cv
Basics
| Name | Melissa Yan |
| melissayan@pm.me | |
| GitHub | https://github.com/melissayan |
| https://www.linkedin.com/in/melissayyan | |
| Google Scholar | https://scholar.google.com/citations?user=qkenELkAAAAJ |
Work
-
2023.12 - Present Postdoctoral Fellow
Norwegian University of Science and Technology, Trondheim, Norway
- Developed a Retrieval‑Augmented Generation (RAG) chatbot with Python, open-source LLMs, Streamlit, and databases, cutting nurses' manual incident-report review time
- Designed and prepared curriculum for a health data and AI course by sourcing datasets, creating syllabus, and managing lab environments
- Mentoring 3 master's students performing unsuperivsed learning to discover signs of sepsis
-
2019.03 - 2023.12 Ph.D. Candidate, Researcher, & Scientific Assistant
Norwegian University of Science and Technology, Trondheim, Norway
- Curated an annotated text dataset and developed a catheter-related infection ontology with clinicians using Python and SPARQL
- Published 5 peer-reviewed papers and presented at 3 international conferences/workshops
- Managed a team of 6 research assistants for data de-identification, management, and annotation
- Mentored 3 master's students developing natrual language processing pipelines to detect and classify catheter-related infections
- Designed and taught a health data analysis course to 28 clinicians and IT professionals
-
2017.04 - 2019.03 Research Associate & Bioinformatician
Oregon Health & Science University, Portland, Oregon, USA
- Automated a genomic analysis pipeline in Bash and R on a SLURM cloud cluster, replacing manual sample classification and ensuring reproducibility
- Built an interactive HTML quality control report for rapid summarization, quality checks, and outlier detection of large genomic datasets
- Updated the variant gene disease catalog in the Macaque Genotype and Phenotype database to aid disease model and translational research
Education
-
2019.03 - 2023.12 Philosophiae Doctor (Ph.D.) in Computer Science
Norwegian University of Science and Technology, Trondheim, Norway
-
2014.09 - 2016.12 -
2012.09 - 2016.06
Projects
-
Annotated Adverse Event Note Terminology and Catheter Infection Indications Ontology
Resources to annotate and infer catether-related infections in incident reports
-
-
-
VNOWCHI: Variable Non-Overlapping Window CBS and HMM Intersect
Copy‑number variant calling pipeline to determine the number of full chromosome sets and sex status of embryos
-
Macaque Genotype and Phenotype Database (mGAP)
Public database with over 15 million annotated genetic variants from thousands of rhesus macaques to support biomedical research
Skills
| Programming | |
| Python | |
| Bash | |
| Java | |
| C++ | |
| C |
| Database and query languages | |
| SPARQL | |
| PostgreSQL | |
| SQL | |
| Neo4j | |
| Cypher |
| Statistical Analysis | |
| R | |
| STATA |
| Cloud Computing | |
| NTNU's HUNT Cloud | |
| OHSU's HPC cluster |
| Tools | |
| Protégé | |
| Streamlit | |
| Docker | |
| Git | |
| SLURM |
| Languages | |
| English (native) | |
| Mandarin (intermediate) | |
| Norwegian (basic) | |
| Taiwanese (basic) | |
| Japanese (basic) |
Volunteer
-
2025.05 - Present -
2024.09 - 2024.09 -
2024.03 - 2025.06 -
2024.02 - 2025.02 Nord University - Faculty of Nursing and Health Science
Speaker on innovative research potential for healthcare students
-
2022.01 - 2025.05 -
2019.06 - 2019.11 -
2014.03 - 2014.05 PSU Innovation Challenge Competition
Mentor for high school students in a health innovation competition
Interests
| Exercise | |
| Parkrun | |
| Walking | |
| Running | |
| Weightlifting |
| Creative pursuits | |
| Digital illustration | |
| Crochet |