feat: add hci converter

.gitignore

@@ -11,4 +11,3 @@ debug
 #Folders
 data/**
 *.ttl
-*.json

Cargo.toml

@@ -3,7 +3,7 @@ resolver = "2"
 
 members = [
   "src/catplus-common",
-  "src/synth-converter",
+  "src/converter",
 ]
 
 

README.md

@@ -2,51 +2,51 @@
 
 ## About
 
-This repository contains all the Zarr converters for the different data types in the Cat+ project (Agilent, UV, IR, etc.)
-The data types are all in different formats, their data and metadata colluded together. The goal will be to convert the metadata to [an established ontology](https://github.com/sdsc-ordes/catplus-ontology/tree/main), and -as much as data format allow- convert the data in [Zarr array](https://zarr.readthedocs.io/en/stable/index.html).
+This repository contains all the converters for the different data types in the Cat+ project (Agilent, UV, IR, etc.)
+The data types are all in different formats, their data and metadata colluded together. The goal will be to convert the metadata to [an established ontology](https://github.com/sdsc-ordes/catplus-ontology/tree/main), and provide the data in their original files.
 
 ## Tools
 
-### synth-converter
-The Synth-converter parses a json input into an rdf graph and serializes the graph to either turtle or jsonld.
-It expects the input to conform to the cat+ ontology and the struct `synth-converter/src/batch.rs`. An example input file is provided in `example/1-Synth.json`.
+### converter
+The converter parses a json input into an rdf graph and serializes the graph to either turtle or jsonld.
+It expects the input to conform to the cat+ ontology and the struct `src/catplus-common/src/models/types.rs`. Example input files are provided in `examples` directory.
 
 #### Usage
 
-The `synth-converter` has three parameters:
+The `converter` has four arguments:
 
+- input_type: currently `synth` (see `examples/1-Synth.json`) or `hci` (see `examples/0-HCI.json`)
 - inputfile: path to input file (relative to top level of the repo or absolute)
 - outputfile: path to output file (relative to top level of the repo or absolute)
-- format: default is "ttl", the other option is jsonld
+- format: rdf output format, currently `turtle` or `jsonld`
 
-The `synth-converter` turns the inputfile into a rdf graph and serilizes it to either turtle or jsonld. The serialization is written to an outputfile.
+The `converter` turns the inputfile into a rdf graph and serializes it to either turtle or jsonld. The serialization is written to the provided outputfile.
+
+Examples
 
 ```
-just run example/1-Synth.json output.ttl
-just run example/1-Synth.json output.json --format jsonld
+just run synth examples/1-Synth.json examples/1-Synth.ttl turtle
+just run hci examples/0-HCI.json examples/0-HCI.ttl jsonld
 ```
 
 ### Architecture
 
-The json input is read with `serde_json`: the transformation of fields is described in the struct `synth-converter/src/batch.rs`
-
-The graph is build via `synth-converter/src/graph/graph_builder.rs` and uses `sophia_rs`. Besides `rdf` and `xsd` that have build in namespaces in `sophia_rs`, all namespaces and terms are provided in `synth-converter/src/graph/namespaces` as constants. This makes the code more readable and also ensures that the rdf iris and namespaces are controlled and spelt correctly.
-Graph serializers and parsers are provided in `synth-converter/src/rdf`. The turtle serializer there is needed for the test.
-The conversion is done in the public crate `synth-converter/src/convert.rs`
+The json input is read with `serde_json`: the transformation into rdf is done by the `src/catplus-common` library.
+It uses `sophia_rs`. The mapping is triggered by `src/catplus-common/src/models/types.rs` and makes use of the namespaces defined at `src/catplus-common/src/graph/namespaces`.
 
 ### Shacl Validation
 
 The rdf graph confirms to the cat+ ontology: https://github.com/sdsc-ordes/catplus-ontology. Currently rust offeres no Shacl Validation Library, but once such a library exists, it would make sense to add a Shacl Validation.
 
-TheShacl Validation can be done manually here: https://www.itb.ec.europa.eu/shacl/any/upload
+The Shacl Validation can be done manually here: https://www.itb.ec.europa.eu/shacl/any/upload
 
 ## Installation guidelines
 
 The repo is setup with nix.
 
 ```
-git clone [email protected]:sdsc-ordes/catplus-zarr-converters.git
-cd catplus-zarr-converters
+git clone [email protected]:sdsc-ordes/catplus-converters.git
+cd catplus-converters
 cargo build
 ```
 
