Welcome! I'm Ludvig Olsen
I'm a Python, Rust, and R developer with a PhD in bioinformatics, working as a Postdoc at the Department of Molecular Medicine (MOMA) at Aarhus University Hospital. Current projects revolve around detection and localization of cancers from cell-free DNA in blood samples.
I worked with deep learning on text at UNSILO and medical imaging data at Cercare Medical.
The aim of my career is to have a very big positive impact on this world of ours! 🌍
- Extract bias-corrected fragmentomics features from cell-free DNA
- Ultra-fast command line tools with high flexibility aimed at both research and production
- Accompanying R and Python packages for downstream analysis
Read more
- Calculate mismatch rates from consensus positions of WGS paired-end reads
- Normalized by the consensus-position opportunities in the same sequencing data
- Quantify the effect of adding/changing filtering steps via positional statistics
Read more
- Divide data into groups
- Create balanced partitions and cross-validation folds
- Perform time series windowing
- Balance existing groups with up- and downsampling
Read more
- Cross-validate regression and classification models
- Evaluate predictions with a tidy output
- Extract challenging observations
- Find baselines for a wide range of metrics
Read more
- Rearrrange data points
- center max value, roll elements, shuffle hierarchy, ... - Mutate data points
- rotate, swirl, cluster, roll values, ... - Scaling and measuring utilities
- MinMax scaling, find angle, find centroid, ...
Read more
- Detect pan-cancer from whole genome sequenced cell-free DNA
- Correlates fragment coverage with chromatin accessibility of 487 cell types
- Use the trained model or train your own
Read more
- Get, set, mutate, update, or delete nested attributes
- Works on dict members and object attributes interchangebly
- Allows regex-based matching on attribute / key names
Read more
- Run repeated nested leave-one-dataset-out cross-validation
- Evaluate predictions with a range of metrics
- Evaluate univariate models
- Classes for handling ROC curves and confusion matrices
Read more