🎓 Study opportunities

At lab42open, we bridge the gap between big biological data and actionable ecological/biodiversity knowledge. We develop open-source tools, deploy workflows, and build text-mining pipelines to understand molecular ecology and biodiversity.

We are looking for motivated students (from Bioinformatics, Computer Science, Data Science, or Biology/Ecology backgrounds) to tackle real-world computational challenges with us. Thesis work collaboration is highly encouraged.

🔬 Open research tracks

Track 1: Biological databases and interactive visualization

  • The Challenge: Creating interactive tools to ease access to key biodiversity and molecular ecology data
  • Related tasks: Extend Odyssey, an R shiny application for the exploration of Molecular Biodiversity in Greece and Norway
  • Ideal Skills: R/R-shiny, web-based application development and API consumption, basic understanding of biological databases and metadata

Track 2: Artificial Intelligence to flag phenomena of interest in biological studies

  • The Challenge:Labeling biological/ecological studies according to phenomena of interest they explore (e.g. pollution, antimicrobial resistance, anthropogenic impact, pathogen surveillance, biodiversity loss)
  • Related tasks:Broaden the scope of the CCMRI techniques, a project that showcases how LLMs can facilitate the detection curation of Climate Change related microbiome studies.
  • Ideal Skills: Python, Ollama, LLMs, BASH/gawk scripting, basic understanding of text mining

Track 3: AI agents for global microbial metabolic mapping under climate change

  • The Challenge: Integrating highly heterogeneous functional and pathway data across diverse microbiome studies to visualize the global metabolic response to climate change.
  • Related tasks:
    • Develop multi-agent LLM frameworks to parse curated CCMRI studies.
    • Extract and normalize metabolic pathway data (e.g., KEGG, MetaCyc).
    • Build an interactive global pathway atlas mapping microbial metabolism.
    • Highlight category-specific metabolic shifts across climate change scenarios.
  • Ideal Skills:
    • Python
    • LLM inference engine and orchestration frameworks (e.g. Ollama and PicoClaw)
    • RAG (Retrieval-Augmented Generation) architectures
    • API integration with biological databases (KEGG, MGnify).
    • Graph networks or interactive data visualization tools.

🛠 Our tech stack at a glance

Python • R • R Shiny• Ollama • LLMs • Gawk • Linux HPC • Git / GitHub

🎯 How to apply

We accept students on a rolling basis depending on project availability and funding resources.

To apply, please send an Email Envelope logo by user Tokyoship via wikimedia commons under CC BY-SA 3.0 with the subject line:
[Join lab42open application] Your Name

Please attach:

  1. A brief CV (1-2 pages)
  2. A short paragraph (3–5 sentences) explaining which research track interests you most and why.
  3. Your expected start date, duration,and any specific university requirements.