@@ -57,17 +57,18 @@ The rust commands can be started via a justfile:
 ```
 just --list
 Available recipes:
-    build *args                      # Build the synth-converter.
-    default                          # Default recipe to list all recipes.
-    nix-develop *args                # Enter a Nix development shell.
-    run input_file output_file *args # Run the synth-converter.
-    test *args                       # Test the synth-converter.
-    fmt *arg                         # Format the synth-converter.
+    build *args                                 # Build all crates
+    default                                     # Default recipe to list all recipes.
+    format *args                                # Format all crates
+    fmt *args                                   # alias for `format`
+    nix-develop *args                           # Enter a Nix development shell.
+    run input_type input_file output_file *args # Run the converter.
+    test *args                                  # Test all crates
 ```
 
 ### Tests
 
-Run the tests with `just test`: only integration tests have been integrated that ensure that the serialized graph in turtle is isomorphic to an expected turtle serialization per valid substructure of the input data: this substructures are action that occur in the synthesis process.
+Run the tests with `just test`: only integration tests have been integrated that ensure that the serialized graph in turtle is isomorphic to an expected turtle serialization of the input data.
 
 ### Contribute
 

examples/0-HCI.json

@@ -0,0 +1,98 @@
+{
+    "hasCampaign": {
+        "campaignName": "Caffeine Synthesis",
+        "description": "1-step N-methylation of theobromine to caffeine",
+        "objective": "High caffeine yield at the end",
+        "campaignClass": "Standard Research",
+        "type": "optimization",
+        "reference": "Substitution reaction - SN2",
+        "hasBatch": {
+            "batchID": "23",
+            "batchName": "20240516",
+            "reactionType": "N-methylation",
+            "reactionName": "Caffeine synthesis",
+            "optimizationType": "Yield optimization",
+            "link": "https://www.sciencedirect.com/science/article/pii/S0187893X15720926"
+        },
+        "hasObjective": {
+            "criteria": "Yield ≥ 90%",
+            "condition": "Reflux in acetone with methyl iodide and potassium carbonate",
+            "description": "Optimize reaction conditions to maximize caffeine yield from theobromine using methyl iodide",
+            "objectiveName": "Maximize caffeine formation"
+        },
+        "hasChemical": [
+            {
+                "chemicalID": "19",
+                "chemicalName": "Sodium methoxide",
+                "CASNumber": "124-41-4",
+                "molecularMass": {
+                    "value": 54.024,
+                    "unit": "g/mol"
+                },
+                "smiles": "C[O-].[Na+]",
+                "swissCatNumber": "SwissCAT-10942334",
+                "keywords": "optional only in HCI file",
+                "Inchi": "InChI=1S/CH3O.Na/c1-2;/h1H3;/q-1;+1",
+                "molecularFormula": "CH3NaO",
+                "density": {
+                    "value": 1.3,
+                    "unit": "g/mL"
+                }
+            },
+            {
+                "chemicalID": "36",
+                "chemicalName": "theobromine",
+                "CASNumber": "83-67-0",
+                "molecularMass": {
+                    "value": 180.160,
+                    "unit": "g/mol"
+                },
+                "smiles": "CN1C=NC2=C1C(=O)NC(=O)N2C",
+                "swissCatNumber": "SwissCAT-5429",
+                "keywords": "optional only in HCI file",
+                "Inchi": "InChI=1S/C7H8N4O2/c1-10-3-8-5-4(10)6(12)9-7(13)11(5)2/h3H,1-2H3,(H,9,12,13)",
+                "molecularFormula": "C7H8N4O2",
+                "density": {
+                    "value": 1.522,
+                    "unit": "g/mL"
+                }
+            },
+            {
+                "chemicalID": "25",
+                "chemicalName": "methyl iodide",
+                "CASNumber": "74-88-4",
+                "molecularMass": {
+                    "value": 141.939,
+                    "unit": "g/mol"
+                },
+                "smiles": "CI",
+                "swissCatNumber": "SwissCAT-6328",
+                "keywords": "optional only in HCI file",
+                "Inchi": "InChI=1S/CH3I/c1-2/h1H3",
+                "molecularFormula": "CH3I",
+                "density": {
+                    "value": 2.28,
+                    "unit": "g/mL"
+                }
+            },
+            {
+                "chemicalID": "79",
+                "chemicalName": "methanol",
+                "CASNumber": "67-56-1",
+                "molecularMass": {
+                    "value": 32.042,
+                    "unit": "g/mol"
+                },
+                "smiles": "CO",
+                "swissCatNumber": "SwissCAT-887",
+                "keywords": "optional only in HCI file",
+                "Inchi": "InChI=1S/CH4O/c1-2/h2H,1H3",
+                "molecularFormula": "CH4O",
+                "density": {
+                    "value": 0.79,
+                    "unit": "g/mL"
+                }
+            }
+        ]
+    }
+}

justfile

@@ -1,3 +1,4 @@
+#!/usr/bin/env bash
 set positional-arguments
 set shell := ["bash", "-cue"]
 
