Search

Supplementary results for experiment 1for the second version of the manuscript titled "Improving generalization of machine learning-identified biomarkers with causal modeling: an investigation into immune receptor diagnostics". Code:https://github.com/uio-bmi/CausalAIRR Preprint:https://arxiv.org/abs/2204.09291

These are results for the AIR part of experiment 3 of the manuscriptImproving generalization of machine learning-identified biomarkers with causal modeling: an investigation into immune receptor diagnostics. Code:https://github.com/uio-bmi/CausalAIRR Preprint:https://arxiv.org/abs/2204.09291

Supplementary results for experiment 2for the second version of the manuscript titled "Improving generalization of machine learning-identified biomarkers with causal modeling: an investigation into immune receptor diagnostics". Code:https://github.com/uio-bmi/CausalAIRR Preprint:https://arxiv.org/abs/2204.09291

Machine learning is increasingly used to discover diagnostic and prognostic biomarkers from high-dimensional molecular data. However, a variety of factors related to experimental design may affect the ability to learn generalizable and clinically applicable diagnostics. Here, we argue that a causal perspective improves the identification of these challenges and formalizes their relation to the robustness and generalization of machine learning-based diagnostics. To make for a concrete discussion, we focus on a specific, recently established high-dimensional biomarker - adaptive immune receptor repertoires (AIRRs). Through simulations, we illustrate how major biological and experimental factors of the AIRR domain may influence the learned biomarkers. In conclusion, we argue that causal modeling improves machine learning-based biomarker robustness by identifying stable relations between variables and by guiding the adjustment of the relations and variables that vary between populations.

Supplemental material, Supplemental Material1 for Transcriptional profiling of human intestinal plasma cells reveals effector functions beyond antibody production by Omri Snir, Chakravarthi Kanduri, Knut E A Lundin, Geir Kjetil Sandve and Ludvig M Sollid in United European Gastroenterology Journal

Supplemental material, Supplemental Material2 for Transcriptional profiling of human intestinal plasma cells reveals effector functions beyond antibody production by Omri Snir, Chakravarthi Kanduri, Knut E A Lundin, Geir Kjetil Sandve and Ludvig M Sollid in United European Gastroenterology Journal

Supplemental Material for CD38 expression on gluten-specific T cells is a robust marker of gluten re-exposure in coeliac disease by Stephanie Zühlke, Louise Fremgaard Risnes, Shiva Dahal-Koirala, Asbjørn Christophersen, Ludvig M Sollid and Knut EA Lundin in United European Gastroenterology Journal