood-framed: + text: wood-framed + concrete: + text: concrete + floor_water_mold_enum: + name: floor_water_mold_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + mold odor: + text: mold odor + wet floor: + text: wet floor + water stains: + text: water stains + wall discoloration: + text: wall discoloration + floor discoloration: + text: floor discoloration + ceiling discoloration: + text: ceiling discoloration + peeling paint or wallpaper: + text: peeling paint or wallpaper + bulging walls: + text: bulging walls + condensation: + text: condensation + freq_clean_enum: + name: freq_clean_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + Daily: + text: Daily + Weekly: + text: Weekly + Monthly: + text: Monthly + Quarterly: + text: Quarterly + Annually: + text: Annually + other: + text: other + furniture_enum: + name: furniture_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + cabinet: + text: cabinet + chair: + text: chair + desks: + text: desks + gender_restroom_enum: + name: gender_restroom_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + all gender: + text: all gender + female: + text: female + gender neurtral: + text: gender neurtral + male: + text: male + male and female: + text: male and female + unisex: + text: unisex + growth_habit_enum: + name: growth_habit_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + erect: + text: erect + semi-erect: + text: semi-erect + spreading: + text: spreading + prostrate: + text: prostrate + handidness_enum: + name: handidness_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + ambidexterity: + text: ambidexterity + left handedness: + text: left handedness + mixed-handedness: + text: mixed-handedness + right handedness: + text: right handedness + hc_produced_enum: + name: hc_produced_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + Oil: + text: Oil + Gas-Condensate: + text: Gas-Condensate + Gas: + text: Gas + Bitumen: + text: Bitumen + Coalbed Methane: + text: Coalbed Methane + other: + text: other + hcr_enum: + name: hcr_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + Oil Reservoir: + text: Oil Reservoir + Gas Reservoir: + text: Gas Reservoir + Oil Sand: + text: Oil Sand + Coalbed: + text: Coalbed + Shale: + text: Shale + Tight Oil Reservoir: + text: Tight Oil Reservoir + Tight Gas Reservoir: + text: Tight Gas Reservoir + other: + text: other + hcr_geol_age_enum: + name: hcr_geol_age_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + Archean: + text: Archean + Cambrian: + text: Cambrian + Carboniferous: + text: Carboniferous + Cenozoic: + text: Cenozoic + Cretaceous: + text: Cretaceous + Devonian: + text: Devonian + Jurassic: + text: Jurassic + Mesozoic: + text: Mesozoic + Neogene: + text: Neogene + Ordovician: + text: Ordovician + Paleogene: + text: Paleogene + Paleozoic: + text: Paleozoic + Permian: + text: Permian + Precambrian: + text: Precambrian + Proterozoic: + text: Proterozoic + Silurian: + text: Silurian + Triassic: + text: Triassic + other: + text: other + heat_cool_type_enum: + name: heat_cool_type_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + radiant system: + text: radiant system + heat pump: + text: heat pump + forced air system: + text: forced air system + steam forced heat: + text: steam forced heat + wood stove: + text: wood stove + heat_deliv_loc_enum: + name: heat_deliv_loc_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + north: + text: north + south: + text: south + east: + text: east + west: + text: west + horizon_enum: + name: horizon_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + O horizon: + text: O horizon + A horizon: + text: A horizon + E horizon: + text: E horizon + B horizon: + text: B horizon + C horizon: + text: C horizon + R layer: + text: R layer + Permafrost: + text: Permafrost + host_sex_enum: + name: host_sex_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + female: + text: female + hermaphrodite: + text: hermaphrodite + male: + text: male + neuter: + text: neuter + indoor_space_enum: + name: indoor_space_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + bedroom: + text: bedroom + office: + text: office + bathroom: + text: bathroom + foyer: + text: foyer + kitchen: + text: kitchen + locker room: + text: locker room + hallway: + text: hallway + elevator: + text: elevator + indoor_surf_enum: + name: indoor_surf_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + cabinet: + text: cabinet + ceiling: + text: ceiling + counter top: + text: counter top + door: + text: door + shelving: + text: shelving + vent cover: + text: vent cover + window: + text: window + wall: + text: wall + int_wall_cond_enum: + name: int_wall_cond_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + new: + text: new + visible wear: + text: visible wear + needs repair: + text: needs repair + damaged: + text: damaged + rupture: + text: rupture + light_type_enum: + name: light_type_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + natural light: + text: natural light + electric light: + text: electric light + desk lamp: + text: desk lamp + flourescent lights: + text: flourescent lights + none: + text: none + lithology_enum: + name: lithology_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + Basement: + text: Basement + Chalk: + text: Chalk + Chert: + text: Chert + Coal: + text: Coal + Conglomerate: + text: Conglomerate + Diatomite: + text: Diatomite + Dolomite: + text: Dolomite + Limestone: + text: Limestone + Sandstone: + text: Sandstone + Shale: + text: Shale + Siltstone: + text: Siltstone + Volcanic: + text: Volcanic + other: + text: other + mech_struc_enum: + name: mech_struc_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + subway: + text: subway + coach: + text: coach + carriage: + text: carriage + elevator: + text: elevator + escalator: + text: escalator + boat: + text: boat + train: + text: train + car: + text: car + bus: + text: bus + occup_document_enum: + name: occup_document_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + automated count: + text: automated count + estimate: + text: estimate + manual count: + text: manual count + videos: + text: videos + organism_count_enum: + name: organism_count_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + ATP: + text: ATP + MPN: + text: MPN + other: + text: other + oxy_stat_samp_enum: + name: oxy_stat_samp_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + aerobic: + text: aerobic + anaerobic: + text: anaerobic + other: + text: other + plant_growth_med_enum: + name: plant_growth_med_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + other artificial liquid medium: + text: other artificial liquid medium + other artificial solid medium: + text: other artificial solid medium + peat moss: + text: peat moss + perlite: + text: perlite + pumice: + text: pumice + sand: + text: sand + soil: + text: soil + vermiculite: + text: vermiculite + water: + text: water + plant_sex_enum: + name: plant_sex_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + Androdioecious: + text: Androdioecious + Androecious: + text: Androecious + Androgynous: + text: Androgynous + Androgynomonoecious: + text: Androgynomonoecious + Andromonoecious: + text: Andromonoecious + Bisexual: + text: Bisexual + Dichogamous: + text: Dichogamous + Diclinous: + text: Diclinous + Dioecious: + text: Dioecious + Gynodioecious: + text: Gynodioecious + Gynoecious: + text: Gynoecious + Gynomonoecious: + text: Gynomonoecious + Hermaphroditic: + text: Hermaphroditic + Imperfect: + text: Imperfect + Monoclinous: + text: Monoclinous + Monoecious: + text: Monoecious + Perfect: + text: Perfect + Polygamodioecious: + text: Polygamodioecious + Polygamomonoecious: + text: Polygamomonoecious + Polygamous: + text: Polygamous + Protandrous: + text: Protandrous + Protogynous: + text: Protogynous + Subandroecious: + text: Subandroecious + Subdioecious: + text: Subdioecious + Subgynoecious: + text: Subgynoecious + Synoecious: + text: Synoecious + Trimonoecious: + text: Trimonoecious + Trioecious: + text: Trioecious + Unisexual: + text: Unisexual + profile_position_enum: + name: profile_position_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + summit: + text: summit + shoulder: + text: shoulder + backslope: + text: backslope + footslope: + text: footslope + toeslope: + text: toeslope + quad_pos_enum: + name: quad_pos_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + North side: + text: North side + West side: + text: West side + South side: + text: South side + East side: + text: East side + rel_samp_loc_enum: + name: rel_samp_loc_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + edge of car: + text: edge of car + center of car: + text: center of car + under a seat: + text: under a seat + rel_to_oxygen_enum: + name: rel_to_oxygen_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + aerobe: + text: aerobe + anaerobe: + text: anaerobe + facultative: + text: facultative + microaerophilic: + text: microaerophilic + microanaerobe: + text: microanaerobe + obligate aerobe: + text: obligate aerobe + obligate anaerobe: + text: obligate anaerobe + room_condt_enum: + name: room_condt_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + new: + text: new + visible wear: + text: visible wear + needs repair: + text: needs repair + damaged: + text: damaged + rupture: + text: rupture + visible signs of mold/mildew: + text: visible signs of mold/mildew + room_connected_enum: + name: room_connected_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + attic: + text: attic + bathroom: + text: bathroom + closet: + text: closet + conference room: + text: conference room + elevator: + text: elevator + examining room: + text: examining room + hallway: + text: hallway + kitchen: + text: kitchen + mail room: + text: mail room + office: + text: office + stairwell: + text: stairwell + room_loc_enum: + name: room_loc_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + corner room: + text: corner room + interior room: + text: interior room + exterior wall: + text: exterior wall + room_samp_pos_enum: + name: room_samp_pos_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + north corner: + text: north corner + south corner: + text: south corner + west corner: + text: west corner + east corner: + text: east corner + northeast corner: + text: northeast corner + northwest corner: + text: northwest corner + southeast corner: + text: southeast corner + southwest corner: + text: southwest corner + center: + text: center + room_type_enum: + name: room_type_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + attic: + text: attic + bathroom: + text: bathroom + closet: + text: closet + conference room: + text: conference room + elevator: + text: elevator + examining room: + text: examining room + hallway: + text: hallway + kitchen: + text: kitchen + mail room: + text: mail room + private office: + text: private office + open office: + text: open office + stairwell: + text: stairwell + ',restroom': + text: ',restroom' + lobby: + text: lobby + vestibule: + text: vestibule + mechanical or electrical room: + text: mechanical or electrical room + data center: + text: data center + laboratory_wet: + text: laboratory_wet + laboratory_dry: + text: laboratory_dry + gymnasium: + text: gymnasium + natatorium: + text: natatorium + auditorium: + text: auditorium + lockers: + text: lockers + cafe: + text: cafe + warehouse: + text: warehouse + samp_capt_status_enum: + name: samp_capt_status_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + active surveillance in response to an outbreak: + text: active surveillance in response to an outbreak + active surveillance not initiated by an outbreak: + text: active surveillance not initiated by an outbreak + farm sample: + text: farm sample + market sample: + text: market sample + other: + text: other + samp_collect_point_enum: + name: samp_collect_point_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + well: + text: well + test well: + text: test well + drilling rig: + text: drilling rig + wellhead: + text: wellhead + separator: + text: separator + storage tank: + text: storage tank + other: + text: other + samp_dis_stage_enum: + name: samp_dis_stage_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + dissemination: + text: dissemination + growth and reproduction: + text: growth and reproduction + infection: + text: infection + inoculation: + text: inoculation + penetration: + text: penetration + other: + text: other + samp_floor_enum: + name: samp_floor_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + 1st floor: + text: 1st floor + 2nd floor: + text: 2nd floor + basement: + text: basement + lobby: + text: lobby + samp_md_enum: + name: samp_md_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + DF: + text: DF + RT: + text: RT + KB: + text: KB + MSL: + text: MSL + other: + text: other + samp_subtype_enum: + name: samp_subtype_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + oil phase: + text: oil phase + water phase: + text: water phase + biofilm: + text: biofilm + not applicable: + text: not applicable + other: + text: other + samp_weather_enum: + name: samp_weather_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + clear sky: + text: clear sky + cloudy: + text: cloudy + foggy: + text: foggy + hail: + text: hail + rain: + text: rain + snow: + text: snow + sleet: + text: sleet + sunny: + text: sunny + windy: + text: windy + season_use_enum: + name: season_use_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + Spring: + text: Spring + Summer: + text: Summer + Fall: + text: Fall + Winter: + text: Winter + sediment_type_enum: + name: sediment_type_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + biogenous: + text: biogenous + cosmogenous: + text: cosmogenous + hydrogenous: + text: hydrogenous + lithogenous: + text: lithogenous + shading_device_cond_enum: + name: shading_device_cond_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + damaged: + text: damaged + needs repair: + text: needs repair + new: + text: new + rupture: + text: rupture + visible wear: + text: visible wear + shading_device_type_enum: + name: shading_device_type_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + bahama shutters: + text: bahama shutters + exterior roll blind: + text: exterior roll blind + gambrel awning: + text: gambrel awning + hood awning: + text: hood awning + porchroller awning: + text: porchroller awning + sarasota shutters: + text: sarasota shutters + slatted aluminum: + text: slatted aluminum + solid aluminum awning: + text: solid aluminum awning + sun screen: + text: sun screen + tree: + text: tree + trellis: + text: trellis + venetian awning: + text: venetian awning + soil_horizon_enum: + name: soil_horizon_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + O horizon: + text: O horizon + A horizon: + text: A horizon + E horizon: + text: E horizon + B horizon: + text: B horizon + C horizon: + text: C horizon + R layer: + text: R layer + Permafrost: + text: Permafrost + specific_enum: + name: specific_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + operation: + text: operation + as built: + text: as built + construction: + text: construction + bid: + text: bid + design: + text: design + photos: + text: photos + sr_dep_env_enum: + name: sr_dep_env_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + Lacustine: + text: Lacustine + Fluvioldeltaic: + text: Fluvioldeltaic + Fluviomarine: + text: Fluviomarine + Marine: + text: Marine + other: + text: other + sr_geol_age_enum: + name: sr_geol_age_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + Archean: + text: Archean + Cambrian: + text: Cambrian + Carboniferous: + text: Carboniferous + Cenozoic: + text: Cenozoic + Cretaceous: + text: Cretaceous + Devonian: + text: Devonian + Jurassic: + text: Jurassic + Mesozoic: + text: Mesozoic + Neogene: + text: Neogene + Ordovician: + text: Ordovician + Paleogene: + text: Paleogene + Paleozoic: + text: Paleozoic + Permian: + text: Permian + Precambrian: + text: Precambrian + Proterozoic: + text: Proterozoic + Silurian: + text: Silurian + Triassic: + text: Triassic + other: + text: other + sr_kerog_type_enum: + name: sr_kerog_type_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + Type I: + text: Type I + Type II: + text: Type II + Type III: + text: Type III + Type IV: + text: Type IV + other: + text: other + sr_lithology_enum: + name: sr_lithology_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + Clastic: + text: Clastic + Carbonate: + text: Carbonate + Coal: + text: Coal + Biosilicieous: + text: Biosilicieous + other: + text: other + substructure_type_enum: + name: substructure_type_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + crawlspace: + text: crawlspace + slab on grade: + text: slab on grade + basement: + text: basement + surf_air_cont_enum: + name: surf_air_cont_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + dust: + text: dust + organic matter: + text: organic matter + particulate matter: + text: particulate matter + volatile organic compounds: + text: volatile organic compounds + biological contaminants: + text: biological contaminants + radon: + text: radon + nutrients: + text: nutrients + biocides: + text: biocides + surf_material_enum: + name: surf_material_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + adobe: + text: adobe + carpet: + text: carpet + cinder blocks: + text: cinder blocks + concrete: + text: concrete + hay bales: + text: hay bales + glass: + text: glass + metal: + text: metal + paint: + text: paint + plastic: + text: plastic + stainless steel: + text: stainless steel + stone: + text: stone + stucco: + text: stucco + tile: + text: tile + vinyl: + text: vinyl + wood: + text: wood + tidal_stage_enum: + name: tidal_stage_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + low tide: + text: low tide + ebb tide: + text: ebb tide + flood tide: + text: flood tide + high tide: + text: high tide + tillage_enum: + name: tillage_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + drill: + text: drill + cutting disc: + text: cutting disc + ridge till: + text: ridge till + strip tillage: + text: strip tillage + zonal tillage: + text: zonal tillage + chisel: + text: chisel + tined: + text: tined + mouldboard: + text: mouldboard + disc plough: + text: disc plough + train_line_enum: + name: train_line_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + red: + text: red + green: + text: green + orange: + text: orange + train_stat_loc_enum: + name: train_stat_loc_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + south station above ground: + text: south station above ground + south station underground: + text: south station underground + south station amtrak: + text: south station amtrak + forest hills: + text: forest hills + riverside: + text: riverside + train_stop_loc_enum: + name: train_stop_loc_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + end: + text: end + mid: + text: mid + downtown: + text: downtown + vis_media_enum: + name: vis_media_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + photos: + text: photos + videos: + text: videos + commonly of the building: + text: commonly of the building + site context (adjacent buildings, vegetation, terrain, streets): + text: site context (adjacent buildings, vegetation, terrain, streets) + interiors: + text: interiors + equipment: + text: equipment + 3D scans: + text: 3D scans + wall_const_type_enum: + name: wall_const_type_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + frame construction: + text: frame construction + joisted masonry: + text: joisted masonry + light noncombustible: + text: light noncombustible + masonry noncombustible: + text: masonry noncombustible + modified fire resistive: + text: modified fire resistive + fire resistive: + text: fire resistive + wall_finish_mat_enum: + name: wall_finish_mat_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + plaster: + text: plaster + gypsum plaster: + text: gypsum plaster + veneer plaster: + text: veneer plaster + gypsum board: + text: gypsum board + tile: + text: tile + terrazzo: + text: terrazzo + stone facing: + text: stone facing + acoustical treatment: + text: acoustical treatment + wood: + text: wood + metal: + text: metal + masonry: + text: masonry + wall_loc_enum: + name: wall_loc_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + north: + text: north + south: + text: south + east: + text: east + west: + text: west + wall_surf_treatment_enum: + name: wall_surf_treatment_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + painted: + text: painted + wall paper: + text: wall paper + no treatment: + text: no treatment + paneling: + text: paneling + stucco: + text: stucco + fabric: + text: fabric + wall_texture_enum: + name: wall_texture_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + crows feet: + text: crows feet + crows-foot stomp: + text: crows-foot stomp + double skip: + text: double skip + hawk and trowel: + text: hawk and trowel + knockdown: + text: knockdown + popcorn: + text: popcorn + orange peel: + text: orange peel + rosebud stomp: + text: rosebud stomp + Santa-Fe texture: + text: Santa-Fe texture + skip trowel: + text: skip trowel + smooth: + text: smooth + stomp knockdown: + text: stomp knockdown + swirl: + text: swirl + water_feat_type_enum: + name: water_feat_type_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + fountain: + text: fountain + pool: + text: pool + standing feature: + text: standing feature + stream: + text: stream + waterfall: + text: waterfall + weekday_enum: + name: weekday_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + Monday: + text: Monday + Tuesday: + text: Tuesday + Wednesday: + text: Wednesday + Thursday: + text: Thursday + Friday: + text: Friday + Saturday: + text: Saturday + Sunday: + text: Sunday + window_cond_enum: + name: window_cond_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + damaged: + text: damaged + needs repair: + text: needs repair + new: + text: new + rupture: + text: rupture + visible wear: + text: visible wear + window_cover_enum: + name: window_cover_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + blinds: + text: blinds + curtains: + text: curtains + none: + text: none + window_horiz_pos_enum: + name: window_horiz_pos_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + left: + text: left + middle: + text: middle + right: + text: right + window_loc_enum: + name: window_loc_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + north: + text: north + south: + text: south + east: + text: east + west: + text: west + window_mat_enum: + name: window_mat_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + clad: + text: clad + fiberglass: + text: fiberglass + metal: + text: metal + vinyl: + text: vinyl + wood: + text: wood + window_type_enum: + name: window_type_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + single-hung sash window: + text: single-hung sash window + horizontal sash window: + text: horizontal sash window + fixed window: + text: fixed window + window_vert_pos_enum: + name: window_vert_pos_enum + from_schema: NMDC_enums_roundtrip + permissible_values: + bottom: + text: bottom + middle: + text: middle + top: + text: top + low: + text: low + high: + text: high + processing_institution_enum: + name: processing_institution_enum + comments: + - This will become the range of processing_institution.omics processing + - use ROR meanings like https://ror.org/0168r3w48 for UCSD + from_schema: NMDC_enums_roundtrip + permissible_values: + University of California, San Diego: + text: University of California, San Diego + meaning: https://ror.org/0168r3w48 + Joint Genome Institute: + text: Joint Genome Institute + meaning: https://ror.org/04xm1d337 + Environmental Molecular Sciences Laboratory: + text: Environmental Molecular Sciences Laboratory + meaning: https://ror.org/04rc0xn13 + comments: + - replaces Environmental Molecular Science Laboratory + - replaces Environmental Molecular Sciences Lab diff --git a/util/institution_classes.py b/util/institution_classes.py new file mode 100644 index 0000000000..7dc5b14585 --- /dev/null +++ b/util/institution_classes.py @@ -0,0 +1,46 @@ +from linkml_runtime import SchemaView + +schema_source = "../src/schema/nmdc.yaml" + +slots_to_classes = {} +classes_to_slots = {} + +print(f"Loading schema from {schema_source}") +schema_view = SchemaView(schema_source) +print(f"Loaded {schema_view.schema.name}") + +print(f"Getting slots") +all_slots = schema_view.all_slots() + +# print(type(all_slots)) +# + +# what do we trust? keys? .names? .alias? + +slot_keys = list(all_slots.keys()) + +print(f"Associating slots with induced classes") +all_classes = schema_view.all_classes() +for k, v in all_classes.items(): + i_c = schema_view.induced_class(k) + i_c_attribute_names = list(i_c.attributes.keys()) + classes_to_slots[k] = i_c_attribute_names + +# I'm still not convinced that these are useful: +# domain=None +# domain_of=[] + +print(f"Associating classes with slots") +for k, v in classes_to_slots.items(): + for i in v: + if i in slots_to_classes: + slots_to_classes[i].append(k) + else: + slots_to_classes[i] = [k] + +print(f"Finding slots with the substring 'institution'.") +institution_keys = [i for i in slot_keys if "institution" in i] + +print(f"Reporting classes that use a slot with the substring 'institution'") +for i in institution_keys: + print(f" {i}: {slots_to_classes[i]}") diff --git a/util/processing_institution_enum.yaml b/util/processing_institution_enum.yaml new file mode 100644 index 0000000000..5166db314b --- /dev/null +++ b/util/processing_institution_enum.yaml @@ -0,0 +1,19 @@ +processing_institution_enum: + name: processing_institution_enum + comments: + - This will become the range of processing_institution.omics processing + - use ROR meanings like https://ror.org/0168r3w48 for UCSD + from_schema: NMDC_enums_roundtrip + permissible_values: + University of California, San Diego: + text: University of California, San Diego + meaning: https://ror.org/0168r3w48 + Joint Genome Institute: + text: Joint Genome Institute + meaning: https://ror.org/04xm1d337 + Environmental Molecular Sciences Laboratory: + text: Environmental Molecular Sciences Laboratory + meaning: https://ror.org/04rc0xn13 + comments: + - replaces Environmental Molecular Science Laboratory + - replaces Environmental Molecular Sciences Lab \ No newline at end of file