@@ -20,10 +21,10 @@ alias fmt := format
 format *args:
     cargo fmt {{args}}
 
-# Run the synth-converter.
-run input_file output_file *args:
-    cd "{{root_dir}}/src/synth-converter" && \
-    cargo run --bin synth-converter "{{root_dir}}/{{input_file}}" "{{root_dir}}/{{output_file}}" {{args}}
+# Run the converter.
+run input_type input_file output_file *args:
+    cd "{{root_dir}}/src/converter" && \
+    cargo run --bin converter "{{input_type}}" "{{root_dir}}/{{input_file}}" "{{root_dir}}/{{output_file}}" {{args}}
 
 # Enter a Nix development shell.
 nix-develop *args:

src/catplus-common/src/graph/namespaces/allocom.rs

@@ -0,0 +1,10 @@
+use lazy_static::lazy_static;
+use sophia::api::ns::Namespace;
+use sophia_api::namespace;
+namespace! {
+    "http://purl.allotrope.org/ontologies/common#",
+    AFC_0000090
+}
+lazy_static! {
+    pub static ref ns: Namespace<&'static str> = Namespace::new(PREFIX.as_str()).unwrap();
+}

src/catplus-common/src/graph/namespaces/allohdf.rs

@@ -0,0 +1,10 @@
+use lazy_static::lazy_static;
+use sophia::api::ns::Namespace;
+use sophia_api::namespace;
+namespace! {
+    "http://purl.allotrope.org/ontologies/hdf5/1.8#",
+    HardLink
+}
+lazy_static! {
+    pub static ref ns: Namespace<&'static str> = Namespace::new(PREFIX.as_str()).unwrap();
+}

src/catplus-common/src/graph/namespaces/allores.rs

@@ -3,18 +3,19 @@ use sophia::api::ns::Namespace;
 use sophia_api::namespace;
 namespace! {
     "http://purl.allotrope.org/ontologies/result#",
+    AFR_0001606,
+    AFR_0001723,
+    AFR_0001952,
+    AFR_0002036,
     AFR_0002240,
-    AFR_0002296,
-    AFR_0002295,
     AFR_0002294,
+    AFR_0002295,
+    AFR_0002296,
+    AFR_0002423,
     AFR_0002464,
+    AFR_0002764,
     AFRE_0000001,
-    AFX_0000622,
-    AFR_0002423,
-    AFR_0001606,
-    AFR_0001723,
-    AFR_0001952,
-    AFR_0002036
+    AFX_0000622
 }
 lazy_static! {
     pub static ref ns: Namespace<&'static str> = Namespace::new(PREFIX.as_str()).unwrap();

src/catplus-common/src/graph/namespaces/cat.rs

@@ -6,34 +6,41 @@ namespace! {
     AddAction,
     Batch,
     Campaign,
-    ContainerPositionAndQuantity,
-    Experiment,
-    FiltrateAction,
-    Observation,
-    Sample,
-    SetPressureAction,
-    SetTemperatureAction,
-    SetVacuumAction,
-    ShakeAction,
-    speedTumbleStirrerShape,
+    campaignClass,
+    campaignType,
     casNumber,
     chemicalName,
     containerBarcode,
     containerID,
+    ContainerPositionAndQuantity,
+    criteria,
     dispenseType,
     errorMargin,
     expectedDatum,
+    Experiment,
+    FiltrateAction,
+    genericObjective,
     hasBatch,
     hasCampaign,
+    hasChemical,
     hasContainerPositionAndQuantity,
+    hasObjective,
     hasSample,
-    hasChemical,
     internalBarCode,
     measuredQuantity,
     Objective,
+    Observation,
+    optimizationType,
+    reactionSubType,
+    reactionType,
     role,
-    setTemperatureAction,
+    Sample,
+    SetPressureAction,
+    SetTemperatureAction,
+    SetVacuumAction,
+    ShakeAction,
     speedInRPM,
+    speedTumbleStirrerShape,
     subEquipmentName,
     swissCatNumber,
     temperatureShakerShape,

src/catplus-common/src/graph/namespaces/mod.rs

@@ -1,3 +1,5 @@
+pub mod allocom;
+pub mod allohdf;
 pub mod alloproc;
 pub mod alloqual;
 pub mod allores;

src/catplus-common/src/graph/namespaces/obo.rs

@@ -4,6 +4,7 @@ use sophia_api::namespace;
 namespace! {
     "http://purl.obolibrary.org/obo/",
     CHEBI_25367,
+    IAO_0000005,
     PATO_0001019
 }
 lazy_static! {