Presentation Open Access

Interpretable classification of molecular measurements via pathway-induced multiple kernel learning

Cadow Joris

Roadmap

Molecular data classification: use network topology as a regulariser, define meta-features using pathway information Pathway-Induced. Multiple Kernel Learning (PIMKL): concept, pathway induction, multiple kernel learning PIMKL benchmarking: benchmark against other prior knowledge informed methods on multiple breast cancer cohorts.
PIMKL application: detects tumor samples accurately, integrates multiple omics seamlessly, identifies relevant pathways for each data type.

Files (3.1 MB)
Name Size
pimkl_slides_ismbeccb2019.pdf
md5:e56578d909431e88de335e8d50d21489
3.1 MB Download
38
37
views
downloads
All versions This version
Views 3838
Downloads 3737
Data volume 113.8 MB113.8 MB
Unique views 3636
Unique downloads 3636

Share

Cite as