Merge pull request #169 from pyscal/update_ontology

Update ontology

.gitignore

@@ -5,6 +5,13 @@ rdf_structure_store/
 *.db
 wf*
 *.data
+*.ipynb
+*.dump
+*POSCAR*
+*.tar.gz
+*.in
+*.dot
+*.png
 
 # Byte-compiled / optimized / DLL files
 __pycache__/

atomrdf/data/cmso.owl

@@ -9,16 +9,23 @@
      xmlns:xsd="http://www.w3.org/2001/XMLSchema#"
      xmlns:rdfs="http://www.w3.org/2000/01/rdf-schema#"
      xmlns:skos="http://www.w3.org/2004/02/skos/core#"
-     xmlns:terms="http://purl.org/dc/terms/">
+     xmlns:terms="http://purl.org/dc/terms/"
+     xmlns:schema="https://schema.org/">
     <owl:Ontology rdf:about="http://purls.helmholtz-metadaten.de/cmso/">
-        <terms:contributor>https://orcid.org/0000-0001-9560-4728</terms:contributor>
-        <terms:contributor>https://orcid.org/0000-0002-5149-603X</terms:contributor>
-        <terms:contributor>https://orcid.org/0000-0002-6776-1213</terms:contributor>
-        <terms:contributor>https://orcid.org/0000-0003-0698-4891</terms:contributor>
-        <terms:creator>https://orcid.org/0000-0001-7564-7990</terms:creator>
+        <terms:contributor rdf:resource="https://orcid.org/0000-0001-9560-4728"/>
+        <terms:contributor rdf:resource="https://orcid.org/0000-0002-5149-603X"/>
+        <terms:contributor rdf:resource="https://orcid.org/0000-0002-6776-1213"/>
+        <terms:contributor rdf:resource="https://orcid.org/0000-0003-0698-4891"/>
+        <terms:creator rdf:resource="https://orcid.org/0000-0001-7564-7990"/>
         <terms:description>CMSO is an ontology that aims to describe computational materials science samples (or structures), including crystalline defects.</terms:description>
+        <terms:license rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://creativecommons.org/licenses/by/4.0/</terms:license>
         <terms:title>Computational Material Sample Ontology (CMSO)</terms:title>
+        <rdfs:seeAlso rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://github.com/OCDO/cmso-ontology</rdfs:seeAlso>
         <owl:versionInfo rdf:datatype="http://www.w3.org/2001/XMLSchema#string">0.0.1</owl:versionInfo>
+        <schema:citation rdf:datatype="http://www.w3.org/2001/XMLSchema#string">Azocar Guzman, A., Menon, S., Hofmann, V., Hickel, T., Sandfeld. S. (2024), Computational Material Sample Ontology, https://purls.helmholtz-metadaten.de/cmso/</schema:citation>
+        <schema:creativeWorkStatus rdf:datatype="http://www.w3.org/2001/XMLSchema#string">Pre-release</schema:creativeWorkStatus>
+        <schema:funder rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://ror.org/05qj6w324</schema:funder>
+        <schema:logo rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://raw.githubusercontent.com/OCDO/.github/refs/heads/main/profile/ocdo_logo.png</schema:logo>
     </owl:Ontology>
 
 
@@ -40,6 +47,12 @@
 
 
 
+    <!-- http://purl.obolibrary.org/obo/IAO_0000112 -->
+
+    <owl:AnnotationProperty rdf:about="http://purl.obolibrary.org/obo/IAO_0000112"/>
+
+
+
     <!-- http://purl.obolibrary.org/obo/IAO_0000114 -->
 
     <owl:AnnotationProperty rdf:about="http://purl.obolibrary.org/obo/IAO_0000114"/>
@@ -105,6 +118,18 @@ We also have the outstanding issue of how to aim different definitions to differ
 
 
 
+    <!-- http://purl.obolibrary.org/obo/OBCS_0000221 -->
+
+    <owl:AnnotationProperty rdf:about="http://purl.obolibrary.org/obo/OBCS_0000221">
+        <obo:IAO_0000112>A normal distribution probability density function has a formula of:
+f(x) = 1/(√(2 π) σ) e^-((x - μ)^2/(2 σ^2))</obo:IAO_0000112>
+        <obo:IAO_0000115>An annotation property that represents a mathematical formula.</obo:IAO_0000115>
+        <obo:IAO_0000117>Asiyah Yu Lin, Jie Zheng, Yongqun He</obo:IAO_0000117>
+        <rdfs:label xml:lang="en">mathematical formula</rdfs:label>
+    </owl:AnnotationProperty>
+
+
+
     <!-- http://purl.org/dc/elements/1.1/contributor -->
 
