This repository contains software to create and deploy CDEs
To use CDE in box solutions clone this repository to your machine.
git clone https://github.com/ejp-rd-vp/cde-in-boxThe docker-compose.yml file in directory cde-in-box/bootstrap will setup up graphDB triple store and creates fdp and cde repositories in graphDB. These two repositories are used by other services in CDE in box so make sure that bootstrap services are property setup before you proceed further.
To run docker-compose.yml file in cde-in-box/bootstrap you need graphDB triple store free edition. Follow the steps below to get free edition of graphdb.
Step 1: GO to this url and registry to download GraphDB free edition.
Step 2: The download will be sent to your email. From the email follow link to download page and click on "Download as a stand-alone server". This step will download "graphdb-free-{version}-dist.zip" file to your machine.
Step 3: Move "graphdb-free-{version}-dist.zip" file to the following location
mv graphdb-free-{version}-dist.zip cde-in-box/bootstrap/graph-dbStep 4: If your graphdb version is different from 9.7.0 then change the version number of graph DB in the docker-compose file.
graph_db:
build:
context: ./graph-db
dockerfile: Dockerfile
args:
version: 9.7.0Once you have done above configurations you can run bootstrap services by running docker-compose.yml file in cde-in-box/bootstrap directory.
docker-compose up -dIf the deployment is successful then you can access the graphDB by visiting the following URL.
| Service name | Local deployment | Production deployment |
|---|---|---|
| GraphDB | http://localhost:7200 | http://SERVER-IP:7200 |
By default GraphDB service is secured so you need credentials to login to the graphDB. Please find the default graphDB's credentials in the table below.
| Username | Password |
|---|---|
admin |
root |
The docker-compose.yml file in directory cde-in-box/metadata will setup up FAIR Data Point and connects FAIR Data Point to triple store created in the bootstrapping step.
Step 1: Before you run metadata services make sure that graphDB triple store is up running. You can check by going to this url http:server_ip:7200
Step 2: Check if fdp repository is available in the graphDB triple store.
Once you have done above checks you can run metadata services by running docker-compose.yml file in cde-in-box/metadata directory.
docker-compose up -dIf the deployment is successful then you can access the FAIR Data Point by visiting the following URL.
| Service name | Local deployment | Production deployment |
|---|---|---|
| FAIR Data Point | http://localhost:8080 | http://SERVER-IP:8080 |
In order to add content to the FAIR Data Point you need credentials with write access. Please find the default FAIR Data Point's credentials in the table below.
| Username | Password |
|---|---|
albert.einstein@example.com |
password |
- In the
data-capturedirectory, rundocker-compose up. - Once it's started up, in the browser go to http://localhost:8080
- Log in with username
admin, passwordadmin - Create a new database
cde - In the schema, upload the file
data-capture/emx2/emx2-cde-fdp-rml-compat-v2.xlsx - Open the cde schema settings and make user
anonymousroleViewer. - You can edit the data in the Patient table.
- Once a minute, the data will be exported to the data directory of the transformation services
Step 1: Create the following folder structure, relative to where you plan to keep your pre and post-transformed data:
.
./data/
./data/mydataX.csv (input csv files, e.g. "height.csv")
./data/mydataY.csv...
./data/triples/ (output FAIR data ends up here)
./config/
./config/XXXX_yarrrml_template.yaml (XXXX is a one-word tag of the "type" of data, e.g. "height")
Step 2: Running data transformation services
Once you have done the above configurations you can run data transformation services setup by running ``docker-compose.ymlfile incde-in-box/cde-ready-to-go` directory.
IN THE FOLDER THAT CONTAINS THE ./data/triples and ./config and subfolders
docker-compose up -dStep 3: Executing transformations
Put an appropriately columned XXXX.csv into the ./data folder
Put a matching YARRRML template file called XXXX_yarrrml_template.yaml into the ./config folder
call the url: http://localhost:4567 to trigger the transformation of each CSV file, and auto-load into graphDB (this will over-write what is currrently loaded! We will make this behaviour more flexible later)
There is sample data in the "sample_data" folder that can be used to test your installation.
In the GraphDB, you can now explore the generated graph: http://localhost:7200/graphs-visualizations?uri=http:%2F%2Fmarks.test%2Fthis%2Findividual_Patient001%23Person
Or execute sparql queries, for example to count patients with a given disease:
PREFIX sio: <http://semanticscience.org/resource/>
PREFIX obo: <http://purl.obolibrary.org/obo/>
PREFIX ordo: <http://www.orpha.net/ORDO/>
PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
SELECT (COUNT(DISTINCT ?person) AS ?num_of_person) ?ordo_class_iri WHERE {
VALUES (?ordo_class_iri) {(<http://www.orpha.net/ORDO/Orphanet_166260>)} # Dentinogenesis imperfecta type 2
# GET person(s) and their roles
?person sio:SIO_000228 ?role.
# CHECK if one of these roles is `rdf:type` patient role
?role rdf:type obo:OBI_0000093.
# GET all the processes where this role is relaized in
?role sio:SIO_000356 ?process.
# CHECK if one of these procceses of `rdf:type` medical diagnosis process
?process rdf:type sio:SIO_001001.
# GET all the outputs of this process
?process sio:SIO_000229 ?output.
# CHECK if one of these output(s) of `rdf:type` information content entity
?output rdf:type sio:SIO_000015.
# GET disease linked to this output
?output sio:SIO_000628 ?disease.
# CHECK if the diseases the person is diagonosis with is one of the diseases in our list
?disease a ?ordo_class_iri
} GROUP BY ?ordo_class_iri