DataSubstrate.yaml

---
data_substrates_collection:
  - id: B2AI_SUBSTRATE:1
    name: Array
    subclass_of:
      - B2AI_SUBSTRATE:7
    edam_id: edam.data:2082
    ncit_id: ncit:C26358
    category: B2AI_SUBSTRATE:DataSubstrate
    description:
      A data type that represents a collection of elements (values or variables),
      each selected by one or more indices.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
    related_to:
      - B2AI_STANDARD:392
      - B2AI_STANDARD:394
      - B2AI_STANDARD:722
      - B2AI_STANDARD:834
  - id: B2AI_SUBSTRATE:2
    name: Associative Array
    subclass_of:
      - B2AI_SUBSTRATE:1
    category: B2AI_SUBSTRATE:DataSubstrate
    description:
      A data structure that stores a collection of key-value pairs, where
      each key is associated with a value. It allows for fast and efficient lookups
      by using the keys as indices to access the corresponding values.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:3
    name: BIDS
    subclass_of:
      - B2AI_SUBSTRATE:19
      - B2AI_SUBSTRATE:49
    related_to:
      - B2AI_STANDARD:33
    metadata_storage:
      - JSON
    category: B2AI_SUBSTRATE:DataSubstrate
    description: Data conforming to the Brain Imaging Data Structure (BIDS).
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:4
    name: BigQuery
    subclass_of:
      - B2AI_SUBSTRATE:5
    related_to:
      - B2AI_STANDARD:735
    category: B2AI_SUBSTRATE:DataSubstrate
    description:
      A fully managed, serverless data warehouse that enables scalable analysis
      over petabytes of data. It is a Platform as a Service (PaaS) that supports querying
      using ANSI SQL.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:5
    name: Column Store
    subclass_of:
      - B2AI_SUBSTRATE:9
    category: B2AI_SUBSTRATE:DataSubstrate
    description: A database that stores data tables by column rather than by row.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:6
    name: Comma-separated values
    subclass_of:
      - B2AI_SUBSTRATE:10
    edam_id: edam.format:3752
    ncit_id: ncit:C182456
    file_extensions:
      - csv
    limitations:
      - Differences in newline characters can cause inconsistency across operating systems.
    category: B2AI_SUBSTRATE:DataSubstrate
    description:
      Any text or mixed data with distinct records in columns separated by
      commas and rows separated by newlines.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
    related_to:
      - B2AI_STANDARD:347
      - B2AI_STANDARD:378
      - B2AI_STANDARD:783
      - B2AI_STANDARD:878
  - id: B2AI_SUBSTRATE:7
    name: Data
    edam_id: edam.data:0006
    mesh_id: mesh:D064886
    ncit_id: ncit:C25474
    category: B2AI_SUBSTRATE:DataSubstrate
    description: Any collection of discrete values conveying information.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:8
    name: Data Frame
    subclass_of:
      - B2AI_SUBSTRATE:7
    category: B2AI_SUBSTRATE:DataSubstrate
    description:
      A data structure that organizes data into a 2-dimensional table of
      rows and columns.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
    related_to:
      - B2AI_STANDARD:813
      - B2AI_STANDARD:862
  - id: B2AI_SUBSTRATE:9
    name: Database
    subclass_of:
      - B2AI_SUBSTRATE:7
    mesh_id: mesh:D019991
    ncit_id: ncit:C15426
    category: B2AI_SUBSTRATE:DataSubstrate
    description:
      An organized collection of structured information, stored electronically
      and organized for rapid search and retrieval.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
    related_to:
      - B2AI_STANDARD:202
      - B2AI_STANDARD:712
      - B2AI_STANDARD:797
      - B2AI_STANDARD:801
      - B2AI_STANDARD:802
      - B2AI_STANDARD:815
      - B2AI_STANDARD:861
      - B2AI_STANDARD:871
  - id: B2AI_SUBSTRATE:10
    name: Delimited Text
    subclass_of:
      - B2AI_SUBSTRATE:43
    edam_id: edam.format:3751
    file_extensions:
      - txt
    category: B2AI_SUBSTRATE:DataSubstrate
    description:
      Any data with distinct records separated or delimited by a specific
      character pattern.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:11
    name: DICOM
    subclass_of:
      - B2AI_SUBSTRATE:36
    related_to:
      - B2AI_STANDARD:8
      - B2AI_STANDARD:79
      - B2AI_STANDARD:80
      - B2AI_STANDARD:81
      - B2AI_STANDARD:82
      - B2AI_STANDARD:83
      - B2AI_STANDARD:84
      - B2AI_STANDARD:85
      - B2AI_STANDARD:86
      - B2AI_STANDARD:87
      - B2AI_STANDARD:88
      - B2AI_STANDARD:89
      - B2AI_STANDARD:90
      - B2AI_STANDARD:91
      - B2AI_STANDARD:92
      - B2AI_STANDARD:93
      - B2AI_STANDARD:94
      - B2AI_STANDARD:95
      - B2AI_STANDARD:96
      - B2AI_STANDARD:97
      - B2AI_STANDARD:98
      - B2AI_STANDARD:849
    metadata_storage:
      - File headers
    edam_id: edam.format:3548
    ncit_id: ncit:C63537
    file_extensions:
      - dicom
      - dcm
    limitations:
      - Files are generally named using unique identifiers that may not be compatible
        across all operating systems (i.e., they may be too long).
