Workshop Overview
Natural Language Processing (NLP) and graph analysis stand as two fundamental pillars of biomedical informatics, providing effective tools to extract, represent, and analyze relevant information. Due to the abundance of unstructured text data in the biomedical context, NLP techniques facilitate the analysis of Electronic Health Records (EHRs) and other types of biomedical data. Indeed, NLP techniques allow for the precise identification of concepts, entities, and relationships through the application of advanced syntactic and semantic analysis, enabling a better understanding of the grammatical structure and meaning within biomedical texts. Leveraging this data is crucial for extracting specific information (such as diagnoses and treatments for diseases), classifying and grouping texts based on predefined criteria, and analyzing sentiments, thereby revealing the emotions and opinions expressed in documents.
On the other hand, graph analysis emerges as a powerful methodology to represent and analyze complex interactions among biomedical entities. Biomedical graphs enable the modeling of relationships between proteins, genes, diseases, and drugs, providing a holistic view of the complexity of biological and pathological systems. Techniques for graph analysis in the biomedical domain include constructing graphs using nodes and edges to represent entities and their interactions, topological analysis to identify relevant patterns and structures, prediction of new interactions among biomedical entities, and visualization of graphs to facilitate visual comprehension of the data.
Topics of Interest
The ultimate goal of this workshop is to provide to participants the opportunity of introducing and discussing new methods, theoretical approaches, algorithms, and software tools that are relevant to explore the synergies between natural language processing (NLP) and graph analysis in the biomedical domain.
The list of topics for the workshop, that has not to be intended as exhaustive, is reported below.
- Multimodal Biomedical Data Representation in Knowledge Graphs
- NLP-Enhanced prediction of drug-target interactions
- Semantic annotation for biomedical literature extraction
- Personalized medicine recommendations via NLP-driven graph mining
- Pharmacovigilance monitoring with NLP-enabled graph analytics
- Disease progression modeling with NLP
- Text mining EHR for patient similarity graphs
- Biomarker discovery via NLP-guided graph analysis
- Drug repurposing with NLP and graph analysis
- Natural language query systems for Biomedical Knowledge Graphs
- Generative models in Biomedical Graph completion
- Anomaly detection in Biomedical data by graph analysis
- Advanced visualization for Big Data Graphs in Biomedicine
Important dates
Oct 10, 2024: Due date for full workshop papers submission (submit your paper here)
Nov 5, 2024: Notification of paper acceptance to authors
Nov 21, 2024: Camera-ready of accepted papers
Dec 3-6, 2024: Workshop