     <owl:AnnotationProperty rdf:about="http://purl.org/dc/elements/1.1/contributor"/>
@@ -180,6 +205,16 @@ We also have the outstanding issue of how to aim different definitions to differ
 
 
 
+    <!-- http://purl.org/dc/terms/license -->
+
+    <owl:AnnotationProperty rdf:about="http://purl.org/dc/terms/license">
+        <rdfs:label xml:lang="en-us">License</rdfs:label>
+        <skos:definition xml:lang="en-us">A legal document giving official permission to do something with the resource.</skos:definition>
+        <rdfs:range rdf:resource="http://purl.org/dc/terms/LicenseDocument"/>
+    </owl:AnnotationProperty>
+
+
+
     <!-- http://purl.org/dc/terms/tableOfContents -->
 
     <owl:AnnotationProperty rdf:about="http://purl.org/dc/terms/tableOfContents">
@@ -255,6 +290,30 @@ We also have the outstanding issue of how to aim different definitions to differ
 
 
 
+    <!-- https://schema.org/citation -->
+
+    <owl:AnnotationProperty rdf:about="https://schema.org/citation"/>
+
+
+
+    <!-- https://schema.org/creativeWorkStatus -->
+
+    <owl:AnnotationProperty rdf:about="https://schema.org/creativeWorkStatus"/>
+
+
+
+    <!-- https://schema.org/funder -->
+
+    <owl:AnnotationProperty rdf:about="https://schema.org/funder"/>
+
+
+
+    <!-- https://schema.org/logo -->
+
+    <owl:AnnotationProperty rdf:about="https://schema.org/logo"/>
+
+
+
     <!-- 
     ///////////////////////////////////////////////////////////////////////////////////////
     //
@@ -392,6 +451,18 @@ We also have the outstanding issue of how to aim different definitions to differ
 
 
 
+    <!-- http://purls.helmholtz-metadaten.de/cmso/hasNormalVector -->
+
+    <owl:ObjectProperty rdf:about="http://purls.helmholtz-metadaten.de/cmso/hasNormalVector">
+        <rdfs:subPropertyOf rdf:resource="http://purls.helmholtz-metadaten.de/cmso/hasVector"/>
+        <rdfs:domain rdf:resource="http://purls.helmholtz-metadaten.de/cmso/Plane"/>
+        <rdfs:range rdf:resource="http://purls.helmholtz-metadaten.de/cmso/NormalVector"/>
+        <obo:IAO_0000115 rdf:datatype="http://www.w3.org/2001/XMLSchema#string">The relation between a plane and a vector normal to it.</obo:IAO_0000115>
+        <rdfs:label rdf:datatype="http://www.w3.org/2001/XMLSchema#string">has normal vector</rdfs:label>
+    </owl:ObjectProperty>
+
+
+
     <!-- http://purls.helmholtz-metadaten.de/cmso/hasSimulationCell -->
 
     <owl:ObjectProperty rdf:about="http://purls.helmholtz-metadaten.de/cmso/hasSimulationCell">
@@ -634,6 +705,17 @@ We also have the outstanding issue of how to aim different definitions to differ
 
 
 
+    <!-- http://purls.helmholtz-metadaten.de/cmso/hasDistanceFromOrigin -->
+
+    <owl:DatatypeProperty rdf:about="http://purls.helmholtz-metadaten.de/cmso/hasDistanceFromOrigin">
+        <rdfs:domain rdf:resource="http://purls.helmholtz-metadaten.de/cmso/Plane"/>
+        <rdfs:range rdf:resource="http://www.w3.org/2001/XMLSchema#float"/>
+        <obo:IAO_0000115 rdf:datatype="http://www.w3.org/2001/XMLSchema#string">A data property linking an plane with the value of distance from its origin.</obo:IAO_0000115>
+        <rdfs:label rdf:datatype="http://www.w3.org/2001/XMLSchema#string">has distance from origin</rdfs:label>
+    </owl:DatatypeProperty>
+
+
+
     <!-- http://purls.helmholtz-metadaten.de/cmso/hasElementRatio -->
 
     <owl:DatatypeProperty rdf:about="http://purls.helmholtz-metadaten.de/cmso/hasElementRatio">
@@ -1080,6 +1162,16 @@ We also have the outstanding issue of how to aim different definitions to differ
 
 
 
