Positions
Internship 2023:
Graph-based label propagation methods for gene function prediction
Internship 2022
Data integration and data mining: Development of text mining approaches to identify gene-phenotype interactions
Stages 2021
Stage 2: Vérification de la qualité et raisonnement sur les données issues de la plateforme AgroLD
2019 Internships
AgroLD project :
Internship 1: Knowledge graph augmentation with structured web markup and json-api. (Semantic web). (Provided)
The objective will be to develop methods that will aggregate external information (such as web pages or web services) with the content of the knowledge graph.
Internship 2: Knowledge discovery: explore semantic web methods to aid the process of hypotheses generation by retrieving implicit knowledge, (e.g. inference rules OWL, SHACL, SPIN) (Semantic web).
Internship 3: Develop bioinformatic analyses workflows and visualization tools for biological use cases. Given biological questions and input data, develop analytical methods to query, filter and rank results. Develop methods to visualize data according several focus.
Internship 5 / Graph Visualisation: explore methods and API to display knowledge graph query results such as (cytoscape js, Knetmaps, D3Js, etc.) Develop a solution allowing querying RDF graph database and visualize contextual results. (Provided)
NLP & Bioinformatics
Internship 1 /Entity recognition in tweets: Data Mining and NLP for knowledge extraction: explore methods to extract biological entities and their relationships in twitter raw text. Develop an RDF models to convert findings into RDF instances (Semantic web). (provided)
Internship 2 / search engine for pubmed entries linked to gene and protein name: Develop a search engine elastic-search to index Pubmed abstract and use entity NER tools and semantic web tool to identify entities to index. (NLP, Semantic web, bioinformatics) (Provided)
Internship 3 /Extract semi-structured information from scientific publications: Adapt existing JAVA QTL-Table Miner application tools to extract and filter the content of tables/spreadsheet available in biomedical publication. Develop an RDF models to convert findings into RDF instances (Semantic web).
Bioinformatics:
internship 1 : Machine learning-based gene prioritization methods for identifying candidate genes in GWAS loci. (provided)
Internship 2 : Prioritizing genomic variants (Provided)