chemicalml 0.1.0 → 0.2.1

data/data/dictionaries/cif.yaml

@@ -0,0 +1,155 @@
+# CIF Core Definitions Dictionary
+#
+# Source: http://www.xml-cml.org/dictionary/cif/
+# License: CC-BY-3.0 (http://creativecommons.org/licenses/by/3.0/)
+#
+# Derived from the Crystallographic Information File (CIF) core
+# dictionary. Covers crystallographic concepts referenced from CML
+# crystal elements and properties.
+
+---
+namespace: http://www.xml-cml.org/dictionary/cif/
+prefix: cif
+title: CIF Core Definitions
+description: |
+  Crystallographic concepts from the CIF core dictionary, mapped
+  to CML dictionary entries. Used with the CML <crystal> element
+  and crystallographic properties.
+
+entries:
+  - id: cell_length_a
+    term: Unit Cell Length a
+    definition: The length of the unit cell a axis.
+    data_type: xsd:double
+    unit_type: unitType:length
+    units: unit:angstrom
+
+  - id: cell_length_b
+    term: Unit Cell Length b
+    definition: The length of the unit cell b axis.
+    data_type: xsd:double
+    unit_type: unitType:length
+    units: unit:angstrom
+
+  - id: cell_length_c
+    term: Unit Cell Length c
+    definition: The length of the unit cell c axis.
+    data_type: xsd:double
+    unit_type: unitType:length
+    units: unit:angstrom
+
+  - id: cell_angle_alpha
+    term: Unit Cell Angle Alpha
+    definition: The inter-axial angle between the b and c cell axes.
+    data_type: xsd:double
+    unit_type: unitType:angle
+    units: unit:degree
+
+  - id: cell_angle_beta
+    term: Unit Cell Angle Beta
+    definition: The inter-axial angle between the a and c cell axes.
+    data_type: xsd:double
+    unit_type: unitType:angle
+    units: unit:degree
+
+  - id: cell_angle_gamma
+    term: Unit Cell Angle Gamma
+    definition: The inter-axial angle between the a and b cell axes.
+    data_type: xsd:double
+    unit_type: unitType:angle
+    units: unit:degree
+
+  - id: cell_volume
+    term: Unit Cell Volume
+    definition: The volume of the crystallographic unit cell.
+    data_type: xsd:double
+    unit_type: unitType:volume
+    units: unit:angstrom3
+
+  - id: cell_formula_units
+    term: Formula Units Per Cell (Z)
+    definition: The number of formula units in the unit cell.
+    data_type: xsd:integer
+    unit_type: unitType:dimensionless
+
+  - id: crystal_system
+    term: Crystal System
+    definition: One of the seven crystal systems (triclinic, monoclinic, orthorhombic, tetragonal, trigonal, hexagonal, cubic).
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+    enum:
+      kind: closed
+      values:
+        - triclinic
+        - monoclinic
+        - orthorhombic
+        - tetragonal
+        - trigonal
+        - hexagonal
+        - cubic
+
+  - id: space_group_name
+    term: Space Group Name
+    definition: The Hermann-Mauguin symbol for the crystal space group.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+
+  - id: space_group_number
+    term: Space Group Number
+    definition: The International Tables space group number (1-230).
+    data_type: xsd:integer
+    unit_type: unitType:dimensionless
+
+  - id: symmetry_equiv_pos
+    term: Symmetry Equivalent Position
+    definition: A symmetry-equivalent atomic position in fractional coordinates.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+
+  - id: atom_site_fract_x
+    term: Atom Fractional X
+    definition: The x coordinate of an atom in fractional cell units.
+    data_type: xsd:double
+    unit_type: unitType:dimensionless
+
+  - id: atom_site_fract_y
+    term: Atom Fractional Y
+    definition: The y coordinate of an atom in fractional cell units.
+    data_type: xsd:double
+    unit_type: unitType:dimensionless
+
+  - id: atom_site_fract_z
+    term: Atom Fractional Z
+    definition: The z coordinate of an atom in fractional cell units.
+    data_type: xsd:double
+    unit_type: unitType:dimensionless
+
+  - id: atom_site_occupancy
+    term: Atom Site Occupancy
+    definition: The fractional occupancy of an atomic site.
+    data_type: xsd:double
+    unit_type: unitType:dimensionless
+
+  - id: atom_site_B_iso
+    term: Atom Isotropic B Factor
+    definition: The isotropic atomic displacement parameter (B factor).
+    data_type: xsd:double
+    unit_type: unitType:area
+    units: unit:angstrom2
+
+  - id: diffrn_radiation_wavelength
+    term: Radiation Wavelength
+    definition: The wavelength of the radiation used in diffraction.
+    data_type: xsd:double
+    unit_type: unitType:length
+    units: unit:angstrom
+
+  - id: refln_d_resolution
+    term: Resolution (d-spacing)
+    definition: The highest-resolution d-spacing in the diffraction data.
+    data_type: xsd:double
+    unit_type: unitType:length
+    units: unit:angstrom