+    <!-- http://purls.helmholtz-metadaten.de/cmso/LatticePlane -->
+
+    <owl:Class rdf:about="http://purls.helmholtz-metadaten.de/cmso/LatticePlane">
+        <rdfs:subClassOf rdf:resource="http://purls.helmholtz-metadaten.de/cmso/Plane"/>
+        <obo:IAO_0000115 rdf:datatype="http://www.w3.org/2001/XMLSchema#string">In crystallography, lattice planes are sets of parallel mathematical planes, where each lattice point is on a lattice plane. The lattice plane of a crystal is represented by three integers —h,k,l— which are referred to as the Miller indices.</obo:IAO_0000115>
+        <rdfs:label rdf:datatype="http://www.w3.org/2001/XMLSchema#string">Lattice Plane</rdfs:label>
+    </owl:Class>
+
+
+
     <!-- http://purls.helmholtz-metadaten.de/cmso/LatticeVector -->
 
     <owl:Class rdf:about="http://purls.helmholtz-metadaten.de/cmso/LatticeVector">
@@ -1174,6 +1266,16 @@ We also have the outstanding issue of how to aim different definitions to differ
 
 
 
+    <!-- http://purls.helmholtz-metadaten.de/cmso/NormalVector -->
+
+    <owl:Class rdf:about="http://purls.helmholtz-metadaten.de/cmso/NormalVector">
+        <rdfs:subClassOf rdf:resource="http://purls.helmholtz-metadaten.de/cmso/Vector"/>
+        <obo:IAO_0000115 rdf:datatype="http://www.w3.org/2001/XMLSchema#string">The normal vector is a vector perpendicular to a given object.</obo:IAO_0000115>
+        <rdfs:label rdf:datatype="http://www.w3.org/2001/XMLSchema#string">Normal Vector</rdfs:label>
+    </owl:Class>
+
+
+
     <!-- http://purls.helmholtz-metadaten.de/cmso/Occupancy -->
 
     <owl:Class rdf:about="http://purls.helmholtz-metadaten.de/cmso/Occupancy">
@@ -1185,6 +1287,17 @@ We also have the outstanding issue of how to aim different definitions to differ
 
 
 
+    <!-- http://purls.helmholtz-metadaten.de/cmso/Plane -->
+
+    <owl:Class rdf:about="http://purls.helmholtz-metadaten.de/cmso/Plane">
+        <obo:IAO_0000115 rdf:datatype="http://www.w3.org/2001/XMLSchema#string">In mathematics, a plane is a two-dimensional space or flat surface that extends indefinitely.</obo:IAO_0000115>
+        <obo:OBCS_0000221 rdf:datatype="http://www.w3.org/2001/XMLSchema#string">𝑎 𝑥 + 𝑏 𝑦 + 𝑐 𝑧 + 𝑑 = 0</obo:OBCS_0000221>
+        <rdfs:comment rdf:datatype="http://www.w3.org/2001/XMLSchema#string">The equation of a plane is 𝑎 𝑥 + 𝑏 𝑦 + 𝑐 𝑧 + 𝑑 = 0 , where 𝑎 , 𝑏 , and 𝑐 are the components of the normal vector ⃑ 𝑛 = ( 𝑎 , 𝑏 , 𝑐 ) , which is perpendicular to the plane or any vector parallel to the plane.</rdfs:comment>
+        <rdfs:label rdf:datatype="http://www.w3.org/2001/XMLSchema#string">Plane</rdfs:label>
+    </owl:Class>
+
+
+
     <!-- http://purls.helmholtz-metadaten.de/cmso/SimulationCell -->
 
     <owl:Class rdf:about="http://purls.helmholtz-metadaten.de/cmso/SimulationCell">

atomrdf/data/pldo.owl

@@ -331,6 +331,8 @@ We also have the outstanding issue of how to aim different definitions to differ
         <rdfs:domain rdf:resource="http://purls.helmholtz-metadaten.de/pldo/GrainBoundary"/>
         <rdfs:range rdf:resource="http://www.w3.org/2001/XMLSchema#float"/>
         <obo:IAO_0000115 rdf:datatype="http://www.w3.org/2001/XMLSchema#string">A data property indicating the misorientation angle (θ) of the grains with respect to each other.</obo:IAO_0000115>
+        <obo:IAO_0000119 rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://doi.org/10.1016/j.actamat.2022.118006</obo:IAO_0000119>
+        <rdfs:comment rdf:datatype="http://www.w3.org/2001/XMLSchema#string">A disorientation angle can also be used to describe the grain boundary and is defined by the minimum misorientation angle when the misorientation axis is found in the standard stereographic triangle.</rdfs:comment>
         <rdfs:label>has misorientation angle</rdfs:label>
     </owl:DatatypeProperty>
 

atomrdf/graph.py

@@ -916,6 +916,8 @@ def archive(self, package_name, format="turtle", compress=True, add_simulations=
         # now go through each sample, and copy the file, at the same time fix the paths
         for sample in self.sample_ids:
             filepath = self.value(URIRef(f"{sample}_Position"), CMSO.hasPath).toPython()
+            #filepath has to fixed with the correct prefix as needed
+            filepath = os.path.join(self.structure_store, os.path.basename(filepath))
             shutil.copy(filepath, structure_store)
 
             # now we have to remove the old path, and fix new
@@ -1500,10 +1502,11 @@ def _get_ancestor(self, prop, prov):
         propname = _name(prop)
 
         operation = [x[1] for x in self.triples((prop, ASMO.wasCalculatedBy, None))]
+
         if len(operation) > 0:
             parent = [x[2] for x in self.triples((prop, ASMO.wasCalculatedBy, None))]
             operation = operation[0]
-            parent = parent[0]        
+            parent = parent[0]      
             prov[propname]['operation'] = 'output_parameter'
             prov[propname]['inputs'] = {}
             prov[propname]['inputs']['0'] = _name(parent)
@@ -1583,7 +1586,7 @@ def _get_ancestor(self, prop, prov):
                 prov[propname]['inputs']['1'] = _name(dividend)
                 self._add_to_dict(divisor, prov)
                 self._add_to_dict(dividend, prov)
-
+        print(operation)
         prov[propname]['found'] = True
         return prov
 

atomrdf/namespace.py

@@ -83,9 +83,9 @@ def __init__(self, infile, delimiter="/"):
 PLDO = Namespace(os.path.join(file_location, "data/pldo.owl"))
 PODO = Namespace(os.path.join(file_location, "data/podo.owl"))
 ASMO = Namespace(os.path.join(file_location, "data/asmo.owl"))
+MATH = Namespace(os.path.join(file_location, "data/asmo.owl"))
+
 PROV = RDFLibNamespace("http://www.w3.org/ns/prov#")
 MDO = RDFLibNamespace("https://w3id.org/mdo/calculation/")
-
-MATH = RDFLibNamespace("http://purls.helmholtz-metadaten.de/asmo/")
 UNSAFECMSO = RDFLibNamespace("http://purls.helmholtz-metadaten.de/cmso/")
 UNSAFEASMO = RDFLibNamespace("http://purls.helmholtz-metadaten.de/asmo/")

atomrdf/network/ontology.py

@@ -34,10 +34,10 @@ def read_ontology():
     file_location = os.path.dirname(__file__).split("/")
     file_location = "/".join(file_location[:-1])
 
-    cmso = OntologyNetwork(os.path.join(file_location, "data/cmso.owl")) #eb8a58a60af1759afc4115ae395ad62ddffb6844
-    pldo = OntologyNetwork(os.path.join(file_location, "data/pldo.owl")) #d15d27712e3f64b405d75c70ad970c9d54ff0b51
+    cmso = OntologyNetwork(os.path.join(file_location, "data/cmso.owl")) #b7c8f3544d16d0ec9a9aace682da0e6abba1c57f
+    pldo = OntologyNetwork(os.path.join(file_location, "data/pldo.owl")) #688ce36a3e6520a6e280bb248789c231d3c36f25
     podo = OntologyNetwork(os.path.join(file_location, "data/podo.owl")) #6a74d511c5b78042e1cb7a6e76e948fa56de598e
-    asmo = OntologyNetwork(os.path.join(file_location, "data/asmo.owl")) #c7e2da99b9126844f19f225c6a10cdb01aeb55e6
+    asmo = OntologyNetwork(os.path.join(file_location, "data/asmo.owl")) #688ce36a3e6520a6e280bb248789c231d3c36f25
     ldo = OntologyNetwork(os.path.join(file_location, "data/ldo.owl")) #e23fa9930351787e701347878a3e1a0e3924d084
 
