← All projects Ongoing work

Biotech / sosci research pipelines

Reusable science-of-science pipelines for biotech topics, from corpus to topics and dashboards.

My role

Python, database and BERTopic pipelines at CognosX.

Outputs

biotech repository and research pipeline scripts

Methods and tools

  • Python
  • DuckDB
  • BERTopic
  • cuML
  • UMAP
  • HDBSCAN
  • embeddings

Skills

  • Pipeline architecture
  • multilingual NLP
  • GPU workflow