data/data/dictionaries/cml.yaml

@@ -0,0 +1,172 @@
+# CML Fundamental Chemistry Concepts Dictionary
+#
+# Source: http://www.xml-cml.org/dictionary/cml/
+# License: CC-BY-3.0 (http://creativecommons.org/licenses/by/3.0/)
+
+---
+namespace: http://www.xml-cml.org/dictionary/cml/
+prefix: cml
+title: Fundamental Chemistry Concepts
+description: |
+  Common chemistry concepts referenced from CML attributes and
+  properties. These cover molar mass, boiling/melting points,
+  density, and other fundamental physical properties.
+
+entries:
+  - id: molmass
+    term: Molar Mass
+    definition: The mass of one mole of a substance.
+    data_type: xsd:double
+    unit_type: unitType:mass
+    units: unit:g
+
+  - id: bp
+    term: Boiling Point
+    definition: The temperature at which a substance boils at standard pressure.
+    data_type: xsd:double
+    unit_type: unitType:temperature
+    units: unit:K
+
+  - id: mp
+    term: Melting Point
+    definition: The temperature at which a substance melts at standard pressure.
+    data_type: xsd:double
+    unit_type: unitType:temperature
+    units: unit:K
+
+  - id: density
+    term: Density
+    definition: Mass per unit volume of a substance.
+    data_type: xsd:double
+    unit_type: unitType:density
+    units: unit:g_cm3
+
+  - id: refractiveIndex
+    term: Refractive Index
+    definition: The ratio of the speed of light in a vacuum to that in the substance.
+    data_type: xsd:double
+    unit_type: unitType:dimensionless
+
+  - id: solubility
+    term: Solubility
+    definition: The maximum amount of solute that dissolves in a solvent at a given temperature.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+
+  - id: vaporPressure
+    term: Vapor Pressure
+    definition: The pressure exerted by a vapor in equilibrium with its condensed phases.
+    data_type: xsd:double
+    unit_type: unitType:pressure
+    units: unit:Pa
+
+  - id: flashPoint
+    term: Flash Point
+    definition: The lowest temperature at which a liquid gives off enough vapor to ignite.
+    data_type: xsd:double
+    unit_type: unitType:temperature
+    units: unit:K
+
+  - id: autoignitionTemp
+    term: Autoignition Temperature
+    definition: The lowest temperature at which a substance spontaneously ignites.
+    data_type: xsd:double
+    unit_type: unitType:temperature
+    units: unit:K
+
+  - id: pH
+    term: pH
+    definition: The negative logarithm of the hydrogen ion concentration.
+    data_type: xsd:double
+    unit_type: unitType:dimensionless
+
+  - id: viscosity
+    term: Viscosity
+    definition: A measure of a fluid's resistance to flow.
+    data_type: xsd:double
+    unit_type: unitType:viscosity
+    units: unit:Pa_s
+
+  - id: surfaceTension
+    term: Surface Tension
+    definition: The force per unit length acting along the surface of a liquid.
+    data_type: xsd:double
+    unit_type: unitType:surfaceTension
+    units: unit:N_m
+
+  - id: dipoleMoment
+    term: Dipole Moment
+    definition: The electric dipole moment of a molecule.
+    data_type: xsd:double
+    unit_type: unitType:dipoleMoment
+    units: unit:D
+
+  - id: polarizability
+    term: Polarizability
+    definition: The tendency of a charge distribution to be distorted by an external electric field.
+    data_type: xsd:double
+    unit_type: unitType:polarizability
+    units: unit:A3
+
+  - id: heatOfFormation
+    term: Heat of Formation
+    definition: The enthalpy change when one mole of a compound is formed from its elements.
+    data_type: xsd:double
+    unit_type: unitType:energy
+    units: unit:kJ_mol
+
+  - id: entropy
+    term: Entropy
+    definition: A measure of the disorder or randomness in a system.
+    data_type: xsd:double
+    unit_type: unitType:entropy
+    units: unit:J_molK
+
+  - id: freeEnergy
+    term: Gibbs Free Energy
+    definition: The thermodynamic potential that measures the maximum reversible work.
+    data_type: xsd:double
+    unit_type: unitType:energy
+    units: unit:kJ_mol
+
+  - id: ionizationEnergy
+    term: Ionization Energy
+    definition: The energy required to remove an electron from a gaseous atom or ion.
+    data_type: xsd:double
+    unit_type: unitType:energy
+    units: unit:eV
+
+  - id: electronAffinity
+    term: Electron Affinity
+    definition: The energy change when an electron is added to a neutral atom.
+    data_type: xsd:double
+    unit_type: unitType:energy
+    units: unit:eV
+
+  - id: electronegativity
+    term: Electronegativity
+    definition: A measure of the tendency of an atom to attract bonding electrons.
+    data_type: xsd:double
+    unit_type: unitType:dimensionless
+
+  - id: bondEnergy
+    term: Bond Energy
+    definition: The energy required to break one mole of a specific bond in a substance.
+    data_type: xsd:double
+    unit_type: unitType:energy
+    units: unit:kJ_mol
+
+  - id: bondLength
+    term: Bond Length
+    definition: The average distance between nuclei of two bonded atoms.
+    data_type: xsd:double
+    unit_type: unitType:length
+    units: unit:angstrom
+
+  - id: bondAngle
+    term: Bond Angle
+    definition: The angle formed between two adjacent bonds at a common atom.
+    data_type: xsd:double
+    unit_type: unitType:angle
+    units: unit:degree