      - Patient data is included in each image file header so all files must be processed
        in order to anonymize them.
    category: B2AI_SUBSTRATE:DataSubstrate
    description: An image and metadata format for radiology imaging.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:12
    name: Directed acyclic graph
    subclass_of:
      - B2AI_SUBSTRATE:14
    ncit_id: ncit:C45803
    category: B2AI_SUBSTRATE:DataSubstrate
    description: A directed graph with no directed cycles.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:13
    name: Document Database
    subclass_of:
      - B2AI_SUBSTRATE:9
    related_to:
      - B2AI_STANDARD:797
    category: B2AI_SUBSTRATE:DataSubstrate
    description: A database that stores and retrieves information in documents.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:14
    name: Graph
    subclass_of:
      - B2AI_SUBSTRATE:7
    related_to:
      - B2AI_STANDARD:768
      - B2AI_STANDARD:802
    edam_id: edam.format:3617
    ncit_id: ncit:C75914
    category: B2AI_SUBSTRATE:DataSubstrate
    description:
      A structure of nodes (sometimes called vertices) and edges between
      them.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:15
    name: Graph Database
    subclass_of:
      - B2AI_SUBSTRATE:9
      - B2AI_SUBSTRATE:14
    related_to:
      - B2AI_STANDARD:768
      - B2AI_STANDARD:802
    category: B2AI_SUBSTRATE:DataSubstrate
    description:
      A type of database that stores nodes and relationships instead of tables
      or documents.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:16
    name: HDF5
    subclass_of:
      - B2AI_SUBSTRATE:18
    related_to:
      - B2AI_STANDARD:71
      - B2AI_STANDARD:218
      - B2AI_STANDARD:339
      - B2AI_STANDARD:340
      - B2AI_STANDARD:379
    edam_id: edam.format:3590
    ncit_id: ncit:C184763
    file_extensions:
      - h5
      - hdf5
    limitations:
      - Structure is not optimized for data access through cloud storage infrastructure.
    category: B2AI_SUBSTRATE:DataSubstrate
    description:
      A data model, library, and file format for storing and managing data.
      It supports an unlimited variety of datatypes, and is designed for flexible and
      efficient I/O and for high volume and complex data.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:17
    name: Heap
    subclass_of:
      - Tree
    category: B2AI_SUBSTRATE:DataSubstrate
    description: A complete binary tree, i.e., each node has no more than two children.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:18
    name: Hierarchical Array
    subclass_of:
      - B2AI_SUBSTRATE:1
    category: B2AI_SUBSTRATE:DataSubstrate
    description:
      A data structure of a list, such that list elements may be subsets
      of other elements.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:19
    name: Image
    subclass_of:
      - B2AI_SUBSTRATE:7
    related_to:
      - B2AI_STANDARD:98
      - B2AI_STANDARD:307
      - B2AI_STANDARD:316
      - B2AI_STANDARD:344
      - B2AI_STANDARD:362
      - B2AI_STANDARD:375
      - B2AI_STANDARD:377
      - B2AI_STANDARD:383
      - B2AI_STANDARD:390
    edam_id: edam.data:2968
    ncit_id: ncit:C48179
    category: B2AI_SUBSTRATE:DataSubstrate
    description: Any visual representation of something.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:20
    name: JSON
    subclass_of:
      - B2AI_SUBSTRATE:2
      - B2AI_SUBSTRATE:18
    edam_id: edam.format:3464
    ncit_id: ncit:C184769
    file_extensions:
      - json
    category: B2AI_SUBSTRATE:DataSubstrate
    description:
      JavaScript Object Notation (JSON) is a lightweight format for storing
      and transporting data.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:21
    name: KGX TSV
    subclass_of:
      - B2AI_SUBSTRATE:32
      - B2AI_SUBSTRATE:41
    related_to:
      - B2AI_STANDARD:346
    file_extensions:
      - tsv
    category: B2AI_SUBSTRATE:DataSubstrate
    description: A tab-delimited data format for exchanging property graph data.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:22
    name: MongoDB
    subclass_of:
      - B2AI_SUBSTRATE:13
    related_to:
      - B2AI_STANDARD:797
    file_extensions:
      - mongo
    limitations:
      - The maximum size of an individual document in MongoDB is 16MB with a nested depth
        of 100 levels.
