About Me
I am Heidi Putkuri currently pursuing a Master’s in Life Science Informatics at the University of Helsinki. While I am very much interested in biological data my current interet are leaning more towards general data science and MLOPS. I am currently finishing my Master’s thesis while studying Machine learnin and data science in the University of applied sciences of Kajaani remotely.
Projects
Machine learning project in Molecular Biology
https://github.com/heksaani/ML-in-molecular-biology/blob/main/GROUP_WORK/GROUP.ipynb
It was a great learning experience as my first group project and I learned a lot about working in a team and using version control. We used Python and Flask to create a web application that allows users to upload citations and then download them in a bibtext format. We did all of this while using Scrum as our project management method.
This was my first application and I used Python and Flask to create a web application that allows users to make todo’s
Experience
University of Helsinki
Research Assistant, Master thesis student
June 2024 - October 2024
https://www.helsinki.fi/en/researchgroups/bioinformatics-and-evolution
Analyzing microbial methylation data to classify taxa using machine learning
Folkhälsan Research Center
Research Assistant
January 2023 - June 2024
https://www.folkhalsan.fi/en/knowledge/research/genetics/group-turunen/
Using different bioinformatic tools to primarily analyse sequencing data.
Education
Kajaani University of Applied Science
Information and communication technology engineer specializing in data science and machine learning
2024 -
https://kamk.fi/koulutukset/tieto-ja-viestintatekniikan-insinoori-datasta-tekoalyyn-paakaupunkiseutu-monimuoto/
University of Helsinki
Master of Science in Bioinformatics and Systems Medicine
2022 -
https://www.helsinki.fi/en/degree-programmes/life-science-informatics-masters-programme
University of Helsinki
Bachelor of Science in Molecular Biology
2019 - 2022
Minoring in computer science, math and statistics
Technical Skills
Programming Languages
Proficient in a variety of programming languages used in software development, data analysis, and machine learning:
- Python: Extensive use in data science, machine learning, and software development.
- R: Applied for statistical analysis and data visualization in biological data.
- Java: My first language, only used it to get me started with programming.
- Bash: Learned the basics in school and then used it in my reasearch assistant job.
- HTML/CSS: I have basic knowledge in HTML + CSS and have used it in some of my projects.
Other Tools
Experience with a range of IT tools and technologies:
- MLflow: For managing the ML lifecycle, including experimentation and deployment.
- Deepchecks: validating ML data and models.
- Optuna: hyperparameter optimization framerwork.
- Kubeflow: building and deploying machine learning (ML) workflows using Docker containers.
- Docker: Basic knowledge how docker images function and how to use the images
- Prometheus, Grafana, Evidently: model and data evaluation, monitoring and testing.
- Git: Used for version control in software and data science projects.
- Unix/Linux: Proficient in using Unix-like environments for data processing.
- High-Performance Computing (HPC) Platforms: Experienced in leveraging HPC for large data analysis and large-scale computational tasks. For example batch jobs with Slurm.
- Amazon aws S3 object storage: Handling data from and to object storage using python cli tools.
A Little More About Me
More about me
In my free time, I’ve developed an interest in creating a project with an Arduino microprocessor. I am also interested in poetry, photography and wondering around in the nature.