Commit 288a2cb4 authored by jcorvi's avatar jcorvi

Merge branch 'master' into 'develop'

# Conflicts:
#   .gitlab-ci.yml
parents 3930554f 5f9fcf45
# etransafe preclinical text-mining pipeline
## Description
Nextflow pipeline that made use of software container (dockers) in order to detect findings on preclinical studies.
## Pipeline overview
![preclinical text-mining solution overview](overview.png)
![preclinical text-mining solution ner](terminology.png)
## To run the pipeline.
Open the run.sh file and configure the corresponding parameters when needed.
Then to run the pipeline simple execute **bash run.sh**
## Components and modules used in the pipeline
### (Text Mining - Generic Tools GitLab Group) https://gitlab.bsc.es/inb/text-mining/generic-tools
* **nlp-gate-generic-component**: Text mining GATE generic component for run in Batch/Pipeline mode using software containers (dockers). This tool execute the Default Gazetteer or Flexible Gazetteer Lookup given dictionaries passed as parameters and, in a second stage, execute JAPE rules given a main.jape file. This component is instantiated by other specific domain modules.
* **nlp-standard-preprocessing**: dockerization of stanford corenlp preprocessing tasks; sentence splitting, tokenization, part of speech (POS), other features: word types, lemma, kinds, formats, length and masks.
* **import-json-to-mongo**: this component inserts and push json files into a mongo database.
### (Text Mining - Bio Tools GitLab Group) https://gitlab.bsc.es/inb/text-mining/bio-tools
* **hepatotoxicity-annotation**: This library annotated text with hepatotoxicity terms related to liver findings, liver markers and CYPs genes that are relevant in hepatotoxicity events. It uses data that were obtained in a previous work: The LIMTOX system http://limtox.bioinfo.cnio.es/. Is an instance of nlp-gate-generic-component.
* **cdisc-etox-annotation**: This component annotated text using CDISC SEND and eTOX (OntoBrowser) terminologies. These terminologies are oriented to the preclinical study reports. Is an instance of nlp-gate-generic-component.
* **dnorm-gate-wrapper**: This component is a Gate wrapper of the Dnorm application (Diseases Tagger). Could be easily downloaded and run as a docker container.
* **linnaeus-gate-wrapper**: This component is a Gate wrapper of the Linnaeus application (Species Tagger). Could be easily downloaded and run as a docker container.
### (eTRANSAFE GitLab Group) https://gitlab.bsc.es/inb/etransafe
* **pretox-app**: Web Application written in angular in order to show and manually curate preclinical toxicological findings.
* **pretox-rest-api**: Api rest that retrieves relevant preclinical toxicological information.
* **ades-relation-extraction**: Relation extraction in order to obtain preclinical toxicological findings.
* **ades-ner-postprocessing**: Postprocessing jape rules execution for the detection of preclinical toxicological findings.
* **ades-export-to-json**: export findings annotated in XML GATE format to JSON format.
## Built With
* [Docker](https://www.docker.com/) - Docker Containers
* [Nextflow](https://www.nextflow.com/) - Nextflow
* [Maven](https://maven.apache.org/) - Dependency Management
## Versioning
We use [SemVer](http://semver.org/) for versioning. For the versions available, see the [tags on this repository](https://gitlab.bsc.es/inb/etransafe/etransafe-text-mining-pipeline/-/tags).
## Authors
* **Javier Corvi**
## License
This project is licensed under the GNU GENERAL PUBLIC LICENSE Version 3 - see the [LICENSE](LICENSE) file for details
// General configuration used in all profiles
manifest {
description = 'eTRANSAFE Treatment related findings pipeline'
description = 'eTRANSAFE Treatment related findings pipeline'
mainScript = 'pipeline.nf'
author = 'Javier Corvi'
homepage = 'https://gitlab.bsc.es/inb/etransafe/etransafe-text-mining-pipeline'
}
tower {
......@@ -113,6 +116,6 @@ profiles {
}
}
}
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment