AI-assisted research
Designing workflows where AI supports data retrieval, transformation, statistical analysis, visualization, and reproducible reporting while keeping decisions inspectable.
Akewak Jeba
Data science · AI · Open science
I build research tools that turn complex data into usable knowledge.
I’m Akewak Jeba, a data scientist and scientific software developer at the intersection of artificial intelligence, cultural heritage, computational biology, and reproducible research.
$ whoami → data scientist_
R · Python
AI + Research
Open Source
4×automated refreshes each day
—public GitHub repositories
—GitHub followers
loading…last automated refresh
What I do
Research engineering from data access to reproducible analysis.
My work combines statistical computing, machine learning, APIs, software engineering, and open research infrastructure. I focus on making complex datasets easier to retrieve, analyze, validate, and reuse.
Scientific software
Building open-source R tooling and data pipelines for cultural heritage metadata, bibliographic data, omics, and interactive analysis.
Reproducible data science
Connecting APIs, structured metadata, statistical methods, CI/CD, documentation, and scalable computing into research workflows that others can rerun.
Selected work
Open tools and research projects.
finna
An R interface for programmatic access to the Finna API, enabling reproducible retrieval and analysis of Finnish library, archive, and museum metadata.
finto
Tools for working with Finnish ontology and vocabulary services, supporting concept search, semantic enrichment, and multilingual cultural heritage workflows.
fennica
Computational access and analysis workflows for Finnish national bibliography data, supporting large-scale studies of publishing and literary history.
LimROTS + iSEEtree
Contributions to statistical and interactive tools for robust differential expression analysis and exploration of hierarchical biological data.
Live GitHub
Repository activity, refreshed automatically.
A scheduled GitHub Action refreshes this portfolio four times per day, records the update in version control, and republishes the site. The cards below are populated from the latest public GitHub data.
Loading GitHub activity…
Live repository information will appear here.
Toolbox
Technologies I use to ship research.
RPythonSQLQuartoShinyMachine LearningLLMsNLPDockerGitHub ActionsLinuxHPCAWSAPIsPostgreSQLJavaScript
Interested in research, data, or scientific software?
I’m always interested in useful collaborations where rigorous data science and good software engineering meet.