    category: B2AI_SUBSTRATE:DataSubstrate
    description:
      A non-relational document database that provides support for JSON-like
      storage.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:23
    name: MySQL
    subclass_of:
      - B2AI_SUBSTRATE:37
    related_to:
      - B2AI_STANDARD:801
    file_extensions:
      - mysql
      - sql
    category: B2AI_SUBSTRATE:DataSubstrate
    description:
      A relational database management system developed by Oracle that is
      based on structured query language (SQL).
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:24
    name: N-Dimensional Array
    subclass_of:
      - B2AI_SUBSTRATE:1
    category: B2AI_SUBSTRATE:DataSubstrate
    description:
      A data structure that can store a collection of items, where each item
      is identified by a set of indices. The number of indices required to identify
      an item is referred to as the dimension of the array, hence the name N-dimensional
      array.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:25
    name: Neo4j
    subclass_of:
      - B2AI_SUBSTRATE:15
    related_to:
      - B2AI_STANDARD:802
    limitations:
      - All data is stored locally - this can cause slowdowns when data exceeds available
        memory.
    category: B2AI_SUBSTRATE:DataSubstrate
    description: A popular graph database platform.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:26
    name: Neural Network Model
    subclass_of:
      - B2AI_SUBSTRATE:7
    mesh_id: mesh:D016571
    ncit_id: ncit:C17429
    category: B2AI_SUBSTRATE:DataSubstrate
    description: The result of training a neural network on a certain set of inputs.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:27
    name: NNEF
    subclass_of:
      - B2AI_SUBSTRATE:26
    related_to:
      - B2AI_STANDARD:354
    file_extensions:
      - nnef
    category: B2AI_SUBSTRATE:DataSubstrate
    description:
      An exchange format for neural network models produced using Torch,
      Caffe, TensorFlow, Theano, Chainer, Caffe2, PyTorch, or MXNet.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:28
    name: ONNX
    subclass_of:
      - B2AI_SUBSTRATE:26
    related_to:
      - B2AI_STANDARD:357
    file_extensions:
      - onnx
    category: B2AI_SUBSTRATE:DataSubstrate
    description: An open format built to represent machine learning models.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:29
    name: Pandas DataFrame
    subclass_of:
      - B2AI_SUBSTRATE:8
    related_to:
      - B2AI_STANDARD:813
    category: B2AI_SUBSTRATE:DataSubstrate
    description:
      A two-dimensional, size-mutable, potentially heterogeneous tabular
      data object.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:30
    name: Parquet
    subclass_of:
      - B2AI_SUBSTRATE:5
    related_to:
      - B2AI_STANDARD:359
    file_extensions:
      - parquet
      - pqt
    category: B2AI_SUBSTRATE:DataSubstrate
    description:
      Apache Parquet is a free and open-source column-oriented data storage
      format in the Apache Hadoop ecosystem.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:31
    name: PostgreSQL
    subclass_of:
      - B2AI_SUBSTRATE:37
    related_to:
      - B2AI_STANDARD:815
    file_extensions:
      - sql
    category: B2AI_SUBSTRATE:DataSubstrate
    description:
      An open-source relational database management system emphasizing extensibility
      and SQL compliance.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:32
    name: Property graph
    subclass_of:
      - B2AI_SUBSTRATE:14
    category: B2AI_SUBSTRATE:DataSubstrate
    description:
      A graph model in which nodes and edges may be assigned properties (i.e.,
      values or key-value pairs).
