coderdata.yaml

id: http://w3id.org/linkml/examples/coderdata
name: coderdata
prefixes:
   linkml: https://w3id.org/linkml
   coderdata: https://w3id.org/linkml/examples/coderdata
   schema: http://schema.org/
imports:
   - linkml:types
default_range: string
default_prefix: coderdata

slots:
  entrez_id:
    description: Gene id according to NCBI
    range: integer
  improve_sample_id:
    description: Unique sample identifier for this dataset, generated by this package
    identifier: true
    slot_uri: schema:identifier
    range: integer
  improve_drug_id:
    description: Unique identifier for this dataset, one for each smile string.
    identifier: true
    slot_uri: schema:identifier
  time:
    range: float
    description: Time at which measurement was administered, unit below.
  time_unit:
    description: Unit of time in which drug treatment was measured, e.g. minutes, hours, weeks.
  source:
    description: Source of data generated. 
  study:
    description: Study informatiom identifying where/when data was collected.
  other_id:
    description: other identifier
    recommended: true
    range: linkml:Any
  other_id_source:
    description: source of other identifier

classes:
  Gene:
    description: All genes used in coderdata
    slots:
      - entrez_id
      - other_id
      - other_id_source
    attributes:
      gene_symbol:
        required: true
        description: HGNC Gene symbol or synomym
  Sample:
    description: Unique samples identified for each experiment, used to cross reference omics data to drug data.
    slots:
      - improve_sample_id
      - other_id
      - other_id_source
    attributes:
      common_name:
        description: name for drug
        range: linkml:Any
      cancer_type:
        description: Type of cancer
      other_names:
        description: Other name for sample
        range: linkml:Any
      species:
        description: Species
      model_type:
        description: Type of model, must be confined to our existing set of definitions
        range: Models
  Drug:
    description: List of chemicals/drugs used in the data package. Each identifer corresponds to a distinct structure.
    slots:
      - improve_drug_id
    attributes:
      chem_name:
        description: Name of drug
        range: linkml:Any
      canSMILES:
        description: Canonical SMILE string
      isoSMILES:
        description: Isomeric SMILE string
      InChIKey:
        description: InChIKey
      formula:
        description: Chemical formula
      weight:
        description: Molecular weight
        range: linkml:Any
      pubchem_id:
        description: PubChem Identifier for this drug, can be many.
        range: int
  Drug Descriptor:
    description: Computational summary of drug chemical properties
    slots:
      - improve_drug_id
    attributes:
      structural_descriptor:
        description: string name describing structural descriptor
      descriptor_value:
        range: linkml:Any
        description: value representing descriptor value
  Transcriptomics:
    description:
    slots:
      - entrez_id
      - improve_sample_id
      - source
      - study
    attributes:
      transcriptomics:
         range: float
         description: Transcripts per million of sample at baseline.
  Proteomics:
    slots:
      - entrez_id
      - improve_sample_id
      - source
      - study
    attributes:
      proteomics:
         range: float
         description: Log-normalized log ratio of proteomics measurements of sample at baseline.
  Copy Number:
    slots:
      - entrez_id
      - improve_sample_id
      - source
      - study
    attributes:
      copy_number:
        range: float
        description: Copy number measurements of sample at baseline
      copy_call:
        range: CopyCall
        description: Categorical variable defining copy number measurement.
  Mutations:
    slots:
      - entrez_id
      - improve_sample_id
      - source
      - study
    attributes:
      mutation:
        description: Description of the mutation, when available. 
      variant_classification:
        description: Classification of the variant
        range: Variant
  Experiments:
    slots:
      - improve_drug_id
      - improve_sample_id
      - source
      - study
      - time
      - time_unit
    attributes:
      dose_response_metric:
        range: CurveMetric
        description: Metric by which dose response value is measured
      dose_response_value:
        description: Value of metric
        range: linkml:Any
  Perturbations:
    slots:
      - entrez_id
      - improve_sample_id
      - time
      - time_unit
      - source
      - study
    attributes:
      data_value:
        range: float
        description: Response value of the gene
      data_type:
        description: The value represented in the data value
      perturbation:
        description: Drug or gene id that was perturbed
        range: integer
      perturbation_type:
        description: The perturbagen that was used
        range: CellPerturbation
  Combinations:
    slots:
      - improve_sample_id
      - source
      - study
    attributes:
      drug_drug_2:
        description: improve_drug_id of first drug
      improve_drug_2:
        description: imrrove_drug_id of second drug
      drug_combination_metric:
        description: metric calculated for synergy, or other metric of two drugs
      drug_combination_value:
        description: value of metric for synergy or combination
enums:
  ResponseMetric:
    permissible_values:
      fit_auc:
        description: Area under the fitted curve
      fit_ic50:
        description: Concetration at which inhibitor binding is reduced by half
      fit_ec50:
        description: Concentration required to have half cells with adverse effect
      fit_ec50se:
        description: Standard error in EC50 calculation
      fit_einf:
        description: Fraction of cells not susceptible to the drug
      fit_hs:
        description: Hill slop binding cooperativity
      fit_r2:
        description: R2 value between fit and actual data
      aac:
        description: Area above curve measured by integrating the data points
      auc:
        description: Area under the curve measured by integrating data points
      dss:
        description: I believe this is the drug sensitivity score
      mrecist:
        description: For PDX data this value should be either Progressive Disease, Stable Disease, Partial Response or Complete Response.
      gc_auc:
        description: Area under tumor growth curve
      efs:
        description: event free survival
      os:
        description: overall survival
      tgi:
        description: tumor growth inhibitiojn
      kulgap:
        description: kl divergence based metric
  CellPerturbation:
    permissible_values:
      gene_ko:
        description: Gene loss via CRISPR or other screen
      drug:
        description: Drug treatment
  Models:
    permissible_values:
      cell line:
      organoid:
      tumor:
      patient derived xenograft:
      ex vivo:
  Variant:
    permissible_values:
      3'UTR:
      3'Flank:
      5'Flank:
      5'UTR:
      Undetermined:
      De_novo_Start_InFrame:
      De_novo_Start_OutOfFrame:
      Frame_Shift_Del:
      Frame_Shift_Ins:
      Frameshift_Variant:
      Protein_Altering_Variant:
      IGR:
      In_Frame_Del:
      In_Frame_Ins:
      Intron:
      Missense_Mutation:
      Nonsense_Mutation:
      Nonstop_Mutation:
      RNA:
      Start_Codon_SNP:
      Start_Codon_Del:
      Start_Codon_Ins:      
      Stop_Codon_Del:
      Stop_Codon_Ins:
      Silent:
      Splice_Site:
      Splice_Region:
      Translation_Start_Site:
  CopyCall:
    permissible_values:
      amp:
      gain:
      diploid:
      het loss:
      deep del: