chemicalml 0.1.0

data/chemicalml.gemspec

@@ -0,0 +1,35 @@
+# frozen_string_literal: true
+
+require_relative "lib/chemicalml/version"
+
+Gem::Specification.new do |spec|
+  spec.name          = "chemicalml"
+  spec.version       = Chemicalml::VERSION
+  spec.authors       = ["Ribose Inc."]
+  spec.email         = ["open.source@ribose.com"]
+
+  spec.summary       = "ChemML — Chemical Markup Language (CML) for Ruby."
+  spec.description   = "ChemML provides a lutaml-model-based Ruby object model for the " \
+                       "Chemical Markup Language (CML). Parse, manipulate, and serialize " \
+                       "CML XML with full round-trip fidelity. Designed as a sibling model " \
+                       "to other chemistry model layers (e.g. AsciiChem)."
+  spec.homepage      = "https://github.com/lutaml/chemicalml"
+  spec.license       = "BSD-2-Clause"
+  spec.required_ruby_version = Gem::Requirement.new(">= 3.3.0")
+
+  spec.metadata["homepage_uri"] = spec.homepage
+  spec.metadata["source_code_uri"] = "https://github.com/lutaml/chemicalml"
+  spec.metadata["changelog_uri"] = "https://github.com/lutaml/chemicalml/blob/main/CHANGELOG.md"
+  spec.metadata["rubygems_mfa_required"] = "true"
+
+  spec.files = Dir.chdir(File.expand_path(__dir__)) do
+    `git ls-files -z`.split("\x0").reject do |f|
+      f.match(%r{^(test|spec|features)/})
+    end
+  end
+  spec.bindir        = "exe"
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  spec.add_dependency "lutaml-model", "~> 0.8.0"
+end

data/data/dictionaries/_index.yaml

@@ -0,0 +1,14 @@
+# Index of built-in CML dictionaries shipped with ChemicalML.
+#
+# Each entry maps the dictionary short name (used as the YAML
+# filename stem under data/dictionaries/) to its wire prefix.
+
+---
+compchem:
+  prefix: compchem
+unit_type:
+  prefix: unitType
+unit_si:
+  prefix: si
+unit_non_si:
+  prefix: nonsi

data/data/dictionaries/compchem.yaml

@@ -0,0 +1,481 @@
+# CompChem Dictionary — canonical CML concepts used by the CompChem convention.
+#
+# Source: http://www.xml-cml.org/dictionary/compchem/
+# Authors: Peter Murray-Rust, Weerapong Phadungsukanan, Jens Thomas
+# License: CC-BY-3.0 (http://creativecommons.org/licenses/by/3.0/)
+#
+# Each entry below mirrors the upstream <entry> elements. Descriptions
+# are paraphrased for length; the upstream XML remains authoritative.
+
+---
+namespace: http://www.xml-cml.org/dictionary/compchem/
+prefix: compchem
+title: Computational Chemistry Core Concepts
+description: |
+  Toplevel dictionary for computational chemistry. Concepts in this
+  dictionary are general throughout computational chemistry and are
+  used extensively in the CompChem convention to describe the
+  structure of computational chemistry.
+
+entries:
+  - id: jobList
+    term: Job List
+    definition: A list of sequential computational jobs.
+    description: |
+      A quantum chemistry calculation is often comprised of a series of
+      subtasks (e.g. coarse optimisation -> fine optimisation -> NMR
+      spectrum analysis). The jobList concept captures these successive
+      subtasks and links the information from one subtask to the next.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+
+  - id: job
+    term: Job
+    definition: A computational job performed by quantum chemistry software.
+    description: |
+      The job concept represents a computational job performed by
+      quantum chemistry software, e.g. geometry optimisation,
+      frequency analysis. The job can be considered as the unit of
+      work that would be submitted to a computational resource.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+
+  - id: initialization
+    term: Initialization
+    definition: An initialization module for a computational job or calculation.
+    description: |
+      Represents the concept of the model parameters and inputs. The
+      module defines the calculation, so that it should be possible to
+      reproduce the calculation based solely on the data in this
+      module.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+
+  - id: calculation
+    term: Calculation
+    definition: A calculation module for a computational job.
+    description: |
+      Represents the concept of the model calculation, optimisation or
+      iteration processes for a computational job. Calculations can be
+      nested to any level.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+
+  - id: finalization
+    term: Finalization
+    definition: A finalization module for a computational job or calculation.
+    description: |
+      Represents the concept of the model results for a computational
+      job or calculation. Usually the output properties of the final
+      calculation carried out by the job.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+
+  - id: environment
+    term: Environment
+    definition: A module describing the computing environment.
+    description: |
+      Refers to the hardware platform, software application, the
+      operating system, and any hardware and software configurations
+      used to run the job or computational task.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+
+  - id: program
+    term: Program
+    definition: The name of the computational chemistry program being run.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+    enum:
+      kind: open
+      values:
+        - nwchem
+        - gaussian
+        - gulp
+
+  - id: programVersion
+    term: Program Version
+    definition: The version of the code that was used to run the calculation.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+
+  - id: hostName
+    term: Host Name
+    definition: The name of the host that the program was run on.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+
+  - id: executable
+    term: Executable
+    definition: The path to the executable program.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+
+  - id: runDate
+    term: Run Date
+    definition: The date that the job commenced.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+
+  - id: compileDate
+    term: Compile Date
+    definition: The date that the executable was compiled.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+
+  - id: numProc
+    term: Number of Processors
+    definition: The number of processors used to run the job.
+    data_type: xsd:integer
+    unit_type: unitType:dimensionless
+
+  - id: method
+    term: Method
+    definition: The type of computational method used in the calculation.
+    description: |
+      Identifies the broad class of computation. Examples: SCF, DFT, MP2.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+    enum:
+      kind: open
+      values:
+        - scf
+        - dft
+        - mp2
+        - cc
+        - semiempirical
+
+  - id: task
+    term: Task
+    definition: The task being carried out by the job or calculation.
+    description: |
+      Describes what the job or calculation aims to do. Example values:
+      energy, frequency, geometry_optimization, gradient,
+      initial_guess, iteration, step.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+    enum:
+      kind: open
+      values:
+        - energy
+        - frequency
+        - geometry_optimization
+        - gradient
+        - initial_guess
+        - iteration
+        - step
+
+  - id: iterationIndex
+    term: Iteration Index
+    definition: The serial number of an iteration.
+    data_type: xsd:integer
+    unit_type: unitType:dimensionless
+
+  - id: charge
+    term: Total Charge
+    definition: The total charge on the system in elementary charge units.
+    data_type: xsd:double
+    unit_type: unitType:electricCharge
+    units: unit:e
+
+  - id: spinMultiplicity
+    term: Spin Multiplicity
+    definition: |
+      The spin multiplicity, equal to (number of alpha electrons) -
+      (number of beta electrons) + 1.
+    data_type: xsd:integer
+    unit_type: unitType:dimensionless
+
+  - id: numAtoms
+    term: Number of Atoms
+    definition: The total number of atoms in a molecule or other collection.
+    data_type: xsd:integer
+    unit_type: unitType:dimensionless
+
+  - id: numElectrons
+    term: Number of Electrons
+    definition: The total number of electrons in a system.
+    data_type: xsd:integer
+    unit_type: unitType:dimensionless
+
+  - id: numAlphaElectrons
+    term: Number of Alpha Electrons
+    definition: The total number of alpha spin electrons in a system.
+    data_type: xsd:integer
+    unit_type: unitType:dimensionless
+
+  - id: numBetaElectrons
+    term: Number of Beta Electrons
+    definition: The total number of beta spin electrons in a system.
+    data_type: xsd:integer
+    unit_type: unitType:dimensionless
+
+  - id: numClosedShells
+    term: Number of Closed Shells
+    definition: The number of closed shells.
+    data_type: xsd:integer
+    unit_type: unitType:dimensionless
+
+  - id: numOpenShells
+    term: Number of Open Shells
+    definition: The number of open shells.
+    data_type: xsd:integer
+    unit_type: unitType:dimensionless
+
+  - id: pointGroup
+    term: Point Group
+    definition: The molecular point group in Schoenflies notation.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+
+  - id: wavefunctionType
+    term: Wavefunction Type
+    definition: The type of wavefunction.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+    enum:
+      kind: open
+      values:
+        - closed
+        - open
+        - restricted open
+
+  - id: basisSet
+    term: Basis Set
+    definition: A list container for all information related to the basis set.
+    description: |
+      The basis set is the set of functions from which the electron
+      orbitals are constructed.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+
+  - id: basisSetLabel
+    term: Basis Set Label
+    definition: The name of the basis set.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+
+  - id: basisSetType
+    term: Basis Set Type
+    definition: The type of the basis set.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+    enum:
+      kind: closed
+      values:
+        - orbital
+        - dftorb
+        - dftxfit
+        - dftcfit
+        - periodic
+        - ecporb
+        - spinorb
+        - polarization
+        - diffuse
+        - tight
+        - rydberg
+
+  - id: basisSetHarmonicType
+    term: Basis Set Harmonic Type
+    definition: The type of the angular functions used in the basis set.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+    enum:
+      kind: closed
+      values:
+        - cartesian
+        - spherical
+
+  - id: basisSetContractionType
+    term: Basis Set Contraction Type
+    definition: How the gaussian functions in the basis are contracted.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+    enum:
+      kind: closed
+      values:
+        - segmented
+        - general
+        - uncontracted
+
+  - id: basisSetShell
+    term: Basis Set Shell
+    definition: The label for the contraction shell.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+    enum:
+      kind: closed
+      values:
+        - S
+        - P
+        - SP
+        - D
+        - F
+        - G
+        - H
+        - I
+        - K
+        - L
+        - M
+
+  - id: dftFunctional
+    term: DFT Functional
+    definition: A list container for all information related to a DFT functional.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+
+  - id: dftFunctionalLabel
+    term: DFT Functional Label
+    definition: The name of the DFT functional used.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+
+  - id: totalEnergy
+    term: Total Energy
+    definition: The total energy for a system of electrons and nuclei.
+    description: |
+      Formed from the sum of the nuclear, one- and two-electron
+      energies. The exact meaning is determined by the parameters in
+      the initialization module of the calculation.
+    data_type: xsd:double
+    unit_type: unitType:energy
+    units: unit:hartree
+
+  - id: scfEnergy
+    term: SCF Energy
+    definition: The Hartree-Fock Self-Consistent Field component of the energy.
+    data_type: xsd:double
+    unit_type: unitType:energy
+    units: unit:hartree
+
+  - id: nuclearRepulsionEnergy
+    term: Nuclear Repulsion Energy
+    definition: |
+      The potential energy arising from Coulombic nuclei-nuclei
+      repulsions.
+    data_type: xsd:double
+    unit_type: unitType:energy
+    units: unit:hartree
+
+  - id: e1Energy
+    term: One-electron Energy
+    definition: The one-electron kinetic energy component of the Hamiltonian.
+    data_type: xsd:double
+    unit_type: unitType:energy
+    units: unit:hartree
+
+  - id: e2Energy
+    term: Two-electron Energy
+    definition: The two-electron energy.
+    data_type: xsd:double
+    unit_type: unitType:energy
+    units: unit:hartree
+
+  - id: coulombEnergy
+    term: Coulomb Energy
+    definition: |
+      The Coulomb component of the electronic energy in a Density
+      Functional Calculation.
+    data_type: xsd:double
+    unit_type: unitType:energy
+    units: unit:hartree
+
+  - id: xcEnergy
+    term: Exchange-Correlation Energy
+    definition: The exchange-correlation energy.
+    data_type: xsd:double
+    unit_type: unitType:energy
+    units: unit:hartree
+
+  - id: correlationEnergy
+    term: Correlation Energy
+    definition: The correlation energy.
+    data_type: xsd:double
+    unit_type: unitType:energy
+    units: unit:hartree
+
+  - id: cpuTime
+    term: CPU Time
+    definition: Elapsed CPU time.
+    data_type: xsd:double
+    unit_type: unitType:time
+    units: unit:s
+
+  - id: wallTime
+    term: Wall Time
+    definition: Elapsed wall-clock time.
+    data_type: xsd:double
+    unit_type: unitType:time
+    units: unit:s
+
+  - id: title
+    term: Title
+    definition: An arbitrary human-readable title for the calculation.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+
+  - id: UUID
+    term: UUID
+    definition: A Universally Unique Identifier as per RFC 4122.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+
+  - id: atomType
+    term: Atom Type
+    definition: The type of the element (the atomic symbol).
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+
+  - id: numElectronsReplaced
+    term: Number of Electrons Replaced
+    definition: The number of electrons replaced by an Effective Core Potential.
+    data_type: xsd:integer
+    unit_type: unitType:dimensionless
+
+  - id: inputFile
+    term: Input File
+    definition: A module for a single literal representation of an input file.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+
+  - id: inputFileList
+    term: Input File List
+    definition: A module containing a list of input files.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none
+
+  - id: inputFileName
+    term: Input File Name
+    definition: A representation of the name of a single input file.
+    data_type: xsd:string
+    unit_type: unitType:none
+    units: unit:none