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:33
    name: PyTorch Tensor
    subclass_of:
      - B2AI_SUBSTRATE:42
    related_to:
      - B2AI_STANDARD:354
      - B2AI_STANDARD:401
      - B2AI_STANDARD:765
      - B2AI_STANDARD:788
      - B2AI_STANDARD:816
    category: B2AI_SUBSTRATE:DataSubstrate
    description:
      In PyTorch, a torch.Tensor is a multi-dimensional matrix containing
      elements of a single data type.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:34
    name: R data.frame
    subclass_of:
      - B2AI_SUBSTRATE:8
    related_to:
      - B2AI_STANDARD:833
    limitations:
      - Memory-limited.
    category: B2AI_SUBSTRATE:DataSubstrate
    description:
      A tightly coupled collection of variables that shares many of the properties
      of matrices and of lists.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:35
    name: R tibble
    subclass_of:
      - B2AI_SUBSTRATE:8
    related_to:
      - B2AI_STANDARD:833
    category: B2AI_SUBSTRATE:DataSubstrate
    description:
      A redesigned version of an R data frame. Never changes the input type,
      can have columns that are lists, can have non-standard variable names, can start
      with a number or contain spaces, only recycles vectors of length 1, and never
      creates row names.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:36
    name: Raster Image
    subclass_of:
      - B2AI_SUBSTRATE:19
    category: B2AI_SUBSTRATE:DataSubstrate
    description:
      Any visual representation of something represented as a two-dimensional
      matrix of pixel values denoting intensity, potentially accompanied by other values
      for colors or other image properties (e.g., compression).
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:37
    name: Relational Database
    subclass_of:
      - B2AI_SUBSTRATE:9
    related_to:
      - B2AI_STANDARD:801
      - B2AI_STANDARD:815
    category: B2AI_SUBSTRATE:DataSubstrate
    description:
      A database that stores and provides access to data points related to
      one another.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:38
    name: Set
    subclass_of:
      - B2AI_SUBSTRATE:7
    category: B2AI_SUBSTRATE:DataSubstrate
    description: A sorted data structure of unique elements of the same type.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:39
    name: String
    subclass_of:
      - B2AI_SUBSTRATE:7
    ncit_id: ncit:C45253
    category: B2AI_SUBSTRATE:DataSubstrate
    description:
      An array data structure of bytes (or words) that stores a sequence
      of elements, typically characters, using some character encoding.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:40
    name: SummarizedExperiment
    subclass_of:
      - B2AI_SUBSTRATE:18
    related_to:
      - B2AI_STANDARD:705
      - B2AI_STANDARD:833
      - B2AI_STANDARD:286
    category: B2AI_SUBSTRATE:DataSubstrate
    description:
      The SummarizedExperiment Bioconductor container contains one or more
      assays, each represented by a matrix-like object of numeric or other mode. The
      rows typically represent genomic ranges of interest and the columns represent
      samples.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:41
    name: Tab-separated values
    subclass_of:
      - B2AI_SUBSTRATE:10
    edam_id: edam.format:3475
    ncit_id: ncit:C164049
    file_extensions:
      - tsv
    limitations:
      - Differences in newline characters can cause inconsistency across operating systems.
    category: B2AI_SUBSTRATE:DataSubstrate
    description:
      Any text or mixed data with distinct records in columns separated by
      tab characters and rows separated by newlines.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:42
    name: Tensor
    subclass_of:
      - B2AI_SUBSTRATE:7
    related_to:
      - B2AI_STANDARD:354
      - B2AI_STANDARD:374
      - B2AI_STANDARD:770
      - B2AI_STANDARD:831
    category: B2AI_SUBSTRATE:DataSubstrate
    description:
      An algebraic object that describes a multilinear relationship between
      sets of algebraic objects related to a vector space.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:43
    name: Text
    subclass_of:
      - B2AI_SUBSTRATE:39
    edam_id: edam.data:2526
    ncit_id: ncit:C25704
    file_extensions:
      - txt
    category: B2AI_SUBSTRATE:DataSubstrate
    description:
      Any form of written information that is composed of letters, words,
      and sentences. This may include anything from written documents, articles, or
      books, to emails, social media posts, and transcribed speech. It may also include
      unstructured, human-readable fields of documents containing other data.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:44
    name: Tree
    subclass_of:
      - B2AI_SUBSTRATE:14
    ncit_id: ncit:C45418