     # combine them

atomrdf/properties.py

@@ -440,4 +440,4 @@ def _get_symmetry_dict(system):
     atom_types = system._structure_dict["species"]
 
     results = spglib.get_symmetry_dataset((box, direct_coordinates, atom_types))
-    return results["international"], results["number"]
+    return results.international, results.number

atomrdf/sample.py

@@ -4,7 +4,7 @@
 In this module a new Sample class is defined.
 """
 from pyscal3.atoms import AttrSetter
-from atomrdf.namespace import CMSO, PLDO, PODO, ASMO, PROV, Literal
+from atomrdf.namespace import CMSO, PLDO, PODO, ASMO, PROV, Literal, UNSAFEASMO
 from rdflib import RDFS, Namespace, RDF, URIRef
 import numpy as np
 import uuid
@@ -22,8 +22,9 @@ def __init__(self, name, sample_id, graph):
         #create attributes
         self.properties = AttrSetter()
         mapdict = {
-            'volume': self._volume,
-            'no_of_atoms': self._no_of_atoms,
+            'SimulationCellVolume': self._volume,
+            'NumberOfAtoms': self._no_of_atoms,
+            'SimulationCellLengths': self._simulation_cell_lengths,
         }
         self.properties._add_attribute(mapdict)
 
@@ -55,37 +56,50 @@ def structure(self):
 
     @property
     def _volume(self):
+        """
+        Volume of the sample, PhysicalQuantity
+        """
+        #get the simulation cell
         simcell = self._graph.value(self._sample_id, CMSO.hasSimulationCell)
+        #get the volume, these are volume objects now!
         volume = self._graph.value(simcell, CMSO.hasVolume)
+        volume_value = self._graph.value(volume, ASMO.hasValue)
 
-        #initially query if there is property with label volume
+        #find there are already volume attached as calculated property
         inps = [k[2] for k in self._graph.triples((self._sample_id, CMSO.hasCalculatedProperty, None))]
+        #initially query if there is property with label volume
         labels = [self._graph.value(inp, RDFS.label) for inp in inps]
-        if not "Volume" in labels:
-            parent = self._graph.create_node(URIRef(f'property:{uuid.uuid4()}'), CMSO.CalculatedProperty)
-            self._graph.add((parent, ASMO.hasValue, Literal(volume.toPython())))
-            self._graph.add((parent, RDFS.label, Literal("Volume")))
-            self._graph.add((self._sample_id, CMSO.hasCalculatedProperty, parent))
-            self._graph.add((parent, ASMO.hasUnit, URIRef(f"http://qudt.org/vocab/unit/ANGSTROM3")))
+        if not "SimulationCellVolume" in labels:
+            #add this as a calculated property
+            self._graph.add((self._sample_id, CMSO.hasCalculatedProperty, volume))
+            parent = volume            
         else:
-            parent = inps[labels.index("Volume")]
-        return Property(volume.toPython(), graph=self._graph, parent=parent, unit='ANGSTROM3', sample_parent=self._sample_id)
+            parent = inps[labels.index("SimulationCellVolume")]
+        return Property(volume_value.toPython(), graph=self._graph, parent=parent, unit='ANGSTROM3', sample_parent=self._sample_id)
 
     @property
     def _no_of_atoms(self):
         no_atoms = self._graph.value(self._sample_id, CMSO.hasNumberOfAtoms)
         inps = [k[2] for k in self._graph.triples((self._sample_id, CMSO.hasCalculatedProperty, None))]
         labels = [self._graph.value(inp, RDFS.label) for inp in inps]
         if not "NumberOfAtoms" in labels:
-            parent = self._graph.create_node(URIRef(f'property:{uuid.uuid4()}'), CMSO.CalculatedProperty)
+            parent = self._graph.create_node(URIRef(f'property:{uuid.uuid4()}'), UNSAFEASMO.InputParameter)
             self._graph.add((parent, ASMO.hasValue, Literal(no_atoms.toPython())))
             self._graph.add((parent, RDFS.label, Literal("NumberOfAtoms")))
             self._graph.add((self._sample_id, CMSO.hasCalculatedProperty, parent))
         else:
             parent = inps[labels.index("NumberOfAtoms")]
         return Property(no_atoms.toPython(), graph=self._graph, parent=parent, sample_parent=self._sample_id)
 
-
+    @property
+    def _simulation_cell_lengths(self):
+        simcell = self._graph.value(self._sample_id, CMSO.hasSimulationCell)
+        simcelllength = self._graph.value(simcell, CMSO.hasLength)
+        x = self._graph.value(simcelllength, CMSO.hasLength_x).toPython()
+        y = self._graph.value(simcelllength, CMSO.hasLength_y).toPython()
+        z = self._graph.value(simcelllength, CMSO.hasLength_z).toPython()
+        return Property([x, y, z], graph=self._graph, parent=simcelllength, sample_parent=self._sample_id)
+
     @property
     def _input_properties(self):
         activity = self._graph.value(self._sample_id, PROV.wasGeneratedBy)