data/data/dictionaries/cml_formula.yaml

@@ -0,0 +1,63 @@
+# CML Chemical Formula Conventions Dictionary
+#
+# Source: http://www.xml-cml.org/dictionary/cml/formula/
+# License: CC-BY-3.0 (http://creativecommons.org/licenses/by/3.0/)
+
+---
+namespace: http://www.xml-cml.org/dictionary/cml/formula/
+prefix: cmlFormula
+title: Chemical Formula Conventions
+description: |
+  Conventions for identifying the formula representation used in
+  CML <formula> elements. The dictRef or convention attribute
+  on a <formula> points to one of these entries.
+
+entries:
+  - id: empirical
+    term: Empirical Formula
+    definition: The simplest whole-number ratio of atoms in a compound.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+
+  - id: molecular
+    term: Molecular Formula
+    definition: The actual number of atoms of each element in a molecule.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+
+  - id: structural
+    term: Structural Formula
+    definition: A formula showing the arrangement of atoms in a molecule.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+
+  - id: condensed
+    term: Condensed Formula
+    definition: A formula written on a single line showing element groups.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+
+  - id: hill
+    term: Hill System Formula
+    definition: A formula following the Hill system ordering convention.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+
+  - id: smiles
+    term: SMILES Formula
+    definition: A formula expressed in SMILES line notation.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+
+  - id: latex
+    term: LaTeX Formula
+    definition: A formula expressed using LaTeX markup.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none