data/data/dictionaries/unit_non_si.yaml

@@ -0,0 +1,53 @@
+# Non-SI Units Dictionary
+#
+# Source: http://www.xml-cml.org/unit/nonSi/
+# License: CC-BY-3.0 (http://creativecommons.org/licenses/by/3.0/)
+
+---
+namespace: http://www.xml-cml.org/unit/nonSi/
+prefix: nonsi
+title: Non-SI Units
+description: |
+  Common non-SI units accepted for use with CML, with their parent SI
+  unit and conversion factor.
+
+entries:
+  - id: angstrom
+    term: ångström
+    definition: A unit of length equal to 1e-10 metre.
+  - id: hartree
+    term: hartree
+    definition: The atomic unit of energy, ~4.359744e-18 J.
+  - id: bohr
+    term: bohr
+    definition: The atomic unit of length, ~5.29177e-11 m.
+  - id: dalton
+    term: dalton
+    definition: A unit of mass equal to the unified atomic mass unit.
+  - id: elementary_charge
+    term: elementary charge
+    definition: A unit of electric charge equal to ~1.602176634e-19 C.
+  - id: degree
+    term: degree
+    definition: A unit of angle equal to pi/180 radian.
+  - id: minute
+    term: minute
+    definition: A unit of time equal to 60 seconds.
+  - id: hour
+    term: hour
+    definition: A unit of time equal to 3600 seconds.
+  - id: day
+    term: day
+    definition: A unit of time equal to 86 400 seconds.
+  - id: electronvolt
+    term: electronvolt
+    definition: A unit of energy equal to the work done on an electron moving through 1 volt of potential difference.
+  - id: liter
+    term: liter
+    definition: A unit of volume equal to 1e-3 cubic metre.
+  - id: bar
+    term: bar
+    definition: A unit of pressure equal to 1e5 pascal.
+  - id: atmosphere
+    term: atmosphere
+    definition: A unit of pressure equal to ~101 325 pascal.

data/data/dictionaries/unit_si.yaml

@@ -0,0 +1,87 @@
+# SI Units Dictionary
+#
+# Source: http://www.xml-cml.org/unit/si/
+# License: CC-BY-3.0 (http://creativecommons.org/licenses/by/3.0/)
+
+---
+namespace: http://www.xml-cml.org/unit/si/
+prefix: si
+title: SI Units
+description: |
+  The International System of Units (SI). Each entry maps a unit id
+  (abbreviation) to its full title, symbol, parentSI reference,
+  multiplier/constant to SI, and unit type.
+
+entries:
+  - id: m
+    term: metre
+    definition: The SI base unit of length.
+  - id: kg
+    term: kilogram
+    definition: The SI base unit of mass.
+  - id: s
+    term: second
+    definition: The SI base unit of time.
+  - id: A
+    term: ampere
+    definition: The SI base unit of electric current.
+  - id: K
+    term: kelvin
+    definition: The SI base unit of thermodynamic temperature.
+  - id: mol
+    term: mole
+    definition: The SI base unit of amount of substance.
+  - id: cd
+    term: candela
+    definition: The SI base unit of luminous intensity.
+  - id: rad
+    term: radian
+    definition: The SI derived unit of angle.
+  - id: sr
+    term: steradian
+    definition: The SI derived unit of solid angle.
+  - id: Hz
+    term: hertz
+    definition: The SI derived unit of frequency.
+  - id: N
+    term: newton
+    definition: The SI derived unit of force.
+  - id: Pa
+    term: pascal
+    definition: The SI derived unit of pressure.
+  - id: J
+    term: joule
+    definition: The SI derived unit of energy.
+  - id: W
+    term: watt
+    definition: The SI derived unit of power.
+  - id: C
+    term: coulomb
+    definition: The SI derived unit of electric charge.
+  - id: V
+    term: volt
+    definition: The SI derived unit of electric potential.
+  - id: F
+    term: farad
+    definition: The SI derived unit of electric capacitance.
+  - id: ohm
+    term: ohm
+    definition: The SI derived unit of electric resistance.
+  - id: S
+    term: siemens
+    definition: The SI derived unit of electric conductance.
+  - id: Wb
+    term: weber
+    definition: The SI derived unit of magnetic flux.
+  - id: T
+    term: tesla
+    definition: The SI derived unit of magnetic flux density.
+  - id: H
+    term: henry
+    definition: The SI derived unit of inductance.
+  - id: none
+    term: none
+    definition: |
+      Used as the units for an entry that conceptually should not have
+      units (per the CML dictionary convention, MUST be referenced via
+      http://www.xml-cml.org/unit/si#none when unitType is `none`).