Dr. Jorge Abreu-Vicente
Astrophysicist • AI/ML Researcher • Science Communicator
About
I research how to use natural language processing (NLP) and artificial intelligence to build open science tools that revolutionize the way we do and understand science.
My work spans from developing generative means of structuring biomedical data via large language models (LLMs) and knowledge graphs (KGs) to creating semantic maps of scientific knowledge.
I use these technologies to annotate and curate molecular and cell biology knowledge into data structures that are understandable by both humans and machines.
My background in astrophysics, where I studied molecular cloud structure and star formation at galactic scales, provides a unique perspective on handling complex, multi-dimensional datasets and understanding universal patterns in complex systems..
Experience
Academic Research
Senior Staff: Machine Learning Developer
EMBO (European Molecular Biology Organization)
Heidelberg, Germany
Research and development of computing language models for biomedical data curation. Generation of knowledge graph for molecular and cell biology. Transforming open science through AI initiatives.
Resources & Code
Postdoctoral Researcher and PhD Student
Max Planck Institute for Astronomy
Heidelberg, Germany
World-class research on star formation and molecular cloud structure at Galactic scales.
Research Associate
Instituto de Astrofísica de Andalucía
Granada, Spain
Automated data processing and analysis pipeline for the IRAM 30m telescope.
Astronomer on Duty, IRAM 30m Telescope
Instituto de Radioastronomía Milimétrica (IRAM)
Granada, Spain
Quality assurance of observational data. Spectral and image processing and analysis. Writing technical documentation and reports.
Industry
Head of Center of Excellence Data Science and Innovation
CAMELOT Group
Mannheim, Germany
Lead company-wide AI transformation. Leading collaboration and connection with AWS. Data strategy design and lead implementation of Camelot Data Intelligent Digital Services. Intelligent document processing: Automated data extraction from unstructured documents.
Data Scientist
Datavard AG
Heidelberg, Germany
Creation and development of award-winning application. Evaluation and implementation of data science projects. Fast iteration and experimentation, complex application prototyping.
Featured Projects
Open-source platform for biomedical application of large language models. Published in Nature Biotechnology (2025). Democratizing AI in biomedical research through transparent, customizable conversational interfaces with RAG, knowledge graph integration, and local LLM support.
The largest Named Entity Recognition (NER) and Named Entity Linking (NEL) dataset in biomedical sciences. Integrating AI-ready curation directly into the publishing workflow at EMBO Press. Paper approved for publication in Bioinformatics (Oxford University Press).
Creating a semantic atlas of all biomedical knowledge using novel self-supervised learning (Barlow Twins, VICReg) to map 35+ million papers beyond citations and impact factors. Building comprehensive knowledge landscapes using graph databases, knowledge graphs, and semantic embeddings.
A science-backed personal journey helping others overcome panic attacks and anxiety through lived experience. Currently seeking publisher. Combining autobiographical chapters with evidence-based techniques for recovery.
Discovery of large-scale filamentary structures forming a galactic skeleton, challenging theoretical models and revealing key insights into star formation at galactic scales. Published in Astronomy & Astrophysics.
First systematic study of density distribution in molecular clouds across the Galactic plane, revealing the roles of turbulence and gravity in star formation. Published in Astronomy & Astrophysics.
Innovative recalibration of Herschel and Planck telescope data achieving unparalleled precision in mapping molecular cloud temperature and density across the Galactic plane. Published in Astronomy & Astrophysics.
Education
Ph.D. cum laude in Natural Sciences
Ruprecht-Karls-Universität Heidelberg
Heidelberg, Germany
Thesis: Molecular cloud structure at Galactic scales. Written score: 1/1. Member of the prestigious International Max Planck Research School.
View ThesisM.S. in Physics and Mathematics
IRAM & Universidad de Granada
Granada, Spain
Thesis: Carbono ionizado en el eje mayor de M33. Honors in Master Thesis.
B.S. in Physics
Universidad de La Laguna
La Laguna, Spain
Graduated with honors in optics.
Publications
10+ peer-reviewed publications
Refereed Publications
A platform for the biomedical application of large language models
Lobentanzer, S., Feng, S., Bruderer, N., Maier, A., Wang, C., Baumbach, J., Abreu-Vicente, J., et al. • Nature Biotechnology 43, 166-169
The SourceData-NLP dataset: integrating curation into scientific publishing for training large language models
Abreu-Vicente, J., Sonntag, H., Eidens, T., Lemberger, T. • Bioinformatics (accepted for publication)
Constraining the Dust Opacity Law in Three Small and Isolated Molecular Clouds
Webb, K. A. et al. • ApJ 849, 13W
Resolving fragmentation of high line-mass filaments with ALMA: integral-shaped filament in Orion A
Kainulainen, Stutz, Stanke, Abreu-Vicente et al. • A&A 600, A141
Fourier-space combination of Planck and Herschel images
J. Abreu-Vicente et al. • A&A, 604A, A65
Honors & Awards
Selected for book 'Inspiraciones Nocturnas VII'
Diversidad Literaria
Most Innovative Project 2018
IA4SP (Datavard AG)
3rd Prize in the Innojam
SAP Campus Basel
Cover Page of Astronomy and Astrophysics Journal
A&A Journal
PhD Fellowship
International Max Planck Research School
Master Thesis Honors (10/10)
Universidad de Granada
Media, Outreach & Teaching
Science-backed book on overcoming panic attacks and anxiety. Currently seeking publisher. Website and blog documenting the journey and recovery process.
Four chapters with Dr. Francisco Parra-Rojas.
Amateur astronomy company and YouTube channel.
Luciérnagas, Radiotelevisión diocesana
Astronomy in Elementary School
Colegio PP Somascos, A Guarda, Spain
Teacher for Astronomical Lab Course
Stellar photometry - MPIA/Ruprecht Karls-Universität Heidelberg