data/data/dictionaries/cml_name.yaml

@@ -0,0 +1,84 @@
+# CML Chemical Naming Conventions Dictionary
+#
+# Source: http://www.xml-cml.org/dictionary/cml/name/
+# License: CC-BY-3.0 (http://creativecommons.org/licenses/by/3.0/)
+
+---
+namespace: http://www.xml-cml.org/dictionary/cml/name/
+prefix: cmlName
+title: Chemical Naming Conventions
+description: |
+  Conventions for identifying the naming scheme used in CML <name>
+  elements. The dictRef on a <name> points to one of these entries
+  to indicate the naming convention.
+
+entries:
+  - id: iupac
+    term: IUPAC Name
+    definition: Systematic name following IUPAC nomenclature rules.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+
+  - id: trivial
+    term: Trivial Name
+    definition: A common or trade name not following systematic nomenclature.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+
+  - id: cas
+    term: CAS Registry Number
+    definition: A unique identifier assigned by the Chemical Abstracts Service.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+
+  - id: inchi
+    term: InChI
+    definition: International Chemical Identifier — a textual identifier for chemical substances.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+
+  - id: inchikey
+    term: InChIKey
+    definition: A hashed version of the InChI for compact storage and searching.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+
+  - id: smiles
+    term: SMILES
+    definition: Simplified Molecular-Input Line-Entry System — a line notation for molecular structures.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+
+  - id: pubchem
+    term: PubChem CID
+    definition: PubChem Compound Identifier.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+
+  - id: chemspider
+    term: ChemSpider ID
+    definition: ChemSpider database identifier.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+
+  - id: drugbank
+    term: DrugBank ID
+    definition: DrugBank database identifier.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+
+  - id: chebi
+    term: ChEBI ID
+    definition: Chemical Entities of Biological Interest database identifier.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none

data/data/dictionaries/unit_non_si.yaml

@@ -48,6 +48,36 @@ entries:
   - id: bar
     term: bar
     definition: A unit of pressure equal to 1e5 pascal.
+  - id: g_cm3
+    term: grams per cubic centimeter
+    definition: A unit of density equal to 1 g/cm³.
+  - id: Pa_s
+    term: pascal-second
+    definition: The SI derived unit of dynamic viscosity.
+  - id: N_m
+    term: newton per meter
+    definition: A unit of surface tension.
+  - id: D
+    term: debye
+    definition: A unit of electric dipole moment, equal to ~3.33564e-30 C·m.
+  - id: A3
+    term: cubic angstrom
+    definition: A unit of volume equal to 1e-30 m³.
+  - id: kJ_mol
+    term: kilojoule per mole
+    definition: A unit of molar energy equal to 1000 J/mol.
+  - id: J_molK
+    term: joule per mole-kelvin
+    definition: A unit of molar entropy or molar heat capacity.
+  - id: eV
+    term: electronvolt
+    definition: A unit of energy equal to ~1.602e-19 J.
+  - id: angstrom2
+    term: square angstrom
+    definition: A unit of area equal to 1e-20 m².
+  - id: angstrom3
+    term: cubic angstrom
+    definition: A unit of volume equal to 1e-30 m³.
   - id: atmosphere
     term: atmosphere
     definition: A unit of pressure equal to ~101 325 pascal.

data/data/dictionaries/unit_type.yaml

@@ -87,6 +87,18 @@ entries:
   - id: inductance
     term: Inductance
     definition: A measure of the property of an electric conductor to oppose changes in current.
+  - id: density
+    term: Density
+    definition: Mass per unit volume.
+  - id: viscosity
+    term: Viscosity
+    definition: A fluid resistance to gradual deformation by shear stress or tensile stress.
+  - id: surfaceTension
+    term: Surface Tension
+    definition: The force per unit length acting along the surface of a liquid.
+  - id: entropy
+    term: Entropy
+    definition: A thermodynamic quantity representing the unavailability of a system thermal energy.
   - id: frequency
     term: Frequency
     definition: A measure of the number of occurrences of a repeating event per unit time.

data/lib/chemicalml/cml/aliases.rb

@@ -0,0 +1,20 @@
+# frozen_string_literal: true
+
+# Generates all backward-compatible `Chemicalml::Cml::*` aliases
+# pointing at the corresponding `Schema3::*` classes.
+#
+# All 36 aliases are generated in a single file (loaded lazily when
+# the first alias is referenced) rather than 36 individual files.
+# This is DRY without violating the autoload rule: the file loads
+# lazily via autoload, and const_set here ALIASES existing classes
+# (Schema3::Foo already exists) rather than creating new ones.
+
+module Chemicalml
+  module Cml
+    Elements::ALL.each_key do |class_name|
+      next if const_defined?(class_name, false)
+
+      const_set(class_name, Schema3.const_get(class_name))
+    end
+  end
+end