    category: B2AI_SUBSTRATE:DataSubstrate
    description:
      An undirected graph with each pair of vertices connected by no more
      than one path. Also known as a connected acyclic undirected graph.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:45
    name: Trie
    subclass_of:
      - B2AI_SUBSTRATE:44
    category: B2AI_SUBSTRATE:DataSubstrate
    description: A sorted, associative tree. Also known as a radix tree or prefix tree.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:46
    name: Vector
    subclass_of:
      - B2AI_SUBSTRATE:7
    ncit_id: ncit:C54169
    category: B2AI_SUBSTRATE:DataSubstrate
    description:
      A mathematical object that has magnitude and direction. A vector is
      often represented as a one-dimensional array or list with numerical elements.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:47
    name: Vector Image
    subclass_of:
      - B2AI_SUBSTRATE:19
    category: B2AI_SUBSTRATE:DataSubstrate
    description:
      Any visual representation of something represented as a set of geometric
      shapes defined on a Cartesian plane.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:48
    name: Waveform Audio File Format
    subclass_of:
      - B2AI_SUBSTRATE:49
    related_to:
      - B2AI_STANDARD:387
    metadata_storage:
      - File headers
    file_extensions:
      - wav
    category: B2AI_SUBSTRATE:DataSubstrate
    description:
      An audio file format standard. Generally supported by digital audio
      software.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:49
    name: Waveform Data
    subclass_of:
      - B2AI_SUBSTRATE:7
    related_to:
      - B2AI_STANDARD:308
      - B2AI_STANDARD:314
      - B2AI_STANDARD:315
      - B2AI_STANDARD:331
      - B2AI_STANDARD:351
      - B2AI_STANDARD:352
      - B2AI_STANDARD:356
      - B2AI_STANDARD:387
    category: B2AI_SUBSTRATE:DataSubstrate
    description: The two-dimensional representation of a signal as a function of time.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:50
    name: xarray
    subclass_of:
      - B2AI_SUBSTRATE:24
    related_to:
      - B2AI_STANDARD:392
    category: B2AI_SUBSTRATE:DataSubstrate
    description:
      A format for defining arrays with labels in the form of dimensions,
      coordinates, and attributes on top of raw NumPy-like arrays, which allows for
      more intuitive, more concise, and less error-prone user experience.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:51
    name: Zarr
    subclass_of:
      - B2AI_SUBSTRATE:24
    related_to:
      - B2AI_STANDARD:394
    edam_id: edam.format:3915
    file_extensions:
      - zarr
    category: B2AI_SUBSTRATE:DataSubstrate
    description:
      A format for storage of large N-dimensional typed arrays. Has implementations
      in multiple programming languages.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:52
    name: Compressed Data
    subclass_of:
      - B2AI_SUBSTRATE:7
    related_to:
      - B2AI_STANDARD:384
      - B2AI_STANDARD:395
    ncit_id: ncit:C190416
    file_extensions:
      - tar
      - zip
    limitations:
      - Must be decompressed before reading.
      - Compression may be lossy, i.e., it discards information in the process of encoding.
    category: B2AI_SUBSTRATE:DataSubstrate
    description:
      Data in which information is represented with fewer bits than the original,
      uncompressed representation.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:53
    name: BED
    subclass_of:
      - B2AI_SUBSTRATE:10
    related_to:
      - B2AI_STANDARD:36
    metadata_storage:
      - File headers
    edam_id: edam.format:3003
    ncit_id: ncit:C153367
    file_extensions:
      - txt
      - bed
    category: B2AI_SUBSTRATE:DataSubstrate
    description:
      BED (Browser Extensible Data) format provides a flexible way to define
      the data lines that are displayed in a genome annotation track.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
  - id: B2AI_SUBSTRATE:54
    name: Vector Database
    subclass_of:
      - B2AI_SUBSTRATE:9
    related_to:
      - B2AI_STANDARD:871
    category: B2AI_SUBSTRATE:DataSubstrate
    description: A database that stores and retrieves information represented as high-dimensional vectors. The original data may be very unstructured.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: ORCID:0000-0001-5705-7831
    contribution_date: "2023-05-23"
  - id: B2AI_SUBSTRATE:55
    name: Pinecone
    category: B2AI_SUBSTRATE:DataSubstrate
    subclass_of:
      - B2AI_SUBSTRATE:54
    description: A vector database. Includes a single-stage filtering function allowing complex searches in single queries.
    contributor_name: Harry Caufield
    contributor_github_name: caufieldjh
    contributor_orcid: 0000-0001-5705-7831
    contribution_date: "2023-05-23"