data/lib/chemicalml/cml/base/abundance.rb

@@ -0,0 +1,34 @@
+# frozen_string_literal: true
+
+module Chemicalml
+  module Cml
+    module Base
+      module Abundance
+        def self.included(klass)
+          klass.class_eval do
+            include Chemicalml::Cml::Role::Abundance
+            attribute :id, :string
+            attribute :title, :string
+            attribute :dict_ref, :string
+            attribute :convention, :string
+
+            attribute :min, :string
+            attribute :max, :string
+            attribute :units, :string
+            xml do
+              namespace Chemicalml::Cml::Namespace
+              root "abundance"
+              map_attribute "id", to: :id
+              map_attribute "title", to: :title
+              map_attribute "dictRef", to: :dict_ref
+              map_attribute "convention", to: :convention
+              map_attribute "min", to: :min
+              map_attribute "max", to: :max
+              map_attribute "units", to: :units
+            end
+          end
+        end
+      end
+    end
+  end
+end

data/lib/chemicalml/cml/base/action.rb

@@ -0,0 +1,50 @@
+# frozen_string_literal: true
+
+module Chemicalml
+  module Cml
+    module Base
+      module Action
+        def self.included(klass)
+          klass.class_eval do
+            include Chemicalml::Cml::Role::Action
+            attribute :id, :string
+            attribute :title, :string
+            attribute :dict_ref, :string
+            attribute :convention, :string
+            attribute :order, :string
+
+            attribute :units, :string
+            attribute :start, :string
+            attribute :start_condition, :string
+            attribute :duration, :string
+            attribute :end, :string
+            attribute :end_condition, :string
+            attribute :type, :string
+            attribute :action_order, :string
+            attribute :count, :string
+            attribute :ref, :string
+            xml do
+              namespace Chemicalml::Cml::Namespace
+              root "action"
+              map_attribute "id", to: :id
+              map_attribute "title", to: :title
+              map_attribute "dictRef", to: :dict_ref
+              map_attribute "convention", to: :convention
+              map_attribute "order", to: :order
+              map_attribute "units", to: :units
+              map_attribute "start", to: :start
+              map_attribute "startCondition", to: :start_condition
+              map_attribute "duration", to: :duration
+              map_attribute "end", to: :end
+              map_attribute "endCondition", to: :end_condition
+              map_attribute "type", to: :type
+              map_attribute "actionOrder", to: :action_order
+              map_attribute "count", to: :count
+              map_attribute "ref", to: :ref
+            end
+          end
+        end
+      end
+    end
+  end
+end

data/lib/chemicalml/cml/base/action_list.rb

@@ -0,0 +1,51 @@
+# frozen_string_literal: true
+
+module Chemicalml
+  module Cml
+    module Base
+      module ActionList
+        def self.included(klass)
+          klass.class_eval do
+            include Chemicalml::Cml::Role::ActionList
+            attribute :id, :string
+            attribute :title, :string
+            attribute :dict_ref, :string
+            attribute :convention, :string
+            attribute :order, :string
+
+                        attribute :actions, :action, collection: true
+
+            attribute :start, :string
+            attribute :start_condition, :string
+            attribute :duration, :string
+            attribute :end, :string
+            attribute :end_condition, :string
+            attribute :units, :string
+            attribute :count, :string
+            attribute :type, :string
+            attribute :action_order, :string
+            xml do
+              namespace Chemicalml::Cml::Namespace
+              map_element "action", to: :actions
+              root "actionList"
+              map_attribute "id", to: :id
+              map_attribute "title", to: :title
+              map_attribute "dictRef", to: :dict_ref
+              map_attribute "convention", to: :convention
+              map_attribute "order", to: :order
+              map_attribute "start", to: :start
+              map_attribute "startCondition", to: :start_condition
+              map_attribute "duration", to: :duration
+              map_attribute "end", to: :end
+              map_attribute "endCondition", to: :end_condition
+              map_attribute "units", to: :units
+              map_attribute "count", to: :count
+              map_attribute "type", to: :type
+              map_attribute "actionOrder", to: :action_order
+            end
+          end
+        end
+      end
+    end
+  end
+end